Skip to content

Instantly share code, notes, and snippets.

@vanshg
Created March 21, 2021 21:59
Show Gist options
  • Save vanshg/0a7e53434fff171cdc4e921700c4d4eb to your computer and use it in GitHub Desktop.
Save vanshg/0a7e53434fff171cdc4e921700c4d4eb to your computer and use it in GitHub Desktop.
e=0 episode_reward=-385.9421852283017 epsilon=0.9902473782645512 avg=-385.9421852283017 independent_100_runs=-1011.9808541753459
e=1 episode_reward=-139.78551105987427 epsilon=0.9836345678377172 avg=-262.86384814408797 independent_100_runs=-620.6122728004954
e=2 episode_reward=-73.5144356879426 epsilon=0.9733599273999418 avg=-199.74737732537287 independent_100_runs=-112.43838788425847
e=3 episode_reward=-369.817489183475 epsilon=0.9637707295039442 avg=-242.2649052898984 independent_100_runs=-78.33101171808353
e=4 episode_reward=-168.0187847488219 epsilon=0.9568561568510938 avg=-227.4156811816831 independent_100_runs=-114.83203727111434
e=5 episode_reward=-161.5511523688159 epsilon=0.948472346345676 avg=-216.43825971287188 independent_100_runs=-123.68688581448887
e=6 episode_reward=-197.21611387943437 epsilon=0.9399739703614417 avg=-213.6922388795237 independent_100_runs=-204.24846108216877
e=7 episode_reward=-136.87769394935395 epsilon=0.9337902616531741 avg=-204.09042076325244 independent_100_runs=-203.8005187344964
e=8 episode_reward=-308.5977056206814 epsilon=0.9231126536824614 avg=-215.70234130296677 independent_100_runs=-250.34934646477097
e=9 episode_reward=-248.50308207212186 epsilon=0.9149329955488482 avg=-218.9824153798823 independent_100_runs=-480.28196620076733
e=10 episode_reward=-138.23764546998694 epsilon=0.9010403756394627 avg=-211.64198175170998 independent_100_runs=-139.0528227804992
e=11 episode_reward=-205.6085719516212 epsilon=0.8931456134926097 avg=-211.1391976017026 independent_100_runs=-212.3177425368637
e=12 episode_reward=-100.3846015457421 epsilon=0.8872699696109162 avg=-202.61961328970563 independent_100_runs=-113.1976488257809
e=13 episode_reward=-89.04251697533851 epsilon=0.8780897229382887 avg=-194.50696355296512 independent_100_runs=-59.42511478830729
e=14 episode_reward=-170.793480015466 epsilon=0.8673548374849623 avg=-192.9260646504652 independent_100_runs=-56.86894348441565
e=15 episode_reward=-254.3349603949136 epsilon=0.854697348969847 avg=-196.76412063449322 independent_100_runs=-149.86101457063506
e=16 episode_reward=-535.6715787767066 epsilon=0.8416351934382658 avg=-216.69985346638813 independent_100_runs=-220.43199050439657
e=17 episode_reward=-133.48825210208187 epsilon=0.8289384434161338 avg=-212.07698672392667 independent_100_runs=-156.9122620849735
e=18 episode_reward=-9.43214437839778 epsilon=0.8200336355010579 avg=-201.41146870574093 independent_100_runs=-85.65042517511523
e=19 episode_reward=-36.96141799749333 epsilon=0.8133365205280116 avg=-193.18896617032857 independent_100_runs=-58.32413094802154
e=20 episode_reward=-139.34725178630748 epsilon=0.8067747775562383 avg=-190.62507500918468 independent_100_runs=-2.2119112999843615
e=21 episode_reward=-195.09803856764324 epsilon=0.7983475414416326 avg=-190.82839153456916 independent_100_runs=-25.02267463945469
e=22 episode_reward=-374.57073984779043 epsilon=0.7906406239189183 avg=-198.81718928731792 independent_100_runs=-92.7995313167889
e=23 episode_reward=-173.86052838495908 epsilon=0.7808967299796155 avg=-197.77732841638627 independent_100_runs=-170.51795089094463
e=24 episode_reward=-269.6376105093169 epsilon=0.767886605456872 avg=-200.6517397001035 independent_100_runs=-126.4911137982501
e=25 episode_reward=72.18629641827727 epsilon=0.694878546995098 avg=-190.15796908016577 independent_100_runs=-202.88086427402638
e=26 episode_reward=-150.96734630571513 epsilon=0.6843957401023685 avg=-188.7064645329639 independent_100_runs=-501.84483399022474
e=27 episode_reward=-34.56141095071867 epsilon=0.6792817179026336 avg=-183.20128404788372 independent_100_runs=-288.4010222710291
e=28 episode_reward=-127.44283256014354 epsilon=0.6684991617668709 avg=-181.27857882416853 independent_100_runs=-66.31526123663978
e=29 episode_reward=-198.89155483521083 epsilon=0.6574273788832035 avg=-181.8656780245366 independent_100_runs=-174.69379320084872
e=30 episode_reward=107.75182287872462 epsilon=0.5949214096804725 avg=-172.52317799539915 independent_100_runs=-249.36647584079003
e=31 episode_reward=-327.331845737167 epsilon=0.5846003417079073 avg=-177.3609488623294 independent_100_runs=-96.39662545729264
e=32 episode_reward=-132.45589184642733 epsilon=0.5763572690287326 avg=-176.0001895588172 independent_100_runs=-261.11874220868305
e=33 episode_reward=-72.35000474539785 epsilon=0.5687989696836411 avg=-172.95165471136372 independent_100_runs=-156.3555488774392
e=34 episode_reward=-231.02696019853406 epsilon=0.5606665518357548 avg=-174.61094915385428 independent_100_runs=-254.18696973031936
e=35 episode_reward=118.32292706089711 epsilon=0.5073602744464892 avg=-166.47389703677786 independent_100_runs=-37.98294007337722
e=36 episode_reward=-363.4667352647022 epsilon=0.4954270716674468 avg=-171.79802779969472 independent_100_runs=-118.73494864781286
e=37 episode_reward=-83.6999295507232 epsilon=0.48644276418721516 avg=-169.47965679314282 independent_100_runs=-64.51127183908665
e=38 episode_reward=-406.5781154904719 epsilon=0.47690545157513753 avg=-175.5591044520487 independent_100_runs=-73.77643077336174
e=39 episode_reward=-78.57820053156183 epsilon=0.46980490203115843 avg=-173.13458185403655 independent_100_runs=-1.5086783950829636
e=40 episode_reward=-7.263850614560496 epsilon=0.4577925854667971 avg=-169.08895426282982 independent_100_runs=-373.23043623874514
e=41 episode_reward=-97.46272579510384 epsilon=0.4478306337649301 avg=-167.38356787074113 independent_100_runs=-694.9816335033798
e=42 episode_reward=-104.40400503353702 epsilon=0.438436088644296 avg=-165.91892687452707 independent_100_runs=-298.12663627837503
e=43 episode_reward=-159.84173965825107 epsilon=0.43130402298038956 avg=-165.78080898324808 independent_100_runs=-596.2926328355677
e=44 episode_reward=-522.1109406592543 epsilon=0.4236943578310804 avg=-173.69925635382597 independent_100_runs=-546.8463395239049
e=45 episode_reward=-88.56901055367793 epsilon=0.41847272772444155 avg=-171.84859883643145 independent_100_runs=-497.5611736530466
e=46 episode_reward=-137.6686338786547 epsilon=0.4086710427627667 avg=-171.12136553945749 independent_100_runs=-235.7707222911822
e=47 episode_reward=-15.509765546255423 epsilon=0.40214379792789484 avg=-167.87945720626578 independent_100_runs=-159.2812418092031
e=48 episode_reward=-12.175005035896305 epsilon=0.39710832440181526 avg=-164.70181532523782 independent_100_runs=-103.22837736229499
e=49 episode_reward=-243.2249901043957 epsilon=0.3877294900282468 avg=-166.272278820821 independent_100_runs=-207.23014616971173
e=50 episode_reward=-87.518481708743 epsilon=0.3791783939394074 avg=-164.72808672058414 independent_100_runs=-119.42282342149785
e=51 episode_reward=-253.34329379136906 epsilon=0.37338349219808126 avg=-166.43222531809926 independent_100_runs=-238.56686938391135
e=52 episode_reward=-72.1358646498834 epsilon=0.36540449323538227 avg=-164.6530487017178 independent_100_runs=-76.34006101264315
e=53 episode_reward=-203.05794158707587 epsilon=0.359820095052409 avg=-165.36425042181705 independent_100_runs=-92.88059066756021
e=54 episode_reward=-113.33296921014495 epsilon=0.3494647542842402 avg=-164.41822712705937 independent_100_runs=-194.6791531031587
e=55 episode_reward=-215.58490916251154 epsilon=0.34484741555067727 avg=-165.33191787769243 independent_100_runs=-170.3157910097612
e=56 episode_reward=-70.10054663365048 epsilon=0.3392716895103295 avg=-163.66119206639345 independent_100_runs=-168.37997363556084
e=57 episode_reward=-124.25105699050394 epsilon=0.3353922208063622 avg=-162.98170697887812 independent_100_runs=-263.43934425687235
e=58 episode_reward=-261.61619173747 epsilon=0.3284877725859433 avg=-164.65347790698985 independent_100_runs=-165.58870224816135
e=59 episode_reward=-118.05749880664487 epsilon=0.3191937164821629 avg=-163.87687825531745 independent_100_runs=-514.218736256838
e=60 episode_reward=-216.44063383970388 epsilon=0.3151969085808133 avg=-164.7385791665369 independent_100_runs=-782.2200653829013
e=61 episode_reward=-88.43532772461782 epsilon=0.3102867174667387 avg=-163.50788156263496 independent_100_runs=-686.3226381175283
e=62 episode_reward=-154.08617682794628 epsilon=0.30533085526465514 avg=-163.3583306938304 independent_100_runs=-775.7421914033794
e=63 episode_reward=-129.4793837699632 epsilon=0.3012665105123294 avg=-162.82897214814494 independent_100_runs=-323.08669118392436
e=64 episode_reward=-270.22848081923325 epsilon=0.2939454070826226 avg=-164.4812722815463 independent_100_runs=-182.6028002036297
e=65 episode_reward=-25.098762249157247 epsilon=0.29040992369221447 avg=-162.36941606893433 independent_100_runs=-127.35077022224162
e=66 episode_reward=-15.068896634715685 epsilon=0.2863150405097061 avg=-160.17090085349824 independent_100_runs=-234.66741940670724
e=67 episode_reward=-142.68526096127124 epsilon=0.27899432740332675 avg=-159.91375909037723 independent_100_runs=-196.49855514842932
e=68 episode_reward=-225.4265961448545 epsilon=0.2718336095833709 avg=-160.86322049696386 independent_100_runs=-211.32268942294724
e=69 episode_reward=-126.50587767954417 epsilon=0.2676257018952356 avg=-160.3724013138579 independent_100_runs=-165.8423176049424
e=70 episode_reward=-186.86604816228862 epsilon=0.2532523973456116 avg=-160.7455512694696 independent_100_runs=-392.033518536994
e=71 episode_reward=-143.851968030811 epsilon=0.23657923988379756 avg=-160.51091816893268 independent_100_runs=-208.59499235877777
e=72 episode_reward=-51.88367718723568 epsilon=0.22857890866868447 avg=-159.02287377192312 independent_100_runs=-183.12474201586832
e=73 episode_reward=-208.93642644178536 epsilon=0.2242766947525304 avg=-159.6973812404348 independent_100_runs=-138.333562890009
e=74 episode_reward=-225.1514699985722 epsilon=0.21782218697918707 avg=-160.57010242387662 independent_100_runs=-153.01075011320484
e=75 episode_reward=-66.86046091307713 epsilon=0.2137865610075486 avg=-159.33708082505032 independent_100_runs=-540.8468793565544
e=76 episode_reward=-353.24431823960094 epsilon=0.21026682276101732 avg=-161.8553566356289 independent_100_runs=-129.68513995554625
e=77 episode_reward=-399.92029942309927 epsilon=0.20680503276560924 avg=-164.90747128675034 independent_100_runs=-210.7486060550486
e=78 episode_reward=43.8327533178641 epsilon=0.20307504056042205 avg=-162.2651899626413 independent_100_runs=-288.7541951212915
e=79 episode_reward=-172.43255220667035 epsilon=0.19871556558302653 avg=-162.39228199069163 independent_100_runs=-138.355024204069
e=80 episode_reward=-122.10787566845624 epsilon=0.1953267160657498 avg=-161.8949436410344 independent_100_runs=-164.45377179889897
e=81 episode_reward=-135.3324926299967 epsilon=0.1921108969334997 avg=-161.5710113116315 independent_100_runs=-148.94888631529963
e=82 episode_reward=-131.6354974627888 epsilon=0.18923167128994553 avg=-161.21034247007918 independent_100_runs=-225.2499789166463
e=83 episode_reward=-258.13330426660195 epsilon=0.18321684987764683 avg=-162.3641872533711 independent_100_runs=-141.41704312475778
e=84 episode_reward=235.5395809126647 epsilon=0.17173750684536793 avg=-157.68296645141774 independent_100_runs=-92.03812268574451
e=85 episode_reward=-29.539518634395463 epsilon=0.16390137139048802 avg=-156.19292636052214 independent_100_runs=-74.59164688038071
e=86 episode_reward=-187.03816224565105 epsilon=0.1598384468374648 avg=-156.54746930173053 independent_100_runs=-149.32677236563322
e=87 episode_reward=0.4473374914592938 epsilon=0.1554092861800447 avg=-154.76343740635335 independent_100_runs=-129.32566364223064
e=88 episode_reward=266.8706151133297 epsilon=0.14977892111342886 avg=-150.02597614208725 independent_100_runs=-273.8050086973282
e=89 episode_reward=216.369987717644 epsilon=0.14068976491504737 avg=-145.95490987697912 independent_100_runs=-75.43913650400587
e=90 episode_reward=-276.55025504270776 epsilon=0.1376970720662608 avg=-147.390023560119 independent_100_runs=-279.8090023959739
e=91 episode_reward=-385.2914544881647 epsilon=0.13265533219479242 avg=-149.9759086789021 independent_100_runs=-210.930114946544
e=92 episode_reward=-196.2597532860226 epsilon=0.13010649497082802 avg=-150.47358442736575 independent_100_runs=-266.78866155213024
e=93 episode_reward=-234.58205635968113 epsilon=0.12423202630777894 avg=-151.3683554053691 independent_100_runs=-286.9315326387286
