Last active
July 24, 2017 22:04
-
-
Save AdamStelmaszczyk/8451948a806837af5b1fe930a4285d76 to your computer and use it in GitHub Desktop.
TRPO on CartPole-v0
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
$ python examples/quickstart.py | |
[2017-07-24 23:13:32,771] Making new env: CartPole-v0 | |
Finished episode 1 after 40 timesteps (reward: 40.0) | |
Finished episode 2 after 25 timesteps (reward: 25.0) | |
Finished episode 3 after 20 timesteps (reward: 20.0) | |
Finished episode 4 after 36 timesteps (reward: 36.0) | |
Finished episode 5 after 21 timesteps (reward: 21.0) | |
Finished episode 6 after 44 timesteps (reward: 44.0) | |
Finished episode 7 after 12 timesteps (reward: 12.0) | |
Finished episode 8 after 16 timesteps (reward: 16.0) | |
Finished episode 9 after 14 timesteps (reward: 14.0) | |
Finished episode 10 after 26 timesteps (reward: 26.0) | |
Finished episode 11 after 31 timesteps (reward: 31.0) | |
Finished episode 12 after 37 timesteps (reward: 37.0) | |
Finished episode 13 after 24 timesteps (reward: 24.0) | |
Finished episode 14 after 27 timesteps (reward: 27.0) | |
Finished episode 15 after 16 timesteps (reward: 16.0) | |
Finished episode 16 after 18 timesteps (reward: 18.0) | |
Finished episode 17 after 15 timesteps (reward: 15.0) | |
Finished episode 18 after 24 timesteps (reward: 24.0) | |
Finished episode 19 after 14 timesteps (reward: 14.0) | |
Finished episode 20 after 18 timesteps (reward: 18.0) | |
Finished episode 21 after 10 timesteps (reward: 10.0) | |
Finished episode 22 after 38 timesteps (reward: 38.0) | |
Finished episode 23 after 18 timesteps (reward: 18.0) | |
Finished episode 24 after 12 timesteps (reward: 12.0) | |
Finished episode 25 after 18 timesteps (reward: 18.0) | |
Finished episode 26 after 43 timesteps (reward: 43.0) | |
Finished episode 27 after 15 timesteps (reward: 15.0) | |
Finished episode 28 after 22 timesteps (reward: 22.0) | |
Finished episode 29 after 38 timesteps (reward: 38.0) | |
Finished episode 30 after 21 timesteps (reward: 21.0) | |
Finished episode 31 after 15 timesteps (reward: 15.0) | |
Finished episode 32 after 30 timesteps (reward: 30.0) | |
Finished episode 33 after 16 timesteps (reward: 16.0) | |
Finished episode 34 after 10 timesteps (reward: 10.0) | |
Finished episode 35 after 23 timesteps (reward: 23.0) | |
Finished episode 36 after 15 timesteps (reward: 15.0) | |
Finished episode 37 after 62 timesteps (reward: 62.0) | |
Finished episode 38 after 26 timesteps (reward: 26.0) | |
Finished episode 39 after 14 timesteps (reward: 14.0) | |
Finished episode 40 after 26 timesteps (reward: 26.0) | |
Finished episode 41 after 17 timesteps (reward: 17.0) | |
Finished episode 42 after 30 timesteps (reward: 30.0) | |
Finished episode 43 after 26 timesteps (reward: 26.0) | |
Finished episode 44 after 35 timesteps (reward: 35.0) | |
Finished episode 45 after 15 timesteps (reward: 15.0) | |
Finished episode 46 after 18 timesteps (reward: 18.0) | |
Finished episode 47 after 28 timesteps (reward: 28.0) | |
Finished episode 48 after 18 timesteps (reward: 18.0) | |
Finished episode 49 after 26 timesteps (reward: 26.0) | |
Finished episode 50 after 66 timesteps (reward: 66.0) | |
Finished episode 51 after 14 timesteps (reward: 14.0) | |
Finished episode 52 after 35 timesteps (reward: 35.0) | |
Finished episode 53 after 17 timesteps (reward: 17.0) | |
Finished episode 54 after 27 timesteps (reward: 27.0) | |
Finished episode 55 after 39 timesteps (reward: 39.0) | |
Finished episode 56 after 18 timesteps (reward: 18.0) | |
Finished episode 57 after 14 timesteps (reward: 14.0) | |
Finished episode 58 after 77 timesteps (reward: 77.0) | |
Finished episode 59 after 57 timesteps (reward: 57.0) | |
Finished episode 60 after 45 timesteps (reward: 45.0) | |
Finished episode 61 after 13 timesteps (reward: 13.0) | |
Finished episode 62 after 22 timesteps (reward: 22.0) | |
Finished episode 63 after 32 timesteps (reward: 32.0) | |
Finished episode 64 after 15 timesteps (reward: 15.0) | |
Finished episode 65 after 31 timesteps (reward: 31.0) | |
Finished episode 66 after 40 timesteps (reward: 40.0) | |
Finished episode 67 after 45 timesteps (reward: 45.0) | |
Finished episode 68 after 44 timesteps (reward: 44.0) | |
Finished episode 69 after 40 timesteps (reward: 40.0) | |
Finished episode 70 after 74 timesteps (reward: 74.0) | |
Finished episode 71 after 24 timesteps (reward: 24.0) | |
Finished episode 72 after 37 timesteps (reward: 37.0) | |
Finished episode 73 after 24 timesteps (reward: 24.0) | |
Finished episode 74 after 29 timesteps (reward: 29.0) | |
Finished episode 75 after 50 timesteps (reward: 50.0) | |
Finished episode 76 after 13 timesteps (reward: 13.0) | |
Finished episode 77 after 39 timesteps (reward: 39.0) | |
Finished episode 78 after 28 timesteps (reward: 28.0) | |
Finished episode 79 after 28 timesteps (reward: 28.0) | |
Finished episode 80 after 20 timesteps (reward: 20.0) | |
Finished episode 81 after 19 timesteps (reward: 19.0) | |
Finished episode 82 after 29 timesteps (reward: 29.0) | |
Finished episode 83 after 33 timesteps (reward: 33.0) | |
Finished episode 84 after 75 timesteps (reward: 75.0) | |
Finished episode 85 after 23 timesteps (reward: 23.0) | |
Finished episode 86 after 54 timesteps (reward: 54.0) | |
Finished episode 87 after 20 timesteps (reward: 20.0) | |
Finished episode 88 after 43 timesteps (reward: 43.0) | |
Finished episode 89 after 12 timesteps (reward: 12.0) | |
Finished episode 90 after 37 timesteps (reward: 37.0) | |
Finished episode 91 after 51 timesteps (reward: 51.0) | |
Finished episode 92 after 58 timesteps (reward: 58.0) | |
Finished episode 93 after 29 timesteps (reward: 29.0) | |
Finished episode 94 after 43 timesteps (reward: 43.0) | |
Finished episode 95 after 72 timesteps (reward: 72.0) | |
Finished episode 96 after 64 timesteps (reward: 64.0) | |
Finished episode 97 after 23 timesteps (reward: 23.0) | |
Finished episode 98 after 46 timesteps (reward: 46.0) | |
Finished episode 99 after 42 timesteps (reward: 42.0) | |
Finished episode 100 after 62 timesteps (reward: 62.0) | |
Finished episode 101 after 35 timesteps (reward: 35.0) | |
Finished episode 102 after 59 timesteps (reward: 59.0) | |
Finished episode 103 after 164 timesteps (reward: 164.0) | |
Finished episode 104 after 90 timesteps (reward: 90.0) | |
Finished episode 105 after 33 timesteps (reward: 33.0) | |
Finished episode 106 after 38 timesteps (reward: 38.0) | |
Finished episode 107 after 44 timesteps (reward: 44.0) | |
Finished episode 108 after 55 timesteps (reward: 55.0) | |
Finished episode 109 after 18 timesteps (reward: 18.0) | |
Finished episode 110 after 34 timesteps (reward: 34.0) | |
Finished episode 111 after 33 timesteps (reward: 33.0) | |
Finished episode 112 after 22 timesteps (reward: 22.0) | |
Finished episode 113 after 56 timesteps (reward: 56.0) | |
Finished episode 114 after 117 timesteps (reward: 117.0) | |
Finished episode 115 after 60 timesteps (reward: 60.0) | |
Finished episode 116 after 43 timesteps (reward: 43.0) | |
Finished episode 117 after 36 timesteps (reward: 36.0) | |
Finished episode 118 after 72 timesteps (reward: 72.0) | |
Finished episode 119 after 96 timesteps (reward: 96.0) | |
Finished episode 120 after 27 timesteps (reward: 27.0) | |
Finished episode 121 after 43 timesteps (reward: 43.0) | |
Finished episode 122 after 81 timesteps (reward: 81.0) | |
Finished episode 123 after 76 timesteps (reward: 76.0) | |
Finished episode 124 after 30 timesteps (reward: 30.0) | |
Finished episode 125 after 64 timesteps (reward: 64.0) | |
Finished episode 126 after 64 timesteps (reward: 64.0) | |
Finished episode 127 after 34 timesteps (reward: 34.0) | |
Finished episode 128 after 20 timesteps (reward: 20.0) | |
Finished episode 129 after 42 timesteps (reward: 42.0) | |
Finished episode 130 after 103 timesteps (reward: 103.0) | |
Finished episode 131 after 25 timesteps (reward: 25.0) | |
Finished episode 132 after 103 timesteps (reward: 103.0) | |
Finished episode 133 after 65 timesteps (reward: 65.0) | |
Finished episode 134 after 34 timesteps (reward: 34.0) | |
Finished episode 135 after 88 timesteps (reward: 88.0) | |
Finished episode 136 after 68 timesteps (reward: 68.0) | |
Finished episode 137 after 69 timesteps (reward: 69.0) | |
Finished episode 138 after 68 timesteps (reward: 68.0) | |
Finished episode 139 after 76 timesteps (reward: 76.0) | |
Finished episode 140 after 87 timesteps (reward: 87.0) | |
Finished episode 141 after 98 timesteps (reward: 98.0) | |
Finished episode 142 after 47 timesteps (reward: 47.0) | |
Finished episode 143 after 58 timesteps (reward: 58.0) | |
Finished episode 144 after 102 timesteps (reward: 102.0) | |
Finished episode 145 after 40 timesteps (reward: 40.0) | |
Finished episode 146 after 61 timesteps (reward: 61.0) | |
Finished episode 147 after 69 timesteps (reward: 69.0) | |
Finished episode 148 after 44 timesteps (reward: 44.0) | |
Finished episode 149 after 63 timesteps (reward: 63.0) | |
Finished episode 150 after 83 timesteps (reward: 83.0) | |
Finished episode 151 after 41 timesteps (reward: 41.0) | |
Finished episode 152 after 69 timesteps (reward: 69.0) | |
Finished episode 153 after 66 timesteps (reward: 66.0) | |
Finished episode 154 after 56 timesteps (reward: 56.0) | |
Finished episode 155 after 58 timesteps (reward: 58.0) | |
Finished episode 156 after 70 timesteps (reward: 70.0) | |
Finished episode 157 after 104 timesteps (reward: 104.0) | |
Finished episode 158 after 58 timesteps (reward: 58.0) | |
Finished episode 159 after 86 timesteps (reward: 86.0) | |
Finished episode 160 after 70 timesteps (reward: 70.0) | |
Finished episode 161 after 55 timesteps (reward: 55.0) | |
Finished episode 162 after 112 timesteps (reward: 112.0) | |
Finished episode 163 after 45 timesteps (reward: 45.0) | |
Finished episode 164 after 82 timesteps (reward: 82.0) | |
Finished episode 165 after 82 timesteps (reward: 82.0) | |
Finished episode 166 after 68 timesteps (reward: 68.0) | |
Finished episode 167 after 73 timesteps (reward: 73.0) | |
Finished episode 168 after 81 timesteps (reward: 81.0) | |
Finished episode 169 after 86 timesteps (reward: 86.0) | |
Finished episode 170 after 85 timesteps (reward: 85.0) | |
Finished episode 171 after 56 timesteps (reward: 56.0) | |
Finished episode 172 after 64 timesteps (reward: 64.0) | |
Finished episode 173 after 68 timesteps (reward: 68.0) | |
Finished episode 174 after 76 timesteps (reward: 76.0) | |
Finished episode 175 after 70 timesteps (reward: 70.0) | |
Finished episode 176 after 87 timesteps (reward: 87.0) | |
Finished episode 177 after 140 timesteps (reward: 140.0) | |
Finished episode 178 after 62 timesteps (reward: 62.0) | |
Finished episode 179 after 55 timesteps (reward: 55.0) | |
Finished episode 180 after 61 timesteps (reward: 61.0) | |
Finished episode 181 after 117 timesteps (reward: 117.0) | |
Finished episode 182 after 128 timesteps (reward: 128.0) | |
Finished episode 183 after 59 timesteps (reward: 59.0) | |
Finished episode 184 after 43 timesteps (reward: 43.0) | |
Finished episode 185 after 57 timesteps (reward: 57.0) | |
Finished episode 186 after 45 timesteps (reward: 45.0) | |
Finished episode 187 after 68 timesteps (reward: 68.0) | |
Finished episode 188 after 168 timesteps (reward: 168.0) | |
Finished episode 189 after 67 timesteps (reward: 67.0) | |
Finished episode 190 after 68 timesteps (reward: 68.0) | |
Finished episode 191 after 64 timesteps (reward: 64.0) | |
Finished episode 192 after 73 timesteps (reward: 73.0) | |
Finished episode 193 after 142 timesteps (reward: 142.0) | |
Finished episode 194 after 85 timesteps (reward: 85.0) | |
Finished episode 195 after 50 timesteps (reward: 50.0) | |
Finished episode 196 after 63 timesteps (reward: 63.0) | |
Finished episode 197 after 65 timesteps (reward: 65.0) | |
Finished episode 198 after 141 timesteps (reward: 141.0) | |
Finished episode 199 after 165 timesteps (reward: 165.0) | |
Finished episode 200 after 72 timesteps (reward: 72.0) | |
Finished episode 201 after 66 timesteps (reward: 66.0) | |
Finished episode 202 after 88 timesteps (reward: 88.0) | |
Finished episode 203 after 102 timesteps (reward: 102.0) | |
Finished episode 204 after 95 timesteps (reward: 95.0) | |
Finished episode 205 after 93 timesteps (reward: 93.0) | |
Finished episode 206 after 76 timesteps (reward: 76.0) | |
Finished episode 207 after 96 timesteps (reward: 96.0) | |
Finished episode 208 after 97 timesteps (reward: 97.0) | |
Finished episode 209 after 84 timesteps (reward: 84.0) | |
Finished episode 210 after 71 timesteps (reward: 71.0) | |
Finished episode 211 after 64 timesteps (reward: 64.0) | |
Finished episode 212 after 95 timesteps (reward: 95.0) | |
Finished episode 213 after 62 timesteps (reward: 62.0) | |
Finished episode 214 after 70 timesteps (reward: 70.0) | |
Finished episode 215 after 98 timesteps (reward: 98.0) | |
Finished episode 216 after 57 timesteps (reward: 57.0) | |
Finished episode 217 after 92 timesteps (reward: 92.0) | |
Finished episode 218 after 77 timesteps (reward: 77.0) | |
Finished episode 219 after 68 timesteps (reward: 68.0) | |
Finished episode 220 after 77 timesteps (reward: 77.0) | |
Finished episode 221 after 130 timesteps (reward: 130.0) | |
Finished episode 222 after 78 timesteps (reward: 78.0) | |
Finished episode 223 after 59 timesteps (reward: 59.0) | |
Finished episode 224 after 93 timesteps (reward: 93.0) | |
Finished episode 225 after 90 timesteps (reward: 90.0) | |
Finished episode 226 after 75 timesteps (reward: 75.0) | |
Finished episode 227 after 112 timesteps (reward: 112.0) | |
Finished episode 228 after 65 timesteps (reward: 65.0) | |
Finished episode 229 after 92 timesteps (reward: 92.0) | |
Finished episode 230 after 122 timesteps (reward: 122.0) | |
Finished episode 231 after 69 timesteps (reward: 69.0) | |
Finished episode 232 after 103 timesteps (reward: 103.0) | |
Finished episode 233 after 95 timesteps (reward: 95.0) | |
Finished episode 234 after 84 timesteps (reward: 84.0) | |
Finished episode 235 after 66 timesteps (reward: 66.0) | |
Finished episode 236 after 71 timesteps (reward: 71.0) | |
Finished episode 237 after 51 timesteps (reward: 51.0) | |
Finished episode 238 after 90 timesteps (reward: 90.0) | |
Finished episode 239 after 51 timesteps (reward: 51.0) | |
Finished episode 240 after 78 timesteps (reward: 78.0) | |
Finished episode 241 after 96 timesteps (reward: 96.0) | |
Finished episode 242 after 69 timesteps (reward: 69.0) | |
Finished episode 243 after 118 timesteps (reward: 118.0) | |
Finished episode 244 after 88 timesteps (reward: 88.0) | |
Finished episode 245 after 56 timesteps (reward: 56.0) | |
Finished episode 246 after 92 timesteps (reward: 92.0) | |
Finished episode 247 after 127 timesteps (reward: 127.0) | |
Finished episode 248 after 60 timesteps (reward: 60.0) | |
Finished episode 249 after 111 timesteps (reward: 111.0) | |
Finished episode 250 after 67 timesteps (reward: 67.0) | |
Finished episode 251 after 120 timesteps (reward: 120.0) | |
Finished episode 252 after 71 timesteps (reward: 71.0) | |
Finished episode 253 after 55 timesteps (reward: 55.0) | |
Finished episode 254 after 97 timesteps (reward: 97.0) | |
Finished episode 255 after 97 timesteps (reward: 97.0) | |
Finished episode 256 after 84 timesteps (reward: 84.0) | |
Finished episode 257 after 102 timesteps (reward: 102.0) | |
Finished episode 258 after 86 timesteps (reward: 86.0) | |
Finished episode 259 after 93 timesteps (reward: 93.0) | |
Finished episode 260 after 104 timesteps (reward: 104.0) | |
Finished episode 261 after 52 timesteps (reward: 52.0) | |
Finished episode 262 after 78 timesteps (reward: 78.0) | |
Finished episode 263 after 79 timesteps (reward: 79.0) | |
Finished episode 264 after 86 timesteps (reward: 86.0) | |
Finished episode 265 after 58 timesteps (reward: 58.0) | |
Finished episode 266 after 119 timesteps (reward: 119.0) | |
Finished episode 267 after 93 timesteps (reward: 93.0) | |
Finished episode 268 after 81 timesteps (reward: 81.0) | |
Finished episode 269 after 84 timesteps (reward: 84.0) | |
Finished episode 270 after 108 timesteps (reward: 108.0) | |
Finished episode 271 after 89 timesteps (reward: 89.0) | |
Finished episode 272 after 87 timesteps (reward: 87.0) | |
Finished episode 273 after 99 timesteps (reward: 99.0) | |
Finished episode 274 after 122 timesteps (reward: 122.0) | |
Finished episode 275 after 60 timesteps (reward: 60.0) | |
Finished episode 276 after 124 timesteps (reward: 124.0) | |
Finished episode 277 after 82 timesteps (reward: 82.0) | |
Finished episode 278 after 56 timesteps (reward: 56.0) | |
Finished episode 279 after 85 timesteps (reward: 85.0) | |
Finished episode 280 after 52 timesteps (reward: 52.0) | |
Finished episode 281 after 107 timesteps (reward: 107.0) | |
Finished episode 282 after 84 timesteps (reward: 84.0) | |
Finished episode 283 after 102 timesteps (reward: 102.0) | |
Finished episode 284 after 86 timesteps (reward: 86.0) | |
Finished episode 285 after 95 timesteps (reward: 95.0) | |
Finished episode 286 after 87 timesteps (reward: 87.0) | |
Finished episode 287 after 55 timesteps (reward: 55.0) | |
Finished episode 288 after 82 timesteps (reward: 82.0) | |
Finished episode 289 after 99 timesteps (reward: 99.0) | |
Finished episode 290 after 106 timesteps (reward: 106.0) | |
Finished episode 291 after 77 timesteps (reward: 77.0) | |
Finished episode 292 after 93 timesteps (reward: 93.0) | |
Finished episode 293 after 54 timesteps (reward: 54.0) | |
Finished episode 294 after 61 timesteps (reward: 61.0) | |
Finished episode 295 after 81 timesteps (reward: 81.0) | |
Finished episode 296 after 90 timesteps (reward: 90.0) | |
Finished episode 297 after 74 timesteps (reward: 74.0) | |
Finished episode 298 after 101 timesteps (reward: 101.0) | |
Finished episode 299 after 82 timesteps (reward: 82.0) | |
Finished episode 300 after 97 timesteps (reward: 97.0) | |
Finished episode 301 after 77 timesteps (reward: 77.0) | |
Finished episode 302 after 104 timesteps (reward: 104.0) | |
Finished episode 303 after 96 timesteps (reward: 96.0) | |
Finished episode 304 after 93 timesteps (reward: 93.0) | |
Finished episode 305 after 79 timesteps (reward: 79.0) | |
Finished episode 306 after 200 timesteps (reward: 200.0) | |
Finished episode 307 after 104 timesteps (reward: 104.0) | |
Finished episode 308 after 113 timesteps (reward: 113.0) | |
Finished episode 309 after 84 timesteps (reward: 84.0) | |
Finished episode 310 after 107 timesteps (reward: 107.0) | |
Finished episode 311 after 111 timesteps (reward: 111.0) | |
Finished episode 312 after 93 timesteps (reward: 93.0) | |
Finished episode 313 after 153 timesteps (reward: 153.0) | |
Finished episode 314 after 101 timesteps (reward: 101.0) | |
Finished episode 315 after 107 timesteps (reward: 107.0) | |
Finished episode 316 after 112 timesteps (reward: 112.0) | |
Finished episode 317 after 110 timesteps (reward: 110.0) | |
Finished episode 318 after 69 timesteps (reward: 69.0) | |
Finished episode 319 after 144 timesteps (reward: 144.0) | |
Finished episode 320 after 100 timesteps (reward: 100.0) | |
Finished episode 321 after 116 timesteps (reward: 116.0) | |
Finished episode 322 after 124 timesteps (reward: 124.0) | |
Finished episode 323 after 102 timesteps (reward: 102.0) | |
Finished episode 324 after 109 timesteps (reward: 109.0) | |
Finished episode 325 after 106 timesteps (reward: 106.0) | |
Finished episode 326 after 126 timesteps (reward: 126.0) | |
Finished episode 327 after 53 timesteps (reward: 53.0) | |
Finished episode 328 after 85 timesteps (reward: 85.0) | |
Finished episode 329 after 104 timesteps (reward: 104.0) | |
Finished episode 330 after 97 timesteps (reward: 97.0) | |
Finished episode 331 after 158 timesteps (reward: 158.0) | |
Finished episode 332 after 131 timesteps (reward: 131.0) | |
Finished episode 333 after 89 timesteps (reward: 89.0) | |
Finished episode 334 after 171 timesteps (reward: 171.0) | |
Finished episode 335 after 108 timesteps (reward: 108.0) | |
Finished episode 336 after 99 timesteps (reward: 99.0) | |
Finished episode 337 after 113 timesteps (reward: 113.0) | |
Finished episode 338 after 94 timesteps (reward: 94.0) | |
Finished episode 339 after 138 timesteps (reward: 138.0) | |
Finished episode 340 after 157 timesteps (reward: 157.0) | |
Finished episode 341 after 62 timesteps (reward: 62.0) | |
Finished episode 342 after 69 timesteps (reward: 69.0) | |
Finished episode 343 after 58 timesteps (reward: 58.0) | |
Finished episode 344 after 89 timesteps (reward: 89.0) | |
Finished episode 345 after 92 timesteps (reward: 92.0) | |
Finished episode 346 after 97 timesteps (reward: 97.0) | |
Finished episode 347 after 105 timesteps (reward: 105.0) | |
Finished episode 348 after 59 timesteps (reward: 59.0) | |
Finished episode 349 after 99 timesteps (reward: 99.0) | |
Finished episode 350 after 108 timesteps (reward: 108.0) | |
Finished episode 351 after 124 timesteps (reward: 124.0) | |
Finished episode 352 after 132 timesteps (reward: 132.0) | |
Finished episode 353 after 119 timesteps (reward: 119.0) | |
Finished episode 354 after 94 timesteps (reward: 94.0) | |
Finished episode 355 after 109 timesteps (reward: 109.0) | |
Finished episode 356 after 144 timesteps (reward: 144.0) | |
Finished episode 357 after 59 timesteps (reward: 59.0) | |
Finished episode 358 after 101 timesteps (reward: 101.0) | |
Finished episode 359 after 102 timesteps (reward: 102.0) | |
Finished episode 360 after 94 timesteps (reward: 94.0) | |
Finished episode 361 after 111 timesteps (reward: 111.0) | |
Finished episode 362 after 138 timesteps (reward: 138.0) | |
Finished episode 363 after 106 timesteps (reward: 106.0) | |
Finished episode 364 after 140 timesteps (reward: 140.0) | |
Finished episode 365 after 119 timesteps (reward: 119.0) | |
Finished episode 366 after 187 timesteps (reward: 187.0) | |
Finished episode 367 after 92 timesteps (reward: 92.0) | |
Finished episode 368 after 55 timesteps (reward: 55.0) | |
Finished episode 369 after 113 timesteps (reward: 113.0) | |
Finished episode 370 after 126 timesteps (reward: 126.0) | |
Finished episode 371 after 56 timesteps (reward: 56.0) | |
Finished episode 372 after 110 timesteps (reward: 110.0) | |
Finished episode 373 after 100 timesteps (reward: 100.0) | |
Finished episode 374 after 97 timesteps (reward: 97.0) | |
Finished episode 375 after 53 timesteps (reward: 53.0) | |
Finished episode 376 after 98 timesteps (reward: 98.0) | |
Finished episode 377 after 93 timesteps (reward: 93.0) | |
Finished episode 378 after 95 timesteps (reward: 95.0) | |
Finished episode 379 after 56 timesteps (reward: 56.0) | |
Finished episode 380 after 58 timesteps (reward: 58.0) | |
Finished episode 381 after 102 timesteps (reward: 102.0) | |
Finished episode 382 after 108 timesteps (reward: 108.0) | |
Finished episode 383 after 121 timesteps (reward: 121.0) | |
Finished episode 384 after 70 timesteps (reward: 70.0) | |
Finished episode 385 after 141 timesteps (reward: 141.0) | |
Finished episode 386 after 145 timesteps (reward: 145.0) | |
Finished episode 387 after 92 timesteps (reward: 92.0) | |
Finished episode 388 after 64 timesteps (reward: 64.0) | |
Finished episode 389 after 57 timesteps (reward: 57.0) | |
Finished episode 390 after 93 timesteps (reward: 93.0) | |
Finished episode 391 after 100 timesteps (reward: 100.0) | |
Finished episode 392 after 126 timesteps (reward: 126.0) | |
Finished episode 393 after 69 timesteps (reward: 69.0) | |
Finished episode 394 after 93 timesteps (reward: 93.0) | |
Finished episode 395 after 93 timesteps (reward: 93.0) | |
Finished episode 396 after 111 timesteps (reward: 111.0) | |
Finished episode 397 after 99 timesteps (reward: 99.0) | |
Finished episode 398 after 88 timesteps (reward: 88.0) | |
Finished episode 399 after 112 timesteps (reward: 112.0) | |
Finished episode 400 after 115 timesteps (reward: 115.0) | |
Finished episode 401 after 56 timesteps (reward: 56.0) | |
Finished episode 402 after 62 timesteps (reward: 62.0) | |
Finished episode 403 after 97 timesteps (reward: 97.0) | |
Finished episode 404 after 105 timesteps (reward: 105.0) | |
Finished episode 405 after 113 timesteps (reward: 113.0) | |
Finished episode 406 after 113 timesteps (reward: 113.0) | |
Finished episode 407 after 113 timesteps (reward: 113.0) | |
Finished episode 408 after 65 timesteps (reward: 65.0) | |
Finished episode 409 after 92 timesteps (reward: 92.0) | |
Finished episode 410 after 85 timesteps (reward: 85.0) | |
Finished episode 411 after 68 timesteps (reward: 68.0) | |
Finished episode 412 after 132 timesteps (reward: 132.0) | |
Finished episode 413 after 67 timesteps (reward: 67.0) | |
Finished episode 414 after 92 timesteps (reward: 92.0) | |
Finished episode 415 after 62 timesteps (reward: 62.0) | |
Finished episode 416 after 92 timesteps (reward: 92.0) | |
Finished episode 417 after 97 timesteps (reward: 97.0) | |
Finished episode 418 after 98 timesteps (reward: 98.0) | |
Finished episode 419 after 93 timesteps (reward: 93.0) | |
Finished episode 420 after 102 timesteps (reward: 102.0) | |
Finished episode 421 after 90 timesteps (reward: 90.0) | |
Finished episode 422 after 101 timesteps (reward: 101.0) | |
Finished episode 423 after 149 timesteps (reward: 149.0) | |
Finished episode 424 after 85 timesteps (reward: 85.0) | |