e=94 episode_reward=-103.18365996313291 epsilon=0.12163806340330371 avg=-150.8611480849245 independent_100_runs=-252.5837411588991
e=95 episode_reward=-124.67207516718157 epsilon=0.11931284307279298 avg=-150.58834524203138 independent_100_runs=-287.45784079972276
e=96 episode_reward=-210.52111081264252 epsilon=0.11773640995621194 avg=-151.206208804615 independent_100_runs=-374.831880312361
e=97 episode_reward=-236.90057198274462 epsilon=0.11279208483598177 avg=-152.08064108194287 independent_100_runs=-272.8235451697451
e=98 episode_reward=-79.23652712951151 epsilon=0.11063596329439043 avg=-151.34484195111023 independent_100_runs=-201.33458081583322
e=99 episode_reward=-231.73736457159535 epsilon=0.10695877838873524 avg=-152.14876717731508 independent_100_runs=-175.67791366989283
e=100 episode_reward=-79.71374728886082 epsilon=0.10453713492925723 avg=-149.08648279792067 independent_100_runs=-332.5396044043321
e=101 episode_reward=-363.6262262784981 epsilon=0.10274410725311922 avg=-151.3248899501069 independent_100_runs=-305.2170174914498
e=102 episode_reward=-158.4803533918314 epsilon=0.10151848512488924 avg=-152.1745491271458 independent_100_runs=-276.69651740026484
e=103 episode_reward=-88.5243136664041 epsilon=0.10036768885614482 avg=-149.3616173719751 independent_100_runs=-166.55849935646916
e=104 episode_reward=-72.79315216050786 epsilon=0.09747918531087302 avg=-148.40936104609193 independent_100_runs=-69.40236545468478
e=105 episode_reward=-330.80126856330423 epsilon=0.09591266723932104 avg=-150.10186220803683 independent_100_runs=-168.00264222464423
e=106 episode_reward=-564.9181775288943 epsilon=0.09385368021811356 avg=-153.77888284453144 independent_100_runs=-416.10290454274326
e=107 episode_reward=-199.78834527659822 epsilon=0.09199516083341126 avg=-154.40798935780387 independent_100_runs=-98.9417584974141
e=108 episode_reward=176.6822867312585 epsilon=0.08611061328624767 avg=-149.55518943428447 independent_100_runs=-59.59860668458987
e=109 episode_reward=-224.41744052346587 epsilon=0.08330686974481696 avg=-149.31433301879792 independent_100_runs=-53.728675865941504
e=110 episode_reward=-129.7845345343901 epsilon=0.08198450087216189 avg=-149.22980190944196 independent_100_runs=-197.65777207495034
e=111 episode_reward=-302.31365018334895 epsilon=0.08022451412489778 avg=-150.19685269175923 independent_100_runs=-187.90939294251842
e=112 episode_reward=-322.5868678075732 epsilon=0.07909331995102684 avg=-152.41887535437755 independent_100_runs=-235.00778398261826
e=113 episode_reward=-290.05825961987546 epsilon=0.07642628682700205 avg=-154.4290327808229 independent_100_runs=-135.489167755775
e=114 episode_reward=-163.00951709912624 epsilon=0.0749503377102579 avg=-154.3511931516595 independent_100_runs=-416.85064959756926
e=115 episode_reward=-587.6017333850281 epsilon=0.07367951985418181 avg=-157.68386088156066 independent_100_runs=-283.5720855482373
e=116 episode_reward=-548.6141284620004 epsilon=0.07221327333606271 avg=-157.81328637841358 independent_100_runs=-511.5005869654981
e=117 episode_reward=-185.16243967480267 epsilon=0.07078328393110833 avg=-158.33002825414079 independent_100_runs=-382.29948923309763
e=118 episode_reward=-474.19230550267474 epsilon=0.06793292457273792 avg=-162.97762986538356 independent_100_runs=-318.64823127209854
e=119 episode_reward=-499.24041097689525 epsilon=0.06688803084331181 avg=-167.60041979517757 independent_100_runs=-180.43117745487555
e=120 episode_reward=-312.24227405434056 epsilon=0.06603727794487561 avg=-169.3293700178579 independent_100_runs=-248.35689629569305
e=121 episode_reward=-292.6578507657574 epsilon=0.06430375771122998 avg=-170.30496813983905 independent_100_runs=-206.39447629391543
e=122 episode_reward=-271.5369850230454 epsilon=0.06282901001703273 avg=-169.2746305915916 independent_100_runs=-195.5940211769199
e=123 episode_reward=-138.23720685894037 epsilon=0.06175753854149681 avg=-168.91839737633143 independent_100_runs=-263.904661056722
e=124 episode_reward=-172.17138518583056 epsilon=0.059472508548425916 avg=-167.94373512309653 independent_100_runs=-272.5012463087063
e=125 episode_reward=-145.7087666647609 epsilon=0.05887482968691017 avg=-170.1226857539269 independent_100_runs=-259.4306282239327
e=126 episode_reward=-246.77194569944018 epsilon=0.05753034251098656 avg=-171.08073174786415 independent_100_runs=-197.96930774108975
e=127 episode_reward=-353.0097208790914 epsilon=0.05628406227631319 avg=-174.26521484714786 independent_100_runs=-307.43537517522094
e=128 episode_reward=-481.0028727679846 epsilon=0.05526890751552519 avg=-177.80081524922633 independent_100_runs=-138.84838099022033
e=129 episode_reward=-38.640749216026535 epsilon=0.05458777078073013 avg=-176.19830719303448 independent_100_runs=-149.42592176839372
e=130 episode_reward=-206.89080653888138 epsilon=0.05329852643727298 avg=-179.34473348721053 independent_100_runs=-209.75800779483367
e=131 episode_reward=-62.809127241729996 epsilon=0.04928918934544283 avg=-176.69950630225617 independent_100_runs=-234.49518851949716
e=132 episode_reward=-391.3604596741215 epsilon=0.04843893361510754 avg=-179.28855198053307 independent_100_runs=-148.54536528827919
e=133 episode_reward=-38.4761904870532 epsilon=0.04765574020449964 avg=-178.94981383794965 independent_100_runs=-274.7425333015679
e=134 episode_reward=-350.05407439122393 epsilon=0.04677749254778872 avg=-180.14008497987655 independent_100_runs=-137.62088805674267
e=135 episode_reward=-262.3000423461675 epsilon=0.04603957550706484 avg=-183.9463146739472 independent_100_runs=-296.93806565797684
e=136 episode_reward=-449.71113667439636 epsilon=0.045513126947264976 avg=-184.80875868804415 independent_100_runs=-76.74877126734674
e=137 episode_reward=-294.23125830118636 epsilon=0.044736956556020266 avg=-186.9140719755488 independent_100_runs=-448.3563495264045
e=138 episode_reward=-49.244773252386395 epsilon=0.04411497211513581 avg=-183.34073855316794 independent_100_runs=-369.7428614683906
e=139 episode_reward=-378.7148048365301 epsilon=0.0436803670056791 avg=-186.3421045962176 independent_100_runs=-354.71585795741964
e=140 episode_reward=-492.3348480598802 epsilon=0.043012809362973824 avg=-191.19281457067086 independent_100_runs=-380.6560503498977
e=141 episode_reward=-528.4399578944799 epsilon=0.04254649246890439 avg=-195.50258689166458 independent_100_runs=-400.29244817232194
e=142 episode_reward=-252.52964907667757 epsilon=0.04192141014528717 avg=-196.98384333209597 independent_100_runs=-32.886944066581044
e=143 episode_reward=-69.18335986136816 epsilon=0.041251846415027514 avg=-196.0772595341271 independent_100_runs=-109.2497155468635
e=144 episode_reward=-125.99203924208611 epsilon=0.04075568211271202 avg=-192.11607051995546 independent_100_runs=-82.14341397449061
e=145 episode_reward=-301.52494779134827 epsilon=0.04000059516997725 avg=-194.24562989233215 independent_100_runs=-504.2694409096559
e=146 episode_reward=-289.836464815507 epsilon=0.038903839329088356 avg=-195.7673082017007 independent_100_runs=-209.52344300906657
e=147 episode_reward=-298.7447233607261 epsilon=0.037863651481118 avg=-198.59965777984544 independent_100_runs=-57.524793053966306
e=148 episode_reward=158.6228818901846 epsilon=0.03607821328017128 avg=-196.89167891058463 independent_100_runs=-353.5565365426072
e=149 episode_reward=-169.39840226882555 epsilon=0.03559440625571399 avg=-196.15341303222894 independent_100_runs=-237.85351354956455
e=150 episode_reward=-217.70672277576386 epsilon=0.03502239408236723 avg=-197.45529544289914 independent_100_runs=-331.7206833420714
e=151 episode_reward=-254.16516485140198 epsilon=0.03413374221170114 avg=-197.46351415349946 independent_100_runs=-136.30523684593828
e=152 episode_reward=-78.36036969375388 epsilon=0.03349464105947989 avg=-197.52575920393815 independent_100_runs=-107.50419361056014
e=153 episode_reward=-204.20435470802715 epsilon=0.03306531383765098 avg=-197.53722333514764 independent_100_runs=-251.34282165597358
e=154 episode_reward=-46.97835624047188 epsilon=0.032429997478051455 avg=-196.87367720545092 independent_100_runs=-93.72801747084674
e=155 episode_reward=-220.87460340580196 epsilon=0.03206237654628497 avg=-196.92657414788388 independent_100_runs=-357.7846996579514
e=156 episode_reward=-90.2913846574734 epsilon=0.03123008701104387 avg=-197.12848252812208 independent_100_runs=-357.4529841676161
e=157 episode_reward=-232.03093166456887 epsilon=0.030449838560234133 avg=-198.20628127486273 independent_100_runs=-244.65406338464388
e=158 episode_reward=-296.29856716598005 epsilon=0.029603105822140773 avg=-198.55310502914782 independent_100_runs=-351.6675934206337
e=159 episode_reward=-14.651681596695923 epsilon=0.029223659475557835 avg=-197.51904685704838 independent_100_runs=-240.39515054278087
e=160 episode_reward=-242.1430006910635 epsilon=0.028587728065811523 avg=-197.77607052556192 independent_100_runs=-97.9146939701433
e=161 episode_reward=-24.484418365866816 epsilon=0.028198727479550875 avg=-197.13656143197443 independent_100_runs=-352.977466532972
e=162 episode_reward=-310.0485602203939 epsilon=0.027898594662852987 avg=-198.69618526589892 independent_100_runs=-332.5584171074304
e=163 episode_reward=-261.1450981287702 epsilon=0.027532734906933583 avg=-200.01284240948698 independent_100_runs=-223.54452212438053
e=164 episode_reward=-203.4829663689284 epsilon=0.02712009326272397 avg=-199.3453872649839 independent_100_runs=-209.45328025824926
e=165 episode_reward=-257.2380846795537 epsilon=0.026402892323720454 avg=-201.66678048928787 independent_100_runs=-229.9341157831875
e=166 episode_reward=-209.6187789053409 epsilon=0.025895587614127597 avg=-203.6122793119941 independent_100_runs=-164.31645614090937
e=167 episode_reward=-206.25586485097682 epsilon=0.025319414341305517 avg=-204.24798535089113 independent_100_runs=-348.9620261428015
e=168 episode_reward=-82.6722986874205 epsilon=0.024566161731056257 avg=-202.82044237631678 independent_100_runs=-221.78173928106364
e=169 episode_reward=-341.69108056596764 epsilon=0.024241578811877173 avg=-204.97229440518106 independent_100_runs=-129.88276635911564
e=170 episode_reward=-232.8079256304281 epsilon=0.023883039114631396 avg=-205.4317131798624 independent_100_runs=-143.38481493553508
e=171 episode_reward=-69.61018988280702 epsilon=0.02338436160488844 avg=-204.68929539838237 independent_100_runs=-113.83743039136398
e=172 episode_reward=-276.42501733232314 epsilon=0.022997066318117716 avg=-206.9347087998333 independent_100_runs=-279.4696418386486
e=173 episode_reward=-206.00602445141146 epsilon=0.022494381149485137 avg=-206.9054047799295 independent_100_runs=-140.14778553014273
e=174 episode_reward=-114.60161890116885 epsilon=0.022033510880309734 avg=-205.79990626895548 independent_100_runs=-135.0203200471834
e=175 episode_reward=-84.33759186364773 epsilon=0.021629618260652694 avg=-205.97467757846118 independent_100_runs=-108.2330270103654
e=176 episode_reward=-69.88973270406652 epsilon=0.021256499791566213 avg=-203.14113172310581 independent_100_runs=-83.9082972437854
e=177 episode_reward=-154.469129717495 epsilon=0.020984038474989825 avg=-200.6866200260498 independent_100_runs=-168.46271143774408
e=178 episode_reward=-169.29327088130972 epsilon=0.02071921314535501 avg=-202.81788026804156 independent_100_runs=-139.3508428412785
e=179 episode_reward=-195.1615934280325 epsilon=0.02017128585840553 avg=-203.04517068025515 independent_100_runs=-155.90069708908305
e=180 episode_reward=-62.385219751641166 epsilon=0.01980549027558923 avg=-202.44794412108706 independent_100_runs=-95.97413663793569
e=181 episode_reward=-104.10396400138589 epsilon=0.01933772769906333 avg=-202.13565883480092 independent_100_runs=-109.58224642929274
e=182 episode_reward=-313.39659301895495 epsilon=0.01894342604451264 avg=-203.95326979036258 independent_100_runs=-239.84188621849054
e=183 episode_reward=-142.0664520716038 epsilon=0.018573874112202203 avg=-202.79260126841262 independent_100_runs=-162.19899543508728
e=184 episode_reward=-169.1501291299133 epsilon=0.018180596620575116 avg=-206.8394983688384 independent_100_runs=-251.9830692916022
e=185 episode_reward=-331.4809576908343 epsilon=0.01785804327837135 avg=-209.8589127594028 independent_100_runs=-194.11022069463772
e=186 episode_reward=-108.64829430342817 epsilon=0.01718010580987462 avg=-209.07501407998058 independent_100_runs=-147.87636553153004
e=187 episode_reward=-295.7020072139028 epsilon=0.016604111913513697 avg=-212.03650752703416 independent_100_runs=-202.28182467808674
e=188 episode_reward=-220.56871874752616 epsilon=0.01627693988664626 avg=-216.91090086564276 independent_100_runs=-209.75787064677505
e=189 episode_reward=-56.54862803727315 epsilon=0.016012161947316503 avg=-219.64008702319188 independent_100_runs=-459.7337141778093
e=190 episode_reward=-530.3382702599989 epsilon=0.01577376008204608 avg=-222.17796717536478 independent_100_runs=-276.3520710586193
e=191 episode_reward=-314.27511410223906 epsilon=0.015436683542878324 avg=-221.46780377150554 independent_100_runs=-238.2470024661903
e=192 episode_reward=-243.09317275604297 epsilon=0.015131001596967621 avg=-221.93613796620576 independent_100_runs=-308.97056883673895
e=193 episode_reward=-190.09916702408748 epsilon=0.014812103638294678 avg=-221.4913090728498 independent_100_runs=-139.66729004278912
e=194 episode_reward=-38.70115551414541 epsilon=0.014501376846802983 avg=-220.84648402835995 independent_100_runs=-197.23825213028613
e=195 episode_reward=-240.8284329952862 epsilon=0.01409954031073106 avg=-222.00804760664101 independent_100_runs=-214.94308226845675
e=196 episode_reward=-336.9201897598924 epsilon=0.01394807707584897 avg=-223.27203839611354 independent_100_runs=-185.74132577695815
e=197 episode_reward=-194.0007669613784 epsilon=0.013665038402700752 avg=-222.84304034589985 independent_100_runs=-297.54337725812763
e=198 episode_reward=-255.2371285004238 epsilon=0.013446782049793143 avg=-224.60304635960895 independent_100_runs=-287.6494482552072
e=199 episode_reward=-178.23894910038948 epsilon=0.013238629652248476 avg=-224.06806220489688 independent_100_runs=-337.7896712727265
e=200 episode_reward=-55.49496552295874 epsilon=0.012911750580735798 avg=-223.82587438723786 independent_100_runs=-280.8678959998663
e=201 episode_reward=-25.903048725025783 epsilon=0.012635833603571569 avg=-220.44864261170315 independent_100_runs=-167.45217661245408
e=202 episode_reward=-53.72552629294217 epsilon=0.012349746904919036 avg=-219.40109434071425 independent_100_runs=-197.1560342250324
e=203 episode_reward=-498.4397779399275 epsilon=0.01199073291351643 avg=-223.5002489834495 independent_100_runs=-150.51526527115195
e=204 episode_reward=-201.94914710322928 epsilon=0.011711050862133006 avg=-224.79180893287673 independent_100_runs=-104.21399503322809
e=205 episode_reward=-221.89074024330887 epsilon=0.011338809371023688 avg=-223.70270364967678 independent_100_runs=-104.71288630834489
e=206 episode_reward=-137.00591988382266 epsilon=0.010963039984828064 avg=-219.42358107322607 independent_100_runs=-130.04504899813054
e=207 episode_reward=3.1071801043413387 epsilon=0.010442950774724829 avg=-217.3946258194167 independent_100_runs=-149.17803395782113
e=208 episode_reward=-327.3130875737678 epsilon=0.010157636617303501 avg=-222.43457956246692 independent_100_runs=-292.8301964092443
e=209 episode_reward=-377.04355231491377 epsilon=0.01 avg=-223.96084068038138 independent_100_runs=-338.2453999606176
e=210 episode_reward=-114.22411545661103 epsilon=0.01 avg=-223.8052364896036 independent_100_runs=-123.383933993726
e=211 episode_reward=-339.98351225517683 epsilon=0.01 avg=-224.18193511032183 independent_100_runs=-188.84695224210023
e=212 episode_reward=-219.16656985273758 epsilon=0.01 avg=-223.1477321307735 independent_100_runs=-168.80138127974206
e=213 episode_reward=-269.8752465851462 epsilon=0.01 avg=-222.9459020004262 independent_100_runs=-172.9541134741611
e=214 episode_reward=-266.5296215112503 epsilon=0.01 avg=-223.9811030445475 independent_100_runs=-319.25670562164703
e=215 episode_reward=-207.12587481479298 epsilon=0.01 avg=-220.17634445884508 independent_100_runs=-94.72476231609691
e=216 episode_reward=-568.294485084675 epsilon=0.01 avg=-220.37314802507188 independent_100_runs=-307.91389496615767
e=217 episode_reward=-102.25363840461958 epsilon=0.01 avg=-219.54406001237004 independent_100_runs=-207.31749647639413
e=218 episode_reward=-471.2741900743238 epsilon=0.01 avg=-219.51487885808652 independent_100_runs=-82.35920367402272
e=219 episode_reward=-118.03631698526708 epsilon=0.01 avg=-215.70283791817027 independent_100_runs=-116.03564219576852
e=220 episode_reward=-238.76138524510426 epsilon=0.01 avg=-214.9680290300779 independent_100_runs=-153.3980899024618
e=221 episode_reward=-375.23473893157984 epsilon=0.01 avg=-215.7937979117361 independent_100_runs=-185.15847809277227
e=222 episode_reward=-127.56193293795727 epsilon=0.01 avg=-214.35404739088526 independent_100_runs=-161.980758799793
e=223 episode_reward=-92.53087844060785 epsilon=0.01 avg=-213.89698410670192 independent_100_runs=-207.7787775362106
e=224 episode_reward=-209.67606393022345 epsilon=0.01 avg=-214.27203089414587 independent_100_runs=-131.698529046536
e=225 episode_reward=-205.99477938070123 epsilon=0.01 avg=-214.87489102130522 independent_100_runs=-98.93924878393574
e=226 episode_reward=-141.13363864972033 epsilon=0.01 avg=-213.81850795080803 independent_100_runs=-113.46508303368209
e=227 episode_reward=-218.32894089955744 epsilon=0.01 avg=-212.4717001510127 independent_100_runs=-103.67558087622295
e=228 episode_reward=7.810548435075887 epsilon=0.01 avg=-207.5835659389821 independent_100_runs=-112.78906139016006
e=229 episode_reward=-160.66723882138612 epsilon=0.01 avg=-208.80383083503568 independent_100_runs=-121.39965303810773
e=230 episode_reward=-163.08441733948285 epsilon=0.01 avg=-208.3657669430417 independent_100_runs=-117.76576509193065
e=231 episode_reward=-236.217572794623 epsilon=0.01 avg=-210.09985139857065 independent_100_runs=-155.61695574982036
e=232 episode_reward=-121.7034613705887 epsilon=0.01 avg=-207.4032814155353 independent_100_runs=-163.65089846839135
e=233 episode_reward=-166.11294540693171 epsilon=0.01 avg=-208.67964896473407 independent_100_runs=-117.88465085420292
e=234 episode_reward=-42.11205177807152 epsilon=0.01 avg=-205.60022873860257 independent_100_runs=-119.38235696793414
e=235 episode_reward=-130.78044604400438 epsilon=0.01 avg=-204.2850327755809 independent_100_runs=-140.70507226096115
e=236 episode_reward=-52.62685615860477 epsilon=0.01 avg=-200.314189970423 independent_100_runs=-164.73023992787958
e=237 episode_reward=-198.73615450023271 epsilon=0.01 avg=-199.3592389324135 independent_100_runs=-185.09122153021795
e=238 episode_reward=-219.6098518583474 epsilon=0.01 avg=-201.0628897184731 independent_100_runs=-264.18198399202544
e=239 episode_reward=-275.08869198664263 epsilon=0.01 avg=-200.02662858997417 independent_100_runs=-211.78693213599843
e=240 episode_reward=-177.5457735529423 epsilon=0.01 avg=-196.87873784490478 independent_100_runs=-201.12306453377474
e=241 episode_reward=-92.76019422147263 epsilon=0.01 avg=-192.52194020817475 independent_100_runs=-149.93225931153103
e=242 episode_reward=-355.4426282098675 epsilon=0.01 avg=-193.5510699995067 independent_100_runs=-214.452193712599
e=243 episode_reward=-281.2145520922144 epsilon=0.01 avg=-195.6713819218151 independent_100_runs=-165.6230075501991
e=244 episode_reward=-81.02520668833566 epsilon=0.01 avg=-195.22171359627762 independent_100_runs=-57.20116201303221
e=245 episode_reward=-232.01832898506115 epsilon=0.01 avg=-194.52664740821479 independent_100_runs=-137.66318148963614
e=246 episode_reward=-423.2274066504069 epsilon=0.01 avg=-195.86055682656377 independent_100_runs=-454.9676336854273
e=247 episode_reward=-22.79050437000903 epsilon=0.01 avg=-193.10101463665663 independent_100_runs=-137.9305971508491
e=248 episode_reward=-190.46782342970343 epsilon=0.01 avg=-196.59192168985544 independent_100_runs=-136.40858964961544
e=249 episode_reward=-143.785904003374 epsilon=0.01 avg=-196.33579670720093 independent_100_runs=-163.77942470664146
e=250 episode_reward=-112.29039480941012 epsilon=0.01 avg=-195.28163342753737 independent_100_runs=-100.2907669493824
e=251 episode_reward=-228.17029549778837 epsilon=0.01 avg=-195.02168473400124 independent_100_runs=-325.88045416061453
e=252 episode_reward=-209.3593364363121 epsilon=0.01 avg=-196.33167440142682 independent_100_runs=-259.7511649482815
e=253 episode_reward=-240.19881731703774 epsilon=0.01 avg=-196.69161902751696 independent_100_runs=-170.4382755601273
e=254 episode_reward=-105.56588585856372 epsilon=0.01 avg=-197.27749432369785 independent_100_runs=-162.1584420621658
e=255 episode_reward=-396.7321527875462 epsilon=0.01 avg=-199.03606981751534 independent_100_runs=-330.0336746302883
e=256 episode_reward=-181.31329755504765 epsilon=0.01 avg=-199.94628894649108 independent_100_runs=-417.90428188820727
e=257 episode_reward=-775.3547033341686 epsilon=0.01 avg=-205.37952666318702 independent_100_runs=-238.52498772293816
e=258 episode_reward=-491.68288006133935 epsilon=0.01 avg=-207.33336979214062 independent_100_runs=-145.97820059083028
e=259 episode_reward=-82.87759652453126 epsilon=0.01 avg=-208.01562894141898 independent_100_runs=-317.561911628177
e=260 episode_reward=-235.40236885459092 epsilon=0.01 avg=-207.94822262305425 independent_100_runs=-325.1023121789477
e=261 episode_reward=-415.9240367107717 epsilon=0.01 avg=-211.86261880650326 independent_100_runs=-182.9278378309902
e=262 episode_reward=-108.49082185565956 epsilon=0.01 avg=-209.8470414228559 independent_100_runs=-124.09222158048178
e=263 episode_reward=-221.25817547987089 epsilon=0.01 avg=-209.44817219636695 independent_100_runs=-123.29119866041066
e=264 episode_reward=-87.06895899153868 epsilon=0.01 avg=-208.28403212259306 independent_100_runs=-243.78502054775396
e=265 episode_reward=-234.98884074940997 epsilon=0.01 avg=-208.06153968329164 independent_100_runs=-163.10805307265176
e=266 episode_reward=-251.61593554226258 epsilon=0.01 avg=-208.48151124966088 independent_100_runs=-293.2013892839462
e=267 episode_reward=-359.04577145452026 epsilon=0.01 avg=-210.0094103156963 independent_100_runs=-317.7459008041262
e=268 episode_reward=-216.28408952114796 epsilon=0.01 avg=-211.3455282240336 independent_100_runs=-102.51746753835907
e=269 episode_reward=-88.6759895825571 epsilon=0.01 avg=-208.81537731419948 independent_100_runs=-151.5431294040479
e=270 episode_reward=14.674758259721273 epsilon=0.01 avg=-206.34055047529796 independent_100_runs=-126.33611204017444
e=271 episode_reward=-55.359148793214324 epsilon=0.01 avg=-206.19804006440205 independent_100_runs=-150.91515032002937
e=272 episode_reward=-252.9587407510561 epsilon=0.01 avg=-205.96337729858936 independent_100_runs=-163.03026179856897
e=273 episode_reward=-323.42955560413634 epsilon=0.01 avg=-207.13761261011663 independent_100_runs=-355.92644557487847
e=274 episode_reward=-208.21966895871023 epsilon=0.01 avg=-208.073793110692 independent_100_runs=-121.78433676986522
e=275 episode_reward=-350.1795467959623 epsilon=0.01 avg=-210.73221266001522 independent_100_runs=-246.57715990574036
e=276 episode_reward=-353.65146858063554 epsilon=0.01 avg=-213.56983001878092 independent_100_runs=-145.19132858264896
e=277 episode_reward=-223.39365946715046 epsilon=0.01 avg=-214.25907531627746 independent_100_runs=-154.7748204499545
e=278 episode_reward=-293.7312880696049 epsilon=0.01 avg=-215.5034554881604 independent_100_runs=-243.29628710329564
e=279 episode_reward=-359.4980330795293 epsilon=0.01 avg=-217.14681988467535 independent_100_runs=-259.2213391562221
e=280 episode_reward=-342.8510997875669 epsilon=0.01 avg=-219.9514786850346 independent_100_runs=-247.9446721814672
e=281 episode_reward=-202.47361527590323 epsilon=0.01 avg=-220.93517519777978 independent_100_runs=-215.23333646940776
e=282 episode_reward=-275.0186995158326 epsilon=0.01 avg=-220.55139626274857 independent_100_runs=-286.3431076707433
e=283 episode_reward=-80.62941936646712 epsilon=0.01 avg=-219.93702593569725 independent_100_runs=-112.01217224567716
e=284 episode_reward=-83.54545368421486 epsilon=0.01 avg=-219.08097918124025 independent_100_runs=-122.22280172520081
e=285 episode_reward=-86.54711157466667 epsilon=0.01 avg=-216.63164072007854 independent_100_runs=-380.8872339940575
e=286 episode_reward=-291.1399259764331 epsilon=0.01 avg=-218.4565570368086 independent_100_runs=-423.84682842873343
e=287 episode_reward=-425.05864759136614 epsilon=0.01 avg=-219.7501234405832 independent_100_runs=-434.7316827549109
e=288 episode_reward=-562.7508560308481 epsilon=0.01 avg=-223.17194481341645 independent_100_runs=-450.6502244745785
e=289 episode_reward=-182.57338306956973 epsilon=0.01 avg=-224.4321923637394 independent_100_runs=-423.3210816696812
e=290 episode_reward=-297.3133906168363 epsilon=0.01 avg=-222.10194356730776 independent_100_runs=-248.05557953549385