Finished episode 425 after 95 timesteps (reward: 95.0) | |
Finished episode 426 after 93 timesteps (reward: 93.0) | |
Finished episode 427 after 140 timesteps (reward: 140.0) | |
Finished episode 428 after 60 timesteps (reward: 60.0) | |
Finished episode 429 after 105 timesteps (reward: 105.0) | |
Finished episode 430 after 126 timesteps (reward: 126.0) | |
Finished episode 431 after 167 timesteps (reward: 167.0) | |
Finished episode 432 after 58 timesteps (reward: 58.0) | |
Finished episode 433 after 73 timesteps (reward: 73.0) | |
Finished episode 434 after 140 timesteps (reward: 140.0) | |
Finished episode 435 after 60 timesteps (reward: 60.0) | |
Finished episode 436 after 122 timesteps (reward: 122.0) | |
Finished episode 437 after 101 timesteps (reward: 101.0) | |
Finished episode 438 after 91 timesteps (reward: 91.0) | |
Finished episode 439 after 57 timesteps (reward: 57.0) | |
Finished episode 440 after 106 timesteps (reward: 106.0) | |
Finished episode 441 after 60 timesteps (reward: 60.0) | |
Finished episode 442 after 137 timesteps (reward: 137.0) | |
Finished episode 443 after 61 timesteps (reward: 61.0) | |
Finished episode 444 after 110 timesteps (reward: 110.0) | |
Finished episode 445 after 127 timesteps (reward: 127.0) | |
Finished episode 446 after 99 timesteps (reward: 99.0) | |
Finished episode 447 after 57 timesteps (reward: 57.0) | |
Finished episode 448 after 111 timesteps (reward: 111.0) | |
Finished episode 449 after 96 timesteps (reward: 96.0) | |
Finished episode 450 after 72 timesteps (reward: 72.0) | |
Finished episode 451 after 63 timesteps (reward: 63.0) | |
Finished episode 452 after 98 timesteps (reward: 98.0) | |
Finished episode 453 after 67 timesteps (reward: 67.0) | |
Finished episode 454 after 87 timesteps (reward: 87.0) | |
Finished episode 455 after 57 timesteps (reward: 57.0) | |
Finished episode 456 after 69 timesteps (reward: 69.0) | |
Finished episode 457 after 68 timesteps (reward: 68.0) | |
Finished episode 458 after 62 timesteps (reward: 62.0) | |
Finished episode 459 after 126 timesteps (reward: 126.0) | |
Finished episode 460 after 69 timesteps (reward: 69.0) | |
Finished episode 461 after 69 timesteps (reward: 69.0) | |
Finished episode 462 after 145 timesteps (reward: 145.0) | |
Finished episode 463 after 62 timesteps (reward: 62.0) | |
Finished episode 464 after 100 timesteps (reward: 100.0) | |
Finished episode 465 after 65 timesteps (reward: 65.0) | |
Finished episode 466 after 67 timesteps (reward: 67.0) | |
Finished episode 467 after 62 timesteps (reward: 62.0) | |
Finished episode 468 after 54 timesteps (reward: 54.0) | |
Finished episode 469 after 63 timesteps (reward: 63.0) | |
Finished episode 470 after 54 timesteps (reward: 54.0) | |
Finished episode 471 after 94 timesteps (reward: 94.0) | |
Finished episode 472 after 59 timesteps (reward: 59.0) | |
Finished episode 473 after 107 timesteps (reward: 107.0) | |
Finished episode 474 after 58 timesteps (reward: 58.0) | |
Finished episode 475 after 111 timesteps (reward: 111.0) | |
Finished episode 476 after 114 timesteps (reward: 114.0) | |
Finished episode 477 after 107 timesteps (reward: 107.0) | |
Finished episode 478 after 107 timesteps (reward: 107.0) | |
Finished episode 479 after 54 timesteps (reward: 54.0) | |
Finished episode 480 after 142 timesteps (reward: 142.0) | |
Finished episode 481 after 106 timesteps (reward: 106.0) | |
Finished episode 482 after 107 timesteps (reward: 107.0) | |
Finished episode 483 after 117 timesteps (reward: 117.0) | |
Finished episode 484 after 59 timesteps (reward: 59.0) | |
Finished episode 485 after 97 timesteps (reward: 97.0) | |
Finished episode 486 after 62 timesteps (reward: 62.0) | |
Finished episode 487 after 58 timesteps (reward: 58.0) | |
Finished episode 488 after 61 timesteps (reward: 61.0) | |
Finished episode 489 after 126 timesteps (reward: 126.0) | |
Finished episode 490 after 82 timesteps (reward: 82.0) | |
Finished episode 491 after 66 timesteps (reward: 66.0) | |
Finished episode 492 after 68 timesteps (reward: 68.0) | |
Finished episode 493 after 72 timesteps (reward: 72.0) | |
Finished episode 494 after 93 timesteps (reward: 93.0) | |
Finished episode 495 after 72 timesteps (reward: 72.0) | |
Finished episode 496 after 69 timesteps (reward: 69.0) | |
Finished episode 497 after 109 timesteps (reward: 109.0) | |
Finished episode 498 after 122 timesteps (reward: 122.0) | |
Finished episode 499 after 70 timesteps (reward: 70.0) | |
Finished episode 500 after 69 timesteps (reward: 69.0) | |
Finished episode 501 after 94 timesteps (reward: 94.0) | |
Finished episode 502 after 110 timesteps (reward: 110.0) | |
Finished episode 503 after 65 timesteps (reward: 65.0) | |
Finished episode 504 after 71 timesteps (reward: 71.0) | |
Finished episode 505 after 112 timesteps (reward: 112.0) | |
Finished episode 506 after 161 timesteps (reward: 161.0) | |
Finished episode 507 after 117 timesteps (reward: 117.0) | |
Finished episode 508 after 106 timesteps (reward: 106.0) | |
Finished episode 509 after 70 timesteps (reward: 70.0) | |
Finished episode 510 after 134 timesteps (reward: 134.0) | |
Finished episode 511 after 96 timesteps (reward: 96.0) | |
Finished episode 512 after 67 timesteps (reward: 67.0) | |
Finished episode 513 after 117 timesteps (reward: 117.0) | |
Finished episode 514 after 59 timesteps (reward: 59.0) | |
Finished episode 515 after 110 timesteps (reward: 110.0) | |
Finished episode 516 after 79 timesteps (reward: 79.0) | |
Finished episode 517 after 96 timesteps (reward: 96.0) | |
Finished episode 518 after 120 timesteps (reward: 120.0) | |
Finished episode 519 after 80 timesteps (reward: 80.0) | |
Finished episode 520 after 65 timesteps (reward: 65.0) | |
Finished episode 521 after 129 timesteps (reward: 129.0) | |
Finished episode 522 after 127 timesteps (reward: 127.0) | |
Finished episode 523 after 97 timesteps (reward: 97.0) | |
Finished episode 524 after 119 timesteps (reward: 119.0) | |
Finished episode 525 after 66 timesteps (reward: 66.0) | |
Finished episode 526 after 67 timesteps (reward: 67.0) | |
Finished episode 527 after 97 timesteps (reward: 97.0) | |
Finished episode 528 after 68 timesteps (reward: 68.0) | |
Finished episode 529 after 76 timesteps (reward: 76.0) | |
Finished episode 530 after 94 timesteps (reward: 94.0) | |
Finished episode 531 after 106 timesteps (reward: 106.0) | |
Finished episode 532 after 100 timesteps (reward: 100.0) | |
Finished episode 533 after 63 timesteps (reward: 63.0) | |
Finished episode 534 after 70 timesteps (reward: 70.0) | |
Finished episode 535 after 67 timesteps (reward: 67.0) | |
Finished episode 536 after 161 timesteps (reward: 161.0) | |
Finished episode 537 after 70 timesteps (reward: 70.0) | |
Finished episode 538 after 76 timesteps (reward: 76.0) | |
Finished episode 539 after 71 timesteps (reward: 71.0) | |
Finished episode 540 after 69 timesteps (reward: 69.0) | |
Finished episode 541 after 70 timesteps (reward: 70.0) | |
Finished episode 542 after 64 timesteps (reward: 64.0) | |
Finished episode 543 after 60 timesteps (reward: 60.0) | |
Finished episode 544 after 66 timesteps (reward: 66.0) | |
Finished episode 545 after 104 timesteps (reward: 104.0) | |
Finished episode 546 after 104 timesteps (reward: 104.0) | |
Finished episode 547 after 69 timesteps (reward: 69.0) | |
Finished episode 548 after 69 timesteps (reward: 69.0) | |
Finished episode 549 after 72 timesteps (reward: 72.0) | |
Finished episode 550 after 126 timesteps (reward: 126.0) | |
Finished episode 551 after 122 timesteps (reward: 122.0) | |
Finished episode 552 after 104 timesteps (reward: 104.0) | |
Finished episode 553 after 105 timesteps (reward: 105.0) | |
Finished episode 554 after 97 timesteps (reward: 97.0) | |
Finished episode 555 after 86 timesteps (reward: 86.0) | |
Finished episode 556 after 65 timesteps (reward: 65.0) | |
Finished episode 557 after 67 timesteps (reward: 67.0) | |
Finished episode 558 after 80 timesteps (reward: 80.0) | |
Finished episode 559 after 114 timesteps (reward: 114.0) | |
Finished episode 560 after 76 timesteps (reward: 76.0) | |
Finished episode 561 after 62 timesteps (reward: 62.0) | |
Finished episode 562 after 126 timesteps (reward: 126.0) | |
Finished episode 563 after 64 timesteps (reward: 64.0) | |
Finished episode 564 after 69 timesteps (reward: 69.0) | |
Finished episode 565 after 130 timesteps (reward: 130.0) | |
Finished episode 566 after 124 timesteps (reward: 124.0) | |
Finished episode 567 after 90 timesteps (reward: 90.0) | |
Finished episode 568 after 67 timesteps (reward: 67.0) | |
Finished episode 569 after 72 timesteps (reward: 72.0) | |
Finished episode 570 after 100 timesteps (reward: 100.0) | |
Finished episode 571 after 73 timesteps (reward: 73.0) | |
Finished episode 572 after 99 timesteps (reward: 99.0) | |
Finished episode 573 after 65 timesteps (reward: 65.0) | |
Finished episode 574 after 121 timesteps (reward: 121.0) | |
Finished episode 575 after 65 timesteps (reward: 65.0) | |
Finished episode 576 after 72 timesteps (reward: 72.0) | |
Finished episode 577 after 61 timesteps (reward: 61.0) | |
Finished episode 578 after 62 timesteps (reward: 62.0) | |
Finished episode 579 after 71 timesteps (reward: 71.0) | |
Finished episode 580 after 64 timesteps (reward: 64.0) | |
Finished episode 581 after 68 timesteps (reward: 68.0) | |
Finished episode 582 after 76 timesteps (reward: 76.0) | |
Finished episode 583 after 104 timesteps (reward: 104.0) | |
Finished episode 584 after 67 timesteps (reward: 67.0) | |
Finished episode 585 after 70 timesteps (reward: 70.0) | |
Finished episode 586 after 66 timesteps (reward: 66.0) | |
Finished episode 587 after 87 timesteps (reward: 87.0) | |
Finished episode 588 after 72 timesteps (reward: 72.0) | |
Finished episode 589 after 85 timesteps (reward: 85.0) | |
Finished episode 590 after 64 timesteps (reward: 64.0) | |
Finished episode 591 after 64 timesteps (reward: 64.0) | |
Finished episode 592 after 110 timesteps (reward: 110.0) | |
Finished episode 593 after 118 timesteps (reward: 118.0) | |
Finished episode 594 after 79 timesteps (reward: 79.0) | |
Finished episode 595 after 67 timesteps (reward: 67.0) | |
Finished episode 596 after 80 timesteps (reward: 80.0) | |
Finished episode 597 after 69 timesteps (reward: 69.0) | |
Finished episode 598 after 73 timesteps (reward: 73.0) | |
Finished episode 599 after 61 timesteps (reward: 61.0) | |
Finished episode 600 after 113 timesteps (reward: 113.0) | |
Finished episode 601 after 64 timesteps (reward: 64.0) | |
Finished episode 602 after 63 timesteps (reward: 63.0) | |
Finished episode 603 after 79 timesteps (reward: 79.0) | |
Finished episode 604 after 67 timesteps (reward: 67.0) | |
Finished episode 605 after 106 timesteps (reward: 106.0) | |
Finished episode 606 after 78 timesteps (reward: 78.0) | |
Finished episode 607 after 106 timesteps (reward: 106.0) | |
Finished episode 608 after 77 timesteps (reward: 77.0) | |
Finished episode 609 after 64 timesteps (reward: 64.0) | |
Finished episode 610 after 84 timesteps (reward: 84.0) | |
Finished episode 611 after 63 timesteps (reward: 63.0) | |
Finished episode 612 after 72 timesteps (reward: 72.0) | |
Finished episode 613 after 83 timesteps (reward: 83.0) | |
Finished episode 614 after 123 timesteps (reward: 123.0) | |
Finished episode 615 after 112 timesteps (reward: 112.0) | |
Finished episode 616 after 70 timesteps (reward: 70.0) | |
Finished episode 617 after 68 timesteps (reward: 68.0) | |
Finished episode 618 after 62 timesteps (reward: 62.0) | |
Finished episode 619 after 122 timesteps (reward: 122.0) | |
Finished episode 620 after 60 timesteps (reward: 60.0) | |
Finished episode 621 after 109 timesteps (reward: 109.0) | |
Finished episode 622 after 67 timesteps (reward: 67.0) | |
Finished episode 623 after 61 timesteps (reward: 61.0) | |
Finished episode 624 after 78 timesteps (reward: 78.0) | |
Finished episode 625 after 121 timesteps (reward: 121.0) | |
Finished episode 626 after 72 timesteps (reward: 72.0) | |
Finished episode 627 after 64 timesteps (reward: 64.0) | |
Finished episode 628 after 103 timesteps (reward: 103.0) | |
Finished episode 629 after 140 timesteps (reward: 140.0) | |
Finished episode 630 after 97 timesteps (reward: 97.0) | |
Finished episode 631 after 66 timesteps (reward: 66.0) | |
Finished episode 632 after 93 timesteps (reward: 93.0) | |
Finished episode 633 after 65 timesteps (reward: 65.0) | |
Finished episode 634 after 100 timesteps (reward: 100.0) | |
Finished episode 635 after 80 timesteps (reward: 80.0) | |
Finished episode 636 after 79 timesteps (reward: 79.0) | |
Finished episode 637 after 73 timesteps (reward: 73.0) | |
Finished episode 638 after 107 timesteps (reward: 107.0) | |
Finished episode 639 after 66 timesteps (reward: 66.0) | |
Finished episode 640 after 64 timesteps (reward: 64.0) | |
Finished episode 641 after 82 timesteps (reward: 82.0) | |
Finished episode 642 after 130 timesteps (reward: 130.0) | |
Finished episode 643 after 111 timesteps (reward: 111.0) | |
Finished episode 644 after 61 timesteps (reward: 61.0) | |
Finished episode 645 after 120 timesteps (reward: 120.0) | |
Finished episode 646 after 65 timesteps (reward: 65.0) | |
Finished episode 647 after 90 timesteps (reward: 90.0) | |
Finished episode 648 after 78 timesteps (reward: 78.0) | |
Finished episode 649 after 107 timesteps (reward: 107.0) | |
Finished episode 650 after 80 timesteps (reward: 80.0) | |
Finished episode 651 after 112 timesteps (reward: 112.0) | |
Finished episode 652 after 103 timesteps (reward: 103.0) | |
Finished episode 653 after 109 timesteps (reward: 109.0) | |
Finished episode 654 after 66 timesteps (reward: 66.0) | |
Finished episode 655 after 103 timesteps (reward: 103.0) | |
Finished episode 656 after 99 timesteps (reward: 99.0) | |
Finished episode 657 after 114 timesteps (reward: 114.0) | |
Finished episode 658 after 119 timesteps (reward: 119.0) | |
Finished episode 659 after 71 timesteps (reward: 71.0) | |
Finished episode 660 after 132 timesteps (reward: 132.0) | |
Finished episode 661 after 108 timesteps (reward: 108.0) | |
Finished episode 662 after 68 timesteps (reward: 68.0) | |
Finished episode 663 after 95 timesteps (reward: 95.0) | |
Finished episode 664 after 65 timesteps (reward: 65.0) | |
Finished episode 665 after 71 timesteps (reward: 71.0) | |
Finished episode 666 after 90 timesteps (reward: 90.0) | |
Finished episode 667 after 117 timesteps (reward: 117.0) | |
Finished episode 668 after 112 timesteps (reward: 112.0) | |
Finished episode 669 after 61 timesteps (reward: 61.0) | |
Finished episode 670 after 102 timesteps (reward: 102.0) | |
Finished episode 671 after 67 timesteps (reward: 67.0) | |
Finished episode 672 after 102 timesteps (reward: 102.0) | |
Finished episode 673 after 71 timesteps (reward: 71.0) | |
Finished episode 674 after 67 timesteps (reward: 67.0) | |
Finished episode 675 after 68 timesteps (reward: 68.0) | |
Finished episode 676 after 64 timesteps (reward: 64.0) | |
Finished episode 677 after 68 timesteps (reward: 68.0) | |
Finished episode 678 after 77 timesteps (reward: 77.0) | |
Finished episode 679 after 124 timesteps (reward: 124.0) | |
Finished episode 680 after 123 timesteps (reward: 123.0) | |
Finished episode 681 after 64 timesteps (reward: 64.0) | |
Finished episode 682 after 80 timesteps (reward: 80.0) | |
Finished episode 683 after 71 timesteps (reward: 71.0) | |
Finished episode 684 after 77 timesteps (reward: 77.0) | |
Finished episode 685 after 103 timesteps (reward: 103.0) | |
Finished episode 686 after 63 timesteps (reward: 63.0) | |
Finished episode 687 after 107 timesteps (reward: 107.0) | |
Finished episode 688 after 62 timesteps (reward: 62.0) | |
Finished episode 689 after 61 timesteps (reward: 61.0) | |
Finished episode 690 after 112 timesteps (reward: 112.0) | |
Finished episode 691 after 94 timesteps (reward: 94.0) | |
Finished episode 692 after 68 timesteps (reward: 68.0) | |
Finished episode 693 after 136 timesteps (reward: 136.0) | |
Finished episode 694 after 62 timesteps (reward: 62.0) | |
Finished episode 695 after 64 timesteps (reward: 64.0) | |
Finished episode 696 after 66 timesteps (reward: 66.0) | |
Finished episode 697 after 66 timesteps (reward: 66.0) | |
Finished episode 698 after 92 timesteps (reward: 92.0) | |
Finished episode 699 after 108 timesteps (reward: 108.0) | |
Finished episode 700 after 104 timesteps (reward: 104.0) | |
Finished episode 701 after 107 timesteps (reward: 107.0) | |
Finished episode 702 after 87 timesteps (reward: 87.0) | |
Finished episode 703 after 65 timesteps (reward: 65.0) | |
Finished episode 704 after 107 timesteps (reward: 107.0) | |
Finished episode 705 after 110 timesteps (reward: 110.0) | |
Finished episode 706 after 109 timesteps (reward: 109.0) | |
Finished episode 707 after 104 timesteps (reward: 104.0) | |
Finished episode 708 after 119 timesteps (reward: 119.0) | |
Finished episode 709 after 102 timesteps (reward: 102.0) | |
Finished episode 710 after 65 timesteps (reward: 65.0) | |
Finished episode 711 after 66 timesteps (reward: 66.0) | |
Finished episode 712 after 63 timesteps (reward: 63.0) | |
Finished episode 713 after 113 timesteps (reward: 113.0) | |
Finished episode 714 after 68 timesteps (reward: 68.0) | |
Finished episode 715 after 125 timesteps (reward: 125.0) | |
Finished episode 716 after 65 timesteps (reward: 65.0) | |
Finished episode 717 after 107 timesteps (reward: 107.0) | |
Finished episode 718 after 107 timesteps (reward: 107.0) | |
Finished episode 719 after 107 timesteps (reward: 107.0) | |
Finished episode 720 after 69 timesteps (reward: 69.0) | |
Finished episode 721 after 65 timesteps (reward: 65.0) | |
Finished episode 722 after 108 timesteps (reward: 108.0) | |
Finished episode 723 after 67 timesteps (reward: 67.0) | |
Finished episode 724 after 124 timesteps (reward: 124.0) | |
Finished episode 725 after 66 timesteps (reward: 66.0) | |
Finished episode 726 after 111 timesteps (reward: 111.0) | |
Finished episode 727 after 71 timesteps (reward: 71.0) | |
Finished episode 728 after 74 timesteps (reward: 74.0) | |
Finished episode 729 after 106 timesteps (reward: 106.0) | |
Finished episode 730 after 114 timesteps (reward: 114.0) | |
Finished episode 731 after 59 timesteps (reward: 59.0) | |
Finished episode 732 after 100 timesteps (reward: 100.0) | |
Finished episode 733 after 111 timesteps (reward: 111.0) | |
Finished episode 734 after 85 timesteps (reward: 85.0) | |
Finished episode 735 after 70 timesteps (reward: 70.0) | |
Finished episode 736 after 120 timesteps (reward: 120.0) | |
Finished episode 737 after 121 timesteps (reward: 121.0) | |
Finished episode 738 after 112 timesteps (reward: 112.0) | |
Finished episode 739 after 100 timesteps (reward: 100.0) | |
Finished episode 740 after 65 timesteps (reward: 65.0) | |
Finished episode 741 after 63 timesteps (reward: 63.0) | |
Finished episode 742 after 108 timesteps (reward: 108.0) | |
Finished episode 743 after 62 timesteps (reward: 62.0) | |
Finished episode 744 after 60 timesteps (reward: 60.0) | |
Finished episode 745 after 87 timesteps (reward: 87.0) | |
Finished episode 746 after 62 timesteps (reward: 62.0) | |
Finished episode 747 after 105 timesteps (reward: 105.0) | |
Finished episode 748 after 96 timesteps (reward: 96.0) | |
Finished episode 749 after 66 timesteps (reward: 66.0) | |
Finished episode 750 after 89 timesteps (reward: 89.0) | |
Finished episode 751 after 65 timesteps (reward: 65.0) | |
Finished episode 752 after 109 timesteps (reward: 109.0) | |
Finished episode 753 after 85 timesteps (reward: 85.0) | |
Finished episode 754 after 140 timesteps (reward: 140.0) | |
Finished episode 755 after 125 timesteps (reward: 125.0) | |
Finished episode 756 after 102 timesteps (reward: 102.0) | |
Finished episode 757 after 63 timesteps (reward: 63.0) | |
Finished episode 758 after 111 timesteps (reward: 111.0) | |
Finished episode 759 after 99 timesteps (reward: 99.0) | |
Finished episode 760 after 67 timesteps (reward: 67.0) | |
Finished episode 761 after 62 timesteps (reward: 62.0) | |
Finished episode 762 after 63 timesteps (reward: 63.0) | |
Finished episode 763 after 104 timesteps (reward: 104.0) | |
Finished episode 764 after 117 timesteps (reward: 117.0) | |
Finished episode 765 after 114 timesteps (reward: 114.0) | |
Finished episode 766 after 64 timesteps (reward: 64.0) | |
Finished episode 767 after 63 timesteps (reward: 63.0) | |
Finished episode 768 after 99 timesteps (reward: 99.0) | |
Finished episode 769 after 119 timesteps (reward: 119.0) | |
Finished episode 770 after 61 timesteps (reward: 61.0) | |
Finished episode 771 after 70 timesteps (reward: 70.0) | |
Finished episode 772 after 108 timesteps (reward: 108.0) | |
Finished episode 773 after 108 timesteps (reward: 108.0) | |
Finished episode 774 after 111 timesteps (reward: 111.0) | |
Finished episode 775 after 63 timesteps (reward: 63.0) | |
Finished episode 776 after 64 timesteps (reward: 64.0) | |
Finished episode 777 after 105 timesteps (reward: 105.0) | |
Finished episode 778 after 103 timesteps (reward: 103.0) | |
Finished episode 779 after 138 timesteps (reward: 138.0) | |
Finished episode 780 after 70 timesteps (reward: 70.0) | |
Finished episode 781 after 104 timesteps (reward: 104.0) | |
Finished episode 782 after 64 timesteps (reward: 64.0) | |
Finished episode 783 after 100 timesteps (reward: 100.0) | |
Finished episode 784 after 112 timesteps (reward: 112.0) | |
Finished episode 785 after 64 timesteps (reward: 64.0) | |
Finished episode 786 after 107 timesteps (reward: 107.0) | |
Finished episode 787 after 89 timesteps (reward: 89.0) | |
Finished episode 788 after 68 timesteps (reward: 68.0) | |
Finished episode 789 after 65 timesteps (reward: 65.0) | |
Finished episode 790 after 61 timesteps (reward: 61.0) | |
Finished episode 791 after 117 timesteps (reward: 117.0) | |
Finished episode 792 after 122 timesteps (reward: 122.0) | |
Finished episode 793 after 111 timesteps (reward: 111.0) | |
Finished episode 794 after 65 timesteps (reward: 65.0) | |
Finished episode 795 after 69 timesteps (reward: 69.0) | |
Finished episode 796 after 116 timesteps (reward: 116.0) | |
Finished episode 797 after 102 timesteps (reward: 102.0) | |
Finished episode 798 after 109 timesteps (reward: 109.0) | |
Finished episode 799 after 63 timesteps (reward: 63.0) | |
Finished episode 800 after 110 timesteps (reward: 110.0) | |
Finished episode 801 after 69 timesteps (reward: 69.0) | |
Finished episode 802 after 63 timesteps (reward: 63.0) | |
Finished episode 803 after 108 timesteps (reward: 108.0) | |
Finished episode 804 after 123 timesteps (reward: 123.0) | |
Finished episode 805 after 110 timesteps (reward: 110.0) | |
Finished episode 806 after 106 timesteps (reward: 106.0) | |
Finished episode 807 after 88 timesteps (reward: 88.0) | |
Finished episode 808 after 66 timesteps (reward: 66.0) | |
Finished episode 809 after 107 timesteps (reward: 107.0) | |
Finished episode 810 after 119 timesteps (reward: 119.0) | |
Finished episode 811 after 66 timesteps (reward: 66.0) | |
Finished episode 812 after 60 timesteps (reward: 60.0) | |
Finished episode 813 after 100 timesteps (reward: 100.0) | |
Finished episode 814 after 168 timesteps (reward: 168.0) | |
Finished episode 815 after 122 timesteps (reward: 122.0) | |
Finished episode 816 after 113 timesteps (reward: 113.0) | |
Finished episode 817 after 121 timesteps (reward: 121.0) | |
Finished episode 818 after 121 timesteps (reward: 121.0) | |
Finished episode 819 after 62 timesteps (reward: 62.0) | |
Finished episode 820 after 60 timesteps (reward: 60.0) | |
Finished episode 821 after 106 timesteps (reward: 106.0) | |
Finished episode 822 after 109 timesteps (reward: 109.0) | |
Finished episode 823 after 116 timesteps (reward: 116.0) | |
Finished episode 824 after 140 timesteps (reward: 140.0) | |
Finished episode 825 after 102 timesteps (reward: 102.0) | |
Finished episode 826 after 63 timesteps (reward: 63.0) | |
Finished episode 827 after 120 timesteps (reward: 120.0) | |
Finished episode 828 after 120 timesteps (reward: 120.0) | |
Finished episode 829 after 136 timesteps (reward: 136.0) | |
Finished episode 830 after 114 timesteps (reward: 114.0) | |
Finished episode 831 after 137 timesteps (reward: 137.0) | |
Finished episode 832 after 113 timesteps (reward: 113.0) | |
Finished episode 833 after 131 timesteps (reward: 131.0) | |
Finished episode 834 after 68 timesteps (reward: 68.0) | |
Finished episode 835 after 107 timesteps (reward: 107.0) | |
Finished episode 836 after 67 timesteps (reward: 67.0) | |
Finished episode 837 after 106 timesteps (reward: 106.0) | |
Finished episode 838 after 100 timesteps (reward: 100.0) | |
Finished episode 839 after 128 timesteps (reward: 128.0) | |
Finished episode 840 after 111 timesteps (reward: 111.0) | |
Finished episode 841 after 71 timesteps (reward: 71.0) | |
Finished episode 842 after 100 timesteps (reward: 100.0) | |
Finished episode 843 after 100 timesteps (reward: 100.0) | |
Finished episode 844 after 111 timesteps (reward: 111.0) | |
Finished episode 845 after 64 timesteps (reward: 64.0) | |
Finished episode 846 after 104 timesteps (reward: 104.0) | |
Finished episode 847 after 128 timesteps (reward: 128.0) | |
Finished episode 848 after 68 timesteps (reward: 68.0) | |
Finished episode 849 after 101 timesteps (reward: 101.0) | |