e=291 episode_reward=-297.03918007234245 epsilon=0.01 avg=-221.92958422700877 independent_100_runs=-167.62882138698285
e=292 episode_reward=-285.3127098614638 epsilon=0.01 avg=-222.35177959806296 independent_100_runs=-181.6666644177137
e=293 episode_reward=-120.86900781671655 epsilon=0.01 avg=-221.65947800598929 independent_100_runs=-167.02430812286076
e=294 episode_reward=-234.5059703843255 epsilon=0.01 avg=-223.61752615469106 independent_100_runs=-175.78802956868748
e=295 episode_reward=-165.2118591213585 epsilon=0.01 avg=-222.86136041595182 independent_100_runs=-294.2013925017025
e=296 episode_reward=-243.75952623173657 epsilon=0.01 avg=-221.92975378067024 independent_100_runs=-157.72170409798736
e=297 episode_reward=-276.5871674451422 epsilon=0.01 avg=-222.7556177855079 independent_100_runs=-225.3230406165672
e=298 episode_reward=-266.52576446340845 epsilon=0.01 avg=-222.86850414513773 independent_100_runs=-177.42395349001893
e=299 episode_reward=-202.04387407562086 epsilon=0.01 avg=-223.10655339489006 independent_100_runs=-208.07831664794335
e=300 episode_reward=-220.92539553593258 epsilon=0.01 avg=-224.76085769501978 independent_100_runs=-281.6729366415415
e=301 episode_reward=-232.743221823052 epsilon=0.01 avg=-226.82925942600002 independent_100_runs=-151.9582463999164
e=302 episode_reward=-82.28111531552976 epsilon=0.01 avg=-227.11481531622593 independent_100_runs=-99.6467366538031
e=303 episode_reward=-19.46879222404627 epsilon=0.01 avg=-222.32510545906712 independent_100_runs=-122.97507934240554
e=304 episode_reward=31.17611243430585 epsilon=0.01 avg=-219.99385286369176 independent_100_runs=-202.80595804893414
e=305 episode_reward=-168.71542643640367 epsilon=0.01 avg=-219.4620997256227 independent_100_runs=-176.3618502180815
e=306 episode_reward=177.928409790195 epsilon=0.01 avg=-216.3127564288825 independent_100_runs=-108.4064694111814
e=307 episode_reward=-126.1512465122951 epsilon=0.01 avg=-217.6053406950489 independent_100_runs=-100.78802689808518
e=308 episode_reward=-106.56046087773363 epsilon=0.01 avg=-215.39781442808854 independent_100_runs=-110.64424534633619
e=309 episode_reward=21.970622242141914 epsilon=0.01 avg=-211.40767268251798 independent_100_runs=-119.9587301164145
e=310 episode_reward=-492.5007572950704 epsilon=0.01 avg=-215.19043910090258 independent_100_runs=-183.90561089269002
e=311 episode_reward=-207.60043722902162 epsilon=0.01 avg=-213.86660835064106 independent_100_runs=-131.2185340826125
e=312 episode_reward=-76.28112427758246 epsilon=0.01 avg=-212.4377538948895 independent_100_runs=-317.67336499660485
e=313 episode_reward=-581.7013325932094 epsilon=0.01 avg=-215.55601475497016 independent_100_runs=-193.9629099292589
e=314 episode_reward=-396.099302134498 epsilon=0.01 avg=-216.85171156120265 independent_100_runs=-445.64381469134264
e=315 episode_reward=-274.11061822748417 epsilon=0.01 avg=-217.52155899532957 independent_100_runs=-76.80747492741189
e=316 episode_reward=-196.8282685519806 epsilon=0.01 avg=-213.8068968300026 independent_100_runs=-130.3470959532557
e=317 episode_reward=-50.75942865850358 epsilon=0.01 avg=-213.29195473254148 independent_100_runs=-173.13856487467746
e=318 episode_reward=-94.06801605221604 epsilon=0.01 avg=-209.5198929923204 independent_100_runs=-183.53972928145922
e=319 episode_reward=-152.55324287584807 epsilon=0.01 avg=-209.8650622512262 independent_100_runs=-145.60729716375093
e=320 episode_reward=-77.72459755516694 epsilon=0.01 avg=-208.25469437432682 independent_100_runs=-158.87179767611616
e=321 episode_reward=-169.1721393225941 epsilon=0.01 avg=-206.19406837823695 independent_100_runs=-169.96790900076067
e=322 episode_reward=-82.33662109421229 epsilon=0.01 avg=-205.74181525979944 independent_100_runs=-108.07464326002271
e=323 episode_reward=-213.04405514268706 epsilon=0.01 avg=-206.94694702682028 independent_100_runs=-228.28890517559333
e=324 episode_reward=-289.48133910551957 epsilon=0.01 avg=-207.74499977857326 independent_100_runs=-529.1938432780081
e=325 episode_reward=-659.693974866069 epsilon=0.01 avg=-212.28199173342693 independent_100_runs=-510.3101047917313
e=326 episode_reward=-66.79840108610675 epsilon=0.01 avg=-211.53863935779083 independent_100_runs=-188.60393148814288
e=327 episode_reward=-300.0635971035819 epsilon=0.01 avg=-212.35598591983103 independent_100_runs=-345.4142410756656
e=328 episode_reward=-447.2228467657042 epsilon=0.01 avg=-216.90631987183886 independent_100_runs=-359.46550926993916
e=329 episode_reward=-474.98007763006325 epsilon=0.01 avg=-220.04944825992558 independent_100_runs=-404.6948994115677
e=330 episode_reward=-353.4243376695375 epsilon=0.01 avg=-221.95284746322614 independent_100_runs=-263.3706752709487
e=331 episode_reward=-310.09797135993506 epsilon=0.01 avg=-222.69165144887924 independent_100_runs=-227.07464265890118
e=332 episode_reward=-246.61725908918723 epsilon=0.01 avg=-223.9407894260652 independent_100_runs=-369.62998577534535
e=333 episode_reward=-388.267697628528 epsilon=0.01 avg=-226.1623369482812 independent_100_runs=-187.7693588793346
e=334 episode_reward=-410.85416353061345 epsilon=0.01 avg=-229.84975806580664 independent_100_runs=-193.48999344885058
e=335 episode_reward=-328.72333127563456 epsilon=0.01 avg=-231.82918691812299 independent_100_runs=-217.917466657821
e=336 episode_reward=-190.7701509192026 epsilon=0.01 avg=-233.21061986572894 independent_100_runs=-185.33291209671478
e=337 episode_reward=-265.93053923189655 epsilon=0.01 avg=-233.88256371304556 independent_100_runs=-315.2442087092799
e=338 episode_reward=-265.3631777262556 epsilon=0.01 avg=-234.34009697172462 independent_100_runs=-176.89606129680112
e=339 episode_reward=-158.49001114288174 epsilon=0.01 avg=-233.174110163287 independent_100_runs=-177.5379461138803
e=340 episode_reward=-158.11943049717797 epsilon=0.01 avg=-232.9798467327294 independent_100_runs=-143.10144245496454
e=341 episode_reward=-92.14494750244042 epsilon=0.01 avg=-232.97369426553914 independent_100_runs=-142.68723596952933
e=342 episode_reward=-569.3857506060497 epsilon=0.01 avg=-235.1131254895009 independent_100_runs=-202.1784722308457
e=343 episode_reward=-223.69701131530422 epsilon=0.01 avg=-234.53795008173176 independent_100_runs=-288.88717488522076
e=344 episode_reward=-88.82060849899807 epsilon=0.01 avg=-234.61590409983836 independent_100_runs=-301.5775603087983
e=345 episode_reward=-243.15252226686604 epsilon=0.01 avg=-234.7272460326564 independent_100_runs=-278.5696312921565
e=346 episode_reward=-323.89564746930284 epsilon=0.01 avg=-233.73392844084538 independent_100_runs=-211.0514599153776
e=347 episode_reward=-447.9633914607723 epsilon=0.01 avg=-237.98565731175302 independent_100_runs=-316.0786532002327
e=348 episode_reward=-369.0878405204283 epsilon=0.01 avg=-239.77185748266027 independent_100_runs=-236.76165158157943
e=349 episode_reward=-161.1915519208813 epsilon=0.01 avg=-239.94591396183532 independent_100_runs=-196.25443965803674
e=350 episode_reward=-253.98926462167043 epsilon=0.01 avg=-241.36290265995797 independent_100_runs=-208.40254150856327
e=351 episode_reward=-209.71386302001713 epsilon=0.01 avg=-241.17833833518023 independent_100_runs=-176.3450599549034
e=352 episode_reward=-169.8600808436811 epsilon=0.01 avg=-240.78334577925398 independent_100_runs=-181.10246872504817
e=353 episode_reward=-185.25197661561188 epsilon=0.01 avg=-240.23387737223965 independent_100_runs=-239.19639549756118
e=354 episode_reward=-266.4936407027809 epsilon=0.01 avg=-241.84315492068185 independent_100_runs=-212.00638285869172
e=355 episode_reward=-152.1966601074143 epsilon=0.01 avg=-239.3977999938805 independent_100_runs=-188.50544512653653
e=356 episode_reward=-420.8247602133654 epsilon=0.01 avg=-241.7929146204637 independent_100_runs=-216.93782949533332
e=357 episode_reward=-32.82969281501734 epsilon=0.01 avg=-234.36766451527217 independent_100_runs=-186.2324109602487
e=358 episode_reward=-112.90064688594038 epsilon=0.01 avg=-230.5798421835182 independent_100_runs=-428.98432050139365
e=359 episode_reward=-40.03275563528601 epsilon=0.01 avg=-230.15139377462575 independent_100_runs=-152.59276456653936
e=360 episode_reward=-463.749937636957 epsilon=0.01 avg=-232.4348694624494 independent_100_runs=-150.66540290873962
e=361 episode_reward=-101.37907067398334 epsilon=0.01 avg=-229.28941980208145 independent_100_runs=-251.50107050063633
e=362 episode_reward=-287.9742015683578 epsilon=0.01 avg=-231.0842535992085 independent_100_runs=-261.22857808737865
e=363 episode_reward=-261.5445347669026 epsilon=0.01 avg=-231.48711719207876 independent_100_runs=-179.12808674491495
e=364 episode_reward=-69.93016170806499 epsilon=0.01 avg=-231.31572921924405 independent_100_runs=-152.33806010421972
e=365 episode_reward=-338.37469992949656 epsilon=0.01 avg=-232.3495878110449 independent_100_runs=-97.5473745689162
e=366 episode_reward=-471.62898684053073 epsilon=0.01 avg=-234.54971832402757 independent_100_runs=-520.0491193081587
e=367 episode_reward=-357.8786917527412 epsilon=0.01 avg=-234.53804752700978 independent_100_runs=-323.79456150977
e=368 episode_reward=19.665151659928384 epsilon=0.01 avg=-232.17855511519906 independent_100_runs=-164.9161532051746
e=369 episode_reward=-116.97635992315766 epsilon=0.01 avg=-232.46155881860508 independent_100_runs=-199.04591713269815
e=370 episode_reward=-639.6483757588261 epsilon=0.01 avg=-239.00479015879057 independent_100_runs=-739.3683166293713
e=371 episode_reward=-418.1850334336267 epsilon=0.01 avg=-242.6330490051947 independent_100_runs=-492.05759962467863
e=372 episode_reward=-91.26458927885314 epsilon=0.01 avg=-241.01610749047265 independent_100_runs=-96.21097128600694
e=373 episode_reward=-272.08254219467676 epsilon=0.01 avg=-240.50263735637805 independent_100_runs=-203.46100061129619
e=374 episode_reward=-296.46267571733745 epsilon=0.01 avg=-241.38506742396436 independent_100_runs=-238.15276784366696
e=375 episode_reward=-113.56151311937232 epsilon=0.01 avg=-239.0188870871984 independent_100_runs=-163.6879796482339
e=376 episode_reward=-60.66069682544076 epsilon=0.01 avg=-236.08897936964652 independent_100_runs=-249.7989398235721
e=377 episode_reward=-433.2132757269425 epsilon=0.01 avg=-238.18717553224442 independent_100_runs=-211.6824123655924
e=378 episode_reward=-380.3967069816661 epsilon=0.01 avg=-239.05382972136505 independent_100_runs=-303.3487055631032
e=379 episode_reward=-274.66458455926346 epsilon=0.01 avg=-238.2054952361624 independent_100_runs=-294.44948009681775
e=380 episode_reward=-109.48906400184605 epsilon=0.01 avg=-235.87187487830514 independent_100_runs=-153.88636348880945
e=381 episode_reward=-411.47145692644966 epsilon=0.01 avg=-237.9618532948106 independent_100_runs=-185.816154966395
e=382 episode_reward=-506.8045695349757 epsilon=0.01 avg=-240.27971199500206 independent_100_runs=-423.53327591495304
e=383 episode_reward=-8.153340635983241 epsilon=0.01 avg=-239.55495120769723 independent_100_runs=-138.69319085775965
e=384 episode_reward=-523.9012906187579 epsilon=0.01 avg=-243.9585095770427 independent_100_runs=-206.62869462305207
e=385 episode_reward=-219.76518609376893 epsilon=0.01 avg=-245.29069032223367 independent_100_runs=-237.64584095632534
e=386 episode_reward=-36.27741114072171 epsilon=0.01 avg=-242.74206517387657 independent_100_runs=-369.76612638392857
e=387 episode_reward=-284.71786351886095 epsilon=0.01 avg=-241.3386573331515 independent_100_runs=-154.98261590550817
e=388 episode_reward=-289.4494775634672 epsilon=0.01 avg=-238.6056435484777 independent_100_runs=-120.10506016573531
e=389 episode_reward=-229.84055601687677 epsilon=0.01 avg=-239.0783152779508 independent_100_runs=-199.92528535504923
e=390 episode_reward=-237.09738425465378 epsilon=0.01 avg=-238.47615521432894 independent_100_runs=-189.32307054426172
e=391 episode_reward=-123.24214071761611 epsilon=0.01 avg=-236.73818482078164 independent_100_runs=-89.69395833207294
e=392 episode_reward=-303.2642559583738 epsilon=0.01 avg=-236.91770028175077 independent_100_runs=-248.25103300076233
e=393 episode_reward=-0.4331758810963322 epsilon=0.01 avg=-235.71334196239457 independent_100_runs=-115.11609249727884
e=394 episode_reward=-242.34620706239332 epsilon=0.01 avg=-235.7917443291752 independent_100_runs=-88.94482357433012
e=395 episode_reward=-255.2015557197189 epsilon=0.01 avg=-236.69164129515883 independent_100_runs=-169.00619544030306
e=396 episode_reward=-242.7623248096712 epsilon=0.01 avg=-236.6816692809382 independent_100_runs=-283.10568787888764
e=397 episode_reward=-262.7964145128083 epsilon=0.01 avg=-236.54376175161488 independent_100_runs=-262.21153396689164