Finished episode 850 after 131 timesteps (reward: 131.0) | |
Finished episode 851 after 108 timesteps (reward: 108.0) | |
Finished episode 852 after 127 timesteps (reward: 127.0) | |
Finished episode 853 after 116 timesteps (reward: 116.0) | |
Finished episode 854 after 104 timesteps (reward: 104.0) | |
Finished episode 855 after 103 timesteps (reward: 103.0) | |
Finished episode 856 after 115 timesteps (reward: 115.0) | |
Finished episode 857 after 102 timesteps (reward: 102.0) | |
Finished episode 858 after 98 timesteps (reward: 98.0) | |
Finished episode 859 after 119 timesteps (reward: 119.0) | |
Finished episode 860 after 103 timesteps (reward: 103.0) | |
Finished episode 861 after 64 timesteps (reward: 64.0) | |
Finished episode 862 after 102 timesteps (reward: 102.0) | |
Finished episode 863 after 100 timesteps (reward: 100.0) | |
Finished episode 864 after 124 timesteps (reward: 124.0) | |
Finished episode 865 after 125 timesteps (reward: 125.0) | |
Finished episode 866 after 108 timesteps (reward: 108.0) | |
Finished episode 867 after 105 timesteps (reward: 105.0) | |
Finished episode 868 after 118 timesteps (reward: 118.0) | |
Finished episode 869 after 62 timesteps (reward: 62.0) | |
Finished episode 870 after 147 timesteps (reward: 147.0) | |
Finished episode 871 after 128 timesteps (reward: 128.0) | |
Finished episode 872 after 58 timesteps (reward: 58.0) | |
Finished episode 873 after 103 timesteps (reward: 103.0) | |
Finished episode 874 after 106 timesteps (reward: 106.0) | |
Finished episode 875 after 62 timesteps (reward: 62.0) | |
Finished episode 876 after 108 timesteps (reward: 108.0) | |
Finished episode 877 after 101 timesteps (reward: 101.0) | |
Finished episode 878 after 68 timesteps (reward: 68.0) | |
Finished episode 879 after 67 timesteps (reward: 67.0) | |
Finished episode 880 after 200 timesteps (reward: 200.0) | |
Finished episode 881 after 106 timesteps (reward: 106.0) | |
Finished episode 882 after 115 timesteps (reward: 115.0) | |
Finished episode 883 after 105 timesteps (reward: 105.0) | |
Finished episode 884 after 96 timesteps (reward: 96.0) | |
Finished episode 885 after 62 timesteps (reward: 62.0) | |
Finished episode 886 after 100 timesteps (reward: 100.0) | |
Finished episode 887 after 103 timesteps (reward: 103.0) | |
Finished episode 888 after 62 timesteps (reward: 62.0) | |
Finished episode 889 after 66 timesteps (reward: 66.0) | |
Finished episode 890 after 153 timesteps (reward: 153.0) | |
Finished episode 891 after 120 timesteps (reward: 120.0) | |
Finished episode 892 after 112 timesteps (reward: 112.0) | |
Finished episode 893 after 153 timesteps (reward: 153.0) | |
Finished episode 894 after 161 timesteps (reward: 161.0) | |
Finished episode 895 after 103 timesteps (reward: 103.0) | |
Finished episode 896 after 105 timesteps (reward: 105.0) | |
Finished episode 897 after 108 timesteps (reward: 108.0) | |
Finished episode 898 after 60 timesteps (reward: 60.0) | |
Finished episode 899 after 100 timesteps (reward: 100.0) | |
Finished episode 900 after 103 timesteps (reward: 103.0) | |
Finished episode 901 after 135 timesteps (reward: 135.0) | |
Finished episode 902 after 104 timesteps (reward: 104.0) | |
Finished episode 903 after 126 timesteps (reward: 126.0) | |
Finished episode 904 after 184 timesteps (reward: 184.0) | |
Finished episode 905 after 102 timesteps (reward: 102.0) | |
Finished episode 906 after 104 timesteps (reward: 104.0) | |
Finished episode 907 after 115 timesteps (reward: 115.0) | |
Finished episode 908 after 152 timesteps (reward: 152.0) | |
Finished episode 909 after 93 timesteps (reward: 93.0) | |
Finished episode 910 after 112 timesteps (reward: 112.0) | |
Finished episode 911 after 140 timesteps (reward: 140.0) | |
Finished episode 912 after 138 timesteps (reward: 138.0) | |
Finished episode 913 after 159 timesteps (reward: 159.0) | |
Finished episode 914 after 106 timesteps (reward: 106.0) | |
Finished episode 915 after 144 timesteps (reward: 144.0) | |
Finished episode 916 after 168 timesteps (reward: 168.0) | |
Finished episode 917 after 100 timesteps (reward: 100.0) | |
Finished episode 918 after 99 timesteps (reward: 99.0) | |
Finished episode 919 after 103 timesteps (reward: 103.0) | |
Finished episode 920 after 136 timesteps (reward: 136.0) | |
Finished episode 921 after 144 timesteps (reward: 144.0) | |
Finished episode 922 after 146 timesteps (reward: 146.0) | |
Finished episode 923 after 153 timesteps (reward: 153.0) | |
Finished episode 924 after 105 timesteps (reward: 105.0) | |
Finished episode 925 after 101 timesteps (reward: 101.0) | |
Finished episode 926 after 103 timesteps (reward: 103.0) | |
Finished episode 927 after 101 timesteps (reward: 101.0) | |
Finished episode 928 after 137 timesteps (reward: 137.0) | |
Finished episode 929 after 98 timesteps (reward: 98.0) | |
Finished episode 930 after 117 timesteps (reward: 117.0) | |
Finished episode 931 after 105 timesteps (reward: 105.0) | |
Finished episode 932 after 63 timesteps (reward: 63.0) | |
Finished episode 933 after 154 timesteps (reward: 154.0) | |
Finished episode 934 after 138 timesteps (reward: 138.0) | |
Finished episode 935 after 106 timesteps (reward: 106.0) | |
Finished episode 936 after 110 timesteps (reward: 110.0) | |
Finished episode 937 after 119 timesteps (reward: 119.0) | |
Finished episode 938 after 120 timesteps (reward: 120.0) | |
Finished episode 939 after 193 timesteps (reward: 193.0) | |
Finished episode 940 after 112 timesteps (reward: 112.0) | |
Finished episode 941 after 99 timesteps (reward: 99.0) | |
Finished episode 942 after 101 timesteps (reward: 101.0) | |
Finished episode 943 after 115 timesteps (reward: 115.0) | |
Finished episode 944 after 173 timesteps (reward: 173.0) | |
Finished episode 945 after 155 timesteps (reward: 155.0) | |
Finished episode 946 after 109 timesteps (reward: 109.0) | |
Finished episode 947 after 137 timesteps (reward: 137.0) | |
Finished episode 948 after 173 timesteps (reward: 173.0) | |
Finished episode 949 after 162 timesteps (reward: 162.0) | |
Finished episode 950 after 99 timesteps (reward: 99.0) | |
Finished episode 951 after 97 timesteps (reward: 97.0) | |
Finished episode 952 after 160 timesteps (reward: 160.0) | |
Finished episode 953 after 63 timesteps (reward: 63.0) | |
Finished episode 954 after 159 timesteps (reward: 159.0) | |
Finished episode 955 after 149 timesteps (reward: 149.0) | |
Finished episode 956 after 133 timesteps (reward: 133.0) | |
Finished episode 957 after 149 timesteps (reward: 149.0) | |
Finished episode 958 after 141 timesteps (reward: 141.0) | |
Finished episode 959 after 133 timesteps (reward: 133.0) | |
Finished episode 960 after 162 timesteps (reward: 162.0) | |
Finished episode 961 after 101 timesteps (reward: 101.0) | |
Finished episode 962 after 113 timesteps (reward: 113.0) | |
Finished episode 963 after 105 timesteps (reward: 105.0) | |
Finished episode 964 after 177 timesteps (reward: 177.0) | |
Finished episode 965 after 149 timesteps (reward: 149.0) | |
Finished episode 966 after 106 timesteps (reward: 106.0) | |
Finished episode 967 after 200 timesteps (reward: 200.0) | |
Finished episode 968 after 200 timesteps (reward: 200.0) | |
Finished episode 969 after 200 timesteps (reward: 200.0) | |
Finished episode 970 after 140 timesteps (reward: 140.0) | |
Finished episode 971 after 169 timesteps (reward: 169.0) | |
Finished episode 972 after 144 timesteps (reward: 144.0) | |
Finished episode 973 after 97 timesteps (reward: 97.0) | |
Finished episode 974 after 110 timesteps (reward: 110.0) | |
Finished episode 975 after 143 timesteps (reward: 143.0) | |
Finished episode 976 after 99 timesteps (reward: 99.0) | |
Finished episode 977 after 199 timesteps (reward: 199.0) | |
Finished episode 978 after 110 timesteps (reward: 110.0) | |
Finished episode 979 after 200 timesteps (reward: 200.0) | |
Finished episode 980 after 151 timesteps (reward: 151.0) | |
Finished episode 981 after 105 timesteps (reward: 105.0) | |
Finished episode 982 after 155 timesteps (reward: 155.0) | |
Finished episode 983 after 108 timesteps (reward: 108.0) | |
Finished episode 984 after 128 timesteps (reward: 128.0) | |
Finished episode 985 after 154 timesteps (reward: 154.0) | |
Finished episode 986 after 194 timesteps (reward: 194.0) | |
Finished episode 987 after 166 timesteps (reward: 166.0) | |
Finished episode 988 after 149 timesteps (reward: 149.0) | |
Finished episode 989 after 95 timesteps (reward: 95.0) | |
Finished episode 990 after 136 timesteps (reward: 136.0) | |
Finished episode 991 after 131 timesteps (reward: 131.0) | |
Finished episode 992 after 112 timesteps (reward: 112.0) | |
Finished episode 993 after 170 timesteps (reward: 170.0) | |
Finished episode 994 after 155 timesteps (reward: 155.0) | |
Finished episode 995 after 200 timesteps (reward: 200.0) | |
Finished episode 996 after 135 timesteps (reward: 135.0) | |
Finished episode 997 after 122 timesteps (reward: 122.0) | |
Finished episode 998 after 128 timesteps (reward: 128.0) | |
Finished episode 999 after 103 timesteps (reward: 103.0) | |
Finished episode 1000 after 140 timesteps (reward: 140.0) | |
Finished episode 1001 after 101 timesteps (reward: 101.0) | |
Finished episode 1002 after 146 timesteps (reward: 146.0) | |
Finished episode 1003 after 100 timesteps (reward: 100.0) | |
Finished episode 1004 after 108 timesteps (reward: 108.0) | |
Finished episode 1005 after 200 timesteps (reward: 200.0) | |
Finished episode 1006 after 126 timesteps (reward: 126.0) | |
Finished episode 1007 after 125 timesteps (reward: 125.0) | |
Finished episode 1008 after 110 timesteps (reward: 110.0) | |
Finished episode 1009 after 137 timesteps (reward: 137.0) | |
Finished episode 1010 after 124 timesteps (reward: 124.0) | |
Finished episode 1011 after 132 timesteps (reward: 132.0) | |
Finished episode 1012 after 105 timesteps (reward: 105.0) | |
Finished episode 1013 after 97 timesteps (reward: 97.0) | |
Finished episode 1014 after 144 timesteps (reward: 144.0) | |
Finished episode 1015 after 165 timesteps (reward: 165.0) | |
Finished episode 1016 after 125 timesteps (reward: 125.0) | |
Finished episode 1017 after 177 timesteps (reward: 177.0) | |
Finished episode 1018 after 186 timesteps (reward: 186.0) | |
Finished episode 1019 after 116 timesteps (reward: 116.0) | |
Finished episode 1020 after 127 timesteps (reward: 127.0) | |
Finished episode 1021 after 133 timesteps (reward: 133.0) | |
Finished episode 1022 after 131 timesteps (reward: 131.0) | |
Finished episode 1023 after 200 timesteps (reward: 200.0) | |
Finished episode 1024 after 136 timesteps (reward: 136.0) | |
Finished episode 1025 after 200 timesteps (reward: 200.0) | |
Finished episode 1026 after 131 timesteps (reward: 131.0) | |
Finished episode 1027 after 97 timesteps (reward: 97.0) | |
Finished episode 1028 after 200 timesteps (reward: 200.0) | |
Finished episode 1029 after 95 timesteps (reward: 95.0) | |
Finished episode 1030 after 174 timesteps (reward: 174.0) | |
Finished episode 1031 after 155 timesteps (reward: 155.0) | |
Finished episode 1032 after 132 timesteps (reward: 132.0) | |
Finished episode 1033 after 200 timesteps (reward: 200.0) | |
Finished episode 1034 after 151 timesteps (reward: 151.0) | |
Finished episode 1035 after 92 timesteps (reward: 92.0) | |
Finished episode 1036 after 128 timesteps (reward: 128.0) | |
Finished episode 1037 after 173 timesteps (reward: 173.0) | |
Finished episode 1038 after 127 timesteps (reward: 127.0) | |
Finished episode 1039 after 152 timesteps (reward: 152.0) | |
Finished episode 1040 after 145 timesteps (reward: 145.0) | |
Finished episode 1041 after 174 timesteps (reward: 174.0) | |
Finished episode 1042 after 131 timesteps (reward: 131.0) | |
Finished episode 1043 after 138 timesteps (reward: 138.0) | |
Finished episode 1044 after 153 timesteps (reward: 153.0) | |
Finished episode 1045 after 140 timesteps (reward: 140.0) | |
Finished episode 1046 after 127 timesteps (reward: 127.0) | |
Finished episode 1047 after 128 timesteps (reward: 128.0) | |
Finished episode 1048 after 168 timesteps (reward: 168.0) | |
Finished episode 1049 after 200 timesteps (reward: 200.0) | |
Finished episode 1050 after 129 timesteps (reward: 129.0) | |
Finished episode 1051 after 127 timesteps (reward: 127.0) | |
Finished episode 1052 after 147 timesteps (reward: 147.0) | |
Finished episode 1053 after 134 timesteps (reward: 134.0) | |
Finished episode 1054 after 122 timesteps (reward: 122.0) | |
Finished episode 1055 after 151 timesteps (reward: 151.0) | |
Finished episode 1056 after 152 timesteps (reward: 152.0) | |
Finished episode 1057 after 139 timesteps (reward: 139.0) | |
Finished episode 1058 after 159 timesteps (reward: 159.0) | |
Finished episode 1059 after 200 timesteps (reward: 200.0) | |
Finished episode 1060 after 119 timesteps (reward: 119.0) | |
Finished episode 1061 after 101 timesteps (reward: 101.0) | |
Finished episode 1062 after 116 timesteps (reward: 116.0) | |
Finished episode 1063 after 144 timesteps (reward: 144.0) | |
Finished episode 1064 after 142 timesteps (reward: 142.0) | |
Finished episode 1065 after 133 timesteps (reward: 133.0) | |
Finished episode 1066 after 140 timesteps (reward: 140.0) | |
Finished episode 1067 after 123 timesteps (reward: 123.0) | |
Finished episode 1068 after 198 timesteps (reward: 198.0) | |
Finished episode 1069 after 200 timesteps (reward: 200.0) | |
Finished episode 1070 after 140 timesteps (reward: 140.0) | |
Finished episode 1071 after 163 timesteps (reward: 163.0) | |
Finished episode 1072 after 119 timesteps (reward: 119.0) | |
Finished episode 1073 after 125 timesteps (reward: 125.0) | |
Finished episode 1074 after 164 timesteps (reward: 164.0) | |
Finished episode 1075 after 97 timesteps (reward: 97.0) | |
Finished episode 1076 after 106 timesteps (reward: 106.0) | |
Finished episode 1077 after 127 timesteps (reward: 127.0) | |
Finished episode 1078 after 182 timesteps (reward: 182.0) | |
Finished episode 1079 after 135 timesteps (reward: 135.0) | |
Finished episode 1080 after 125 timesteps (reward: 125.0) | |
Finished episode 1081 after 124 timesteps (reward: 124.0) | |
Finished episode 1082 after 124 timesteps (reward: 124.0) | |
Finished episode 1083 after 118 timesteps (reward: 118.0) | |
Finished episode 1084 after 137 timesteps (reward: 137.0) | |
Finished episode 1085 after 131 timesteps (reward: 131.0) | |
Finished episode 1086 after 153 timesteps (reward: 153.0) | |
Finished episode 1087 after 153 timesteps (reward: 153.0) | |
Finished episode 1088 after 135 timesteps (reward: 135.0) | |
Finished episode 1089 after 167 timesteps (reward: 167.0) | |
Finished episode 1090 after 128 timesteps (reward: 128.0) | |
Finished episode 1091 after 163 timesteps (reward: 163.0) | |
Finished episode 1092 after 147 timesteps (reward: 147.0) | |
Finished episode 1093 after 163 timesteps (reward: 163.0) | |
Finished episode 1094 after 189 timesteps (reward: 189.0) | |
Finished episode 1095 after 200 timesteps (reward: 200.0) | |
Finished episode 1096 after 142 timesteps (reward: 142.0) | |
Finished episode 1097 after 153 timesteps (reward: 153.0) | |
Finished episode 1098 after 200 timesteps (reward: 200.0) | |
Finished episode 1099 after 106 timesteps (reward: 106.0) | |
Finished episode 1100 after 179 timesteps (reward: 179.0) | |
Finished episode 1101 after 198 timesteps (reward: 198.0) | |
Finished episode 1102 after 170 timesteps (reward: 170.0) | |
Finished episode 1103 after 200 timesteps (reward: 200.0) | |
Finished episode 1104 after 149 timesteps (reward: 149.0) | |
Finished episode 1105 after 164 timesteps (reward: 164.0) | |
Finished episode 1106 after 166 timesteps (reward: 166.0) | |
Finished episode 1107 after 108 timesteps (reward: 108.0) | |
Finished episode 1108 after 200 timesteps (reward: 200.0) | |
Finished episode 1109 after 180 timesteps (reward: 180.0) | |
Finished episode 1110 after 200 timesteps (reward: 200.0) | |
Finished episode 1111 after 156 timesteps (reward: 156.0) | |
Finished episode 1112 after 129 timesteps (reward: 129.0) | |
Finished episode 1113 after 159 timesteps (reward: 159.0) | |
Finished episode 1114 after 137 timesteps (reward: 137.0) | |
Finished episode 1115 after 188 timesteps (reward: 188.0) | |
Finished episode 1116 after 119 timesteps (reward: 119.0) | |
Finished episode 1117 after 200 timesteps (reward: 200.0) | |
Finished episode 1118 after 194 timesteps (reward: 194.0) | |
Finished episode 1119 after 129 timesteps (reward: 129.0) | |
Finished episode 1120 after 128 timesteps (reward: 128.0) | |
Finished episode 1121 after 120 timesteps (reward: 120.0) | |
Finished episode 1122 after 200 timesteps (reward: 200.0) | |
Finished episode 1123 after 200 timesteps (reward: 200.0) | |
Finished episode 1124 after 175 timesteps (reward: 175.0) | |
Finished episode 1125 after 143 timesteps (reward: 143.0) | |
Finished episode 1126 after 169 timesteps (reward: 169.0) | |
Finished episode 1127 after 144 timesteps (reward: 144.0) | |
Finished episode 1128 after 186 timesteps (reward: 186.0) | |
Finished episode 1129 after 197 timesteps (reward: 197.0) | |
Finished episode 1130 after 155 timesteps (reward: 155.0) | |
Finished episode 1131 after 155 timesteps (reward: 155.0) | |
Finished episode 1132 after 175 timesteps (reward: 175.0) | |
Finished episode 1133 after 141 timesteps (reward: 141.0) | |
Finished episode 1134 after 146 timesteps (reward: 146.0) | |
Finished episode 1135 after 200 timesteps (reward: 200.0) | |
Finished episode 1136 after 138 timesteps (reward: 138.0) | |
Finished episode 1137 after 200 timesteps (reward: 200.0) | |
Finished episode 1138 after 126 timesteps (reward: 126.0) | |
Finished episode 1139 after 200 timesteps (reward: 200.0) | |
Finished episode 1140 after 194 timesteps (reward: 194.0) | |
Finished episode 1141 after 200 timesteps (reward: 200.0) | |
Finished episode 1142 after 142 timesteps (reward: 142.0) | |
Finished episode 1143 after 200 timesteps (reward: 200.0) | |
Finished episode 1144 after 160 timesteps (reward: 160.0) | |
Finished episode 1145 after 143 timesteps (reward: 143.0) | |
Finished episode 1146 after 163 timesteps (reward: 163.0) | |
Finished episode 1147 after 130 timesteps (reward: 130.0) | |
Finished episode 1148 after 200 timesteps (reward: 200.0) | |
Finished episode 1149 after 105 timesteps (reward: 105.0) | |
Finished episode 1150 after 172 timesteps (reward: 172.0) | |
Finished episode 1151 after 160 timesteps (reward: 160.0) | |
Finished episode 1152 after 157 timesteps (reward: 157.0) | |
Finished episode 1153 after 117 timesteps (reward: 117.0) | |
Finished episode 1154 after 186 timesteps (reward: 186.0) | |
Finished episode 1155 after 161 timesteps (reward: 161.0) | |
Finished episode 1156 after 156 timesteps (reward: 156.0) | |
Finished episode 1157 after 191 timesteps (reward: 191.0) | |
Finished episode 1158 after 129 timesteps (reward: 129.0) | |
Finished episode 1159 after 135 timesteps (reward: 135.0) | |
Finished episode 1160 after 126 timesteps (reward: 126.0) | |
Finished episode 1161 after 132 timesteps (reward: 132.0) | |
Finished episode 1162 after 126 timesteps (reward: 126.0) | |
Finished episode 1163 after 200 timesteps (reward: 200.0) | |
Finished episode 1164 after 177 timesteps (reward: 177.0) | |
Finished episode 1165 after 167 timesteps (reward: 167.0) | |
Finished episode 1166 after 159 timesteps (reward: 159.0) | |
Finished episode 1167 after 110 timesteps (reward: 110.0) | |
Finished episode 1168 after 137 timesteps (reward: 137.0) | |
Finished episode 1169 after 200 timesteps (reward: 200.0) | |
Finished episode 1170 after 200 timesteps (reward: 200.0) | |
Finished episode 1171 after 136 timesteps (reward: 136.0) | |
Finished episode 1172 after 200 timesteps (reward: 200.0) | |
Finished episode 1173 after 200 timesteps (reward: 200.0) | |
Finished episode 1174 after 193 timesteps (reward: 193.0) | |
Finished episode 1175 after 159 timesteps (reward: 159.0) | |
Finished episode 1176 after 128 timesteps (reward: 128.0) | |
Finished episode 1177 after 200 timesteps (reward: 200.0) | |
Finished episode 1178 after 141 timesteps (reward: 141.0) | |
Finished episode 1179 after 200 timesteps (reward: 200.0) | |
Finished episode 1180 after 125 timesteps (reward: 125.0) | |
Finished episode 1181 after 161 timesteps (reward: 161.0) | |
Finished episode 1182 after 156 timesteps (reward: 156.0) | |
Finished episode 1183 after 168 timesteps (reward: 168.0) | |
Finished episode 1184 after 200 timesteps (reward: 200.0) | |
Finished episode 1185 after 154 timesteps (reward: 154.0) | |
Finished episode 1186 after 200 timesteps (reward: 200.0) | |
Finished episode 1187 after 142 timesteps (reward: 142.0) | |
Finished episode 1188 after 119 timesteps (reward: 119.0) | |
Finished episode 1189 after 148 timesteps (reward: 148.0) | |
Finished episode 1190 after 200 timesteps (reward: 200.0) | |
Finished episode 1191 after 200 timesteps (reward: 200.0) | |
Finished episode 1192 after 150 timesteps (reward: 150.0) | |
Finished episode 1193 after 127 timesteps (reward: 127.0) | |
Finished episode 1194 after 200 timesteps (reward: 200.0) | |
Finished episode 1195 after 188 timesteps (reward: 188.0) | |
Finished episode 1196 after 147 timesteps (reward: 147.0) | |
Finished episode 1197 after 119 timesteps (reward: 119.0) | |
Finished episode 1198 after 158 timesteps (reward: 158.0) | |
Finished episode 1199 after 159 timesteps (reward: 159.0) | |
Finished episode 1200 after 163 timesteps (reward: 163.0) | |
Finished episode 1201 after 131 timesteps (reward: 131.0) | |
Finished episode 1202 after 174 timesteps (reward: 174.0) | |
Finished episode 1203 after 146 timesteps (reward: 146.0) | |
Finished episode 1204 after 190 timesteps (reward: 190.0) | |
Finished episode 1205 after 179 timesteps (reward: 179.0) | |
Finished episode 1206 after 152 timesteps (reward: 152.0) | |
Finished episode 1207 after 145 timesteps (reward: 145.0) | |
Finished episode 1208 after 184 timesteps (reward: 184.0) | |
Finished episode 1209 after 176 timesteps (reward: 176.0) | |
Finished episode 1210 after 118 timesteps (reward: 118.0) | |
Finished episode 1211 after 180 timesteps (reward: 180.0) | |
Finished episode 1212 after 122 timesteps (reward: 122.0) | |
Finished episode 1213 after 200 timesteps (reward: 200.0) | |
Finished episode 1214 after 119 timesteps (reward: 119.0) | |
Finished episode 1215 after 166 timesteps (reward: 166.0) | |
Finished episode 1216 after 200 timesteps (reward: 200.0) | |
Finished episode 1217 after 200 timesteps (reward: 200.0) | |
Finished episode 1218 after 198 timesteps (reward: 198.0) | |
Finished episode 1219 after 200 timesteps (reward: 200.0) | |
Finished episode 1220 after 200 timesteps (reward: 200.0) | |
Finished episode 1221 after 150 timesteps (reward: 150.0) | |
Finished episode 1222 after 144 timesteps (reward: 144.0) | |
Finished episode 1223 after 160 timesteps (reward: 160.0) | |
Finished episode 1224 after 173 timesteps (reward: 173.0) | |
Finished episode 1225 after 156 timesteps (reward: 156.0) | |
Finished episode 1226 after 128 timesteps (reward: 128.0) | |
Finished episode 1227 after 172 timesteps (reward: 172.0) | |
Finished episode 1228 after 200 timesteps (reward: 200.0) | |
Finished episode 1229 after 169 timesteps (reward: 169.0) | |
Finished episode 1230 after 200 timesteps (reward: 200.0) | |
Finished episode 1231 after 143 timesteps (reward: 143.0) | |
Finished episode 1232 after 190 timesteps (reward: 190.0) | |
Finished episode 1233 after 200 timesteps (reward: 200.0) | |
Finished episode 1234 after 172 timesteps (reward: 172.0) | |
Finished episode 1235 after 180 timesteps (reward: 180.0) | |
Finished episode 1236 after 146 timesteps (reward: 146.0) | |
Finished episode 1237 after 191 timesteps (reward: 191.0) | |
Finished episode 1238 after 200 timesteps (reward: 200.0) | |
Finished episode 1239 after 109 timesteps (reward: 109.0) | |
Finished episode 1240 after 200 timesteps (reward: 200.0) | |
Finished episode 1241 after 157 timesteps (reward: 157.0) | |
Finished episode 1242 after 200 timesteps (reward: 200.0) | |
Finished episode 1243 after 200 timesteps (reward: 200.0) | |
Finished episode 1244 after 138 timesteps (reward: 138.0) | |
Finished episode 1245 after 200 timesteps (reward: 200.0) | |
Finished episode 1246 after 151 timesteps (reward: 151.0) | |
Finished episode 1247 after 153 timesteps (reward: 153.0) | |
Finished episode 1248 after 136 timesteps (reward: 136.0) | |
Finished episode 1249 after 200 timesteps (reward: 200.0) | |
Finished episode 1250 after 200 timesteps (reward: 200.0) | |
Finished episode 1251 after 158 timesteps (reward: 158.0) | |
Finished episode 1252 after 148 timesteps (reward: 148.0) | |
Finished episode 1253 after 200 timesteps (reward: 200.0) | |
Finished episode 1254 after 200 timesteps (reward: 200.0) | |
Finished episode 1255 after 170 timesteps (reward: 170.0) | |
Finished episode 1256 after 125 timesteps (reward: 125.0) | |
Finished episode 1257 after 184 timesteps (reward: 184.0) | |
Finished episode 1258 after 200 timesteps (reward: 200.0) | |
Finished episode 1259 after 137 timesteps (reward: 137.0) | |
Finished episode 1260 after 200 timesteps (reward: 200.0) | |
Finished episode 1261 after 180 timesteps (reward: 180.0) | |
Finished episode 1262 after 147 timesteps (reward: 147.0) | |
Finished episode 1263 after 145 timesteps (reward: 145.0) | |
Finished episode 1264 after 181 timesteps (reward: 181.0) | |
Finished episode 1265 after 163 timesteps (reward: 163.0) | |
Finished episode 1266 after 193 timesteps (reward: 193.0) | |
Finished episode 1267 after 185 timesteps (reward: 185.0) | |
Finished episode 1268 after 143 timesteps (reward: 143.0) | |
Finished episode 1269 after 170 timesteps (reward: 170.0) | |
Finished episode 1270 after 200 timesteps (reward: 200.0) | |
Finished episode 1271 after 135 timesteps (reward: 135.0) | |
Finished episode 1272 after 171 timesteps (reward: 171.0) | |
Finished episode 1273 after 191 timesteps (reward: 191.0) | |
Finished episode 1274 after 187 timesteps (reward: 187.0) | |
Finished episode 1275 after 148 timesteps (reward: 148.0) | |
Finished episode 1276 after 197 timesteps (reward: 197.0) | |
Finished episode 1277 after 163 timesteps (reward: 163.0) | |
Finished episode 1278 after 139 timesteps (reward: 139.0) | |
Finished episode 1279 after 200 timesteps (reward: 200.0) | |
Finished episode 1280 after 183 timesteps (reward: 183.0) | |
Finished episode 1281 after 171 timesteps (reward: 171.0) | |
Finished episode 1282 after 165 timesteps (reward: 165.0) | |
Finished episode 1283 after 146 timesteps (reward: 146.0) | |
Finished episode 1284 after 178 timesteps (reward: 178.0) | |
Finished episode 1285 after 136 timesteps (reward: 136.0) | |
Finished episode 1286 after 183 timesteps (reward: 183.0) | |
Finished episode 1287 after 147 timesteps (reward: 147.0) | |
Finished episode 1288 after 148 timesteps (reward: 148.0) | |
Finished episode 1289 after 200 timesteps (reward: 200.0) | |
Finished episode 1290 after 198 timesteps (reward: 198.0) | |
Finished episode 1291 after 182 timesteps (reward: 182.0) | |
Finished episode 1292 after 132 timesteps (reward: 132.0) | |
Finished episode 1293 after 200 timesteps (reward: 200.0) | |
Finished episode 1294 after 153 timesteps (reward: 153.0) | |
Finished episode 1295 after 200 timesteps (reward: 200.0) | |
Finished episode 1296 after 200 timesteps (reward: 200.0) | |
Finished episode 1297 after 200 timesteps (reward: 200.0) | |
Finished episode 1298 after 175 timesteps (reward: 175.0) | |
Finished episode 1299 after 200 timesteps (reward: 200.0) | |
Finished episode 1300 after 200 timesteps (reward: 200.0) | |
Finished episode 1301 after 174 timesteps (reward: 174.0) | |
Finished episode 1302 after 169 timesteps (reward: 169.0) | |
Finished episode 1303 after 194 timesteps (reward: 194.0) | |
Finished episode 1304 after 166 timesteps (reward: 166.0) | |
Finished episode 1305 after 167 timesteps (reward: 167.0) | |
Finished episode 1306 after 200 timesteps (reward: 200.0) | |
Finished episode 1307 after 200 timesteps (reward: 200.0) | |
Finished episode 1308 after 140 timesteps (reward: 140.0) | |
Finished episode 1309 after 139 timesteps (reward: 139.0) | |
Finished episode 1310 after 174 timesteps (reward: 174.0) | |
Finished episode 1311 after 194 timesteps (reward: 194.0) | |
Finished episode 1312 after 200 timesteps (reward: 200.0) | |
Finished episode 1313 after 172 timesteps (reward: 172.0) | |
Finished episode 1314 after 141 timesteps (reward: 141.0) | |
Finished episode 1315 after 154 timesteps (reward: 154.0) | |
Finished episode 1316 after 150 timesteps (reward: 150.0) | |
Finished episode 1317 after 146 timesteps (reward: 146.0) | |
Finished episode 1318 after 152 timesteps (reward: 152.0) | |
Finished episode 1319 after 200 timesteps (reward: 200.0) | |
Finished episode 1320 after 200 timesteps (reward: 200.0) | |
Finished episode 1321 after 189 timesteps (reward: 189.0) | |
Finished episode 1322 after 200 timesteps (reward: 200.0) | |
Finished episode 1323 after 200 timesteps (reward: 200.0) | |
Finished episode 1324 after 130 timesteps (reward: 130.0) | |
Finished episode 1325 after 189 timesteps (reward: 189.0) | |
Finished episode 1326 after 200 timesteps (reward: 200.0) | |
Finished episode 1327 after 138 timesteps (reward: 138.0) | |
Finished episode 1328 after 184 timesteps (reward: 184.0) | |
Finished episode 1329 after 200 timesteps (reward: 200.0) | |
Finished episode 1330 after 153 timesteps (reward: 153.0) | |
Finished episode 1331 after 181 timesteps (reward: 181.0) | |
Finished episode 1332 after 200 timesteps (reward: 200.0) | |
Finished episode 1333 after 200 timesteps (reward: 200.0) | |
Finished episode 1334 after 170 timesteps (reward: 170.0) | |
Finished episode 1335 after 151 timesteps (reward: 151.0) | |
Finished episode 1336 after 136 timesteps (reward: 136.0) | |
Finished episode 1337 after 179 timesteps (reward: 179.0) | |
Finished episode 1338 after 200 timesteps (reward: 200.0) | |
Finished episode 1339 after 160 timesteps (reward: 160.0) | |
Finished episode 1340 after 180 timesteps (reward: 180.0) | |
Finished episode 1341 after 162 timesteps (reward: 162.0) | |
Finished episode 1342 after 171 timesteps (reward: 171.0) | |
Finished episode 1343 after 200 timesteps (reward: 200.0) | |
Finished episode 1344 after 200 timesteps (reward: 200.0) | |
Finished episode 1345 after 200 timesteps (reward: 200.0) | |
Finished episode 1346 after 148 timesteps (reward: 148.0) | |
Finished episode 1347 after 200 timesteps (reward: 200.0) | |
Finished episode 1348 after 181 timesteps (reward: 181.0) | |
Finished episode 1349 after 200 timesteps (reward: 200.0) | |
Finished episode 1350 after 176 timesteps (reward: 176.0) | |
Finished episode 1351 after 200 timesteps (reward: 200.0) | |
Finished episode 1352 after 200 timesteps (reward: 200.0) | |
Finished episode 1353 after 157 timesteps (reward: 157.0) | |
Finished episode 1354 after 155 timesteps (reward: 155.0) | |
Finished episode 1355 after 200 timesteps (reward: 200.0) | |
Finished episode 1356 after 200 timesteps (reward: 200.0) | |
Finished episode 1357 after 200 timesteps (reward: 200.0) | |
Finished episode 1358 after 134 timesteps (reward: 134.0) | |
Finished episode 1359 after 164 timesteps (reward: 164.0) | |
Finished episode 1360 after 200 timesteps (reward: 200.0) | |
Finished episode 1361 after 139 timesteps (reward: 139.0) | |
Finished episode 1362 after 154 timesteps (reward: 154.0) | |
Finished episode 1363 after 200 timesteps (reward: 200.0) | |
Finished episode 1364 after 197 timesteps (reward: 197.0) | |
Finished episode 1365 after 183 timesteps (reward: 183.0) | |
Finished episode 1366 after 191 timesteps (reward: 191.0) | |
Finished episode 1367 after 200 timesteps (reward: 200.0) | |
Finished episode 1368 after 200 timesteps (reward: 200.0) | |
Finished episode 1369 after 183 timesteps (reward: 183.0) | |
Finished episode 1370 after 200 timesteps (reward: 200.0) | |
Finished episode 1371 after 155 timesteps (reward: 155.0) | |
Finished episode 1372 after 172 timesteps (reward: 172.0) | |
Finished episode 1373 after 200 timesteps (reward: 200.0) | |
Finished episode 1374 after 199 timesteps (reward: 199.0) | |
Finished episode 1375 after 151 timesteps (reward: 151.0) | |
Finished episode 1376 after 149 timesteps (reward: 149.0) | |
Finished episode 1377 after 200 timesteps (reward: 200.0) | |
Finished episode 1378 after 162 timesteps (reward: 162.0) | |
Finished episode 1379 after 175 timesteps (reward: 175.0) | |
Finished episode 1380 after 200 timesteps (reward: 200.0) | |
Finished episode 1381 after 200 timesteps (reward: 200.0) | |
Finished episode 1382 after 200 timesteps (reward: 200.0) | |
Finished episode 1383 after 200 timesteps (reward: 200.0) | |
Finished episode 1384 after 177 timesteps (reward: 177.0) | |
Finished episode 1385 after 200 timesteps (reward: 200.0) | |
Finished episode 1386 after 120 timesteps (reward: 120.0) | |
Finished episode 1387 after 144 timesteps (reward: 144.0) | |
Finished episode 1388 after 200 timesteps (reward: 200.0) | |
Finished episode 1389 after 200 timesteps (reward: 200.0) | |
Finished episode 1390 after 172 timesteps (reward: 172.0) | |
Finished episode 1391 after 200 timesteps (reward: 200.0) | |
Finished episode 1392 after 171 timesteps (reward: 171.0) | |
Finished episode 1393 after 161 timesteps (reward: 161.0) | |
Finished episode 1394 after 118 timesteps (reward: 118.0) | |
Finished episode 1395 after 200 timesteps (reward: 200.0) | |
Finished episode 1396 after 127 timesteps (reward: 127.0) | |
Finished episode 1397 after 131 timesteps (reward: 131.0) | |
Finished episode 1398 after 199 timesteps (reward: 199.0) | |
Finished episode 1399 after 193 timesteps (reward: 193.0) | |
Finished episode 1400 after 155 timesteps (reward: 155.0) | |
Finished episode 1401 after 198 timesteps (reward: 198.0) | |
Finished episode 1402 after 131 timesteps (reward: 131.0) | |
Finished episode 1403 after 200 timesteps (reward: 200.0) | |
Finished episode 1404 after 200 timesteps (reward: 200.0) | |
Finished episode 1405 after 153 timesteps (reward: 153.0) | |
Finished episode 1406 after 195 timesteps (reward: 195.0) | |
Finished episode 1407 after 145 timesteps (reward: 145.0) | |
Finished episode 1408 after 134 timesteps (reward: 134.0) | |
Finished episode 1409 after 171 timesteps (reward: 171.0) | |
Finished episode 1410 after 161 timesteps (reward: 161.0) | |
Finished episode 1411 after 158 timesteps (reward: 158.0) | |
Finished episode 1412 after 176 timesteps (reward: 176.0) | |
Finished episode 1413 after 178 timesteps (reward: 178.0) | |
Finished episode 1414 after 194 timesteps (reward: 194.0) | |
Finished episode 1415 after 156 timesteps (reward: 156.0) | |
Finished episode 1416 after 159 timesteps (reward: 159.0) | |
Finished episode 1417 after 147 timesteps (reward: 147.0) | |
Finished episode 1418 after 133 timesteps (reward: 133.0) | |
Finished episode 1419 after 190 timesteps (reward: 190.0) | |
Finished episode 1420 after 141 timesteps (reward: 141.0) | |
Finished episode 1421 after 200 timesteps (reward: 200.0) | |
Finished episode 1422 after 178 timesteps (reward: 178.0) | |
Finished episode 1423 after 200 timesteps (reward: 200.0) | |
Finished episode 1424 after 129 timesteps (reward: 129.0) | |
Finished episode 1425 after 138 timesteps (reward: 138.0) | |
Finished episode 1426 after 200 timesteps (reward: 200.0) | |
Finished episode 1427 after 126 timesteps (reward: 126.0) | |
Finished episode 1428 after 200 timesteps (reward: 200.0) | |
Finished episode 1429 after 170 timesteps (reward: 170.0) | |
Finished episode 1430 after 154 timesteps (reward: 154.0) | |
Finished episode 1431 after 200 timesteps (reward: 200.0) | |
Finished episode 1432 after 200 timesteps (reward: 200.0) | |
Finished episode 1433 after 158 timesteps (reward: 158.0) | |
Finished episode 1434 after 135 timesteps (reward: 135.0) | |
Finished episode 1435 after 126 timesteps (reward: 126.0) | |
Finished episode 1436 after 146 timesteps (reward: 146.0) | |
Finished episode 1437 after 129 timesteps (reward: 129.0) | |
Finished episode 1438 after 73 timesteps (reward: 73.0) | |
Finished episode 1439 after 200 timesteps (reward: 200.0) | |
Finished episode 1440 after 167 timesteps (reward: 167.0) | |
Finished episode 1441 after 140 timesteps (reward: 140.0) | |
Finished episode 1442 after 200 timesteps (reward: 200.0) | |
Finished episode 1443 after 168 timesteps (reward: 168.0) | |
Finished episode 1444 after 146 timesteps (reward: 146.0) | |
Finished episode 1445 after 134 timesteps (reward: 134.0) | |
Finished episode 1446 after 200 timesteps (reward: 200.0) | |
Finished episode 1447 after 135 timesteps (reward: 135.0) | |
Finished episode 1448 after 128 timesteps (reward: 128.0) | |
Finished episode 1449 after 89 timesteps (reward: 89.0) | |
Finished episode 1450 after 175 timesteps (reward: 175.0) | |
Finished episode 1451 after 140 timesteps (reward: 140.0) | |
Finished episode 1452 after 148 timesteps (reward: 148.0) | |
Finished episode 1453 after 115 timesteps (reward: 115.0) | |
Finished episode 1454 after 200 timesteps (reward: 200.0) | |
Finished episode 1455 after 150 timesteps (reward: 150.0) | |
Finished episode 1456 after 200 timesteps (reward: 200.0) | |
Finished episode 1457 after 200 timesteps (reward: 200.0) | |
Finished episode 1458 after 187 timesteps (reward: 187.0) | |
Finished episode 1459 after 170 timesteps (reward: 170.0) | |
Finished episode 1460 after 200 timesteps (reward: 200.0) | |
Finished episode 1461 after 200 timesteps (reward: 200.0) | |
Finished episode 1462 after 143 timesteps (reward: 143.0) | |
Finished episode 1463 after 200 timesteps (reward: 200.0) | |
Finished episode 1464 after 137 timesteps (reward: 137.0) | |
Finished episode 1465 after 200 timesteps (reward: 200.0) | |
Finished episode 1466 after 160 timesteps (reward: 160.0) | |
Finished episode 1467 after 142 timesteps (reward: 142.0) | |
Finished episode 1468 after 95 timesteps (reward: 95.0) | |
Finished episode 1469 after 200 timesteps (reward: 200.0) | |
Finished episode 1470 after 128 timesteps (reward: 128.0) | |
Finished episode 1471 after 200 timesteps (reward: 200.0) | |
Finished episode 1472 after 167 timesteps (reward: 167.0) | |
Finished episode 1473 after 100 timesteps (reward: 100.0) | |
Finished episode 1474 after 158 timesteps (reward: 158.0) | |
Finished episode 1475 after 164 timesteps (reward: 164.0) | |
Finished episode 1476 after 103 timesteps (reward: 103.0) | |
Finished episode 1477 after 118 timesteps (reward: 118.0) | |
Finished episode 1478 after 175 timesteps (reward: 175.0) | |
Finished episode 1479 after 155 timesteps (reward: 155.0) | |
Finished episode 1480 after 189 timesteps (reward: 189.0) | |
Finished episode 1481 after 76 timesteps (reward: 76.0) | |
Finished episode 1482 after 112 timesteps (reward: 112.0) | |
Finished episode 1483 after 86 timesteps (reward: 86.0) | |
Finished episode 1484 after 145 timesteps (reward: 145.0) | |
Finished episode 1485 after 117 timesteps (reward: 117.0) | |
Finished episode 1486 after 178 timesteps (reward: 178.0) | |
Finished episode 1487 after 61 timesteps (reward: 61.0) | |
Finished episode 1488 after 82 timesteps (reward: 82.0) | |
Finished episode 1489 after 62 timesteps (reward: 62.0) | |
Finished episode 1490 after 105 timesteps (reward: 105.0) | |
Finished episode 1491 after 79 timesteps (reward: 79.0) | |
Finished episode 1492 after 153 timesteps (reward: 153.0) | |
Finished episode 1493 after 63 timesteps (reward: 63.0) | |
Finished episode 1494 after 40 timesteps (reward: 40.0) | |
Finished episode 1495 after 186 timesteps (reward: 186.0) | |
Finished episode 1496 after 168 timesteps (reward: 168.0) | |
Finished episode 1497 after 109 timesteps (reward: 109.0) | |
Finished episode 1498 after 67 timesteps (reward: 67.0) | |
Finished episode 1499 after 59 timesteps (reward: 59.0) | |
Finished episode 1500 after 64 timesteps (reward: 64.0) | |
Finished episode 1501 after 53 timesteps (reward: 53.0) | |
Finished episode 1502 after 79 timesteps (reward: 79.0) | |
Finished episode 1503 after 34 timesteps (reward: 34.0) | |
Finished episode 1504 after 57 timesteps (reward: 57.0) | |
Finished episode 1505 after 38 timesteps (reward: 38.0) | |
Finished episode 1506 after 57 timesteps (reward: 57.0) | |
Finished episode 1507 after 61 timesteps (reward: 61.0) | |
Finished episode 1508 after 61 timesteps (reward: 61.0) | |
Finished episode 1509 after 78 timesteps (reward: 78.0) | |
Finished episode 1510 after 45 timesteps (reward: 45.0) | |
Finished episode 1511 after 79 timesteps (reward: 79.0) | |
Finished episode 1512 after 50 timesteps (reward: 50.0) | |
Finished episode 1513 after 100 timesteps (reward: 100.0) | |
Finished episode 1514 after 82 timesteps (reward: 82.0) | |
Finished episode 1515 after 143 timesteps (reward: 143.0) | |
Finished episode 1516 after 104 timesteps (reward: 104.0) | |
Finished episode 1517 after 38 timesteps (reward: 38.0) | |
Finished episode 1518 after 63 timesteps (reward: 63.0) | |
Finished episode 1519 after 60 timesteps (reward: 60.0) | |
Finished episode 1520 after 63 timesteps (reward: 63.0) | |
Finished episode 1521 after 48 timesteps (reward: 48.0) | |
Finished episode 1522 after 47 timesteps (reward: 47.0) | |
Finished episode 1523 after 63 timesteps (reward: 63.0) | |
Finished episode 1524 after 46 timesteps (reward: 46.0) | |
Finished episode 1525 after 59 timesteps (reward: 59.0) | |
Finished episode 1526 after 49 timesteps (reward: 49.0) | |
Finished episode 1527 after 82 timesteps (reward: 82.0) | |
Finished episode 1528 after 33 timesteps (reward: 33.0) | |
Finished episode 1529 after 68 timesteps (reward: 68.0) | |
Finished episode 1530 after 80 timesteps (reward: 80.0) | |
Finished episode 1531 after 40 timesteps (reward: 40.0) | |
Finished episode 1532 after 59 timesteps (reward: 59.0) | |
Finished episode 1533 after 48 timesteps (reward: 48.0) | |
Finished episode 1534 after 66 timesteps (reward: 66.0) | |
Finished episode 1535 after 74 timesteps (reward: 74.0) | |
Finished episode 1536 after 48 timesteps (reward: 48.0) | |
Finished episode 1537 after 68 timesteps (reward: 68.0) | |
Finished episode 1538 after 37 timesteps (reward: 37.0) | |
Finished episode 1539 after 86 timesteps (reward: 86.0) | |
Finished episode 1540 after 72 timesteps (reward: 72.0) | |
Finished episode 1541 after 86 timesteps (reward: 86.0) | |
Finished episode 1542 after 48 timesteps (reward: 48.0) | |
Finished episode 1543 after 59 timesteps (reward: 59.0) | |
Finished episode 1544 after 27 timesteps (reward: 27.0) | |
Finished episode 1545 after 64 timesteps (reward: 64.0) | |
Finished episode 1546 after 52 timesteps (reward: 52.0) | |
Finished episode 1547 after 68 timesteps (reward: 68.0) | |
Finished episode 1548 after 50 timesteps (reward: 50.0) | |
Finished episode 1549 after 76 timesteps (reward: 76.0) | |
Finished episode 1550 after 75 timesteps (reward: 75.0) | |
Finished episode 1551 after 74 timesteps (reward: 74.0) | |
Finished episode 1552 after 62 timesteps (reward: 62.0) | |
Finished episode 1553 after 63 timesteps (reward: 63.0) | |
Finished episode 1554 after 39 timesteps (reward: 39.0) | |
Finished episode 1555 after 110 timesteps (reward: 110.0) | |
Finished episode 1556 after 52 timesteps (reward: 52.0) | |
Finished episode 1557 after 53 timesteps (reward: 53.0) | |
Finished episode 1558 after 139 timesteps (reward: 139.0) | |
Finished episode 1559 after 64 timesteps (reward: 64.0) | |
Finished episode 1560 after 61 timesteps (reward: 61.0) | |
Finished episode 1561 after 66 timesteps (reward: 66.0) | |
Finished episode 1562 after 44 timesteps (reward: 44.0) | |
Finished episode 1563 after 38 timesteps (reward: 38.0) | |
Finished episode 1564 after 60 timesteps (reward: 60.0) | |
Finished episode 1565 after 49 timesteps (reward: 49.0) | |
Finished episode 1566 after 89 timesteps (reward: 89.0) | |
Finished episode 1567 after 66 timesteps (reward: 66.0) | |
Finished episode 1568 after 38 timesteps (reward: 38.0) | |
Finished episode 1569 after 88 timesteps (reward: 88.0) | |
Finished episode 1570 after 61 timesteps (reward: 61.0) | |
Finished episode 1571 after 47 timesteps (reward: 47.0) | |
Finished episode 1572 after 62 timesteps (reward: 62.0) | |
Finished episode 1573 after 52 timesteps (reward: 52.0) | |
Finished episode 1574 after 63 timesteps (reward: 63.0) | |
Finished episode 1575 after 35 timesteps (reward: 35.0) | |
Finished episode 1576 after 82 timesteps (reward: 82.0) | |
Finished episode 1577 after 51 timesteps (reward: 51.0) | |
Finished episode 1578 after 60 timesteps (reward: 60.0) | |
Finished episode 1579 after 65 timesteps (reward: 65.0) | |
Finished episode 1580 after 57 timesteps (reward: 57.0) | |
Finished episode 1581 after 42 timesteps (reward: 42.0) | |
Finished episode 1582 after 70 timesteps (reward: 70.0) | |
Finished episode 1583 after 48 timesteps (reward: 48.0) | |
Finished episode 1584 after 80 timesteps (reward: 80.0) | |
Finished episode 1585 after 73 timesteps (reward: 73.0) | |
Finished episode 1586 after 38 timesteps (reward: 38.0) | |
Finished episode 1587 after 81 timesteps (reward: 81.0) | |
Finished episode 1588 after 47 timesteps (reward: 47.0) | |
Finished episode 1589 after 58 timesteps (reward: 58.0) | |
Finished episode 1590 after 69 timesteps (reward: 69.0) | |
Finished episode 1591 after 65 timesteps (reward: 65.0) | |
Finished episode 1592 after 43 timesteps (reward: 43.0) | |
Finished episode 1593 after 67 timesteps (reward: 67.0) | |
Finished episode 1594 after 63 timesteps (reward: 63.0) | |
Finished episode 1595 after 63 timesteps (reward: 63.0) | |
Finished episode 1596 after 51 timesteps (reward: 51.0) | |
Finished episode 1597 after 44 timesteps (reward: 44.0) | |
Finished episode 1598 after 100 timesteps (reward: 100.0) | |
Finished episode 1599 after 46 timesteps (reward: 46.0) | |
Finished episode 1600 after 43 timesteps (reward: 43.0) | |
Finished episode 1601 after 92 timesteps (reward: 92.0) | |
Finished episode 1602 after 75 timesteps (reward: 75.0) | |
Finished episode 1603 after 55 timesteps (reward: 55.0) | |
Finished episode 1604 after 37 timesteps (reward: 37.0) | |
Finished episode 1605 after 47 timesteps (reward: 47.0) | |
Finished episode 1606 after 59 timesteps (reward: 59.0) | |
Finished episode 1607 after 60 timesteps (reward: 60.0) | |
Finished episode 1608 after 64 timesteps (reward: 64.0) | |
Finished episode 1609 after 70 timesteps (reward: 70.0) | |
Finished episode 1610 after 32 timesteps (reward: 32.0) | |
Finished episode 1611 after 37 timesteps (reward: 37.0) | |
Finished episode 1612 after 55 timesteps (reward: 55.0) | |
Finished episode 1613 after 56 timesteps (reward: 56.0) | |
Finished episode 1614 after 51 timesteps (reward: 51.0) | |
Finished episode 1615 after 69 timesteps (reward: 69.0) | |
Finished episode 1616 after 65 timesteps (reward: 65.0) | |
Finished episode 1617 after 83 timesteps (reward: 83.0) | |
Finished episode 1618 after 47 timesteps (reward: 47.0) | |
Finished episode 1619 after 46 timesteps (reward: 46.0) | |
Finished episode 1620 after 26 timesteps (reward: 26.0) | |
Finished episode 1621 after 40 timesteps (reward: 40.0) | |
Finished episode 1622 after 80 timesteps (reward: 80.0) | |
Finished episode 1623 after 47 timesteps (reward: 47.0) | |
Finished episode 1624 after 95 timesteps (reward: 95.0) | |
Finished episode 1625 after 40 timesteps (reward: 40.0) | |
Finished episode 1626 after 70 timesteps (reward: 70.0) | |
Finished episode 1627 after 77 timesteps (reward: 77.0) | |
Finished episode 1628 after 46 timesteps (reward: 46.0) | |
Finished episode 1629 after 37 timesteps (reward: 37.0) | |
Finished episode 1630 after 38 timesteps (reward: 38.0) | |
Finished episode 1631 after 72 timesteps (reward: 72.0) | |
Finished episode 1632 after 38 timesteps (reward: 38.0) | |
Finished episode 1633 after 105 timesteps (reward: 105.0) | |
Finished episode 1634 after 63 timesteps (reward: 63.0) | |
Finished episode 1635 after 36 timesteps (reward: 36.0) | |
Finished episode 1636 after 58 timesteps (reward: 58.0) | |
Finished episode 1637 after 67 timesteps (reward: 67.0) | |
Finished episode 1638 after 62 timesteps (reward: 62.0) | |
Finished episode 1639 after 47 timesteps (reward: 47.0) | |
Finished episode 1640 after 54 timesteps (reward: 54.0) | |
Finished episode 1641 after 78 timesteps (reward: 78.0) | |
Finished episode 1642 after 38 timesteps (reward: 38.0) | |
Finished episode 1643 after 38 timesteps (reward: 38.0) | |
Finished episode 1644 after 33 timesteps (reward: 33.0) | |
Finished episode 1645 after 70 timesteps (reward: 70.0) | |
Finished episode 1646 after 81 timesteps (reward: 81.0) | |
Finished episode 1647 after 62 timesteps (reward: 62.0) | |
Finished episode 1648 after 65 timesteps (reward: 65.0) | |
Finished episode 1649 after 53 timesteps (reward: 53.0) | |
Finished episode 1650 after 49 timesteps (reward: 49.0) | |
Finished episode 1651 after 46 timesteps (reward: 46.0) | |
Finished episode 1652 after 48 timesteps (reward: 48.0) | |
Finished episode 1653 after 52 timesteps (reward: 52.0) | |
Finished episode 1654 after 68 timesteps (reward: 68.0) | |
Finished episode 1655 after 59 timesteps (reward: 59.0) | |
Finished episode 1656 after 63 timesteps (reward: 63.0) | |
Finished episode 1657 after 63 timesteps (reward: 63.0) | |
Finished episode 1658 after 55 timesteps (reward: 55.0) | |
Finished episode 1659 after 78 timesteps (reward: 78.0) | |
Finished episode 1660 after 63 timesteps (reward: 63.0) | |
Finished episode 1661 after 61 timesteps (reward: 61.0) | |
Finished episode 1662 after 42 timesteps (reward: 42.0) | |
Finished episode 1663 after 34 timesteps (reward: 34.0) | |
Finished episode 1664 after 101 timesteps (reward: 101.0) | |
Finished episode 1665 after 53 timesteps (reward: 53.0) | |
Finished episode 1666 after 33 timesteps (reward: 33.0) | |
Finished episode 1667 after 58 timesteps (reward: 58.0) | |
Finished episode 1668 after 44 timesteps (reward: 44.0) | |
Finished episode 1669 after 40 timesteps (reward: 40.0) | |
Finished episode 1670 after 48 timesteps (reward: 48.0) | |
Finished episode 1671 after 50 timesteps (reward: 50.0) | |
Finished episode 1672 after 70 timesteps (reward: 70.0) | |
Finished episode 1673 after 58 timesteps (reward: 58.0) | |
Finished episode 1674 after 52 timesteps (reward: 52.0) | |
Finished episode 1675 after 47 timesteps (reward: 47.0) | |
Finished episode 1676 after 45 timesteps (reward: 45.0) | |
Finished episode 1677 after 82 timesteps (reward: 82.0) | |
Finished episode 1678 after 67 timesteps (reward: 67.0) | |