e=398 episode_reward=3.354236537668797 epsilon=0.01 avg=-233.8449617416041 independent_100_runs=-370.4324740606368
e=399 episode_reward=-383.28252517006564 epsilon=0.01 avg=-235.6573482525486 independent_100_runs=-297.4594853312003
e=400 episode_reward=-105.91911233411334 epsilon=0.01 avg=-234.50728542053037 independent_100_runs=-310.87530915939186
e=401 episode_reward=-628.6125928294282 epsilon=0.01 avg=-238.4659791305941 independent_100_runs=-134.3847281803032
e=402 episode_reward=-199.55583174610024 epsilon=0.01 avg=-239.63872629489978 independent_100_runs=-169.209395453192
e=403 episode_reward=-321.8808533367943 epsilon=0.01 avg=-242.66284690602726 independent_100_runs=-384.3580140201191
e=404 episode_reward=-83.57818554427975 epsilon=0.01 avg=-243.81038988581315 independent_100_runs=-179.9852936839523
e=405 episode_reward=-386.7725189718872 epsilon=0.01 avg=-245.990960811168 independent_100_runs=-370.8700974616644
e=406 episode_reward=-438.9294475357003 epsilon=0.01 avg=-252.15953938442698 independent_100_runs=-300.13157812418007
e=407 episode_reward=-202.63118696766895 epsilon=0.01 avg=-252.92433878898072 independent_100_runs=-167.26533584461723
e=408 episode_reward=-437.06332698326645 epsilon=0.01 avg=-256.229367450036 independent_100_runs=-213.9587120977366
e=409 episode_reward=-154.17532374053863 epsilon=0.01 avg=-257.9908269098628 independent_100_runs=-202.91266340032402
e=410 episode_reward=-420.34081239759115 epsilon=0.01 avg=-257.269227460888 independent_100_runs=-245.3293026380777
e=411 episode_reward=-201.46971160510844 epsilon=0.01 avg=-257.2079202046489 independent_100_runs=-219.73830269613075
e=412 episode_reward=-187.16107088012757 epsilon=0.01 avg=-258.31671967067433 independent_100_runs=-391.7198474046566
e=413 episode_reward=-588.9652390768363 epsilon=0.01 avg=-258.3893587355106 independent_100_runs=-277.9083349502699
e=414 episode_reward=-377.5537630437683 epsilon=0.01 avg=-258.2039033446033 independent_100_runs=-238.39597773349576
e=415 episode_reward=-36.072855685848296 epsilon=0.01 avg=-255.8235257191869 independent_100_runs=-375.813269523188
e=416 episode_reward=-109.01662415397179 epsilon=0.01 avg=-254.94540927520683 independent_100_runs=-373.1395235826073
e=417 episode_reward=-740.8810268347407 epsilon=0.01 avg=-261.8466252569692 independent_100_runs=-357.9166178295264
e=418 episode_reward=-223.62024008783607 epsilon=0.01 avg=-263.14214749732537 independent_100_runs=-270.063909638019
e=419 episode_reward=-82.30170270725755 epsilon=0.01 avg=-262.4396320956395 independent_100_runs=-284.0909030610937
e=420 episode_reward=-194.90985637218725 epsilon=0.01 avg=-263.6114846838097 independent_100_runs=-144.1693709393517
e=421 episode_reward=-219.6633433365913 epsilon=0.01 avg=-264.11639672394966 independent_100_runs=-135.05689762511477
e=422 episode_reward=-50.35098713558907 epsilon=0.01 avg=-263.7965403843634 independent_100_runs=-151.32329187355543
e=423 episode_reward=-169.39006899583728 epsilon=0.01 avg=-263.3600005228949 independent_100_runs=-177.18120828173235
e=424 episode_reward=-179.2750655357802 epsilon=0.01 avg=-262.2579377871976 independent_100_runs=-199.54548609151556
e=425 episode_reward=-222.46431229320143 epsilon=0.01 avg=-257.885641161469 independent_100_runs=-146.71997378450303
e=426 episode_reward=-235.6904919659144 epsilon=0.01 avg=-259.574562070267 independent_100_runs=-235.06877813950723
e=427 episode_reward=-180.20539382567443 epsilon=0.01 avg=-258.3759800374879 independent_100_runs=-132.648790148414
e=428 episode_reward=-59.028469276303795 epsilon=0.01 avg=-254.49403626259394 independent_100_runs=-143.7187599111396
e=429 episode_reward=-137.12242656900463 epsilon=0.01 avg=-251.11545975198334 independent_100_runs=-209.98343347062936
e=430 episode_reward=-233.41290094363305 epsilon=0.01 avg=-249.91534538472428 independent_100_runs=-138.95494954886988
e=431 episode_reward=-293.427761928436 epsilon=0.01 avg=-249.74864329040932 independent_100_runs=-450.42042149628503
e=432 episode_reward=-363.94639912493915 epsilon=0.01 avg=-250.9219346907668 independent_100_runs=-196.16279592284454
e=433 episode_reward=-143.49354305849553 epsilon=0.01 avg=-248.4741931450665 independent_100_runs=-175.26107606448764
e=434 episode_reward=-74.03527579894539 epsilon=0.01 avg=-245.10600426774982 independent_100_runs=-213.39940365576473
e=435 episode_reward=-154.62071960597643 epsilon=0.01 avg=-243.36497815105326 independent_100_runs=-118.06319473958456
e=436 episode_reward=-50.07061606509968 epsilon=0.01 avg=-241.95798280251216 independent_100_runs=-828.9372530983833
e=437 episode_reward=-92.31748718308431 epsilon=0.01 avg=-240.2218522820241 independent_100_runs=-314.5011102764317
e=438 episode_reward=-242.25098229365946 epsilon=0.01 avg=-239.99073032769812 independent_100_runs=-194.85127958205948
e=439 episode_reward=-168.45963841849402 epsilon=0.01 avg=-240.09042660045424 independent_100_runs=-320.72971250097623
e=440 episode_reward=-118.91174188872375 epsilon=0.01 avg=-239.6983497143697 independent_100_runs=-115.09068224821254
e=441 episode_reward=-305.70085147234147 epsilon=0.01 avg=-241.83390875406872 independent_100_runs=-385.21055003228895
e=442 episode_reward=-217.24293011881244 epsilon=0.01 avg=-238.31248054919632 independent_100_runs=-240.16586238384636
e=443 episode_reward=-100.92059358004437 epsilon=0.01 avg=-237.08471637184374 independent_100_runs=-210.20931735687017
e=444 episode_reward=-285.66576516419957 epsilon=0.01 avg=-239.0531679384957 independent_100_runs=-222.2180196160207
e=445 episode_reward=-181.73819534608097 epsilon=0.01 avg=-238.4390246692879 independent_100_runs=-296.47448282159314
e=446 episode_reward=33.665870367706674 epsilon=0.01 avg=-234.8634094909178 independent_100_runs=-288.1318110899964
e=447 episode_reward=-424.4711882823247 epsilon=0.01 avg=-234.6284874591333 independent_100_runs=-121.2312363398008
e=448 episode_reward=-188.78140657908025 epsilon=0.01 avg=-232.82542311971986 independent_100_runs=-176.46495485176433
e=449 episode_reward=-281.5616534484981 epsilon=0.01 avg=-234.029124134996 independent_100_runs=-366.13818320034574
e=450 episode_reward=-248.51764930492791 epsilon=0.01 avg=-233.9744079818286 independent_100_runs=-133.66173151555589
e=451 episode_reward=-297.52869285836874 epsilon=0.01 avg=-234.85255628021207 independent_100_runs=-247.37876394638536
e=452 episode_reward=-216.61166689025038 epsilon=0.01 avg=-235.32007214067778 independent_100_runs=-120.55939639704724
e=453 episode_reward=-188.7782607300677 epsilon=0.01 avg=-235.35533498182238 independent_100_runs=-315.5673502807967
e=454 episode_reward=-249.39976509037635 epsilon=0.01 avg=-235.1843962256983 independent_100_runs=-192.12827201310208
e=455 episode_reward=-94.6688609285964 epsilon=0.01 avg=-234.60911823391012 independent_100_runs=-244.81807328440834
e=456 episode_reward=-160.11593907985616 epsilon=0.01 avg=-232.002030022575 independent_100_runs=-248.29758732037863
e=457 episode_reward=-236.59317283497947 epsilon=0.01 avg=-234.03966482277465 independent_100_runs=-272.38537237720243
e=458 episode_reward=-381.62905913401 epsilon=0.01 avg=-236.72694894525532 independent_100_runs=-260.8699171148221
e=459 episode_reward=-233.5853639859882 epsilon=0.01 avg=-238.66247502876234 independent_100_runs=-113.4001991007233
e=460 episode_reward=-266.68131220960083 epsilon=0.01 avg=-236.69178877448877 independent_100_runs=-162.16067046082765
e=461 episode_reward=-71.04299684897734 epsilon=0.01 avg=-236.38842803623874 independent_100_runs=-138.86252977399644
e=462 episode_reward=-207.5183191427505 epsilon=0.01 avg=-235.58386921198263 independent_100_runs=-132.63048653222884
e=463 episode_reward=-197.18756897505864 epsilon=0.01 avg=-234.94029955406418 independent_100_runs=-180.32688808804573
e=464 episode_reward=-192.6996039750124 epsilon=0.01 avg=-236.16799397673367 independent_100_runs=-166.47134279259527
e=465 episode_reward=-344.7845390045213 epsilon=0.01 avg=-236.23209236748392 independent_100_runs=-330.39162283453976
e=466 episode_reward=-34.99097208974517 epsilon=0.01 avg=-231.86571221997607 independent_100_runs=-228.1886168454968
e=467 episode_reward=-235.98220497212657 epsilon=0.01 avg=-230.64674735216994 independent_100_runs=-226.76199449597334
e=468 episode_reward=-495.3269841339671 epsilon=0.01 avg=-235.7966687101089 independent_100_runs=-385.9125865067949
e=469 episode_reward=-385.6972033394541 epsilon=0.01 avg=-238.4838771442719 independent_100_runs=-361.1398651885986
e=470 episode_reward=-481.0287674414578 epsilon=0.01 avg=-236.89768106109818 independent_100_runs=-327.02980647925773
e=471 episode_reward=-337.47775210798983 epsilon=0.01 avg=-236.09060824784186 independent_100_runs=-152.68776382492112
e=472 episode_reward=-56.643538752097264 epsilon=0.01 avg=-235.74439774257428 independent_100_runs=-312.96651839983775
e=473 episode_reward=-296.81641862038913 epsilon=0.01 avg=-235.99173650683142 independent_100_runs=-148.23524803988104
e=474 episode_reward=-448.62463089296983 epsilon=0.01 avg=-237.5133560585877 independent_100_runs=-235.82567096138587
e=475 episode_reward=-168.22461870118218 epsilon=0.01 avg=-238.0599871144058 independent_100_runs=-258.8910849172078
e=476 episode_reward=-61.46746367039289 epsilon=0.01 avg=-238.0680547828553 independent_100_runs=-235.6239498797112
e=477 episode_reward=-224.71968449081785 epsilon=0.01 avg=-235.98311887049402 independent_100_runs=-272.43257207444265
e=478 episode_reward=-211.35755789587157 epsilon=0.01 avg=-234.2927273796361 independent_100_runs=-183.88393203635286
e=479 episode_reward=-166.23702037042767 epsilon=0.01 avg=-233.20845173774774 independent_100_runs=-159.77621577235058
e=480 episode_reward=-249.6698686927277 epsilon=0.01 avg=-234.6102597846565 independent_100_runs=-239.2568977105641
e=481 episode_reward=-175.93729672829116 epsilon=0.01 avg=-232.25491818267494 independent_100_runs=-191.29399592927828
e=482 episode_reward=-213.06685253110393 epsilon=0.01 avg=-229.3175410126363 independent_100_runs=-139.23222026483535
e=483 episode_reward=-216.70313416977672 epsilon=0.01 avg=-231.40303894797424 independent_100_runs=-178.16412863844448
e=484 episode_reward=-90.289726527737 epsilon=0.01 avg=-227.066923307064 independent_100_runs=-238.7352236084488
e=485 episode_reward=-159.51335115292235 epsilon=0.01 avg=-226.4644049576556 independent_100_runs=-199.40664527841034
e=486 episode_reward=-125.5119803627563 epsilon=0.01 avg=-227.3567506498759 independent_100_runs=-196.5598302203862
e=487 episode_reward=-187.32461761235209 epsilon=0.01 avg=-226.38281819081078 independent_100_runs=-181.35823394696953
e=488 episode_reward=-324.1996623284047 epsilon=0.01 avg=-226.73032003846015 independent_100_runs=-311.3669156336936
e=489 episode_reward=-214.50020998087578 epsilon=0.01 avg=-226.57691657810017 independent_100_runs=-281.0566184623978
e=490 episode_reward=-186.0743672779609 epsilon=0.01 avg=-226.0666864083332 independent_100_runs=-185.77793255566928
e=491 episode_reward=-348.3431312406556 epsilon=0.01 avg=-228.31769631356366 independent_100_runs=-199.15471472081646
e=492 episode_reward=-166.45510296401494 epsilon=0.01 avg=-226.94960478362006 independent_100_runs=-244.73336462066302
e=493 episode_reward=-246.57531450479547 epsilon=0.01 avg=-229.41102616985702 independent_100_runs=-124.11835595132139
e=494 episode_reward=-162.5094737942312 epsilon=0.01 avg=-228.61265883717545 independent_100_runs=-332.9065026715216
e=495 episode_reward=-356.0404520290962 epsilon=0.01 avg=-229.62104780026922 independent_100_runs=-192.83199813890377
e=496 episode_reward=-162.19312403062403 epsilon=0.01 avg=-228.81535579247875 independent_100_runs=-320.3142417788093
e=497 episode_reward=-254.31921404461832 epsilon=0.01 avg=-228.73058378779686 independent_100_runs=-137.58270147284807
e=498 episode_reward=-89.81983285771794 epsilon=0.01 avg=-229.6623244817507 independent_100_runs=-312.94180768266403
e=499 episode_reward=-263.41195460353583 epsilon=0.01 avg=-228.4636187760854 independent_100_runs=-333.69407190233994
e=500 episode_reward=-310.38518907863 epsilon=0.01 avg=-230.5082795435305 independent_100_runs=-240.1662544394541
e=501 episode_reward=-238.85628997296672 epsilon=0.01 avg=-226.6107165149659 independent_100_runs=-232.8681743544789
e=502 episode_reward=-224.30144126905577 epsilon=0.01 avg=-226.8581726101955 independent_100_runs=-217.31529271118856
e=503 episode_reward=-354.269235173502 epsilon=0.01 avg=-227.18205642856262 independent_100_runs=-280.3661402645647