Finished episode 1679 after 104 timesteps (reward: 104.0) | |
Finished episode 1680 after 37 timesteps (reward: 37.0) | |
Finished episode 1681 after 64 timesteps (reward: 64.0) | |
Finished episode 1682 after 100 timesteps (reward: 100.0) | |
Finished episode 1683 after 73 timesteps (reward: 73.0) | |
Finished episode 1684 after 65 timesteps (reward: 65.0) | |
Finished episode 1685 after 70 timesteps (reward: 70.0) | |
Finished episode 1686 after 45 timesteps (reward: 45.0) | |
Finished episode 1687 after 58 timesteps (reward: 58.0) | |
Finished episode 1688 after 73 timesteps (reward: 73.0) | |
Finished episode 1689 after 59 timesteps (reward: 59.0) | |
Finished episode 1690 after 76 timesteps (reward: 76.0) | |
Finished episode 1691 after 69 timesteps (reward: 69.0) | |
Finished episode 1692 after 44 timesteps (reward: 44.0) | |
Finished episode 1693 after 52 timesteps (reward: 52.0) | |
Finished episode 1694 after 71 timesteps (reward: 71.0) | |
Finished episode 1695 after 47 timesteps (reward: 47.0) | |
Finished episode 1696 after 67 timesteps (reward: 67.0) | |
Finished episode 1697 after 74 timesteps (reward: 74.0) | |
Finished episode 1698 after 48 timesteps (reward: 48.0) | |
Finished episode 1699 after 34 timesteps (reward: 34.0) | |
Finished episode 1700 after 57 timesteps (reward: 57.0) | |
Finished episode 1701 after 47 timesteps (reward: 47.0) | |
Finished episode 1702 after 49 timesteps (reward: 49.0) | |
Finished episode 1703 after 51 timesteps (reward: 51.0) | |
Finished episode 1704 after 62 timesteps (reward: 62.0) | |
Finished episode 1705 after 81 timesteps (reward: 81.0) | |
Finished episode 1706 after 85 timesteps (reward: 85.0) | |
Finished episode 1707 after 56 timesteps (reward: 56.0) | |
Finished episode 1708 after 39 timesteps (reward: 39.0) | |
Finished episode 1709 after 84 timesteps (reward: 84.0) | |
Finished episode 1710 after 50 timesteps (reward: 50.0) | |
Finished episode 1711 after 46 timesteps (reward: 46.0) | |
Finished episode 1712 after 46 timesteps (reward: 46.0) | |
Finished episode 1713 after 47 timesteps (reward: 47.0) | |
Finished episode 1714 after 52 timesteps (reward: 52.0) | |
Finished episode 1715 after 66 timesteps (reward: 66.0) | |
Finished episode 1716 after 56 timesteps (reward: 56.0) | |
Finished episode 1717 after 42 timesteps (reward: 42.0) | |
Finished episode 1718 after 76 timesteps (reward: 76.0) | |
Finished episode 1719 after 49 timesteps (reward: 49.0) | |
Finished episode 1720 after 61 timesteps (reward: 61.0) | |
Finished episode 1721 after 62 timesteps (reward: 62.0) | |
Finished episode 1722 after 48 timesteps (reward: 48.0) | |
Finished episode 1723 after 47 timesteps (reward: 47.0) | |
Finished episode 1724 after 33 timesteps (reward: 33.0) | |
Finished episode 1725 after 54 timesteps (reward: 54.0) | |
Finished episode 1726 after 40 timesteps (reward: 40.0) | |
Finished episode 1727 after 46 timesteps (reward: 46.0) | |
Finished episode 1728 after 60 timesteps (reward: 60.0) | |
Finished episode 1729 after 68 timesteps (reward: 68.0) | |
Finished episode 1730 after 51 timesteps (reward: 51.0) | |
Finished episode 1731 after 69 timesteps (reward: 69.0) | |
Finished episode 1732 after 34 timesteps (reward: 34.0) | |
Finished episode 1733 after 46 timesteps (reward: 46.0) | |
Finished episode 1734 after 69 timesteps (reward: 69.0) | |
Finished episode 1735 after 51 timesteps (reward: 51.0) | |
Finished episode 1736 after 59 timesteps (reward: 59.0) | |
Finished episode 1737 after 38 timesteps (reward: 38.0) | |
Finished episode 1738 after 55 timesteps (reward: 55.0) | |
Finished episode 1739 after 49 timesteps (reward: 49.0) | |
Finished episode 1740 after 49 timesteps (reward: 49.0) | |
Finished episode 1741 after 38 timesteps (reward: 38.0) | |
Finished episode 1742 after 44 timesteps (reward: 44.0) | |
Finished episode 1743 after 103 timesteps (reward: 103.0) | |
Finished episode 1744 after 60 timesteps (reward: 60.0) | |
Finished episode 1745 after 57 timesteps (reward: 57.0) | |
Finished episode 1746 after 54 timesteps (reward: 54.0) | |
Finished episode 1747 after 45 timesteps (reward: 45.0) | |
Finished episode 1748 after 73 timesteps (reward: 73.0) | |
Finished episode 1749 after 46 timesteps (reward: 46.0) | |
Finished episode 1750 after 66 timesteps (reward: 66.0) | |
Finished episode 1751 after 45 timesteps (reward: 45.0) | |
Finished episode 1752 after 55 timesteps (reward: 55.0) | |
Finished episode 1753 after 37 timesteps (reward: 37.0) | |
Finished episode 1754 after 40 timesteps (reward: 40.0) | |
Finished episode 1755 after 92 timesteps (reward: 92.0) | |
Finished episode 1756 after 39 timesteps (reward: 39.0) | |
Finished episode 1757 after 49 timesteps (reward: 49.0) | |
Finished episode 1758 after 38 timesteps (reward: 38.0) | |
Finished episode 1759 after 34 timesteps (reward: 34.0) | |
Finished episode 1760 after 84 timesteps (reward: 84.0) | |
Finished episode 1761 after 44 timesteps (reward: 44.0) | |
Finished episode 1762 after 42 timesteps (reward: 42.0) | |
Finished episode 1763 after 51 timesteps (reward: 51.0) | |
Finished episode 1764 after 70 timesteps (reward: 70.0) | |
Finished episode 1765 after 48 timesteps (reward: 48.0) | |
Finished episode 1766 after 54 timesteps (reward: 54.0) | |
Finished episode 1767 after 45 timesteps (reward: 45.0) | |
Finished episode 1768 after 38 timesteps (reward: 38.0) | |
Finished episode 1769 after 69 timesteps (reward: 69.0) | |
Finished episode 1770 after 49 timesteps (reward: 49.0) | |
Finished episode 1771 after 46 timesteps (reward: 46.0) | |
Finished episode 1772 after 35 timesteps (reward: 35.0) | |
Finished episode 1773 after 57 timesteps (reward: 57.0) | |
Finished episode 1774 after 47 timesteps (reward: 47.0) | |
Finished episode 1775 after 66 timesteps (reward: 66.0) | |
Finished episode 1776 after 57 timesteps (reward: 57.0) | |
Finished episode 1777 after 47 timesteps (reward: 47.0) | |
Finished episode 1778 after 40 timesteps (reward: 40.0) | |
Finished episode 1779 after 44 timesteps (reward: 44.0) | |
Finished episode 1780 after 59 timesteps (reward: 59.0) | |
Finished episode 1781 after 61 timesteps (reward: 61.0) | |
Finished episode 1782 after 43 timesteps (reward: 43.0) | |
Finished episode 1783 after 48 timesteps (reward: 48.0) | |
Finished episode 1784 after 44 timesteps (reward: 44.0) | |
Finished episode 1785 after 37 timesteps (reward: 37.0) | |
Finished episode 1786 after 46 timesteps (reward: 46.0) | |
Finished episode 1787 after 57 timesteps (reward: 57.0) | |
Finished episode 1788 after 47 timesteps (reward: 47.0) | |
Finished episode 1789 after 77 timesteps (reward: 77.0) | |
Finished episode 1790 after 46 timesteps (reward: 46.0) | |
Finished episode 1791 after 33 timesteps (reward: 33.0) | |
Finished episode 1792 after 46 timesteps (reward: 46.0) | |
Finished episode 1793 after 52 timesteps (reward: 52.0) | |
Finished episode 1794 after 39 timesteps (reward: 39.0) | |
Finished episode 1795 after 54 timesteps (reward: 54.0) | |
Finished episode 1796 after 53 timesteps (reward: 53.0) | |
Finished episode 1797 after 54 timesteps (reward: 54.0) | |
Finished episode 1798 after 48 timesteps (reward: 48.0) | |
Finished episode 1799 after 59 timesteps (reward: 59.0) | |
Finished episode 1800 after 52 timesteps (reward: 52.0) | |
Finished episode 1801 after 38 timesteps (reward: 38.0) | |
Finished episode 1802 after 42 timesteps (reward: 42.0) | |
Finished episode 1803 after 52 timesteps (reward: 52.0) | |
Finished episode 1804 after 55 timesteps (reward: 55.0) | |
Finished episode 1805 after 51 timesteps (reward: 51.0) | |
Finished episode 1806 after 68 timesteps (reward: 68.0) | |
Finished episode 1807 after 33 timesteps (reward: 33.0) | |
Finished episode 1808 after 81 timesteps (reward: 81.0) | |
Finished episode 1809 after 63 timesteps (reward: 63.0) | |
Finished episode 1810 after 55 timesteps (reward: 55.0) | |
Finished episode 1811 after 39 timesteps (reward: 39.0) | |
Finished episode 1812 after 58 timesteps (reward: 58.0) | |
Finished episode 1813 after 60 timesteps (reward: 60.0) | |
Finished episode 1814 after 35 timesteps (reward: 35.0) | |
Finished episode 1815 after 81 timesteps (reward: 81.0) | |
Finished episode 1816 after 53 timesteps (reward: 53.0) | |
Finished episode 1817 after 39 timesteps (reward: 39.0) | |
Finished episode 1818 after 33 timesteps (reward: 33.0) | |
Finished episode 1819 after 39 timesteps (reward: 39.0) | |
Finished episode 1820 after 78 timesteps (reward: 78.0) | |
Finished episode 1821 after 63 timesteps (reward: 63.0) | |
Finished episode 1822 after 47 timesteps (reward: 47.0) | |
Finished episode 1823 after 41 timesteps (reward: 41.0) | |
Finished episode 1824 after 43 timesteps (reward: 43.0) | |
Finished episode 1825 after 45 timesteps (reward: 45.0) | |
Finished episode 1826 after 69 timesteps (reward: 69.0) | |
Finished episode 1827 after 47 timesteps (reward: 47.0) | |
Finished episode 1828 after 38 timesteps (reward: 38.0) | |
Finished episode 1829 after 58 timesteps (reward: 58.0) | |
Finished episode 1830 after 53 timesteps (reward: 53.0) | |
Finished episode 1831 after 39 timesteps (reward: 39.0) | |
Finished episode 1832 after 51 timesteps (reward: 51.0) | |
Finished episode 1833 after 45 timesteps (reward: 45.0) | |
Finished episode 1834 after 33 timesteps (reward: 33.0) | |
Finished episode 1835 after 45 timesteps (reward: 45.0) | |
Finished episode 1836 after 48 timesteps (reward: 48.0) | |
Finished episode 1837 after 34 timesteps (reward: 34.0) | |
Finished episode 1838 after 87 timesteps (reward: 87.0) | |
Finished episode 1839 after 64 timesteps (reward: 64.0) | |
Finished episode 1840 after 33 timesteps (reward: 33.0) | |
Finished episode 1841 after 69 timesteps (reward: 69.0) | |
Finished episode 1842 after 47 timesteps (reward: 47.0) | |
Finished episode 1843 after 26 timesteps (reward: 26.0) | |
Finished episode 1844 after 67 timesteps (reward: 67.0) | |
Finished episode 1845 after 40 timesteps (reward: 40.0) | |
Finished episode 1846 after 58 timesteps (reward: 58.0) | |
Finished episode 1847 after 60 timesteps (reward: 60.0) | |
Finished episode 1848 after 65 timesteps (reward: 65.0) | |
Finished episode 1849 after 60 timesteps (reward: 60.0) | |
Finished episode 1850 after 40 timesteps (reward: 40.0) | |
Finished episode 1851 after 56 timesteps (reward: 56.0) | |
Finished episode 1852 after 35 timesteps (reward: 35.0) | |
Finished episode 1853 after 61 timesteps (reward: 61.0) | |
Finished episode 1854 after 38 timesteps (reward: 38.0) | |
Finished episode 1855 after 53 timesteps (reward: 53.0) | |
Finished episode 1856 after 58 timesteps (reward: 58.0) | |
Finished episode 1857 after 60 timesteps (reward: 60.0) | |
Finished episode 1858 after 38 timesteps (reward: 38.0) | |
Finished episode 1859 after 53 timesteps (reward: 53.0) | |
Finished episode 1860 after 32 timesteps (reward: 32.0) | |
Finished episode 1861 after 45 timesteps (reward: 45.0) | |
Finished episode 1862 after 53 timesteps (reward: 53.0) | |
Finished episode 1863 after 47 timesteps (reward: 47.0) | |
Finished episode 1864 after 53 timesteps (reward: 53.0) | |
Finished episode 1865 after 55 timesteps (reward: 55.0) | |
Finished episode 1866 after 58 timesteps (reward: 58.0) | |
Finished episode 1867 after 34 timesteps (reward: 34.0) | |
Finished episode 1868 after 42 timesteps (reward: 42.0) | |
Finished episode 1869 after 42 timesteps (reward: 42.0) | |
Finished episode 1870 after 63 timesteps (reward: 63.0) | |
Finished episode 1871 after 50 timesteps (reward: 50.0) | |
Finished episode 1872 after 58 timesteps (reward: 58.0) | |
Finished episode 1873 after 44 timesteps (reward: 44.0) | |
Finished episode 1874 after 51 timesteps (reward: 51.0) | |
Finished episode 1875 after 61 timesteps (reward: 61.0) | |
Finished episode 1876 after 36 timesteps (reward: 36.0) | |
Finished episode 1877 after 44 timesteps (reward: 44.0) | |
Finished episode 1878 after 50 timesteps (reward: 50.0) | |
Finished episode 1879 after 52 timesteps (reward: 52.0) | |
Finished episode 1880 after 60 timesteps (reward: 60.0) | |
Finished episode 1881 after 53 timesteps (reward: 53.0) | |
Finished episode 1882 after 44 timesteps (reward: 44.0) | |
Finished episode 1883 after 40 timesteps (reward: 40.0) | |
Finished episode 1884 after 34 timesteps (reward: 34.0) | |
Finished episode 1885 after 56 timesteps (reward: 56.0) | |
Finished episode 1886 after 53 timesteps (reward: 53.0) | |
Finished episode 1887 after 60 timesteps (reward: 60.0) | |
Finished episode 1888 after 39 timesteps (reward: 39.0) | |
Finished episode 1889 after 52 timesteps (reward: 52.0) | |
Finished episode 1890 after 46 timesteps (reward: 46.0) | |
Finished episode 1891 after 41 timesteps (reward: 41.0) | |
Finished episode 1892 after 47 timesteps (reward: 47.0) | |
Finished episode 1893 after 36 timesteps (reward: 36.0) | |
Finished episode 1894 after 46 timesteps (reward: 46.0) | |
Finished episode 1895 after 43 timesteps (reward: 43.0) | |
Finished episode 1896 after 35 timesteps (reward: 35.0) | |
Finished episode 1897 after 45 timesteps (reward: 45.0) | |
Finished episode 1898 after 58 timesteps (reward: 58.0) | |
Finished episode 1899 after 38 timesteps (reward: 38.0) | |
Finished episode 1900 after 40 timesteps (reward: 40.0) | |
Finished episode 1901 after 58 timesteps (reward: 58.0) | |
Finished episode 1902 after 50 timesteps (reward: 50.0) | |
Finished episode 1903 after 83 timesteps (reward: 83.0) | |
Finished episode 1904 after 56 timesteps (reward: 56.0) | |
Finished episode 1905 after 34 timesteps (reward: 34.0) | |
Finished episode 1906 after 66 timesteps (reward: 66.0) | |
Finished episode 1907 after 37 timesteps (reward: 37.0) | |
Finished episode 1908 after 44 timesteps (reward: 44.0) | |
Finished episode 1909 after 40 timesteps (reward: 40.0) | |
Finished episode 1910 after 40 timesteps (reward: 40.0) | |
Finished episode 1911 after 46 timesteps (reward: 46.0) | |
Finished episode 1912 after 61 timesteps (reward: 61.0) | |
Finished episode 1913 after 60 timesteps (reward: 60.0) | |
Finished episode 1914 after 54 timesteps (reward: 54.0) | |
Finished episode 1915 after 66 timesteps (reward: 66.0) | |
Finished episode 1916 after 38 timesteps (reward: 38.0) | |
Finished episode 1917 after 53 timesteps (reward: 53.0) | |
Finished episode 1918 after 31 timesteps (reward: 31.0) | |
Finished episode 1919 after 47 timesteps (reward: 47.0) | |
Finished episode 1920 after 48 timesteps (reward: 48.0) | |
Finished episode 1921 after 52 timesteps (reward: 52.0) | |
Finished episode 1922 after 81 timesteps (reward: 81.0) | |
Finished episode 1923 after 35 timesteps (reward: 35.0) | |
Finished episode 1924 after 45 timesteps (reward: 45.0) | |
Finished episode 1925 after 45 timesteps (reward: 45.0) | |
Finished episode 1926 after 52 timesteps (reward: 52.0) | |
Finished episode 1927 after 47 timesteps (reward: 47.0) | |
Finished episode 1928 after 44 timesteps (reward: 44.0) | |
Finished episode 1929 after 65 timesteps (reward: 65.0) | |
Finished episode 1930 after 38 timesteps (reward: 38.0) | |
Finished episode 1931 after 43 timesteps (reward: 43.0) | |
Finished episode 1932 after 56 timesteps (reward: 56.0) | |
Finished episode 1933 after 47 timesteps (reward: 47.0) | |
Finished episode 1934 after 42 timesteps (reward: 42.0) | |
Finished episode 1935 after 48 timesteps (reward: 48.0) | |
Finished episode 1936 after 71 timesteps (reward: 71.0) | |
Finished episode 1937 after 36 timesteps (reward: 36.0) | |
Finished episode 1938 after 50 timesteps (reward: 50.0) | |
Finished episode 1939 after 58 timesteps (reward: 58.0) | |
Finished episode 1940 after 47 timesteps (reward: 47.0) | |
Finished episode 1941 after 34 timesteps (reward: 34.0) | |
Finished episode 1942 after 26 timesteps (reward: 26.0) | |
Finished episode 1943 after 60 timesteps (reward: 60.0) | |
Finished episode 1944 after 52 timesteps (reward: 52.0) | |
Finished episode 1945 after 46 timesteps (reward: 46.0) | |
Finished episode 1946 after 111 timesteps (reward: 111.0) | |
Finished episode 1947 after 49 timesteps (reward: 49.0) | |
Finished episode 1948 after 71 timesteps (reward: 71.0) | |
Finished episode 1949 after 40 timesteps (reward: 40.0) | |
Finished episode 1950 after 54 timesteps (reward: 54.0) | |
Finished episode 1951 after 51 timesteps (reward: 51.0) | |
Finished episode 1952 after 38 timesteps (reward: 38.0) | |
Finished episode 1953 after 55 timesteps (reward: 55.0) | |
Finished episode 1954 after 56 timesteps (reward: 56.0) | |
Finished episode 1955 after 46 timesteps (reward: 46.0) | |
Finished episode 1956 after 47 timesteps (reward: 47.0) | |
Finished episode 1957 after 34 timesteps (reward: 34.0) | |
Finished episode 1958 after 79 timesteps (reward: 79.0) | |
Finished episode 1959 after 47 timesteps (reward: 47.0) | |
Finished episode 1960 after 33 timesteps (reward: 33.0) | |
Finished episode 1961 after 40 timesteps (reward: 40.0) | |
Finished episode 1962 after 60 timesteps (reward: 60.0) | |
Finished episode 1963 after 51 timesteps (reward: 51.0) | |
Finished episode 1964 after 46 timesteps (reward: 46.0) | |
Finished episode 1965 after 36 timesteps (reward: 36.0) | |
Finished episode 1966 after 32 timesteps (reward: 32.0) | |
Finished episode 1967 after 47 timesteps (reward: 47.0) | |
Finished episode 1968 after 76 timesteps (reward: 76.0) | |
Finished episode 1969 after 54 timesteps (reward: 54.0) | |
Finished episode 1970 after 46 timesteps (reward: 46.0) | |
Finished episode 1971 after 50 timesteps (reward: 50.0) | |
Finished episode 1972 after 41 timesteps (reward: 41.0) | |
Finished episode 1973 after 61 timesteps (reward: 61.0) | |
Finished episode 1974 after 63 timesteps (reward: 63.0) | |
Finished episode 1975 after 31 timesteps (reward: 31.0) | |
Finished episode 1976 after 34 timesteps (reward: 34.0) | |
Finished episode 1977 after 45 timesteps (reward: 45.0) | |
Finished episode 1978 after 60 timesteps (reward: 60.0) | |
Finished episode 1979 after 55 timesteps (reward: 55.0) | |
Finished episode 1980 after 47 timesteps (reward: 47.0) | |
Finished episode 1981 after 49 timesteps (reward: 49.0) | |
Finished episode 1982 after 35 timesteps (reward: 35.0) | |
Finished episode 1983 after 46 timesteps (reward: 46.0) | |
Finished episode 1984 after 37 timesteps (reward: 37.0) | |
Finished episode 1985 after 66 timesteps (reward: 66.0) | |
Finished episode 1986 after 83 timesteps (reward: 83.0) | |
Finished episode 1987 after 53 timesteps (reward: 53.0) | |
Finished episode 1988 after 61 timesteps (reward: 61.0) | |
Finished episode 1989 after 35 timesteps (reward: 35.0) | |
Finished episode 1990 after 39 timesteps (reward: 39.0) | |
Finished episode 1991 after 49 timesteps (reward: 49.0) | |
Finished episode 1992 after 61 timesteps (reward: 61.0) | |
Finished episode 1993 after 34 timesteps (reward: 34.0) | |
Finished episode 1994 after 57 timesteps (reward: 57.0) | |
Finished episode 1995 after 46 timesteps (reward: 46.0) | |
Finished episode 1996 after 58 timesteps (reward: 58.0) | |
Finished episode 1997 after 46 timesteps (reward: 46.0) | |
Finished episode 1998 after 45 timesteps (reward: 45.0) | |
Finished episode 1999 after 45 timesteps (reward: 45.0) | |
Finished episode 2000 after 25 timesteps (reward: 25.0) | |
Finished episode 2001 after 47 timesteps (reward: 47.0) | |
Finished episode 2002 after 34 timesteps (reward: 34.0) | |
Finished episode 2003 after 37 timesteps (reward: 37.0) | |
Finished episode 2004 after 52 timesteps (reward: 52.0) | |
Finished episode 2005 after 27 timesteps (reward: 27.0) | |
Finished episode 2006 after 48 timesteps (reward: 48.0) | |
Finished episode 2007 after 64 timesteps (reward: 64.0) | |
Finished episode 2008 after 34 timesteps (reward: 34.0) | |
Finished episode 2009 after 54 timesteps (reward: 54.0) | |
Finished episode 2010 after 45 timesteps (reward: 45.0) | |
Finished episode 2011 after 49 timesteps (reward: 49.0) | |
Finished episode 2012 after 44 timesteps (reward: 44.0) | |
Finished episode 2013 after 52 timesteps (reward: 52.0) | |
Finished episode 2014 after 35 timesteps (reward: 35.0) | |
Finished episode 2015 after 58 timesteps (reward: 58.0) | |
Finished episode 2016 after 48 timesteps (reward: 48.0) | |
Finished episode 2017 after 39 timesteps (reward: 39.0) | |
Finished episode 2018 after 34 timesteps (reward: 34.0) | |
Finished episode 2019 after 44 timesteps (reward: 44.0) | |
Finished episode 2020 after 66 timesteps (reward: 66.0) | |
Finished episode 2021 after 43 timesteps (reward: 43.0) | |
Finished episode 2022 after 63 timesteps (reward: 63.0) | |
Finished episode 2023 after 43 timesteps (reward: 43.0) | |
Finished episode 2024 after 38 timesteps (reward: 38.0) | |
Finished episode 2025 after 33 timesteps (reward: 33.0) | |
Finished episode 2026 after 55 timesteps (reward: 55.0) | |
Finished episode 2027 after 37 timesteps (reward: 37.0) | |
Finished episode 2028 after 48 timesteps (reward: 48.0) | |
Finished episode 2029 after 34 timesteps (reward: 34.0) | |
Finished episode 2030 after 32 timesteps (reward: 32.0) | |
Finished episode 2031 after 52 timesteps (reward: 52.0) | |
Finished episode 2032 after 52 timesteps (reward: 52.0) | |
Finished episode 2033 after 37 timesteps (reward: 37.0) | |
Finished episode 2034 after 41 timesteps (reward: 41.0) | |
Finished episode 2035 after 41 timesteps (reward: 41.0) | |
Finished episode 2036 after 49 timesteps (reward: 49.0) | |
Finished episode 2037 after 47 timesteps (reward: 47.0) | |
Finished episode 2038 after 34 timesteps (reward: 34.0) | |
Finished episode 2039 after 44 timesteps (reward: 44.0) | |
Finished episode 2040 after 34 timesteps (reward: 34.0) | |
Finished episode 2041 after 52 timesteps (reward: 52.0) | |
Finished episode 2042 after 43 timesteps (reward: 43.0) | |
Finished episode 2043 after 46 timesteps (reward: 46.0) | |
Finished episode 2044 after 35 timesteps (reward: 35.0) | |
Finished episode 2045 after 50 timesteps (reward: 50.0) | |
Finished episode 2046 after 51 timesteps (reward: 51.0) | |
Finished episode 2047 after 60 timesteps (reward: 60.0) | |
Finished episode 2048 after 41 timesteps (reward: 41.0) | |
Finished episode 2049 after 24 timesteps (reward: 24.0) | |
Finished episode 2050 after 33 timesteps (reward: 33.0) | |
Finished episode 2051 after 52 timesteps (reward: 52.0) | |
Finished episode 2052 after 33 timesteps (reward: 33.0) | |
Finished episode 2053 after 33 timesteps (reward: 33.0) | |
Finished episode 2054 after 53 timesteps (reward: 53.0) | |
Finished episode 2055 after 43 timesteps (reward: 43.0) | |
Finished episode 2056 after 41 timesteps (reward: 41.0) | |
Finished episode 2057 after 49 timesteps (reward: 49.0) | |
Finished episode 2058 after 45 timesteps (reward: 45.0) | |
Finished episode 2059 after 24 timesteps (reward: 24.0) | |
Finished episode 2060 after 33 timesteps (reward: 33.0) | |
Finished episode 2061 after 39 timesteps (reward: 39.0) | |
Finished episode 2062 after 34 timesteps (reward: 34.0) | |
Finished episode 2063 after 35 timesteps (reward: 35.0) | |
Finished episode 2064 after 50 timesteps (reward: 50.0) | |
Finished episode 2065 after 37 timesteps (reward: 37.0) | |
Finished episode 2066 after 25 timesteps (reward: 25.0) | |
Finished episode 2067 after 50 timesteps (reward: 50.0) | |
Finished episode 2068 after 42 timesteps (reward: 42.0) | |
Finished episode 2069 after 62 timesteps (reward: 62.0) | |
Finished episode 2070 after 36 timesteps (reward: 36.0) | |
Finished episode 2071 after 58 timesteps (reward: 58.0) | |
Finished episode 2072 after 45 timesteps (reward: 45.0) | |
Finished episode 2073 after 45 timesteps (reward: 45.0) | |
Finished episode 2074 after 43 timesteps (reward: 43.0) | |
Finished episode 2075 after 49 timesteps (reward: 49.0) | |
Finished episode 2076 after 63 timesteps (reward: 63.0) | |
Finished episode 2077 after 53 timesteps (reward: 53.0) | |
Finished episode 2078 after 46 timesteps (reward: 46.0) | |
Finished episode 2079 after 45 timesteps (reward: 45.0) | |
Finished episode 2080 after 24 timesteps (reward: 24.0) | |
Finished episode 2081 after 49 timesteps (reward: 49.0) | |
Finished episode 2082 after 35 timesteps (reward: 35.0) | |
Finished episode 2083 after 40 timesteps (reward: 40.0) | |
Finished episode 2084 after 47 timesteps (reward: 47.0) | |
Finished episode 2085 after 60 timesteps (reward: 60.0) | |
Finished episode 2086 after 46 timesteps (reward: 46.0) | |
Finished episode 2087 after 34 timesteps (reward: 34.0) | |
Finished episode 2088 after 58 timesteps (reward: 58.0) | |
Finished episode 2089 after 25 timesteps (reward: 25.0) | |
Finished episode 2090 after 40 timesteps (reward: 40.0) | |
Finished episode 2091 after 46 timesteps (reward: 46.0) | |
Finished episode 2092 after 51 timesteps (reward: 51.0) | |
Finished episode 2093 after 50 timesteps (reward: 50.0) | |
Finished episode 2094 after 45 timesteps (reward: 45.0) | |
Finished episode 2095 after 44 timesteps (reward: 44.0) | |
Finished episode 2096 after 51 timesteps (reward: 51.0) | |
Finished episode 2097 after 56 timesteps (reward: 56.0) | |
Finished episode 2098 after 45 timesteps (reward: 45.0) | |
Finished episode 2099 after 49 timesteps (reward: 49.0) | |
Finished episode 2100 after 59 timesteps (reward: 59.0) | |
Finished episode 2101 after 56 timesteps (reward: 56.0) | |