e=504 episode_reward=-194.12562333432783 epsilon=0.01 avg=-228.28753080646302 independent_100_runs=-266.7883263936674
e=505 episode_reward=-222.7408239150663 epsilon=0.01 avg=-226.64721385589482 independent_100_runs=-223.4205991271442
e=506 episode_reward=-329.24384354694666 epsilon=0.01 avg=-225.55035781600725 independent_100_runs=-183.5646546520112
e=507 episode_reward=-321.8056056057785 epsilon=0.01 avg=-226.74210200238838 independent_100_runs=-233.74233615744387
e=508 episode_reward=-314.9981835079957 epsilon=0.01 avg=-225.52145056763567 independent_100_runs=-261.0833618102339
e=509 episode_reward=-191.92924610653915 epsilon=0.01 avg=-225.8989897912957 independent_100_runs=-122.93161182073217
e=510 episode_reward=-78.03065101902604 epsilon=0.01 avg=-222.47588817751006 independent_100_runs=-158.28351063577233
e=511 episode_reward=-105.72966639079985 epsilon=0.01 avg=-221.51848772536698 independent_100_runs=-70.65973071412397
e=512 episode_reward=-73.6404018090463 epsilon=0.01 avg=-220.38328103465614 independent_100_runs=-216.40424597240323
e=513 episode_reward=-17.767973792493592 epsilon=0.01 avg=-214.6713083818127 independent_100_runs=-192.06829903514827
e=514 episode_reward=-413.41056102830186 epsilon=0.01 avg=-215.029876361658 independent_100_runs=-235.14070772556715
e=515 episode_reward=-143.75426157357577 epsilon=0.01 avg=-216.10669042053533 independent_100_runs=-205.2740983331056
e=516 episode_reward=-59.078145767009396 epsilon=0.01 avg=-215.60730563666567 independent_100_runs=-198.78233654015744
e=517 episode_reward=-408.2605276483111 epsilon=0.01 avg=-212.2811006448014 independent_100_runs=-193.66420373093857
e=518 episode_reward=-152.2391195923851 epsilon=0.01 avg=-211.5672894398469 independent_100_runs=-214.2510918127713
e=519 episode_reward=-218.3807481709468 epsilon=0.01 avg=-212.92807989448383 independent_100_runs=-110.76310598643322
e=520 episode_reward=-165.04394498610478 epsilon=0.01 avg=-212.62942078062298 independent_100_runs=-121.57052113931883
e=521 episode_reward=-167.70215157775687 epsilon=0.01 avg=-212.10980886303463 independent_100_runs=-436.8306934001606
e=522 episode_reward=-175.08837810751163 epsilon=0.01 avg=-213.35718277275384 independent_100_runs=-153.9015205686397
e=523 episode_reward=-330.47231865908986 epsilon=0.01 avg=-214.96800526938634 independent_100_runs=-158.35116916943042
e=524 episode_reward=-264.7855728299163 epsilon=0.01 avg=-215.82311034232768 independent_100_runs=-282.6399722941781
e=525 episode_reward=-528.4268791975389 epsilon=0.01 avg=-218.88273601137107 independent_100_runs=-351.07326417881785
e=526 episode_reward=-167.16117700677296 epsilon=0.01 avg=-218.19744286177965 independent_100_runs=-237.02551737938663
e=527 episode_reward=-246.52951468599045 epsilon=0.01 avg=-218.8606840703828 independent_100_runs=-218.0887708234339
e=528 episode_reward=-14.908175450566702 epsilon=0.01 avg=-218.41948113212547 independent_100_runs=-236.90613382315914
e=529 episode_reward=-254.39300398485966 epsilon=0.01 avg=-219.59218690628404 independent_100_runs=-226.3644052865043
e=530 episode_reward=-42.62490897464433 epsilon=0.01 avg=-217.6843069865942 independent_100_runs=-231.14236488591018
e=531 episode_reward=-174.75149250318364 epsilon=0.01 avg=-216.49754429234167 independent_100_runs=-214.38381087704767
e=532 episode_reward=-195.20845019058453 epsilon=0.01 avg=-214.8101648029981 independent_100_runs=-173.99480862552983
e=533 episode_reward=-202.53976640105242 epsilon=0.01 avg=-215.40062703642366 independent_100_runs=-191.0888130684803
e=534 episode_reward=-191.52875291473794 epsilon=0.01 avg=-216.57556180758158 independent_100_runs=-140.9230641903222
e=535 episode_reward=48.15744267980176 epsilon=0.01 avg=-214.54778018472382 independent_100_runs=-223.17840422866422
e=536 episode_reward=-257.9195833891624 epsilon=0.01 avg=-216.6262698579644 independent_100_runs=-246.08734911591574
e=537 episode_reward=-230.45256420864933 epsilon=0.01 avg=-218.00762062822002 independent_100_runs=-272.4048802788096
e=538 episode_reward=-363.40833085810306 epsilon=0.01 avg=-219.21919411386446 independent_100_runs=-186.39863648723167
e=539 episode_reward=-269.2874974740729 epsilon=0.01 avg=-220.22747270442028 independent_100_runs=-322.69443620459907
e=540 episode_reward=-319.0004091281279 epsilon=0.01 avg=-222.2283593768143 independent_100_runs=-376.3940404503575
e=541 episode_reward=-293.00931285759725 epsilon=0.01 avg=-222.1014439906669 independent_100_runs=-298.90840124231835
e=542 episode_reward=-184.54238382836397 epsilon=0.01 avg=-221.77443852776238 independent_100_runs=-249.8063851162463
e=543 episode_reward=-211.43153554267704 epsilon=0.01 avg=-222.87954794738874 independent_100_runs=-233.40281435273235
e=544 episode_reward=-137.38770232819695 epsilon=0.01 avg=-221.39676731902873 independent_100_runs=-218.74190344934124
e=545 episode_reward=-270.89161938545556 epsilon=0.01 avg=-222.28830155942248 independent_100_runs=-162.77884911663648
e=546 episode_reward=-103.96598875766095 epsilon=0.01 avg=-223.66462015067617 independent_100_runs=-478.63543287517
e=547 episode_reward=-607.336823596928 epsilon=0.01 avg=-225.49327650382216 independent_100_runs=-547.4555974996184
e=548 episode_reward=-602.6306695071487 epsilon=0.01 avg=-229.63176913310284 independent_100_runs=-357.28877868712465
e=549 episode_reward=-295.77402041581337 epsilon=0.01 avg=-229.773892802776 independent_100_runs=-355.5445085962916
e=550 episode_reward=-106.98676642481858 epsilon=0.01 avg=-228.35858397397493 independent_100_runs=-554.8606399600001
e=551 episode_reward=-862.1040384644484 epsilon=0.01 avg=-234.0043374300357 independent_100_runs=-372.8956491615076
e=552 episode_reward=-124.03542161522729 epsilon=0.01 avg=-233.07857497728548 independent_100_runs=-328.49028953369634
e=553 episode_reward=-947.6017915426735 epsilon=0.01 avg=-240.66681028541151 independent_100_runs=-528.8401569788189
e=554 episode_reward=-900.2704823944825 epsilon=0.01 avg=-247.17551745845265 independent_100_runs=-464.26185297701073
e=555 episode_reward=-426.93471977410275 epsilon=0.01 avg=-250.49817604690773 independent_100_runs=-521.9041370536141
e=556 episode_reward=-500.9991037086462 epsilon=0.01 avg=-253.90700769319562 independent_100_runs=-798.3438478354792
e=557 episode_reward=-456.31134674970343 epsilon=0.01 avg=-256.1041894323429 independent_100_runs=-518.2159278338852
e=558 episode_reward=78.8883157365845 epsilon=0.01 avg=-251.4990156836369 independent_100_runs=-244.6898778141334
e=559 episode_reward=-105.52461436829454 epsilon=0.01 avg=-250.21840818745994 independent_100_runs=-158.58480224309605
e=560 episode_reward=-949.4863009731345 epsilon=0.01 avg=-257.04645807509525 independent_100_runs=-115.89067260043139
e=561 episode_reward=-142.93824826329396 epsilon=0.01 avg=-257.7654105892384 independent_100_runs=-122.49038860836548
e=562 episode_reward=-91.31810762643423 epsilon=0.01 avg=-256.60340847407525 independent_100_runs=-123.55355310330184
e=563 episode_reward=-114.02461316808913 epsilon=0.01 avg=-255.77177891600553 independent_100_runs=-131.46531064929277
e=564 episode_reward=-93.90933618634772 epsilon=0.01 avg=-254.78387623811895 independent_100_runs=-120.18802629353078
e=565 episode_reward=-153.46882812974476 epsilon=0.01 avg=-252.87071912937114 independent_100_runs=-116.11541725059504
e=566 episode_reward=-515.7324322024875 epsilon=0.01 avg=-257.6781337304986 independent_100_runs=-106.48800478971394
e=567 episode_reward=-103.0082425540374 epsilon=0.01 avg=-256.3483941063177 independent_100_runs=-100.88732261230254
e=568 episode_reward=-31.170550978273226 epsilon=0.01 avg=-251.70682977476076 independent_100_runs=-150.81596785548138
e=569 episode_reward=-145.9765686525397 epsilon=0.01 avg=-249.30962342789155 independent_100_runs=-234.23574633852894
e=570 episode_reward=-220.14604451931172 epsilon=0.01 avg=-246.7007961986701 independent_100_runs=-82.82661602207763
e=571 episode_reward=-75.96260271046843 epsilon=0.01 avg=-244.0856447046949 independent_100_runs=-148.78846304314166
e=572 episode_reward=-196.70852034033516 epsilon=0.01 avg=-245.48629452057727 independent_100_runs=-160.25560714348035
e=573 episode_reward=-214.68779395133922 epsilon=0.01 avg=-244.66500827388683 independent_100_runs=-106.52988189241893
e=574 episode_reward=-355.31531225594847 epsilon=0.01 avg=-243.73191508751657 independent_100_runs=-634.3223645115254
e=575 episode_reward=-533.6329457807333 epsilon=0.01 avg=-247.38599835831212 independent_100_runs=-387.67823757512576
e=576 episode_reward=-153.5777148137089 epsilon=0.01 avg=-248.30710086974526 independent_100_runs=-209.24351583939813
e=577 episode_reward=-313.8232486757511 epsilon=0.01 avg=-249.1981365115946 independent_100_runs=-244.1451653449668
e=578 episode_reward=-242.80825068339206 epsilon=0.01 avg=-249.51264343946983 independent_100_runs=-279.09993414536626
e=579 episode_reward=-357.14547904550085 epsilon=0.01 avg=-251.4217280262205 independent_100_runs=-310.1648578407038
e=580 episode_reward=-273.2823925077081 epsilon=0.01 avg=-251.6578532643703 independent_100_runs=-300.5979359204832
e=581 episode_reward=-276.13708132786576 epsilon=0.01 avg=-252.65985111036605 independent_100_runs=-177.5788698193186
e=582 episode_reward=-206.72599982416415 epsilon=0.01 avg=-252.59644258329664 independent_100_runs=-241.41405893610394
e=583 episode_reward=-162.46106577043113 epsilon=0.01 avg=-252.05402189930322 independent_100_runs=-71.66994211684926
e=584 episode_reward=-179.85797558477822 epsilon=0.01 avg=-252.94970438987366 independent_100_runs=-204.59940535826377
e=585 episode_reward=-93.53725293618518 epsilon=0.01 avg=-252.28994340770626 independent_100_runs=-220.4387588652919
e=586 episode_reward=-187.83787048536598 epsilon=0.01 avg=-252.91320230893243 independent_100_runs=-183.4390094955657
e=587 episode_reward=-60.533425817918086 epsilon=0.01 avg=-251.645290390988 independent_100_runs=-167.21751975386528
e=588 episode_reward=-269.85286593659987 epsilon=0.01 avg=-251.10182242706998 independent_100_runs=-208.24766516302446
e=589 episode_reward=-274.64848182842223 epsilon=0.01 avg=-251.70330514554541 independent_100_runs=-238.35324668925387
e=590 episode_reward=-161.58886085219729 epsilon=0.01 avg=-251.45845008128776 independent_100_runs=-226.56636818407438
e=591 episode_reward=-287.24059661878096 epsilon=0.01 avg=-250.84742473506904 independent_100_runs=-289.8499247556299
e=592 episode_reward=-194.15537311510462 epsilon=0.01 avg=-251.12442743657994 independent_100_runs=-264.346439638137
e=593 episode_reward=-227.65082861977632 epsilon=0.01 avg=-250.93518257772968 independent_100_runs=-241.49889139315258
e=594 episode_reward=-302.23878689651895 epsilon=0.01 avg=-252.3324757087526 independent_100_runs=-267.68589576632473
e=595 episode_reward=-191.31340909466957 epsilon=0.01 avg=-250.68520527940836 independent_100_runs=-254.8851993480738
e=596 episode_reward=-141.5988507249935 epsilon=0.01 avg=-250.47926254635203 independent_100_runs=-349.4275217539965
e=597 episode_reward=-542.3281398804819 epsilon=0.01 avg=-253.3593518047107 independent_100_runs=-258.60786340205675
e=598 episode_reward=-613.5018824434542 epsilon=0.01 avg=-258.5961723005681 independent_100_runs=-531.3545489207667
e=599 episode_reward=-564.3214682447226 epsilon=0.01 avg=-261.60526743697994 independent_100_runs=-258.4314729090207
e=600 episode_reward=-559.4416353837025 epsilon=0.01 avg=-264.0958319000307 independent_100_runs=-297.88907584400874
e=601 episode_reward=-512.6561368252895 epsilon=0.01 avg=-266.8338303685539 independent_100_runs=-280.4322056340742
e=602 episode_reward=-97.57874884371105 epsilon=0.01 avg=-265.5666034443004 independent_100_runs=-256.08388285884746
e=603 episode_reward=-365.7585634872173 epsilon=0.01 avg=-265.6814967274376 independent_100_runs=-313.96423445935966
e=604 episode_reward=-126.70260836337414 epsilon=0.01 avg=-265.0072665777281 independent_100_runs=-280.0716218292136
e=605 episode_reward=-665.466860055365 epsilon=0.01 avg=-269.43452693913105 independent_100_runs=-617.6525288594797
e=606 episode_reward=-374.96003771185957 epsilon=0.01 avg=-269.8916888807802 independent_100_runs=-209.8468004290057
e=607 episode_reward=-238.69235717961328 epsilon=0.01 avg=-269.06055639651856 independent_100_runs=-246.93121246808826
e=608 episode_reward=-271.4039184748015 epsilon=0.01 avg=-268.6246137461865 independent_100_runs=-165.35229041700876
e=609 episode_reward=-222.21230726970882 epsilon=0.01 avg=-268.9274443578183 independent_100_runs=-226.3483610498561