Finished episode 2102 after 60 timesteps (reward: 60.0) | |
Finished episode 2103 after 56 timesteps (reward: 56.0) | |
Finished episode 2104 after 62 timesteps (reward: 62.0) | |
Finished episode 2105 after 33 timesteps (reward: 33.0) | |
Finished episode 2106 after 48 timesteps (reward: 48.0) | |
Finished episode 2107 after 32 timesteps (reward: 32.0) | |
Finished episode 2108 after 52 timesteps (reward: 52.0) | |
Finished episode 2109 after 39 timesteps (reward: 39.0) | |
Finished episode 2110 after 43 timesteps (reward: 43.0) | |
Finished episode 2111 after 40 timesteps (reward: 40.0) | |
Finished episode 2112 after 50 timesteps (reward: 50.0) | |
Finished episode 2113 after 50 timesteps (reward: 50.0) | |
Finished episode 2114 after 55 timesteps (reward: 55.0) | |
Finished episode 2115 after 55 timesteps (reward: 55.0) | |
Finished episode 2116 after 47 timesteps (reward: 47.0) | |
Finished episode 2117 after 40 timesteps (reward: 40.0) | |
Finished episode 2118 after 47 timesteps (reward: 47.0) | |
Finished episode 2119 after 59 timesteps (reward: 59.0) | |
Finished episode 2120 after 54 timesteps (reward: 54.0) | |
Finished episode 2121 after 56 timesteps (reward: 56.0) | |
Finished episode 2122 after 33 timesteps (reward: 33.0) | |
Finished episode 2123 after 32 timesteps (reward: 32.0) | |
Finished episode 2124 after 46 timesteps (reward: 46.0) | |
Finished episode 2125 after 37 timesteps (reward: 37.0) | |
Finished episode 2126 after 45 timesteps (reward: 45.0) | |
Finished episode 2127 after 40 timesteps (reward: 40.0) | |
Finished episode 2128 after 47 timesteps (reward: 47.0) | |
Finished episode 2129 after 41 timesteps (reward: 41.0) | |
Finished episode 2130 after 47 timesteps (reward: 47.0) | |
Finished episode 2131 after 55 timesteps (reward: 55.0) | |
Finished episode 2132 after 34 timesteps (reward: 34.0) | |
Finished episode 2133 after 34 timesteps (reward: 34.0) | |
Finished episode 2134 after 38 timesteps (reward: 38.0) | |
Finished episode 2135 after 51 timesteps (reward: 51.0) | |
Finished episode 2136 after 78 timesteps (reward: 78.0) | |
Finished episode 2137 after 69 timesteps (reward: 69.0) | |
Finished episode 2138 after 34 timesteps (reward: 34.0) | |
Finished episode 2139 after 59 timesteps (reward: 59.0) | |
Finished episode 2140 after 62 timesteps (reward: 62.0) | |
Finished episode 2141 after 53 timesteps (reward: 53.0) | |
Finished episode 2142 after 39 timesteps (reward: 39.0) | |
Finished episode 2143 after 68 timesteps (reward: 68.0) | |
Finished episode 2144 after 25 timesteps (reward: 25.0) | |
Finished episode 2145 after 43 timesteps (reward: 43.0) | |
Finished episode 2146 after 51 timesteps (reward: 51.0) | |
Finished episode 2147 after 71 timesteps (reward: 71.0) | |
Finished episode 2148 after 44 timesteps (reward: 44.0) | |
Finished episode 2149 after 43 timesteps (reward: 43.0) | |
Finished episode 2150 after 46 timesteps (reward: 46.0) | |
Finished episode 2151 after 68 timesteps (reward: 68.0) | |
Finished episode 2152 after 38 timesteps (reward: 38.0) | |
Finished episode 2153 after 43 timesteps (reward: 43.0) | |
Finished episode 2154 after 46 timesteps (reward: 46.0) | |
Finished episode 2155 after 24 timesteps (reward: 24.0) | |
Finished episode 2156 after 50 timesteps (reward: 50.0) | |
Finished episode 2157 after 51 timesteps (reward: 51.0) | |
Finished episode 2158 after 50 timesteps (reward: 50.0) | |
Finished episode 2159 after 46 timesteps (reward: 46.0) | |
Finished episode 2160 after 60 timesteps (reward: 60.0) | |
Finished episode 2161 after 44 timesteps (reward: 44.0) | |
Finished episode 2162 after 43 timesteps (reward: 43.0) | |
Finished episode 2163 after 47 timesteps (reward: 47.0) | |
Finished episode 2164 after 42 timesteps (reward: 42.0) | |
Finished episode 2165 after 62 timesteps (reward: 62.0) | |
Finished episode 2166 after 25 timesteps (reward: 25.0) | |
Finished episode 2167 after 39 timesteps (reward: 39.0) | |
Finished episode 2168 after 41 timesteps (reward: 41.0) | |
Finished episode 2169 after 34 timesteps (reward: 34.0) | |
Finished episode 2170 after 52 timesteps (reward: 52.0) | |
Finished episode 2171 after 61 timesteps (reward: 61.0) | |
Finished episode 2172 after 46 timesteps (reward: 46.0) | |
Finished episode 2173 after 39 timesteps (reward: 39.0) | |
Finished episode 2174 after 40 timesteps (reward: 40.0) | |
Finished episode 2175 after 42 timesteps (reward: 42.0) | |
Finished episode 2176 after 45 timesteps (reward: 45.0) | |
Finished episode 2177 after 77 timesteps (reward: 77.0) | |
Finished episode 2178 after 42 timesteps (reward: 42.0) | |
Finished episode 2179 after 45 timesteps (reward: 45.0) | |
Finished episode 2180 after 45 timesteps (reward: 45.0) | |
Finished episode 2181 after 44 timesteps (reward: 44.0) | |
Finished episode 2182 after 35 timesteps (reward: 35.0) | |
Finished episode 2183 after 35 timesteps (reward: 35.0) | |
Finished episode 2184 after 34 timesteps (reward: 34.0) | |
Finished episode 2185 after 27 timesteps (reward: 27.0) | |
Finished episode 2186 after 33 timesteps (reward: 33.0) | |
Finished episode 2187 after 32 timesteps (reward: 32.0) | |
Finished episode 2188 after 31 timesteps (reward: 31.0) | |
Finished episode 2189 after 38 timesteps (reward: 38.0) | |
Finished episode 2190 after 54 timesteps (reward: 54.0) | |
Finished episode 2191 after 48 timesteps (reward: 48.0) | |
Finished episode 2192 after 56 timesteps (reward: 56.0) | |
Finished episode 2193 after 63 timesteps (reward: 63.0) | |
Finished episode 2194 after 54 timesteps (reward: 54.0) | |
Finished episode 2195 after 24 timesteps (reward: 24.0) | |
Finished episode 2196 after 55 timesteps (reward: 55.0) | |
Finished episode 2197 after 44 timesteps (reward: 44.0) | |
Finished episode 2198 after 39 timesteps (reward: 39.0) | |
Finished episode 2199 after 47 timesteps (reward: 47.0) | |
Finished episode 2200 after 56 timesteps (reward: 56.0) | |
Finished episode 2201 after 33 timesteps (reward: 33.0) | |
Finished episode 2202 after 42 timesteps (reward: 42.0) | |
Finished episode 2203 after 39 timesteps (reward: 39.0) | |
Finished episode 2204 after 54 timesteps (reward: 54.0) | |
Finished episode 2205 after 42 timesteps (reward: 42.0) | |
Finished episode 2206 after 31 timesteps (reward: 31.0) | |
Finished episode 2207 after 52 timesteps (reward: 52.0) | |
Finished episode 2208 after 38 timesteps (reward: 38.0) | |
Finished episode 2209 after 31 timesteps (reward: 31.0) | |
Finished episode 2210 after 38 timesteps (reward: 38.0) | |
Finished episode 2211 after 48 timesteps (reward: 48.0) | |
Finished episode 2212 after 40 timesteps (reward: 40.0) | |
Finished episode 2213 after 46 timesteps (reward: 46.0) | |
Finished episode 2214 after 57 timesteps (reward: 57.0) | |
Finished episode 2215 after 53 timesteps (reward: 53.0) | |
Finished episode 2216 after 52 timesteps (reward: 52.0) | |
Finished episode 2217 after 43 timesteps (reward: 43.0) | |
Finished episode 2218 after 39 timesteps (reward: 39.0) | |
Finished episode 2219 after 38 timesteps (reward: 38.0) | |
Finished episode 2220 after 34 timesteps (reward: 34.0) | |
Finished episode 2221 after 40 timesteps (reward: 40.0) | |
Finished episode 2222 after 44 timesteps (reward: 44.0) | |
Finished episode 2223 after 26 timesteps (reward: 26.0) | |
Finished episode 2224 after 47 timesteps (reward: 47.0) | |
Finished episode 2225 after 61 timesteps (reward: 61.0) | |
Finished episode 2226 after 53 timesteps (reward: 53.0) | |
Finished episode 2227 after 39 timesteps (reward: 39.0) | |
Finished episode 2228 after 51 timesteps (reward: 51.0) | |
Finished episode 2229 after 58 timesteps (reward: 58.0) | |
Finished episode 2230 after 56 timesteps (reward: 56.0) | |
Finished episode 2231 after 40 timesteps (reward: 40.0) | |
Finished episode 2232 after 40 timesteps (reward: 40.0) | |
Finished episode 2233 after 24 timesteps (reward: 24.0) | |
Finished episode 2234 after 43 timesteps (reward: 43.0) | |
Finished episode 2235 after 41 timesteps (reward: 41.0) | |
Finished episode 2236 after 45 timesteps (reward: 45.0) | |
Finished episode 2237 after 57 timesteps (reward: 57.0) | |
Finished episode 2238 after 38 timesteps (reward: 38.0) | |
Finished episode 2239 after 48 timesteps (reward: 48.0) | |
Finished episode 2240 after 46 timesteps (reward: 46.0) | |
Finished episode 2241 after 48 timesteps (reward: 48.0) | |
Finished episode 2242 after 41 timesteps (reward: 41.0) | |
Finished episode 2243 after 34 timesteps (reward: 34.0) | |
Finished episode 2244 after 26 timesteps (reward: 26.0) | |
Finished episode 2245 after 40 timesteps (reward: 40.0) | |
Finished episode 2246 after 25 timesteps (reward: 25.0) | |
Finished episode 2247 after 58 timesteps (reward: 58.0) | |
Finished episode 2248 after 39 timesteps (reward: 39.0) | |
Finished episode 2249 after 39 timesteps (reward: 39.0) | |
Finished episode 2250 after 50 timesteps (reward: 50.0) | |
Finished episode 2251 after 46 timesteps (reward: 46.0) | |
Finished episode 2252 after 38 timesteps (reward: 38.0) | |
Finished episode 2253 after 39 timesteps (reward: 39.0) | |
Finished episode 2254 after 49 timesteps (reward: 49.0) | |
Finished episode 2255 after 60 timesteps (reward: 60.0) | |
Finished episode 2256 after 26 timesteps (reward: 26.0) | |
Finished episode 2257 after 50 timesteps (reward: 50.0) | |
Finished episode 2258 after 40 timesteps (reward: 40.0) | |
Finished episode 2259 after 39 timesteps (reward: 39.0) | |
Finished episode 2260 after 39 timesteps (reward: 39.0) | |
Finished episode 2261 after 38 timesteps (reward: 38.0) | |
Finished episode 2262 after 46 timesteps (reward: 46.0) | |
Finished episode 2263 after 45 timesteps (reward: 45.0) | |
Finished episode 2264 after 40 timesteps (reward: 40.0) | |
Finished episode 2265 after 33 timesteps (reward: 33.0) | |
Finished episode 2266 after 49 timesteps (reward: 49.0) | |
Finished episode 2267 after 41 timesteps (reward: 41.0) | |
Finished episode 2268 after 27 timesteps (reward: 27.0) | |
Finished episode 2269 after 43 timesteps (reward: 43.0) | |
Finished episode 2270 after 35 timesteps (reward: 35.0) | |
Finished episode 2271 after 34 timesteps (reward: 34.0) | |
Finished episode 2272 after 34 timesteps (reward: 34.0) | |
Finished episode 2273 after 25 timesteps (reward: 25.0) | |
Finished episode 2274 after 35 timesteps (reward: 35.0) | |
Finished episode 2275 after 47 timesteps (reward: 47.0) | |
Finished episode 2276 after 34 timesteps (reward: 34.0) | |
Finished episode 2277 after 34 timesteps (reward: 34.0) | |
Finished episode 2278 after 53 timesteps (reward: 53.0) | |
Finished episode 2279 after 53 timesteps (reward: 53.0) | |
Finished episode 2280 after 33 timesteps (reward: 33.0) | |
Finished episode 2281 after 41 timesteps (reward: 41.0) | |
Finished episode 2282 after 56 timesteps (reward: 56.0) | |
Finished episode 2283 after 34 timesteps (reward: 34.0) | |
Finished episode 2284 after 36 timesteps (reward: 36.0) | |
Finished episode 2285 after 27 timesteps (reward: 27.0) | |
Finished episode 2286 after 46 timesteps (reward: 46.0) | |
Finished episode 2287 after 24 timesteps (reward: 24.0) | |
Finished episode 2288 after 44 timesteps (reward: 44.0) | |
Finished episode 2289 after 37 timesteps (reward: 37.0) | |
Finished episode 2290 after 50 timesteps (reward: 50.0) | |
Finished episode 2291 after 39 timesteps (reward: 39.0) | |
Finished episode 2292 after 39 timesteps (reward: 39.0) | |
Finished episode 2293 after 24 timesteps (reward: 24.0) | |
Finished episode 2294 after 37 timesteps (reward: 37.0) | |
Finished episode 2295 after 34 timesteps (reward: 34.0) | |
Finished episode 2296 after 43 timesteps (reward: 43.0) | |
Finished episode 2297 after 42 timesteps (reward: 42.0) | |
Finished episode 2298 after 24 timesteps (reward: 24.0) | |
Finished episode 2299 after 42 timesteps (reward: 42.0) | |
Finished episode 2300 after 40 timesteps (reward: 40.0) | |
Finished episode 2301 after 53 timesteps (reward: 53.0) | |
Finished episode 2302 after 38 timesteps (reward: 38.0) | |
Finished episode 2303 after 34 timesteps (reward: 34.0) | |
Finished episode 2304 after 25 timesteps (reward: 25.0) | |
Finished episode 2305 after 34 timesteps (reward: 34.0) | |
Finished episode 2306 after 52 timesteps (reward: 52.0) | |
Finished episode 2307 after 53 timesteps (reward: 53.0) | |
Finished episode 2308 after 36 timesteps (reward: 36.0) | |
Finished episode 2309 after 54 timesteps (reward: 54.0) | |
Finished episode 2310 after 40 timesteps (reward: 40.0) | |
Finished episode 2311 after 40 timesteps (reward: 40.0) | |
Finished episode 2312 after 46 timesteps (reward: 46.0) | |
Finished episode 2313 after 50 timesteps (reward: 50.0) | |
Finished episode 2314 after 35 timesteps (reward: 35.0) | |
Finished episode 2315 after 52 timesteps (reward: 52.0) | |
Finished episode 2316 after 37 timesteps (reward: 37.0) | |
Finished episode 2317 after 46 timesteps (reward: 46.0) | |
Finished episode 2318 after 36 timesteps (reward: 36.0) | |
Finished episode 2319 after 40 timesteps (reward: 40.0) | |
Finished episode 2320 after 35 timesteps (reward: 35.0) | |
Finished episode 2321 after 38 timesteps (reward: 38.0) | |
Finished episode 2322 after 24 timesteps (reward: 24.0) | |
Finished episode 2323 after 35 timesteps (reward: 35.0) | |
Finished episode 2324 after 38 timesteps (reward: 38.0) | |
Finished episode 2325 after 34 timesteps (reward: 34.0) | |
Finished episode 2326 after 46 timesteps (reward: 46.0) | |
Finished episode 2327 after 38 timesteps (reward: 38.0) | |
Finished episode 2328 after 38 timesteps (reward: 38.0) | |
Finished episode 2329 after 33 timesteps (reward: 33.0) | |
Finished episode 2330 after 30 timesteps (reward: 30.0) | |
Finished episode 2331 after 24 timesteps (reward: 24.0) | |
Finished episode 2332 after 40 timesteps (reward: 40.0) | |
Finished episode 2333 after 31 timesteps (reward: 31.0) | |
Finished episode 2334 after 44 timesteps (reward: 44.0) | |
Finished episode 2335 after 48 timesteps (reward: 48.0) | |
Finished episode 2336 after 47 timesteps (reward: 47.0) | |
Finished episode 2337 after 48 timesteps (reward: 48.0) | |
Finished episode 2338 after 51 timesteps (reward: 51.0) | |
Finished episode 2339 after 37 timesteps (reward: 37.0) | |
Finished episode 2340 after 34 timesteps (reward: 34.0) | |
Finished episode 2341 after 27 timesteps (reward: 27.0) | |
Finished episode 2342 after 26 timesteps (reward: 26.0) | |
Finished episode 2343 after 31 timesteps (reward: 31.0) | |
Finished episode 2344 after 39 timesteps (reward: 39.0) | |
Finished episode 2345 after 45 timesteps (reward: 45.0) | |
Finished episode 2346 after 41 timesteps (reward: 41.0) | |
Finished episode 2347 after 36 timesteps (reward: 36.0) | |
Finished episode 2348 after 41 timesteps (reward: 41.0) | |
Finished episode 2349 after 25 timesteps (reward: 25.0) | |
Finished episode 2350 after 42 timesteps (reward: 42.0) | |
Finished episode 2351 after 33 timesteps (reward: 33.0) | |
Finished episode 2352 after 48 timesteps (reward: 48.0) | |
Finished episode 2353 after 48 timesteps (reward: 48.0) | |
Finished episode 2354 after 31 timesteps (reward: 31.0) | |
Finished episode 2355 after 35 timesteps (reward: 35.0) | |
Finished episode 2356 after 33 timesteps (reward: 33.0) | |
Finished episode 2357 after 32 timesteps (reward: 32.0) | |
Finished episode 2358 after 50 timesteps (reward: 50.0) | |
Finished episode 2359 after 32 timesteps (reward: 32.0) | |
Finished episode 2360 after 33 timesteps (reward: 33.0) | |
Finished episode 2361 after 66 timesteps (reward: 66.0) | |
Finished episode 2362 after 44 timesteps (reward: 44.0) | |
Finished episode 2363 after 38 timesteps (reward: 38.0) | |
Finished episode 2364 after 44 timesteps (reward: 44.0) | |
Finished episode 2365 after 24 timesteps (reward: 24.0) | |
Finished episode 2366 after 45 timesteps (reward: 45.0) | |
Finished episode 2367 after 39 timesteps (reward: 39.0) | |
Finished episode 2368 after 32 timesteps (reward: 32.0) | |
Finished episode 2369 after 50 timesteps (reward: 50.0) | |
Finished episode 2370 after 33 timesteps (reward: 33.0) | |
Finished episode 2371 after 24 timesteps (reward: 24.0) | |
Finished episode 2372 after 48 timesteps (reward: 48.0) | |
Finished episode 2373 after 43 timesteps (reward: 43.0) | |
Finished episode 2374 after 25 timesteps (reward: 25.0) | |
Finished episode 2375 after 44 timesteps (reward: 44.0) | |
Finished episode 2376 after 35 timesteps (reward: 35.0) | |
Finished episode 2377 after 39 timesteps (reward: 39.0) | |
Finished episode 2378 after 23 timesteps (reward: 23.0) | |
Finished episode 2379 after 41 timesteps (reward: 41.0) | |
Finished episode 2380 after 44 timesteps (reward: 44.0) | |
Finished episode 2381 after 52 timesteps (reward: 52.0) | |
Finished episode 2382 after 48 timesteps (reward: 48.0) | |
Finished episode 2383 after 51 timesteps (reward: 51.0) | |
Finished episode 2384 after 46 timesteps (reward: 46.0) | |
Finished episode 2385 after 24 timesteps (reward: 24.0) | |
Finished episode 2386 after 24 timesteps (reward: 24.0) | |
Finished episode 2387 after 41 timesteps (reward: 41.0) | |
Finished episode 2388 after 34 timesteps (reward: 34.0) | |
Finished episode 2389 after 24 timesteps (reward: 24.0) | |
Finished episode 2390 after 31 timesteps (reward: 31.0) | |
Finished episode 2391 after 37 timesteps (reward: 37.0) | |
Finished episode 2392 after 50 timesteps (reward: 50.0) | |
Finished episode 2393 after 31 timesteps (reward: 31.0) | |
Finished episode 2394 after 36 timesteps (reward: 36.0) | |
Finished episode 2395 after 37 timesteps (reward: 37.0) | |
Finished episode 2396 after 35 timesteps (reward: 35.0) | |
Finished episode 2397 after 43 timesteps (reward: 43.0) | |
Finished episode 2398 after 34 timesteps (reward: 34.0) | |
Finished episode 2399 after 40 timesteps (reward: 40.0) | |
Finished episode 2400 after 32 timesteps (reward: 32.0) | |
Finished episode 2401 after 42 timesteps (reward: 42.0) | |
Finished episode 2402 after 31 timesteps (reward: 31.0) | |
Finished episode 2403 after 32 timesteps (reward: 32.0) | |
Finished episode 2404 after 41 timesteps (reward: 41.0) | |
Finished episode 2405 after 44 timesteps (reward: 44.0) | |
Finished episode 2406 after 52 timesteps (reward: 52.0) | |
Finished episode 2407 after 44 timesteps (reward: 44.0) | |
Finished episode 2408 after 35 timesteps (reward: 35.0) | |
Finished episode 2409 after 39 timesteps (reward: 39.0) | |
Finished episode 2410 after 35 timesteps (reward: 35.0) | |
Finished episode 2411 after 31 timesteps (reward: 31.0) | |
Finished episode 2412 after 41 timesteps (reward: 41.0) | |
Finished episode 2413 after 23 timesteps (reward: 23.0) | |
Finished episode 2414 after 35 timesteps (reward: 35.0) | |
Finished episode 2415 after 29 timesteps (reward: 29.0) | |
Finished episode 2416 after 49 timesteps (reward: 49.0) | |
Finished episode 2417 after 51 timesteps (reward: 51.0) | |
Finished episode 2418 after 36 timesteps (reward: 36.0) | |
Finished episode 2419 after 34 timesteps (reward: 34.0) | |
Finished episode 2420 after 25 timesteps (reward: 25.0) | |
Finished episode 2421 after 38 timesteps (reward: 38.0) | |
Finished episode 2422 after 25 timesteps (reward: 25.0) | |
Finished episode 2423 after 24 timesteps (reward: 24.0) | |
Finished episode 2424 after 30 timesteps (reward: 30.0) | |
Finished episode 2425 after 29 timesteps (reward: 29.0) | |
Finished episode 2426 after 46 timesteps (reward: 46.0) | |
Finished episode 2427 after 30 timesteps (reward: 30.0) | |
Finished episode 2428 after 33 timesteps (reward: 33.0) | |
Finished episode 2429 after 55 timesteps (reward: 55.0) | |
Finished episode 2430 after 41 timesteps (reward: 41.0) | |
Finished episode 2431 after 25 timesteps (reward: 25.0) | |
Finished episode 2432 after 50 timesteps (reward: 50.0) | |
Finished episode 2433 after 36 timesteps (reward: 36.0) | |
Finished episode 2434 after 31 timesteps (reward: 31.0) | |
Finished episode 2435 after 29 timesteps (reward: 29.0) | |
Finished episode 2436 after 34 timesteps (reward: 34.0) | |
Finished episode 2437 after 38 timesteps (reward: 38.0) | |
Finished episode 2438 after 33 timesteps (reward: 33.0) | |
Finished episode 2439 after 31 timesteps (reward: 31.0) | |
Finished episode 2440 after 33 timesteps (reward: 33.0) | |
Finished episode 2441 after 49 timesteps (reward: 49.0) | |
Finished episode 2442 after 36 timesteps (reward: 36.0) | |
Finished episode 2443 after 39 timesteps (reward: 39.0) | |
Finished episode 2444 after 27 timesteps (reward: 27.0) | |
Finished episode 2445 after 35 timesteps (reward: 35.0) | |
Finished episode 2446 after 45 timesteps (reward: 45.0) | |
Finished episode 2447 after 39 timesteps (reward: 39.0) | |
Finished episode 2448 after 44 timesteps (reward: 44.0) | |
Finished episode 2449 after 38 timesteps (reward: 38.0) | |
Finished episode 2450 after 34 timesteps (reward: 34.0) | |
Finished episode 2451 after 31 timesteps (reward: 31.0) | |
Finished episode 2452 after 49 timesteps (reward: 49.0) | |
Finished episode 2453 after 45 timesteps (reward: 45.0) | |
Finished episode 2454 after 44 timesteps (reward: 44.0) | |
Finished episode 2455 after 25 timesteps (reward: 25.0) | |
Finished episode 2456 after 38 timesteps (reward: 38.0) | |
Finished episode 2457 after 34 timesteps (reward: 34.0) | |
Finished episode 2458 after 42 timesteps (reward: 42.0) | |
Finished episode 2459 after 48 timesteps (reward: 48.0) | |
Finished episode 2460 after 36 timesteps (reward: 36.0) | |
Finished episode 2461 after 49 timesteps (reward: 49.0) | |
Finished episode 2462 after 46 timesteps (reward: 46.0) | |
Finished episode 2463 after 31 timesteps (reward: 31.0) | |
Finished episode 2464 after 28 timesteps (reward: 28.0) | |
Finished episode 2465 after 35 timesteps (reward: 35.0) | |
Finished episode 2466 after 43 timesteps (reward: 43.0) | |
Finished episode 2467 after 46 timesteps (reward: 46.0) | |
Finished episode 2468 after 32 timesteps (reward: 32.0) | |
Finished episode 2469 after 36 timesteps (reward: 36.0) | |
Finished episode 2470 after 36 timesteps (reward: 36.0) | |
Finished episode 2471 after 45 timesteps (reward: 45.0) | |
Finished episode 2472 after 35 timesteps (reward: 35.0) | |
Finished episode 2473 after 37 timesteps (reward: 37.0) | |
Finished episode 2474 after 25 timesteps (reward: 25.0) | |
Finished episode 2475 after 36 timesteps (reward: 36.0) | |
Finished episode 2476 after 45 timesteps (reward: 45.0) | |
Finished episode 2477 after 45 timesteps (reward: 45.0) | |
Finished episode 2478 after 29 timesteps (reward: 29.0) | |
Finished episode 2479 after 33 timesteps (reward: 33.0) | |
Finished episode 2480 after 51 timesteps (reward: 51.0) | |
Finished episode 2481 after 33 timesteps (reward: 33.0) | |
Finished episode 2482 after 48 timesteps (reward: 48.0) | |
Finished episode 2483 after 30 timesteps (reward: 30.0) | |
Finished episode 2484 after 42 timesteps (reward: 42.0) | |
Finished episode 2485 after 26 timesteps (reward: 26.0) | |
Finished episode 2486 after 46 timesteps (reward: 46.0) | |
Finished episode 2487 after 40 timesteps (reward: 40.0) | |
Finished episode 2488 after 33 timesteps (reward: 33.0) | |
Finished episode 2489 after 43 timesteps (reward: 43.0) | |
Finished episode 2490 after 38 timesteps (reward: 38.0) | |
Finished episode 2491 after 33 timesteps (reward: 33.0) | |
Finished episode 2492 after 52 timesteps (reward: 52.0) | |
Finished episode 2493 after 41 timesteps (reward: 41.0) | |
Finished episode 2494 after 36 timesteps (reward: 36.0) | |
Finished episode 2495 after 40 timesteps (reward: 40.0) | |
Finished episode 2496 after 24 timesteps (reward: 24.0) | |
Finished episode 2497 after 27 timesteps (reward: 27.0) | |
Finished episode 2498 after 44 timesteps (reward: 44.0) | |
Finished episode 2499 after 27 timesteps (reward: 27.0) | |
Finished episode 2500 after 35 timesteps (reward: 35.0) | |
Finished episode 2501 after 41 timesteps (reward: 41.0) | |
Finished episode 2502 after 47 timesteps (reward: 47.0) | |
Finished episode 2503 after 31 timesteps (reward: 31.0) | |
Finished episode 2504 after 25 timesteps (reward: 25.0) | |
Finished episode 2505 after 42 timesteps (reward: 42.0) | |
Finished episode 2506 after 24 timesteps (reward: 24.0) | |
Finished episode 2507 after 47 timesteps (reward: 47.0) | |
Finished episode 2508 after 39 timesteps (reward: 39.0) | |
Finished episode 2509 after 35 timesteps (reward: 35.0) | |
Finished episode 2510 after 26 timesteps (reward: 26.0) | |
Finished episode 2511 after 45 timesteps (reward: 45.0) | |
Finished episode 2512 after 29 timesteps (reward: 29.0) | |
Finished episode 2513 after 42 timesteps (reward: 42.0) | |
Finished episode 2514 after 45 timesteps (reward: 45.0) | |
Finished episode 2515 after 23 timesteps (reward: 23.0) | |
Finished episode 2516 after 29 timesteps (reward: 29.0) | |
Finished episode 2517 after 34 timesteps (reward: 34.0) | |
Finished episode 2518 after 34 timesteps (reward: 34.0) | |
Finished episode 2519 after 38 timesteps (reward: 38.0) | |
Finished episode 2520 after 41 timesteps (reward: 41.0) | |
Finished episode 2521 after 38 timesteps (reward: 38.0) | |
Finished episode 2522 after 45 timesteps (reward: 45.0) | |
Finished episode 2523 after 34 timesteps (reward: 34.0) | |
Finished episode 2524 after 32 timesteps (reward: 32.0) | |
Finished episode 2525 after 25 timesteps (reward: 25.0) | |
Finished episode 2526 after 31 timesteps (reward: 31.0) | |
Finished episode 2527 after 33 timesteps (reward: 33.0) | |
Finished episode 2528 after 48 timesteps (reward: 48.0) | |
Finished episode 2529 after 52 timesteps (reward: 52.0) | |
Finished episode 2530 after 27 timesteps (reward: 27.0) | |
Finished episode 2531 after 39 timesteps (reward: 39.0) | |
Finished episode 2532 after 25 timesteps (reward: 25.0) | |
Finished episode 2533 after 30 timesteps (reward: 30.0) | |
Finished episode 2534 after 42 timesteps (reward: 42.0) | |
Finished episode 2535 after 41 timesteps (reward: 41.0) | |
Finished episode 2536 after 35 timesteps (reward: 35.0) | |
Finished episode 2537 after 49 timesteps (reward: 49.0) | |
Finished episode 2538 after 24 timesteps (reward: 24.0) | |
Finished episode 2539 after 32 timesteps (reward: 32.0) | |
Finished episode 2540 after 40 timesteps (reward: 40.0) | |
Finished episode 2541 after 46 timesteps (reward: 46.0) | |
Finished episode 2542 after 23 timesteps (reward: 23.0) | |
Finished episode 2543 after 39 timesteps (reward: 39.0) | |
Finished episode 2544 after 33 timesteps (reward: 33.0) | |
Finished episode 2545 after 33 timesteps (reward: 33.0) | |
Finished episode 2546 after 36 timesteps (reward: 36.0) | |
Finished episode 2547 after 45 timesteps (reward: 45.0) | |
Finished episode 2548 after 36 timesteps (reward: 36.0) | |
Finished episode 2549 after 33 timesteps (reward: 33.0) | |
Finished episode 2550 after 46 timesteps (reward: 46.0) | |
Finished episode 2551 after 35 timesteps (reward: 35.0) | |
Finished episode 2552 after 53 timesteps (reward: 53.0) | |
Finished episode 2553 after 35 timesteps (reward: 35.0) | |
Finished episode 2554 after 26 timesteps (reward: 26.0) | |
Finished episode 2555 after 36 timesteps (reward: 36.0) | |
Finished episode 2556 after 38 timesteps (reward: 38.0) | |
Finished episode 2557 after 24 timesteps (reward: 24.0) | |
Finished episode 2558 after 34 timesteps (reward: 34.0) | |
Finished episode 2559 after 47 timesteps (reward: 47.0) | |
Finished episode 2560 after 59 timesteps (reward: 59.0) | |
Finished episode 2561 after 30 timesteps (reward: 30.0) | |
Finished episode 2562 after 27 timesteps (reward: 27.0) | |
Finished episode 2563 after 24 timesteps (reward: 24.0) | |
Finished episode 2564 after 38 timesteps (reward: 38.0) | |
Finished episode 2565 after 38 timesteps (reward: 38.0) | |
Finished episode 2566 after 34 timesteps (reward: 34.0) | |
Finished episode 2567 after 43 timesteps (reward: 43.0) | |
Finished episode 2568 after 29 timesteps (reward: 29.0) | |
Finished episode 2569 after 26 timesteps (reward: 26.0) | |
Finished episode 2570 after 35 timesteps (reward: 35.0) | |
Finished episode 2571 after 25 timesteps (reward: 25.0) | |
Finished episode 2572 after 37 timesteps (reward: 37.0) | |
Finished episode 2573 after 35 timesteps (reward: 35.0) | |
Finished episode 2574 after 38 timesteps (reward: 38.0) | |
Finished episode 2575 after 23 timesteps (reward: 23.0) | |
Finished episode 2576 after 42 timesteps (reward: 42.0) | |
Finished episode 2577 after 26 timesteps (reward: 26.0) | |
Finished episode 2578 after 48 timesteps (reward: 48.0) | |
Finished episode 2579 after 47 timesteps (reward: 47.0) | |
Finished episode 2580 after 32 timesteps (reward: 32.0) | |
Finished episode 2581 after 43 timesteps (reward: 43.0) | |
Finished episode 2582 after 33 timesteps (reward: 33.0) | |
Finished episode 2583 after 49 timesteps (reward: 49.0) | |
Finished episode 2584 after 36 timesteps (reward: 36.0) | |
Finished episode 2585 after 24 timesteps (reward: 24.0) | |
Finished episode 2586 after 53 timesteps (reward: 53.0) | |
Finished episode 2587 after 40 timesteps (reward: 40.0) | |
Finished episode 2588 after 25 timesteps (reward: 25.0) | |
Finished episode 2589 after 38 timesteps (reward: 38.0) | |
Finished episode 2590 after 27 timesteps (reward: 27.0) | |
Finished episode 2591 after 35 timesteps (reward: 35.0) | |
Finished episode 2592 after 42 timesteps (reward: 42.0) | |
Finished episode 2593 after 42 timesteps (reward: 42.0) | |
Finished episode 2594 after 42 timesteps (reward: 42.0) | |
Finished episode 2595 after 47 timesteps (reward: 47.0) | |
Finished episode 2596 after 46 timesteps (reward: 46.0) | |
Finished episode 2597 after 26 timesteps (reward: 26.0) | |
Finished episode 2598 after 39 timesteps (reward: 39.0) | |
Finished episode 2599 after 46 timesteps (reward: 46.0) | |
Finished episode 2600 after 31 timesteps (reward: 31.0) | |
Finished episode 2601 after 31 timesteps (reward: 31.0) | |
Finished episode 2602 after 29 timesteps (reward: 29.0) | |
Finished episode 2603 after 25 timesteps (reward: 25.0) | |
Finished episode 2604 after 50 timesteps (reward: 50.0) | |
Finished episode 2605 after 36 timesteps (reward: 36.0) | |
Finished episode 2606 after 38 timesteps (reward: 38.0) | |
Finished episode 2607 after 40 timesteps (reward: 40.0) | |
Finished episode 2608 after 42 timesteps (reward: 42.0) | |
Finished episode 2609 after 35 timesteps (reward: 35.0) | |
Finished episode 2610 after 30 timesteps (reward: 30.0) | |
Finished episode 2611 after 35 timesteps (reward: 35.0) | |
Finished episode 2612 after 53 timesteps (reward: 53.0) | |
Finished episode 2613 after 36 timesteps (reward: 36.0) | |
Finished episode 2614 after 35 timesteps (reward: 35.0) | |
Finished episode 2615 after 36 timesteps (reward: 36.0) | |
Finished episode 2616 after 33 timesteps (reward: 33.0) | |
Finished episode 2617 after 24 timesteps (reward: 24.0) | |
Finished episode 2618 after 51 timesteps (reward: 51.0) | |
Finished episode 2619 after 51 timesteps (reward: 51.0) | |
Finished episode 2620 after 40 timesteps (reward: 40.0) | |
Finished episode 2621 after 33 timesteps (reward: 33.0) | |
Finished episode 2622 after 45 timesteps (reward: 45.0) | |
Finished episode 2623 after 40 timesteps (reward: 40.0) | |
Finished episode 2624 after 39 timesteps (reward: 39.0) | |
Finished episode 2625 after 41 timesteps (reward: 41.0) | |
Finished episode 2626 after 38 timesteps (reward: 38.0) | |
Finished episode 2627 after 50 timesteps (reward: 50.0) | |
Finished episode 2628 after 30 timesteps (reward: 30.0) | |
Finished episode 2629 after 30 timesteps (reward: 30.0) | |
Finished episode 2630 after 33 timesteps (reward: 33.0) | |
Finished episode 2631 after 44 timesteps (reward: 44.0) | |
Finished episode 2632 after 43 timesteps (reward: 43.0) | |
Finished episode 2633 after 34 timesteps (reward: 34.0) | |
Finished episode 2634 after 33 timesteps (reward: 33.0) | |
Finished episode 2635 after 33 timesteps (reward: 33.0) | |
Finished episode 2636 after 31 timesteps (reward: 31.0) | |
Finished episode 2637 after 34 timesteps (reward: 34.0) | |
Finished episode 2638 after 39 timesteps (reward: 39.0) | |
Finished episode 2639 after 26 timesteps (reward: 26.0) | |
Finished episode 2640 after 30 timesteps (reward: 30.0) | |
Finished episode 2641 after 34 timesteps (reward: 34.0) | |
Finished episode 2642 after 34 timesteps (reward: 34.0) | |
Finished episode 2643 after 39 timesteps (reward: 39.0) | |
Finished episode 2644 after 39 timesteps (reward: 39.0) | |
Finished episode 2645 after 29 timesteps (reward: 29.0) | |
Finished episode 2646 after 25 timesteps (reward: 25.0) | |
Finished episode 2647 after 44 timesteps (reward: 44.0) | |
Finished episode 2648 after 37 timesteps (reward: 37.0) | |
Finished episode 2649 after 43 timesteps (reward: 43.0) | |
Finished episode 2650 after 40 timesteps (reward: 40.0) | |
Finished episode 2651 after 34 timesteps (reward: 34.0) | |
Finished episode 2652 after 26 timesteps (reward: 26.0) | |
Finished episode 2653 after 24 timesteps (reward: 24.0) | |
Finished episode 2654 after 40 timesteps (reward: 40.0) | |
Finished episode 2655 after 34 timesteps (reward: 34.0) | |
Finished episode 2656 after 26 timesteps (reward: 26.0) | |
Finished episode 2657 after 23 timesteps (reward: 23.0) | |
Finished episode 2658 after 42 timesteps (reward: 42.0) | |
Finished episode 2659 after 48 timesteps (reward: 48.0) | |
Finished episode 2660 after 41 timesteps (reward: 41.0) | |
Finished episode 2661 after 30 timesteps (reward: 30.0) | |
Finished episode 2662 after 36 timesteps (reward: 36.0) | |
Finished episode 2663 after 32 timesteps (reward: 32.0) | |
Finished episode 2664 after 33 timesteps (reward: 33.0) | |
Finished episode 2665 after 34 timesteps (reward: 34.0) | |
Finished episode 2666 after 36 timesteps (reward: 36.0) | |
Finished episode 2667 after 27 timesteps (reward: 27.0) | |
Finished episode 2668 after 33 timesteps (reward: 33.0) | |
Finished episode 2669 after 29 timesteps (reward: 29.0) | |
Finished episode 2670 after 46 timesteps (reward: 46.0) | |
Finished episode 2671 after 27 timesteps (reward: 27.0) | |
Finished episode 2672 after 43 timesteps (reward: 43.0) | |
Finished episode 2673 after 52 timesteps (reward: 52.0) | |
Finished episode 2674 after 33 timesteps (reward: 33.0) | |
Finished episode 2675 after 33 timesteps (reward: 33.0) | |
Finished episode 2676 after 43 timesteps (reward: 43.0) | |
Finished episode 2677 after 31 timesteps (reward: 31.0) | |
Finished episode 2678 after 58 timesteps (reward: 58.0) | |
Finished episode 2679 after 34 timesteps (reward: 34.0) | |
Finished episode 2680 after 28 timesteps (reward: 28.0) | |
Finished episode 2681 after 35 timesteps (reward: 35.0) | |
Finished episode 2682 after 43 timesteps (reward: 43.0) | |
Finished episode 2683 after 25 timesteps (reward: 25.0) | |
Finished episode 2684 after 40 timesteps (reward: 40.0) | |
Finished episode 2685 after 42 timesteps (reward: 42.0) | |
Finished episode 2686 after 39 timesteps (reward: 39.0) | |
Finished episode 2687 after 33 timesteps (reward: 33.0) | |
Finished episode 2688 after 23 timesteps (reward: 23.0) | |
Finished episode 2689 after 45 timesteps (reward: 45.0) | |
Finished episode 2690 after 43 timesteps (reward: 43.0) | |
Finished episode 2691 after 39 timesteps (reward: 39.0) | |
Finished episode 2692 after 40 timesteps (reward: 40.0) | |
Finished episode 2693 after 34 timesteps (reward: 34.0) | |
Finished episode 2694 after 46 timesteps (reward: 46.0) | |
Finished episode 2695 after 40 timesteps (reward: 40.0) | |
Finished episode 2696 after 55 timesteps (reward: 55.0) | |
Finished episode 2697 after 36 timesteps (reward: 36.0) | |
Finished episode 2698 after 29 timesteps (reward: 29.0) | |
Finished episode 2699 after 37 timesteps (reward: 37.0) | |
Finished episode 2700 after 38 timesteps (reward: 38.0) | |
Finished episode 2701 after 36 timesteps (reward: 36.0) | |
Finished episode 2702 after 34 timesteps (reward: 34.0) | |
Finished episode 2703 after 43 timesteps (reward: 43.0) | |
Finished episode 2704 after 37 timesteps (reward: 37.0) | |
Finished episode 2705 after 45 timesteps (reward: 45.0) | |
Finished episode 2706 after 32 timesteps (reward: 32.0) | |
Finished episode 2707 after 24 timesteps (reward: 24.0) | |
Finished episode 2708 after 52 timesteps (reward: 52.0) | |
Finished episode 2709 after 39 timesteps (reward: 39.0) | |
Finished episode 2710 after 38 timesteps (reward: 38.0) | |
Finished episode 2711 after 26 timesteps (reward: 26.0) | |
Finished episode 2712 after 34 timesteps (reward: 34.0) | |
Finished episode 2713 after 49 timesteps (reward: 49.0) | |
Finished episode 2714 after 40 timesteps (reward: 40.0) | |
Finished episode 2715 after 33 timesteps (reward: 33.0) | |
Finished episode 2716 after 23 timesteps (reward: 23.0) | |
Finished episode 2717 after 33 timesteps (reward: 33.0) | |
Finished episode 2718 after 39 timesteps (reward: 39.0) | |
Finished episode 2719 after 25 timesteps (reward: 25.0) | |
Finished episode 2720 after 24 timesteps (reward: 24.0) | |
Finished episode 2721 after 40 timesteps (reward: 40.0) | |
Finished episode 2722 after 31 timesteps (reward: 31.0) | |
Finished episode 2723 after 23 timesteps (reward: 23.0) | |
Finished episode 2724 after 34 timesteps (reward: 34.0) | |
Finished episode 2725 after 42 timesteps (reward: 42.0) | |
Finished episode 2726 after 38 timesteps (reward: 38.0) | |
Finished episode 2727 after 43 timesteps (reward: 43.0) | |
Finished episode 2728 after 45 timesteps (reward: 45.0) | |
Finished episode 2729 after 30 timesteps (reward: 30.0) | |
Finished episode 2730 after 34 timesteps (reward: 34.0) | |
Finished episode 2731 after 34 timesteps (reward: 34.0) | |
Finished episode 2732 after 34 timesteps (reward: 34.0) | |
Finished episode 2733 after 35 timesteps (reward: 35.0) | |
Finished episode 2734 after 37 timesteps (reward: 37.0) | |
Finished episode 2735 after 25 timesteps (reward: 25.0) | |
Finished episode 2736 after 29 timesteps (reward: 29.0) | |
Finished episode 2737 after 25 timesteps (reward: 25.0) | |
Finished episode 2738 after 33 timesteps (reward: 33.0) | |
Finished episode 2739 after 23 timesteps (reward: 23.0) | |
Finished episode 2740 after 42 timesteps (reward: 42.0) | |
Finished episode 2741 after 50 timesteps (reward: 50.0) | |
Finished episode 2742 after 34 timesteps (reward: 34.0) | |
Finished episode 2743 after 35 timesteps (reward: 35.0) | |
Finished episode 2744 after 38 timesteps (reward: 38.0) | |
Finished episode 2745 after 37 timesteps (reward: 37.0) | |
Finished episode 2746 after 35 timesteps (reward: 35.0) | |
Finished episode 2747 after 25 timesteps (reward: 25.0) | |
Finished episode 2748 after 44 timesteps (reward: 44.0) | |
Finished episode 2749 after 37 timesteps (reward: 37.0) | |
Finished episode 2750 after 25 timesteps (reward: 25.0) | |
Finished episode 2751 after 42 timesteps (reward: 42.0) | |
Finished episode 2752 after 39 timesteps (reward: 39.0) | |
Finished episode 2753 after 29 timesteps (reward: 29.0) | |
Finished episode 2754 after 35 timesteps (reward: 35.0) | |
Finished episode 2755 after 36 timesteps (reward: 36.0) | |
Finished episode 2756 after 39 timesteps (reward: 39.0) | |
Finished episode 2757 after 40 timesteps (reward: 40.0) | |
Finished episode 2758 after 41 timesteps (reward: 41.0) | |
Finished episode 2759 after 24 timesteps (reward: 24.0) | |
Finished episode 2760 after 34 timesteps (reward: 34.0) | |
Finished episode 2761 after 34 timesteps (reward: 34.0) | |
Finished episode 2762 after 25 timesteps (reward: 25.0) | |
Finished episode 2763 after 33 timesteps (reward: 33.0) | |
Finished episode 2764 after 43 timesteps (reward: 43.0) | |
Finished episode 2765 after 24 timesteps (reward: 24.0) | |
Finished episode 2766 after 48 timesteps (reward: 48.0) | |
Finished episode 2767 after 38 timesteps (reward: 38.0) | |
Finished episode 2768 after 33 timesteps (reward: 33.0) | |
Finished episode 2769 after 42 timesteps (reward: 42.0) | |
Finished episode 2770 after 36 timesteps (reward: 36.0) | |
Finished episode 2771 after 23 timesteps (reward: 23.0) | |
Finished episode 2772 after 24 timesteps (reward: 24.0) | |
Finished episode 2773 after 40 timesteps (reward: 40.0) | |
Finished episode 2774 after 35 timesteps (reward: 35.0) | |
Finished episode 2775 after 43 timesteps (reward: 43.0) | |
Finished episode 2776 after 34 timesteps (reward: 34.0) | |
Finished episode 2777 after 33 timesteps (reward: 33.0) | |
Finished episode 2778 after 34 timesteps (reward: 34.0) | |
Finished episode 2779 after 34 timesteps (reward: 34.0) | |
Finished episode 2780 after 45 timesteps (reward: 45.0) | |
Finished episode 2781 after 41 timesteps (reward: 41.0) | |
Finished episode 2782 after 27 timesteps (reward: 27.0) | |
Finished episode 2783 after 35 timesteps (reward: 35.0) | |
Finished episode 2784 after 31 timesteps (reward: 31.0) | |
Finished episode 2785 after 29 timesteps (reward: 29.0) | |
Finished episode 2786 after 35 timesteps (reward: 35.0) | |
Finished episode 2787 after 23 timesteps (reward: 23.0) | |
Finished episode 2788 after 38 timesteps (reward: 38.0) | |
Finished episode 2789 after 23 timesteps (reward: 23.0) | |
Finished episode 2790 after 30 timesteps (reward: 30.0) | |
Finished episode 2791 after 33 timesteps (reward: 33.0) | |
Finished episode 2792 after 45 timesteps (reward: 45.0) | |
Finished episode 2793 after 38 timesteps (reward: 38.0) | |
Finished episode 2794 after 34 timesteps (reward: 34.0) | |
Finished episode 2795 after 35 timesteps (reward: 35.0) | |
Finished episode 2796 after 38 timesteps (reward: 38.0) | |
Finished episode 2797 after 37 timesteps (reward: 37.0) | |
Finished episode 2798 after 40 timesteps (reward: 40.0) | |
Finished episode 2799 after 31 timesteps (reward: 31.0) | |
Finished episode 2800 after 24 timesteps (reward: 24.0) | |
Finished episode 2801 after 38 timesteps (reward: 38.0) | |
Finished episode 2802 after 32 timesteps (reward: 32.0) | |
Finished episode 2803 after 36 timesteps (reward: 36.0) | |
Finished episode 2804 after 23 timesteps (reward: 23.0) | |
Finished episode 2805 after 30 timesteps (reward: 30.0) | |
Finished episode 2806 after 34 timesteps (reward: 34.0) | |
Finished episode 2807 after 33 timesteps (reward: 33.0) | |
Finished episode 2808 after 26 timesteps (reward: 26.0) | |
Finished episode 2809 after 31 timesteps (reward: 31.0) | |
Finished episode 2810 after 29 timesteps (reward: 29.0) | |
Finished episode 2811 after 35 timesteps (reward: 35.0) | |
Finished episode 2812 after 49 timesteps (reward: 49.0) | |
Finished episode 2813 after 26 timesteps (reward: 26.0) | |
Finished episode 2814 after 30 timesteps (reward: 30.0) | |
Finished episode 2815 after 30 timesteps (reward: 30.0) | |
Finished episode 2816 after 33 timesteps (reward: 33.0) | |
Finished episode 2817 after 37 timesteps (reward: 37.0) | |
Finished episode 2818 after 26 timesteps (reward: 26.0) | |
Finished episode 2819 after 48 timesteps (reward: 48.0) | |
Finished episode 2820 after 32 timesteps (reward: 32.0) | |
Finished episode 2821 after 34 timesteps (reward: 34.0) | |
Finished episode 2822 after 40 timesteps (reward: 40.0) | |
Finished episode 2823 after 44 timesteps (reward: 44.0) | |
Finished episode 2824 after 27 timesteps (reward: 27.0) | |
Finished episode 2825 after 39 timesteps (reward: 39.0) | |
Finished episode 2826 after 26 timesteps (reward: 26.0) | |
Finished episode 2827 after 29 timesteps (reward: 29.0) | |
Finished episode 2828 after 38 timesteps (reward: 38.0) | |
Finished episode 2829 after 30 timesteps (reward: 30.0) | |
Finished episode 2830 after 30 timesteps (reward: 30.0) | |
Finished episode 2831 after 46 timesteps (reward: 46.0) | |
Finished episode 2832 after 25 timesteps (reward: 25.0) | |
Finished episode 2833 after 39 timesteps (reward: 39.0) | |
Finished episode 2834 after 23 timesteps (reward: 23.0) | |
Finished episode 2835 after 29 timesteps (reward: 29.0) | |
Finished episode 2836 after 35 timesteps (reward: 35.0) | |
Finished episode 2837 after 34 timesteps (reward: 34.0) | |
Finished episode 2838 after 34 timesteps (reward: 34.0) | |
Finished episode 2839 after 31 timesteps (reward: 31.0) | |
Finished episode 2840 after 26 timesteps (reward: 26.0) | |
Finished episode 2841 after 36 timesteps (reward: 36.0) | |
Finished episode 2842 after 41 timesteps (reward: 41.0) | |
Finished episode 2843 after 34 timesteps (reward: 34.0) | |
Finished episode 2844 after 26 timesteps (reward: 26.0) | |
Finished episode 2845 after 25 timesteps (reward: 25.0) | |
Finished episode 2846 after 38 timesteps (reward: 38.0) | |
Finished episode 2847 after 34 timesteps (reward: 34.0) | |
Finished episode 2848 after 42 timesteps (reward: 42.0) | |
Finished episode 2849 after 36 timesteps (reward: 36.0) | |
Finished episode 2850 after 34 timesteps (reward: 34.0) | |
Finished episode 2851 after 27 timesteps (reward: 27.0) | |
Finished episode 2852 after 37 timesteps (reward: 37.0) | |
Finished episode 2853 after 35 timesteps (reward: 35.0) | |
Finished episode 2854 after 44 timesteps (reward: 44.0) | |
Finished episode 2855 after 33 timesteps (reward: 33.0) | |
Finished episode 2856 after 26 timesteps (reward: 26.0) | |
Finished episode 2857 after 39 timesteps (reward: 39.0) | |
Finished episode 2858 after 44 timesteps (reward: 44.0) | |
Finished episode 2859 after 33 timesteps (reward: 33.0) | |
Finished episode 2860 after 39 timesteps (reward: 39.0) | |
Finished episode 2861 after 33 timesteps (reward: 33.0) | |
Finished episode 2862 after 23 timesteps (reward: 23.0) | |
Finished episode 2863 after 29 timesteps (reward: 29.0) | |
Finished episode 2864 after 36 timesteps (reward: 36.0) | |
Finished episode 2865 after 41 timesteps (reward: 41.0) | |
Finished episode 2866 after 23 timesteps (reward: 23.0) | |
Finished episode 2867 after 23 timesteps (reward: 23.0) | |
Finished episode 2868 after 23 timesteps (reward: 23.0) | |
Finished episode 2869 after 44 timesteps (reward: 44.0) | |
Finished episode 2870 after 34 timesteps (reward: 34.0) | |
Finished episode 2871 after 32 timesteps (reward: 32.0) | |
Finished episode 2872 after 35 timesteps (reward: 35.0) | |
Finished episode 2873 after 31 timesteps (reward: 31.0) | |
Finished episode 2874 after 35 timesteps (reward: 35.0) | |
Finished episode 2875 after 38 timesteps (reward: 38.0) | |
Finished episode 2876 after 37 timesteps (reward: 37.0) | |
Finished episode 2877 after 29 timesteps (reward: 29.0) | |
Finished episode 2878 after 35 timesteps (reward: 35.0) | |
Finished episode 2879 after 35 timesteps (reward: 35.0) | |
Finished episode 2880 after 22 timesteps (reward: 22.0) | |
Finished episode 2881 after 41 timesteps (reward: 41.0) | |
Finished episode 2882 after 24 timesteps (reward: 24.0) | |
Finished episode 2883 after 34 timesteps (reward: 34.0) | |
Finished episode 2884 after 49 timesteps (reward: 49.0) | |
Finished episode 2885 after 33 timesteps (reward: 33.0) | |
Finished episode 2886 after 29 timesteps (reward: 29.0) | |
Finished episode 2887 after 28 timesteps (reward: 28.0) | |
Finished episode 2888 after 37 timesteps (reward: 37.0) | |
Finished episode 2889 after 33 timesteps (reward: 33.0) | |
Finished episode 2890 after 45 timesteps (reward: 45.0) | |
Finished episode 2891 after 33 timesteps (reward: 33.0) | |
Finished episode 2892 after 43 timesteps (reward: 43.0) | |
Finished episode 2893 after 39 timesteps (reward: 39.0) | |
Finished episode 2894 after 44 timesteps (reward: 44.0) | |
Finished episode 2895 after 28 timesteps (reward: 28.0) | |
Finished episode 2896 after 42 timesteps (reward: 42.0) | |
Finished episode 2897 after 37 timesteps (reward: 37.0) | |
Finished episode 2898 after 24 timesteps (reward: 24.0) | |
Finished episode 2899 after 44 timesteps (reward: 44.0) | |
Finished episode 2900 after 33 timesteps (reward: 33.0) | |
Finished episode 2901 after 34 timesteps (reward: 34.0) | |
Finished episode 2902 after 37 timesteps (reward: 37.0) | |
Finished episode 2903 after 41 timesteps (reward: 41.0) | |
Finished episode 2904 after 33 timesteps (reward: 33.0) | |
Finished episode 2905 after 38 timesteps (reward: 38.0) | |
Finished episode 2906 after 24 timesteps (reward: 24.0) | |
Finished episode 2907 after 34 timesteps (reward: 34.0) | |
Finished episode 2908 after 30 timesteps (reward: 30.0) | |
Finished episode 2909 after 38 timesteps (reward: 38.0) | |
Finished episode 2910 after 37 timesteps (reward: 37.0) | |
Finished episode 2911 after 42 timesteps (reward: 42.0) | |
Finished episode 2912 after 38 timesteps (reward: 38.0) | |
Finished episode 2913 after 33 timesteps (reward: 33.0) | |
Finished episode 2914 after 41 timesteps (reward: 41.0) | |
Finished episode 2915 after 31 timesteps (reward: 31.0) | |
Finished episode 2916 after 26 timesteps (reward: 26.0) | |
Finished episode 2917 after 23 timesteps (reward: 23.0) | |
Finished episode 2918 after 33 timesteps (reward: 33.0) | |
Finished episode 2919 after 42 timesteps (reward: 42.0) | |
Finished episode 2920 after 36 timesteps (reward: 36.0) | |
Finished episode 2921 after 34 timesteps (reward: 34.0) | |
Finished episode 2922 after 36 timesteps (reward: 36.0) | |
Finished episode 2923 after 27 timesteps (reward: 27.0) | |
Finished episode 2924 after 26 timesteps (reward: 26.0) | |
Finished episode 2925 after 31 timesteps (reward: 31.0) | |
Finished episode 2926 after 38 timesteps (reward: 38.0) | |
Finished episode 2927 after 42 timesteps (reward: 42.0) | |
Finished episode 2928 after 37 timesteps (reward: 37.0) | |
Finished episode 2929 after 34 timesteps (reward: 34.0) | |
Finished episode 2930 after 35 timesteps (reward: 35.0) | |
Finished episode 2931 after 24 timesteps (reward: 24.0) | |
Finished episode 2932 after 24 timesteps (reward: 24.0) | |
Finished episode 2933 after 36 timesteps (reward: 36.0) | |
Finished episode 2934 after 33 timesteps (reward: 33.0) | |
Finished episode 2935 after 37 timesteps (reward: 37.0) | |
Finished episode 2936 after 33 timesteps (reward: 33.0) | |
Finished episode 2937 after 36 timesteps (reward: 36.0) | |
Finished episode 2938 after 27 timesteps (reward: 27.0) | |
Finished episode 2939 after 38 timesteps (reward: 38.0) | |
Finished episode 2940 after 31 timesteps (reward: 31.0) | |
Finished episode 2941 after 33 timesteps (reward: 33.0) | |
Finished episode 2942 after 39 timesteps (reward: 39.0) | |
Finished episode 2943 after 40 timesteps (reward: 40.0) | |
Finished episode 2944 after 24 timesteps (reward: 24.0) | |
Finished episode 2945 after 35 timesteps (reward: 35.0) | |
Finished episode 2946 after 31 timesteps (reward: 31.0) | |
Finished episode 2947 after 38 timesteps (reward: 38.0) | |
Finished episode 2948 after 33 timesteps (reward: 33.0) | |