e=610 episode_reward=-416.94686064967243 epsilon=0.01 avg=-272.3166064541248 independent_100_runs=-370.4495402121557
e=611 episode_reward=-312.82152566884366 epsilon=0.01 avg=-274.38752504690524 independent_100_runs=-157.12206561777847
e=612 episode_reward=-164.51535431771603 epsilon=0.01 avg=-275.2962745719919 independent_100_runs=-207.4395093218211
e=613 episode_reward=-210.68215437968007 epsilon=0.01 avg=-277.2254163778638 independent_100_runs=-212.67345107297064
e=614 episode_reward=-322.8962125748541 epsilon=0.01 avg=-276.3202728933293 independent_100_runs=-291.42059760898604
e=615 episode_reward=-156.1614796284191 epsilon=0.01 avg=-276.4443450738777 independent_100_runs=-78.77184836125582
e=616 episode_reward=-200.87971007158384 epsilon=0.01 avg=-277.8623607169235 independent_100_runs=-204.8176465677977
e=617 episode_reward=-250.8831700621922 epsilon=0.01 avg=-276.2885871410623 independent_100_runs=-197.75774787908705
e=618 episode_reward=-235.0030068600133 epsilon=0.01 avg=-277.1162260137386 independent_100_runs=13.196861659967869
e=619 episode_reward=-276.578369196351 epsilon=0.01 avg=-277.6982022239926 independent_100_runs=-185.4338062782085
e=620 episode_reward=-212.98478479616017 epsilon=0.01 avg=-278.17761062209314 independent_100_runs=-252.01366323482293
e=621 episode_reward=-203.6951797014877 epsilon=0.01 avg=-278.53754090333047 independent_100_runs=-267.5827734803309
e=622 episode_reward=-509.63518258351877 epsilon=0.01 avg=-281.88300894809055 independent_100_runs=-403.77376968266327
e=623 episode_reward=-426.36205698848096 epsilon=0.01 avg=-282.8419063313844 independent_100_runs=-416.8177104304084
e=624 episode_reward=-332.18150790395396 epsilon=0.01 avg=-283.5158656821248 independent_100_runs=-292.84130651537697
e=625 episode_reward=-326.61414288556284 epsilon=0.01 avg=-281.49773831900507 independent_100_runs=-250.5968875529289
e=626 episode_reward=-258.66328810261496 epsilon=0.01 avg=-282.41275942996344 independent_100_runs=-314.7931187051978
e=627 episode_reward=-336.8707009433897 epsilon=0.01 avg=-283.3161712925375 independent_100_runs=-280.4255020968031
e=628 episode_reward=-201.78169812054165 epsilon=0.01 avg=-285.18490651923724 independent_100_runs=-303.90668768882756
e=629 episode_reward=-375.59077806401865 epsilon=0.01 avg=-286.3968842600288 independent_100_runs=-372.3932172499745
e=630 episode_reward=-188.64682618709998 epsilon=0.01 avg=-287.8571034321534 independent_100_runs=-226.91610780836828
e=631 episode_reward=-226.46640821859256 epsilon=0.01 avg=-288.37425258930745 independent_100_runs=-187.1742189465087
e=632 episode_reward=-257.92860624685653 epsilon=0.01 avg=-289.00145414987014 independent_100_runs=-342.3317627203297
e=633 episode_reward=-265.759181352042 epsilon=0.01 avg=-289.63364829938 independent_100_runs=-396.21655115303145
e=634 episode_reward=-219.28415203668655 epsilon=0.01 avg=-289.9112022905995 independent_100_runs=-209.56060408686344
e=635 episode_reward=-186.84023914180324 epsilon=0.01 avg=-292.26117910881555 independent_100_runs=-179.99943914664595
e=636 episode_reward=-110.06106235614105 epsilon=0.01 avg=-290.78259389848535 independent_100_runs=-143.95594793259878
e=637 episode_reward=-492.4239250035495 epsilon=0.01 avg=-293.40230750643434 independent_100_runs=-278.37371094229985
e=638 episode_reward=-411.2110744543536 epsilon=0.01 avg=-293.8803349423968 independent_100_runs=-363.62946618778426
e=639 episode_reward=-252.15602869509323 epsilon=0.01 avg=-293.709020254607 independent_100_runs=-166.11313696825692
e=640 episode_reward=-192.31196309296612 epsilon=0.01 avg=-292.4421357942554 independent_100_runs=-133.49115679428851
e=641 episode_reward=-296.44934209743735 epsilon=0.01 avg=-292.4765360866538 independent_100_runs=-129.50215115266874
e=642 episode_reward=-141.71281896063556 epsilon=0.01 avg=-292.0482404379766 independent_100_runs=-228.93265653219783
e=643 episode_reward=-221.61963416924934 epsilon=0.01 avg=-292.15012142424223 independent_100_runs=-135.3632687591707
e=644 episode_reward=-164.5594416085931 epsilon=0.01 avg=-292.4218388170462 independent_100_runs=-530.0087039579229
e=645 episode_reward=-337.3417485869169 epsilon=0.01 avg=-293.0863401090608 independent_100_runs=-713.5995641394461
e=646 episode_reward=-321.59691356577423 epsilon=0.01 avg=-295.262649357142 independent_100_runs=-271.019665802712
e=647 episode_reward=-162.11573063656368 epsilon=0.01 avg=-290.8104384275384 independent_100_runs=-334.5995764753958
e=648 episode_reward=-332.46032333268977 epsilon=0.01 avg=-288.1087349657938 independent_100_runs=-223.5703594201899
e=649 episode_reward=-799.099580749225 epsilon=0.01 avg=-293.14199056912787 independent_100_runs=-55.11678726782822
e=650 episode_reward=-386.16320926022655 epsilon=0.01 avg=-295.93375499748197 independent_100_runs=-110.56420391489982
e=651 episode_reward=-262.07685577166626 epsilon=0.01 avg=-289.93348317055415 independent_100_runs=-75.95879908633715
e=652 episode_reward=-344.48458286519735 epsilon=0.01 avg=-292.1379747830538 independent_100_runs=-250.12794935416375
e=653 episode_reward=-296.40371678033785 epsilon=0.01 avg=-285.62599403543044 independent_100_runs=-679.5966337834076
e=654 episode_reward=183.05361791980312 epsilon=0.01 avg=-274.79275303228764 independent_100_runs=-750.3509053844889
e=655 episode_reward=-114.33803860141697 epsilon=0.01 avg=-271.66678622056077 independent_100_runs=-810.7994828682015
e=656 episode_reward=-514.6772787824743 epsilon=0.01 avg=-271.80356797129906 independent_100_runs=-35.29313176710978
e=657 episode_reward=-64.72907077819211 epsilon=0.01 avg=-267.88774521158393 independent_100_runs=-43.12753683017351
e=658 episode_reward=-133.2050165359607 epsilon=0.01 avg=-270.0086785343094 independent_100_runs=-237.3503503269077
e=659 episode_reward=-523.2217330462538 epsilon=0.01 avg=-274.185649721089 independent_100_runs=-218.90526576743443
e=660 episode_reward=-321.2500661627214 epsilon=0.01 avg=-267.90328737298483 independent_100_runs=-154.72327961028358
e=661 episode_reward=-255.6125826629539 epsilon=0.01 avg=-269.0300307169815 independent_100_runs=-170.26922280652525
e=662 episode_reward=-169.9394269317737 epsilon=0.01 avg=-269.81624391003487 independent_100_runs=-160.2848000952686
e=663 episode_reward=-120.91330587446959 epsilon=0.01 avg=-269.88513083709864 independent_100_runs=-108.75445212615445
e=664 episode_reward=-385.6171314411794 epsilon=0.01 avg=-272.802208789647 independent_100_runs=-124.50449022212123
e=665 episode_reward=-239.3612621107332 epsilon=0.01 avg=-273.6611331294569 independent_100_runs=-207.04916914199256
e=666 episode_reward=-207.43189146786858 epsilon=0.01 avg=-270.5781277221107 independent_100_runs=-106.37914804747241
e=667 episode_reward=-251.65484348789607 epsilon=0.01 avg=-272.0645937314493 independent_100_runs=-200.34002972426305
e=668 episode_reward=-455.16305854682287 epsilon=0.01 avg=-276.3045188071348 independent_100_runs=-222.7965974966979
e=669 episode_reward=-84.58427017599092 epsilon=0.01 avg=-275.6905958223693 independent_100_runs=-147.33711243381293
e=670 episode_reward=-202.862539389726 epsilon=0.01 avg=-275.5177607710734 independent_100_runs=-247.88884090093882
e=671 episode_reward=-129.9414604703032 epsilon=0.01 avg=-276.0575493486717 independent_100_runs=-225.16890608117467
e=672 episode_reward=-323.7653985874325 epsilon=0.01 avg=-277.3281181311427 independent_100_runs=-233.1841103750259
e=673 episode_reward=-104.92003676238704 epsilon=0.01 avg=-276.23044055925317 independent_100_runs=-219.94222411008013
e=674 episode_reward=-106.97072828828195 epsilon=0.01 avg=-273.7469947195765 independent_100_runs=-173.7063518337834
e=675 episode_reward=-696.2655854069131 epsilon=0.01 avg=-275.3733211158383 independent_100_runs=-228.71944936770655
e=676 episode_reward=-416.267567086171 epsilon=0.01 avg=-278.00021963856295 independent_100_runs=-338.47882382976314
e=677 episode_reward=-390.167382475736 epsilon=0.01 avg=-278.76366097656285 independent_100_runs=-203.2716972955955
e=678 episode_reward=-151.98223728487076 epsilon=0.01 avg=-277.8554008425776 independent_100_runs=-289.4453046952602
e=679 episode_reward=-259.5698145099234 epsilon=0.01 avg=-276.87964419722186 independent_100_runs=-397.99890497826
e=680 episode_reward=-279.0258485967737 epsilon=0.01 avg=-276.9370787581125 independent_100_runs=-251.9513074941853
e=681 episode_reward=-353.9613749863454 epsilon=0.01 avg=-277.71532169469737 independent_100_runs=-222.30294437677676
e=682 episode_reward=-687.459466297562 epsilon=0.01 avg=-282.52265635943127 independent_100_runs=-559.7473936664626
e=683 episode_reward=-449.0494543347402 epsilon=0.01 avg=-285.3885402450744 independent_100_runs=-394.0973840728416
e=684 episode_reward=-298.4563237901604 epsilon=0.01 avg=-286.57452372712817 independent_100_runs=-103.14194193083489
e=685 episode_reward=-25.30246135974336 epsilon=0.01 avg=-285.89217581136376 independent_100_runs=-83.76718390276528
e=686 episode_reward=-140.29750430401538 epsilon=0.01 avg=-285.4167721495503 independent_100_runs=-166.09537411900004
e=687 episode_reward=-260.83899834694387 epsilon=0.01 avg=-287.4198278748405 independent_100_runs=-200.67322264976661
e=688 episode_reward=-128.6720081821174 epsilon=0.01 avg=-286.0080192972957 independent_100_runs=-229.13041553229613
e=689 episode_reward=-460.0022864613305 epsilon=0.01 avg=-287.8615573436248 independent_100_runs=-296.69211691306083
e=690 episode_reward=-141.4800298379359 epsilon=0.01 avg=-287.6604690334822 independent_100_runs=-140.8584221571622
e=691 episode_reward=-217.93540428640162 epsilon=0.01 avg=-286.96741711015835 independent_100_runs=-257.0625544893593
e=692 episode_reward=-410.45716534736755 epsilon=0.01 avg=-289.13043503248105 independent_100_runs=-118.99708156649102
e=693 episode_reward=-37.25976866792743 epsilon=0.01 avg=-287.2265244329625 independent_100_runs=-305.02423412962577
e=694 episode_reward=-483.8920434660637 epsilon=0.01 avg=-289.043056998658 independent_100_runs=-283.84745161343295
e=695 episode_reward=-220.55126465346063 epsilon=0.01 avg=-289.33543555424586 independent_100_runs=-139.4137127321791
e=696 episode_reward=-115.21892418167862 epsilon=0.01 avg=-289.07163628881267 independent_100_runs=-141.55218213155598
e=697 episode_reward=-401.68946348294327 epsilon=0.01 avg=-287.6652495248373 independent_100_runs=-90.89106271182958
e=698 episode_reward=-150.4616958988061 epsilon=0.01 avg=-283.0348476593908 independent_100_runs=-103.08391457721818
e=699 episode_reward=-306.2049688508794 epsilon=0.01 avg=-280.45368266545233 independent_100_runs=-77.30063887958505
e=700 episode_reward=-134.25386388106705 epsilon=0.01 avg=-276.20180495042604 independent_100_runs=-202.29941447651333
e=701 episode_reward=-89.64451015677439 epsilon=0.01 avg=-271.97168868374087 independent_100_runs=-412.53783926480736
e=702 episode_reward=-184.50263066416983 epsilon=0.01 avg=-272.84092750194543 independent_100_runs=-324.8649613237435
e=703 episode_reward=-373.43767665354557 epsilon=0.01 avg=-272.91771863360873 independent_100_runs=-452.6244434249647
e=704 episode_reward=-240.46505997684795 epsilon=0.01 avg=-274.0553431497435 independent_100_runs=-525.7328410577537
e=705 episode_reward=-678.480545688619 epsilon=0.01 avg=-274.1854800060761 independent_100_runs=-562.5710681918704
e=706 episode_reward=-283.38276970518916 epsilon=0.01 avg=-273.2697073260093 independent_100_runs=-383.91114190532966
e=707 episode_reward=-579.1287559021894 epsilon=0.01 avg=-276.6740713132351 independent_100_runs=-374.13389379150357
e=708 episode_reward=-493.8925868897446 epsilon=0.01 avg=-278.8989579973846 independent_100_runs=-360.4277024165505
e=709 episode_reward=-237.9905556518722 epsilon=0.01 avg=-279.0567404812062 independent_100_runs=-416.072741617583
e=710 episode_reward=-383.5933209679805 epsilon=0.01 avg=-278.72320508438924 independent_100_runs=-243.64233364692558
e=711 episode_reward=-118.69172741683576 epsilon=0.01 avg=-276.7819071018692 independent_100_runs=-169.74677876924835
e=712 episode_reward=-499.9261726337438 epsilon=0.01 avg=-280.13601528502943 independent_100_runs=-287.27356611425597
e=713 episode_reward=-260.1470722829754 epsilon=0.01 avg=-280.6306644640624 independent_100_runs=-233.54139398932355
e=714 episode_reward=-382.96339369345833 epsilon=0.01 avg=-281.23133627524845 independent_100_runs=-244.05136467708743
e=715 episode_reward=-403.8938608445091 epsilon=0.01 avg=-283.7086600874093 independent_100_runs=-296.3046336438631
e=716 episode_reward=-192.30297383112233 epsilon=0.01 avg=-283.62289272500476 independent_100_runs=-231.27832007742794
e=717 episode_reward=-340.9973056224537 epsilon=0.01 avg=-284.5240340806074 independent_100_runs=-252.79378760559445
e=718 episode_reward=-262.0856113922191 epsilon=0.01 avg=-284.79486012592946 independent_100_runs=-173.94036715168087
e=719 episode_reward=-160.93625844797708 epsilon=0.01 avg=-283.6384390184457 independent_100_runs=-260.5661095421278
e=720 episode_reward=-191.64719044810664 epsilon=0.01 avg=-283.4250630749652 independent_100_runs=-273.84529268544856
e=721 episode_reward=-221.5119454260012 epsilon=0.01 avg=-283.60323073221036 independent_100_runs=-519.0829608253434
e=722 episode_reward=-351.47418353472983 epsilon=0.01 avg=-282.0216207417224 independent_100_runs=-525.8557709986153
e=723 episode_reward=-342.60699718776766 epsilon=0.01 avg=-281.18407014371525 independent_100_runs=-529.4520898949714
e=724 episode_reward=3.839974609751863 epsilon=0.01 avg=-277.8238553185782 independent_100_runs=-562.7719989146381
e=725 episode_reward=-551.3993059752105 epsilon=0.01 avg=-280.0717069494747 independent_100_runs=-300.0410002290107
e=726 episode_reward=-735.2500368907604 epsilon=0.01 avg=-284.83757443735607 independent_100_runs=-618.1348911863712
e=727 episode_reward=-570.2488250230505 epsilon=0.01 avg=-287.17135567815274 independent_100_runs=-544.7068021126794
e=728 episode_reward=-740.6079487891838 epsilon=0.01 avg=-292.5596181848391 independent_100_runs=-279.08033635335005
e=729 episode_reward=-285.2065492593588 epsilon=0.01 avg=-291.65577589679253 independent_100_runs=-468.1744382167819
e=730 episode_reward=-488.0978940032664 epsilon=0.01 avg=-294.6502865749542 independent_100_runs=-267.3229944609361
e=731 episode_reward=-202.64539280865517 epsilon=0.01 avg=-294.4120764208548 independent_100_runs=-494.3003420125484
e=732 episode_reward=-584.4232006157365 epsilon=0.01 avg=-297.67702236454363 independent_100_runs=-382.1789469910891
e=733 episode_reward=-364.2717172885914 epsilon=0.01 avg=-298.66214772390913 independent_100_runs=-308.35471308796247
e=734 episode_reward=-544.5401498764347 epsilon=0.01 avg=-301.9147077023066 independent_100_runs=-295.14556842304376
e=735 episode_reward=-370.0753184045208 epsilon=0.01 avg=-303.74705849493375 independent_100_runs=-323.7609169119903
e=736 episode_reward=-355.4003525803506 epsilon=0.01 avg=-306.2004513971758 independent_100_runs=-322.90907271271607
e=737 episode_reward=-439.7047124228452 epsilon=0.01 avg=-305.6732592713688 independent_100_runs=-307.16192238178473
e=738 episode_reward=-552.2715059855451 epsilon=0.01 avg=-307.0838635866807 independent_100_runs=-285.90568203126327
e=739 episode_reward=-222.12574214710148 epsilon=0.01 avg=-306.7835607212008 independent_100_runs=-219.5811017784742
e=740 episode_reward=-223.68870719991008 epsilon=0.01 avg=-307.0973281622703 independent_100_runs=-243.1819871370521
e=741 episode_reward=-243.58788516975056 epsilon=0.01 avg=-306.5687135929934 independent_100_runs=-246.9303697117046
e=742 episode_reward=-366.1158460298638 epsilon=0.01 avg=-308.81274386368574 independent_100_runs=-293.88295456164525
e=743 episode_reward=-313.46498931402186 epsilon=0.01 avg=-309.7311974151334 independent_100_runs=-526.4586406423269
e=744 episode_reward=-439.9499144792911 epsilon=0.01 avg=-312.48510214384044 independent_100_runs=-600.7128533952499
e=745 episode_reward=-297.5916129020137 epsilon=0.01 avg=-312.0876007869914 independent_100_runs=-326.20998188516694
e=746 episode_reward=-223.47646464921817 epsilon=0.01 avg=-311.1063962978258 independent_100_runs=-287.4766009530094
e=747 episode_reward=-327.3880248786676 epsilon=0.01 avg=-312.75911924024683 independent_100_runs=-338.03207494429915
e=748 episode_reward=-307.9943150013506 epsilon=0.01 avg=-312.51445915693347 independent_100_runs=-287.7585399819342
e=749 episode_reward=-299.7034347432498 epsilon=0.01 avg=-307.5204976968737 independent_100_runs=-333.6015845943893
e=750 episode_reward=-411.76128533232963 epsilon=0.01 avg=-307.7764784575947 independent_100_runs=-503.900917297951
e=751 episode_reward=-224.57219407452249 epsilon=0.01 avg=-307.4014318406233 independent_100_runs=-361.40675420683743
e=752 episode_reward=-312.0419995501836 epsilon=0.01 avg=-307.07700600747313 independent_100_runs=-306.44908891111356
e=753 episode_reward=-233.3492050644876 epsilon=0.01 avg=-306.44646089031465 independent_100_runs=-270.7701188085229
e=754 episode_reward=-222.49138049332495 epsilon=0.01 avg=-310.5019108744459 independent_100_runs=-552.9172025980389
e=755 episode_reward=-213.44173647448935 epsilon=0.01 avg=-311.49294785317664 independent_100_runs=-198.7260675416884
e=756 episode_reward=-192.41608778874848 epsilon=0.01 avg=-308.2703359432394 independent_100_runs=-184.7703899589066
e=757 episode_reward=-228.5013021903341 epsilon=0.01 avg=-309.9080582573608 independent_100_runs=-276.6712290607367
e=758 episode_reward=22.725518348086936 epsilon=0.01 avg=-308.3487529085203 independent_100_runs=-243.81934112168452
e=759 episode_reward=-165.78568393681877 epsilon=0.01 avg=-304.77439241742593 independent_100_runs=-279.4181039783683
e=760 episode_reward=-245.6098290557444 epsilon=0.01 avg=-304.01799004635615 independent_100_runs=-169.03590209545152
e=761 episode_reward=-241.7380435223778 epsilon=0.01 avg=-303.87924465495047 independent_100_runs=-174.39111401697699
e=762 episode_reward=-345.45058586448897 epsilon=0.01 avg=-305.6343562442776 independent_100_runs=-254.29322357017176
e=763 episode_reward=-32.87589135414768 epsilon=0.01 avg=-304.7539820990744 independent_100_runs=-231.35980254645355
e=764 episode_reward=-241.7548930988275 epsilon=0.01 avg=-303.31535971565086 independent_100_runs=-246.64071730688516
e=765 episode_reward=-239.5451955297783 epsilon=0.01 avg=-303.3171990498413 independent_100_runs=-234.04932970924344
e=766 episode_reward=-230.49676898807414 epsilon=0.01 avg=-303.5478478250434 independent_100_runs=-221.35436139566474
e=767 episode_reward=-235.44105232919065 epsilon=0.01 avg=-303.38570991345637 independent_100_runs=-266.82715839686045
e=768 episode_reward=-206.0090264369075 epsilon=0.01 avg=-300.89416959235723 independent_100_runs=-192.82296177381727
e=769 episode_reward=-191.60129367458438 epsilon=0.01 avg=-301.9643398273431 independent_100_runs=-185.2466352561964
e=770 episode_reward=-223.43648624866438 epsilon=0.01 avg=-302.1700792959325 independent_100_runs=-169.24735688054884
e=771 episode_reward=-245.0854298177363 epsilon=0.01 avg=-303.3215189894068 independent_100_runs=-250.23111623106482
e=772 episode_reward=-225.52046032938753 epsilon=0.01 avg=-302.3390696068264 independent_100_runs=-229.91105589787446
e=773 episode_reward=-175.69218570046226 epsilon=0.01 avg=-303.0467910962072 independent_100_runs=-250.05197413432364
e=774 episode_reward=-97.10082925132225 epsilon=0.01 avg=-302.94809210583753 independent_100_runs=-233.8884165928061
e=775 episode_reward=-376.53877055742566 epsilon=0.01 avg=-299.7508239573426 independent_100_runs=-186.66124007505772
e=776 episode_reward=-183.6027702595104 epsilon=0.01 avg=-297.42417598907605 independent_100_runs=-179.6820064337284
e=777 episode_reward=-243.098726949173 epsilon=0.01 avg=-295.9534894338104 independent_100_runs=-165.28736788522963
e=778 episode_reward=-152.162095991706 epsilon=0.01 avg=-295.95528802087875 independent_100_runs=-142.5056420695481
e=779 episode_reward=-226.5011193624449 epsilon=0.01 avg=-295.624601069404 independent_100_runs=-150.17239479379742
e=780 episode_reward=36.46682960377797 epsilon=0.01 avg=-292.4696742873985 independent_100_runs=-185.80420324441621
e=781 episode_reward=-131.8158182887025 epsilon=0.01 avg=-290.2482187204221 independent_100_runs=-171.22272589244986
e=782 episode_reward=-115.79829146041438 epsilon=0.01 avg=-284.53160697205055 independent_100_runs=-79.20603568574178
e=783 episode_reward=-288.89657112702207 epsilon=0.01 avg=-282.9300781399734 independent_100_runs=-58.33342379197891
e=784 episode_reward=-626.8188396202335 epsilon=0.01 avg=-286.21370329827414 independent_100_runs=-258.66966855381025
e=785 episode_reward=-116.42209620344977 epsilon=0.01 avg=-287.1248996467112 independent_100_runs=-173.64431046363694
e=786 episode_reward=-464.2410513665574 epsilon=0.01 avg=-290.36433511733657 independent_100_runs=-174.7889170762837
e=787 episode_reward=-171.6194631161805 epsilon=0.01 avg=-289.472139765029 independent_100_runs=-138.87645445962508
e=788 episode_reward=-88.109860004026 epsilon=0.01 avg=-289.06651828324806 independent_100_runs=-255.44012567100302
e=789 episode_reward=-415.2186145860475 epsilon=0.01 avg=-288.6186815644952 independent_100_runs=-471.6597787059696
e=790 episode_reward=-369.9251473496503 epsilon=0.01 avg=-290.90313273961243 independent_100_runs=-184.88181421815287
e=791 episode_reward=-414.0301710349591 epsilon=0.01 avg=-292.86408040709796 independent_100_runs=-195.5221290830236
e=792 episode_reward=-145.64581570232644 epsilon=0.01 avg=-290.2159669106475 independent_100_runs=-176.62313690415797
e=793 episode_reward=-367.2441145522239 epsilon=0.01 avg=-293.5158103694905 independent_100_runs=-188.31917484756585
e=794 episode_reward=-278.59943886548064 epsilon=0.01 avg=-291.4628843234847 independent_100_runs=-195.78359173191282
e=795 episode_reward=-101.85317943957139 epsilon=0.01 avg=-290.2759034713457 independent_100_runs=-171.06338258924907
e=796 episode_reward=-145.21358029150647 epsilon=0.01 avg=-290.57585003244407 independent_100_runs=-206.2532395363699
e=797 episode_reward=-305.3501912715609 epsilon=0.01 avg=-289.6124573103302 independent_100_runs=-215.43609603407333
e=798 episode_reward=-548.8943322022321 epsilon=0.01 avg=-293.59678367336454 independent_100_runs=-586.753068487333
e=799 episode_reward=-364.2064846122971 epsilon=0.01 avg=-294.17679883097867 independent_100_runs=-507.72700600570556
e=800 episode_reward=-476.19863144578073 epsilon=0.01 avg=-297.5962465066258 independent_100_runs=-372.08506574334604
e=801 episode_reward=-261.537998084051 epsilon=0.01 avg=-299.3151813858986 independent_100_runs=-409.2878151910364
e=802 episode_reward=-229.56626818811338 epsilon=0.01 avg=-299.765817761138 independent_100_runs=-278.7294456553127
e=803 episode_reward=-224.6082519381048 epsilon=0.01 avg=-298.2775235139836 independent_100_runs=-210.88276104624344
e=804 episode_reward=-132.51640147322718 epsilon=0.01 avg=-297.19803692894743 independent_100_runs=-147.58597418457444
e=805 episode_reward=-236.8994400719509 epsilon=0.01 avg=-292.7822258727807 independent_100_runs=-213.83616302865903
e=806 episode_reward=-271.935727995506 epsilon=0.01 avg=-292.66775545568385 independent_100_runs=-231.91747195486923
e=807 episode_reward=-223.43815044726801 epsilon=0.01 avg=-289.11084940113466 independent_100_runs=-305.0123823807646
e=808 episode_reward=-282.6764479160725 epsilon=0.01 avg=-286.998688011398 independent_100_runs=-208.46936864017385
e=809 episode_reward=-178.71683147421086 epsilon=0.01 avg=-286.40595076962137 independent_100_runs=-149.8169976435771
e=810 episode_reward=-155.6449733227651 epsilon=0.01 avg=-284.1264672931692 independent_100_runs=-103.21150447565081
e=811 episode_reward=-227.90050027376356 epsilon=0.01 avg=-285.21855502173844 independent_100_runs=-156.81703331692228
e=812 episode_reward=-149.91560350031503 epsilon=0.01 avg=-281.71844933040416 independent_100_runs=-141.50488648924522
e=813 episode_reward=-132.1279197737388 epsilon=0.01 avg=-280.4382578053118 independent_100_runs=-143.1377902589863
e=814 episode_reward=-140.93758774653975 epsilon=0.01 avg=-278.0179997458426 independent_100_runs=-158.54978964315814
e=815 episode_reward=-207.52008236247823 epsilon=0.01 avg=-276.0542619610223 independent_100_runs=-221.55469818971386
e=816 episode_reward=-218.05960811801907 epsilon=0.01 avg=-276.31182830389133 independent_100_runs=-286.98863308046094
e=817 episode_reward=-189.89339479176496 epsilon=0.01 avg=-274.8007891955844 independent_100_runs=-215.19520369836687
e=818 episode_reward=-235.23149760387622 epsilon=0.01 avg=-274.53224805770094 independent_100_runs=-313.43557348528515
e=819 episode_reward=-427.4445491852353 epsilon=0.01 avg=-277.19733096507355 independent_100_runs=-269.762232190117
e=820 episode_reward=-286.0497824433262 epsilon=0.01 avg=-278.14135688502574 independent_100_runs=-454.8737375776151
e=821 episode_reward=-455.9156004434168 epsilon=0.01 avg=-280.48539343519985 independent_100_runs=-299.044740307355
e=822 episode_reward=-331.25927385400087 epsilon=0.01 avg=-280.2832443383926 independent_100_runs=-289.83102209901995
e=823 episode_reward=-167.40925148386145 epsilon=0.01 avg=-278.53126688135353 independent_100_runs=-241.07