Finished episode 2949 after 42 timesteps (reward: 42.0) | |
Finished episode 2950 after 35 timesteps (reward: 35.0) | |
Finished episode 2951 after 33 timesteps (reward: 33.0) | |
Finished episode 2952 after 26 timesteps (reward: 26.0) | |
Finished episode 2953 after 36 timesteps (reward: 36.0) | |
Finished episode 2954 after 39 timesteps (reward: 39.0) | |
Finished episode 2955 after 37 timesteps (reward: 37.0) | |
Finished episode 2956 after 34 timesteps (reward: 34.0) | |
Finished episode 2957 after 35 timesteps (reward: 35.0) | |
Finished episode 2958 after 22 timesteps (reward: 22.0) | |
Finished episode 2959 after 48 timesteps (reward: 48.0) | |
Finished episode 2960 after 41 timesteps (reward: 41.0) | |
Finished episode 2961 after 30 timesteps (reward: 30.0) | |
Finished episode 2962 after 41 timesteps (reward: 41.0) | |
Finished episode 2963 after 34 timesteps (reward: 34.0) | |
Finished episode 2964 after 31 timesteps (reward: 31.0) | |
Finished episode 2965 after 33 timesteps (reward: 33.0) | |
Finished episode 2966 after 24 timesteps (reward: 24.0) | |
Finished episode 2967 after 24 timesteps (reward: 24.0) | |
Finished episode 2968 after 23 timesteps (reward: 23.0) | |
Finished episode 2969 after 39 timesteps (reward: 39.0) | |
Finished episode 2970 after 25 timesteps (reward: 25.0) | |
Finished episode 2971 after 35 timesteps (reward: 35.0) | |
Finished episode 2972 after 34 timesteps (reward: 34.0) | |
Finished episode 2973 after 39 timesteps (reward: 39.0) | |
Finished episode 2974 after 31 timesteps (reward: 31.0) | |
Finished episode 2975 after 31 timesteps (reward: 31.0) | |
Finished episode 2976 after 35 timesteps (reward: 35.0) | |
Finished episode 2977 after 27 timesteps (reward: 27.0) | |
Finished episode 2978 after 22 timesteps (reward: 22.0) | |
Finished episode 2979 after 36 timesteps (reward: 36.0) | |
Finished episode 2980 after 23 timesteps (reward: 23.0) | |
Finished episode 2981 after 27 timesteps (reward: 27.0) | |
Finished episode 2982 after 26 timesteps (reward: 26.0) | |
Finished episode 2983 after 31 timesteps (reward: 31.0) | |
Finished episode 2984 after 35 timesteps (reward: 35.0) | |
Finished episode 2985 after 35 timesteps (reward: 35.0) | |
Finished episode 2986 after 36 timesteps (reward: 36.0) | |
Finished episode 2987 after 30 timesteps (reward: 30.0) | |
Finished episode 2988 after 41 timesteps (reward: 41.0) | |
Finished episode 2989 after 41 timesteps (reward: 41.0) | |
Finished episode 2990 after 31 timesteps (reward: 31.0) | |
Finished episode 2991 after 24 timesteps (reward: 24.0) | |
Finished episode 2992 after 29 timesteps (reward: 29.0) | |
Finished episode 2993 after 24 timesteps (reward: 24.0) | |
Finished episode 2994 after 33 timesteps (reward: 33.0) | |
Finished episode 2995 after 35 timesteps (reward: 35.0) | |
Finished episode 2996 after 44 timesteps (reward: 44.0) | |
Finished episode 2997 after 41 timesteps (reward: 41.0) | |
Finished episode 2998 after 38 timesteps (reward: 38.0) | |
Finished episode 2999 after 35 timesteps (reward: 35.0) | |
Finished episode 3000 after 34 timesteps (reward: 34.0) | |
Learning finished. Total episodes: 3000. Average reward of last 100 episodes: 33.38. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
$ python examples/openai_gym.py CartPole-v0 -a TRPOAgent -c examples/configs/trpo_cartpole.json -n examples/configs/trpo_cartpole_network.json | |
[2017-07-24 23:33:57,156] Making new env: CartPole-v0 | |
[2017-07-24 23:33:58,552] Starting TRPOAgent for Environment 'OpenAIGym(CartPole-v0)' | |
[2017-07-24 23:34:03,065] Finished episode 50 after 14 timesteps | |
[2017-07-24 23:34:03,066] Episode reward: 14.0 | |
[2017-07-24 23:34:03,066] Average of last 500 rewards: 2.35 | |
[2017-07-24 23:34:03,066] Average of last 100 rewards: 11.75 | |
[2017-07-24 23:34:06,864] Finished episode 100 after 25 timesteps | |
[2017-07-24 23:34:06,864] Episode reward: 25.0 | |
[2017-07-24 23:34:06,864] Average of last 500 rewards: 5.636 | |
[2017-07-24 23:34:06,864] Average of last 100 rewards: 28.18 | |
[2017-07-24 23:34:15,067] Finished episode 150 after 57 timesteps | |
[2017-07-24 23:34:15,067] Episode reward: 57.0 | |
[2017-07-24 23:34:15,067] Average of last 500 rewards: 12.098 | |
[2017-07-24 23:34:15,067] Average of last 100 rewards: 48.74 | |
[2017-07-24 23:34:42,179] Finished episode 200 after 200 timesteps | |
[2017-07-24 23:34:42,179] Episode reward: 200.0 | |
[2017-07-24 23:34:42,179] Average of last 500 rewards: 30.34 | |
[2017-07-24 23:34:42,179] Average of last 100 rewards: 123.52 | |
[2017-07-24 23:35:15,329] Finished episode 250 after 200 timesteps | |
[2017-07-24 23:35:15,329] Episode reward: 200.0 | |
[2017-07-24 23:35:15,329] Average of last 500 rewards: 49.626 | |
[2017-07-24 23:35:15,329] Average of last 100 rewards: 187.64 | |
[2017-07-24 23:35:42,528] Finished episode 300 after 44 timesteps | |
[2017-07-24 23:35:42,528] Episode reward: 44.0 | |
[2017-07-24 23:35:42,529] Average of last 500 rewards: 67.608 | |
[2017-07-24 23:35:42,529] Average of last 100 rewards: 186.34 | |
[2017-07-24 23:35:59,937] Finished episode 350 after 24 timesteps | |
[2017-07-24 23:35:59,937] Episode reward: 24.0 | |
[2017-07-24 23:35:59,937] Average of last 500 rewards: 79.816 | |
[2017-07-24 23:35:59,937] Average of last 100 rewards: 150.95 | |
[2017-07-24 23:36:08,373] Finished episode 400 after 48 timesteps | |
[2017-07-24 23:36:08,373] Episode reward: 48.0 | |
[2017-07-24 23:36:08,373] Average of last 500 rewards: 86.374 | |
[2017-07-24 23:36:08,374] Average of last 100 rewards: 93.83 | |
[2017-07-24 23:36:16,272] Finished episode 450 after 46 timesteps | |
[2017-07-24 23:36:16,272] Episode reward: 46.0 | |
[2017-07-24 23:36:16,272] Average of last 500 rewards: 91.238 | |
[2017-07-24 23:36:16,273] Average of last 100 rewards: 57.11 | |
[2017-07-24 23:36:24,931] Finished episode 500 after 49 timesteps | |
[2017-07-24 23:36:24,931] Episode reward: 49.0 | |
[2017-07-24 23:36:24,931] Average of last 500 rewards: 95.9 | |
[2017-07-24 23:36:24,931] Average of last 100 rewards: 47.63 | |
[2017-07-24 23:36:31,515] Finished episode 550 after 39 timesteps | |
[2017-07-24 23:36:31,515] Episode reward: 39.0 | |
[2017-07-24 23:36:31,515] Average of last 500 rewards: 98.556 | |
[2017-07-24 23:36:31,515] Average of last 100 rewards: 48.34 | |
[2017-07-24 23:36:42,449] Finished episode 600 after 39 timesteps | |
[2017-07-24 23:36:42,449] Episode reward: 39.0 | |
[2017-07-24 23:36:42,449] Average of last 500 rewards: 100.076 | |
[2017-07-24 23:36:42,449] Average of last 100 rewards: 49.06 | |
[2017-07-24 23:36:50,779] Finished episode 650 after 19 timesteps | |
[2017-07-24 23:36:50,779] Episode reward: 19.0 | |
[2017-07-24 23:36:50,779] Average of last 500 rewards: 98.566 | |
[2017-07-24 23:36:50,779] Average of last 100 rewards: 48.79 | |
[2017-07-24 23:37:00,123] Finished episode 700 after 46 timesteps | |
[2017-07-24 23:37:00,123] Episode reward: 46.0 | |
[2017-07-24 23:37:00,123] Average of last 500 rewards: 84.864 | |
[2017-07-24 23:37:00,123] Average of last 100 rewards: 47.46 | |
[2017-07-24 23:37:07,255] Finished episode 750 after 40 timesteps | |
[2017-07-24 23:37:07,255] Episode reward: 40.0 | |
[2017-07-24 23:37:07,255] Average of last 500 rewards: 70.29 | |
[2017-07-24 23:37:07,255] Average of last 100 rewards: 46.26 | |
[2017-07-24 23:37:13,033] Finished episode 800 after 47 timesteps | |
[2017-07-24 23:37:13,033] Episode reward: 47.0 | |
[2017-07-24 23:37:13,033] Average of last 500 rewards: 57.048 | |
[2017-07-24 23:37:13,034] Average of last 100 rewards: 47.26 | |
[2017-07-24 23:37:19,026] Finished episode 850 after 78 timesteps | |
[2017-07-24 23:37:19,026] Episode reward: 78.0 | |
[2017-07-24 23:37:19,026] Average of last 500 rewards: 50.17 | |
[2017-07-24 23:37:19,027] Average of last 100 rewards: 50.35 | |
[2017-07-24 23:37:28,682] Finished episode 900 after 40 timesteps | |
[2017-07-24 23:37:28,682] Episode reward: 40.0 | |
[2017-07-24 23:37:28,683] Average of last 500 rewards: 48.75 | |
[2017-07-24 23:37:28,683] Average of last 100 rewards: 52.34 | |
[2017-07-24 23:37:37,179] Finished episode 950 after 21 timesteps | |
[2017-07-24 23:37:37,179] Episode reward: 21.0 | |
[2017-07-24 23:37:37,179] Average of last 500 rewards: 49.736 | |
[2017-07-24 23:37:37,179] Average of last 100 rewards: 54.94 | |
[2017-07-24 23:37:45,924] Finished episode 1000 after 119 timesteps | |
[2017-07-24 23:37:45,925] Episode reward: 119.0 | |
[2017-07-24 23:37:45,925] Average of last 500 rewards: 50.534 | |
[2017-07-24 23:37:45,925] Average of last 100 rewards: 56.55 | |
[2017-07-24 23:37:55,521] Finished episode 1050 after 66 timesteps | |
[2017-07-24 23:37:55,521] Episode reward: 66.0 | |
[2017-07-24 23:37:55,521] Average of last 500 rewards: 51.256 | |
[2017-07-24 23:37:55,521] Average of last 100 rewards: 55.94 | |
[2017-07-24 23:38:03,665] Finished episode 1100 after 62 timesteps | |
[2017-07-24 23:38:03,665] Episode reward: 62.0 | |
[2017-07-24 23:38:03,666] Average of last 500 rewards: 52.362 | |
[2017-07-24 23:38:03,666] Average of last 100 rewards: 58.2 | |
[2017-07-24 23:38:12,325] Finished episode 1150 after 39 timesteps | |
[2017-07-24 23:38:12,325] Episode reward: 39.0 | |
[2017-07-24 23:38:12,326] Average of last 500 rewards: 53.712 | |
[2017-07-24 23:38:12,326] Average of last 100 rewards: 61.07 | |
[2017-07-24 23:38:22,569] Finished episode 1200 after 96 timesteps | |
[2017-07-24 23:38:22,570] Episode reward: 96.0 | |
[2017-07-24 23:38:22,570] Average of last 500 rewards: 55.462 | |
[2017-07-24 23:38:22,570] Average of last 100 rewards: 62.96 | |
[2017-07-24 23:38:33,963] Finished episode 1250 after 97 timesteps | |
[2017-07-24 23:38:33,963] Episode reward: 97.0 | |
[2017-07-24 23:38:33,963] Average of last 500 rewards: 57.58 | |
[2017-07-24 23:38:33,963] Average of last 100 rewards: 65.6 | |
[2017-07-24 23:38:47,145] Finished episode 1300 after 87 timesteps | |
[2017-07-24 23:38:47,145] Episode reward: 87.0 | |
[2017-07-24 23:38:47,146] Average of last 500 rewards: 60.018 | |
[2017-07-24 23:38:47,146] Average of last 100 rewards: 70.04 | |
[2017-07-24 23:38:59,393] Finished episode 1350 after 47 timesteps | |
[2017-07-24 23:38:59,393] Episode reward: 47.0 | |
[2017-07-24 23:38:59,393] Average of last 500 rewards: 62.124 | |
[2017-07-24 23:38:59,393] Average of last 100 rewards: 73.07 | |
[2017-07-24 23:39:15,774] Finished episode 1400 after 71 timesteps | |
[2017-07-24 23:39:15,775] Episode reward: 71.0 | |
[2017-07-24 23:39:15,775] Average of last 500 rewards: 66.376 | |
[2017-07-24 23:39:15,775] Average of last 100 rewards: 84.13 | |
[2017-07-24 23:39:31,616] Finished episode 1450 after 95 timesteps | |
[2017-07-24 23:39:31,616] Episode reward: 95.0 | |
[2017-07-24 23:39:31,616] Average of last 500 rewards: 70.024 | |
[2017-07-24 23:39:31,616] Average of last 100 rewards: 94.44 | |
[2017-07-24 23:39:55,149] Finished episode 1500 after 65 timesteps | |
[2017-07-24 23:39:55,150] Episode reward: 65.0 | |
[2017-07-24 23:39:55,150] Average of last 500 rewards: 75.022 | |
[2017-07-24 23:39:55,150] Average of last 100 rewards: 99.78 | |
[2017-07-24 23:40:15,159] Finished episode 1550 after 140 timesteps | |
[2017-07-24 23:40:15,159] Episode reward: 140.0 | |
[2017-07-24 23:40:15,159] Average of last 500 rewards: 80.99 | |
[2017-07-24 23:40:15,159] Average of last 100 rewards: 110.77 | |
[2017-07-24 23:40:40,796] Finished episode 1600 after 200 timesteps | |
[2017-07-24 23:40:40,796] Episode reward: 200.0 | |
[2017-07-24 23:40:40,796] Average of last 500 rewards: 90.83 | |
[2017-07-24 23:40:40,796] Average of last 100 rewards: 137.24 | |
[2017-07-24 23:41:14,188] Finished episode 1650 after 200 timesteps | |
[2017-07-24 23:41:14,189] Episode reward: 200.0 | |
[2017-07-24 23:41:14,189] Average of last 500 rewards: 103.834 | |
[2017-07-24 23:41:14,189] Average of last 100 rewards: 175.29 | |
[2017-07-24 23:41:44,588] Finished episode 1700 after 200 timesteps | |
[2017-07-24 23:41:44,589] Episode reward: 200.0 | |
[2017-07-24 23:41:44,589] Average of last 500 rewards: 117.544 | |
[2017-07-24 23:41:44,589] Average of last 100 rewards: 196.53 | |
[2017-07-24 23:42:21,388] Finished episode 1750 after 200 timesteps | |
[2017-07-24 23:42:21,388] Episode reward: 200.0 | |
[2017-07-24 23:42:21,388] Average of last 500 rewards: 130.714 | |
[2017-07-24 23:42:21,388] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:42:57,761] Finished episode 1800 after 200 timesteps | |
[2017-07-24 23:42:57,761] Episode reward: 200.0 | |
[2017-07-24 23:42:57,762] Average of last 500 rewards: 143.536 | |
[2017-07-24 23:42:57,762] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:43:37,614] Finished episode 1850 after 200 timesteps | |
[2017-07-24 23:43:37,614] Episode reward: 200.0 | |
[2017-07-24 23:43:37,614] Average of last 500 rewards: 156.1 | |
[2017-07-24 23:43:37,614] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:44:10,399] Finished episode 1900 after 200 timesteps | |
[2017-07-24 23:44:10,399] Episode reward: 200.0 | |
[2017-07-24 23:44:10,399] Average of last 500 rewards: 166.71 | |
[2017-07-24 23:44:10,399] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:44:47,013] Finished episode 1950 after 200 timesteps | |
[2017-07-24 23:44:47,014] Episode reward: 200.0 | |
[2017-07-24 23:44:47,014] Average of last 500 rewards: 177.212 | |
[2017-07-24 23:44:47,014] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:45:22,858] Finished episode 2000 after 200 timesteps | |
[2017-07-24 23:45:22,858] Episode reward: 200.0 | |
[2017-07-24 23:45:22,858] Average of last 500 rewards: 186.754 | |
[2017-07-24 23:45:22,858] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:45:59,416] Finished episode 2050 after 200 timesteps | |
[2017-07-24 23:45:59,417] Episode reward: 200.0 | |
[2017-07-24 23:45:59,417] Average of last 500 rewards: 195.058 | |
[2017-07-24 23:45:59,417] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:46:32,864] Finished episode 2100 after 200 timesteps | |
[2017-07-24 23:46:32,864] Episode reward: 200.0 | |
[2017-07-24 23:46:32,865] Average of last 500 rewards: 199.306 | |
[2017-07-24 23:46:32,865] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:47:07,354] Finished episode 2150 after 200 timesteps | |
[2017-07-24 23:47:07,354] Episode reward: 200.0 | |
[2017-07-24 23:47:07,354] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:47:07,354] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:47:46,390] Finished episode 2200 after 200 timesteps | |
[2017-07-24 23:47:46,390] Episode reward: 200.0 | |
[2017-07-24 23:47:46,391] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:47:46,391] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:48:24,063] Finished episode 2250 after 200 timesteps | |
[2017-07-24 23:48:24,063] Episode reward: 200.0 | |
[2017-07-24 23:48:24,063] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:48:24,063] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:48:55,778] Finished episode 2300 after 200 timesteps | |
[2017-07-24 23:48:55,778] Episode reward: 200.0 | |
[2017-07-24 23:48:55,778] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:48:55,778] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:49:32,879] Finished episode 2350 after 200 timesteps | |
[2017-07-24 23:49:32,879] Episode reward: 200.0 | |
[2017-07-24 23:49:32,879] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:49:32,879] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:50:02,159] Finished episode 2400 after 200 timesteps | |
[2017-07-24 23:50:02,160] Episode reward: 200.0 | |
[2017-07-24 23:50:02,160] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:50:02,160] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:50:32,446] Finished episode 2450 after 200 timesteps | |
[2017-07-24 23:50:32,446] Episode reward: 200.0 | |
[2017-07-24 23:50:32,446] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:50:32,446] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:51:03,724] Finished episode 2500 after 200 timesteps | |
[2017-07-24 23:51:03,724] Episode reward: 200.0 | |
[2017-07-24 23:51:03,725] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:51:03,725] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:51:32,435] Finished episode 2550 after 200 timesteps | |
[2017-07-24 23:51:32,435] Episode reward: 200.0 | |
[2017-07-24 23:51:32,435] Average of last 500 rewards: 200.0 | |
[2017-07-24 23:51:32,435] Average of last 100 rewards: 200.0 | |
[2017-07-24 23:52:06,264] Finished episode 2600 after 200 timesteps | |
[2017-07-24 23:52:06,264] Episode reward: 200.0 | |
[2017-07-24 23:52:06,264] Average of last 500 rewards: 199.982 | |
[2017-07-24 23:52:06,264] Average of last 100 rewards: 199.91 | |
[2017-07-24 23:52:42,397] Finished episode 2650 after 200 timesteps | |
[2017-07-24 23:52:42,397] Episode reward: 200.0 | |
[2017-07-24 23:52:42,398] Average of last 500 rewards: 199.658 | |
[2017-07-24 23:52:42,398] Average of last 100 rewards: 198.29 | |
[2017-07-24 23:53:14,423] Finished episode 2700 after 95 timesteps | |
[2017-07-24 23:53:14,423] Episode reward: 95.0 | |
[2017-07-24 23:53:14,423] Average of last 500 rewards: 197.95 | |
[2017-07-24 23:53:14,423] Average of last 100 rewards: 189.84 | |
[2017-07-24 23:53:38,758] Finished episode 2750 after 200 timesteps | |
[2017-07-24 23:53:38,758] Episode reward: 200.0 | |
[2017-07-24 23:53:38,759] Average of last 500 rewards: 193.474 | |
[2017-07-24 23:53:38,759] Average of last 100 rewards: 169.08 | |
[2017-07-24 23:54:02,364] Finished episode 2800 after 140 timesteps | |
[2017-07-24 23:54:02,364] Episode reward: 140.0 | |
[2017-07-24 23:54:02,364] Average of last 500 rewards: 187.796 | |
[2017-07-24 23:54:02,364] Average of last 100 rewards: 149.23 | |
[2017-07-24 23:54:20,819] Finished episode 2850 after 200 timesteps | |
[2017-07-24 23:54:20,820] Episode reward: 200.0 | |
[2017-07-24 23:54:20,820] Average of last 500 rewards: 181.734 | |
[2017-07-24 23:54:20,820] Average of last 100 rewards: 141.3 | |
[2017-07-24 23:54:37,478] Finished episode 2900 after 51 timesteps | |
[2017-07-24 23:54:37,478] Episode reward: 51.0 | |
[2017-07-24 23:54:37,479] Average of last 500 rewards: 173.772 | |
[2017-07-24 23:54:37,479] Average of last 100 rewards: 129.88 | |
[2017-07-24 23:54:55,221] Finished episode 2950 after 172 timesteps | |
[2017-07-24 23:54:55,221] Episode reward: 172.0 | |
[2017-07-24 23:54:55,221] Average of last 500 rewards: 166.134 | |
[2017-07-24 23:54:55,222] Average of last 100 rewards: 122.0 | |
[2017-07-24 23:55:10,472] Finished episode 3000 after 51 timesteps | |
[2017-07-24 23:55:10,472] Episode reward: 51.0 | |
[2017-07-24 23:55:10,472] Average of last 500 rewards: 157.58 | |
[2017-07-24 23:55:10,472] Average of last 100 rewards: 119.04 | |
[2017-07-24 23:55:25,157] Finished episode 3050 after 111 timesteps | |
[2017-07-24 23:55:25,157] Episode reward: 111.0 | |
[2017-07-24 23:55:25,157] Average of last 500 rewards: 147.012 | |
[2017-07-24 23:55:25,157] Average of last 100 rewards: 104.39 | |
[2017-07-24 23:55:37,936] Finished episode 3100 after 87 timesteps | |
[2017-07-24 23:55:37,936] Episode reward: 87.0 | |
[2017-07-24 23:55:37,936] Average of last 500 rewards: 136.35 | |
[2017-07-24 23:55:37,936] Average of last 100 rewards: 93.76 | |
[2017-07-24 23:55:55,122] Finished episode 3150 after 97 timesteps | |
[2017-07-24 23:55:55,122] Episode reward: 97.0 | |
[2017-07-24 23:55:55,122] Average of last 500 rewards: 126.96 | |
[2017-07-24 23:55:55,122] Average of last 100 rewards: 98.03 | |
[2017-07-24 23:56:05,782] Finished episode 3200 after 57 timesteps | |
[2017-07-24 23:56:05,782] Episode reward: 57.0 | |
[2017-07-24 23:56:05,782] Average of last 500 rewards: 117.402 | |
[2017-07-24 23:56:05,782] Average of last 100 rewards: 95.1 | |
[2017-07-24 23:56:21,006] Finished episode 3250 after 95 timesteps | |
[2017-07-24 23:56:21,006] Episode reward: 95.0 | |
[2017-07-24 23:56:21,006] Average of last 500 rewards: 111.792 | |
[2017-07-24 23:56:21,006] Average of last 100 rewards: 93.24 | |
[2017-07-24 23:56:32,185] Finished episode 3300 after 117 timesteps | |
[2017-07-24 23:56:32,185] Episode reward: 117.0 | |
[2017-07-24 23:56:32,185] Average of last 500 rewards: 106.768 | |
[2017-07-24 23:56:32,185] Average of last 100 rewards: 96.06 | |
[2017-07-24 23:56:46,388] Finished episode 3350 after 97 timesteps | |
[2017-07-24 23:56:46,388] Episode reward: 97.0 | |
[2017-07-24 23:56:46,388] Average of last 500 rewards: 101.8 | |
[2017-07-24 23:56:46,389] Average of last 100 rewards: 91.34 | |
[2017-07-24 23:56:57,163] Finished episode 3400 after 87 timesteps | |
[2017-07-24 23:56:57,163] Episode reward: 87.0 | |
[2017-07-24 23:56:57,163] Average of last 500 rewards: 98.604 | |
[2017-07-24 23:56:57,163] Average of last 100 rewards: 89.06 | |
[2017-07-24 23:57:08,079] Finished episode 3450 after 93 timesteps | |
[2017-07-24 23:57:08,080] Episode reward: 93.0 | |
[2017-07-24 23:57:08,080] Average of last 500 rewards: 93.148 | |
[2017-07-24 23:57:08,080] Average of last 100 rewards: 78.74 | |
[2017-07-24 23:57:18,131] Finished episode 3500 after 86 timesteps | |
[2017-07-24 23:57:18,131] Episode reward: 86.0 | |
[2017-07-24 23:57:18,131] Average of last 500 rewards: 88.852 | |
[2017-07-24 23:57:18,131] Average of last 100 rewards: 70.28 | |
[2017-07-24 23:57:28,553] Finished episode 3550 after 38 timesteps | |
[2017-07-24 23:57:28,553] Episode reward: 38.0 | |
[2017-07-24 23:57:28,553] Average of last 500 rewards: 86.378 | |
[2017-07-24 23:57:28,553] Average of last 100 rewards: 70.54 | |
[2017-07-24 23:57:37,775] Finished episode 3600 after 93 timesteps | |
[2017-07-24 23:57:37,775] Episode reward: 93.0 | |
[2017-07-24 23:57:37,775] Average of last 500 rewards: 83.77 | |
[2017-07-24 23:57:37,775] Average of last 100 rewards: 68.35 | |
[2017-07-24 23:57:46,995] Finished episode 3650 after 49 timesteps | |
[2017-07-24 23:57:46,995] Episode reward: 49.0 | |
[2017-07-24 23:57:46,996] Average of last 500 rewards: 79.672 | |
[2017-07-24 23:57:46,996] Average of last 100 rewards: 64.5 | |
[2017-07-24 23:57:58,445] Finished episode 3700 after 27 timesteps | |
[2017-07-24 23:57:58,445] Episode reward: 27.0 | |
[2017-07-24 23:57:58,445] Average of last 500 rewards: 77.506 | |
[2017-07-24 23:57:58,445] Average of last 100 rewards: 63.78 | |
[2017-07-24 23:58:06,858] Finished episode 3750 after 45 timesteps | |
[2017-07-24 23:58:06,858] Episode reward: 45.0 | |
[2017-07-24 23:58:06,858] Average of last 500 rewards: 73.858 | |
[2017-07-24 23:58:06,858] Average of last 100 rewards: 64.17 | |
[2017-07-24 23:58:14,449] Finished episode 3800 after 66 timesteps | |
[2017-07-24 23:58:14,449] Episode reward: 66.0 | |
[2017-07-24 23:58:14,449] Average of last 500 rewards: 70.908 | |
[2017-07-24 23:58:14,449] Average of last 100 rewards: 63.07 | |
[2017-07-24 23:58:24,793] Finished episode 3850 after 72 timesteps | |
[2017-07-24 23:58:24,794] Episode reward: 72.0 | |
[2017-07-24 23:58:24,794] Average of last 500 rewards: 68.334 | |
[2017-07-24 23:58:24,794] Average of last 100 rewards: 63.72 | |
[2017-07-24 23:58:32,903] Finished episode 3900 after 63 timesteps | |
[2017-07-24 23:58:32,903] Episode reward: 63.0 | |
[2017-07-24 23:58:32,903] Average of last 500 rewards: 65.834 | |
[2017-07-24 23:58:32,903] Average of last 100 rewards: 63.69 | |
[2017-07-24 23:58:40,198] Finished episode 3950 after 79 timesteps | |
[2017-07-24 23:58:40,198] Episode reward: 79.0 | |
[2017-07-24 23:58:40,198] Average of last 500 rewards: 64.988 | |
[2017-07-24 23:58:40,199] Average of last 100 rewards: 62.01 | |
[2017-07-24 23:58:48,338] Finished episode 4000 after 78 timesteps | |
[2017-07-24 23:58:48,339] Episode reward: 78.0 | |
[2017-07-24 23:58:48,339] Average of last 500 rewards: 64.22 | |
[2017-07-24 23:58:48,339] Average of last 100 rewards: 62.21 | |
[2017-07-24 23:58:58,363] Finished episode 4050 after 61 timesteps | |
[2017-07-24 23:58:58,363] Episode reward: 61.0 | |
[2017-07-24 23:58:58,363] Average of last 500 rewards: 63.346 | |
[2017-07-24 23:58:58,364] Average of last 100 rewards: 62.33 | |
^CTraceback (most recent call last): | |
File "examples/openai_gym.py", line 121, in <module> | |
main() | |
File "examples/openai_gym.py", line 112, in main | |
runner.run(args.episodes, args.max_timesteps, episode_finished=episode_finished) | |
File "/home/adam/Desktop/running/tensorforce/tensorforce/execution/runner.py", line 144, in run | |
self.agent.observe(reward=reward, terminal=terminal) | |
File "/home/adam/Desktop/running/tensorforce/tensorforce/agents/batch_agent.py", line 85, in observe | |
self.model.update(self.batch) | |
File "/home/adam/Desktop/running/tensorforce/tensorforce/models/trpo_model.py", line 139, in update | |
super(TRPOModel, self).update(batch) | |
File "/home/adam/Desktop/running/tensorforce/tensorforce/models/policy_gradient_model.py", line 128, in update | |
self.baseline.update(states=batch['states'], returns=batch['returns']) | |
File "/home/adam/Desktop/running/tensorforce/tensorforce/core/baselines/mlp.py", line 66, in update | |
self.session.run(self.optimize, {self.state: states, self.returns: returns}) | |
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 895, in run | |
run_metadata_ptr) | |
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1093, in _run | |
np_val = np.asarray(subfeed_val, dtype=subfeed_dtype) | |
KeyboardInterrupt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment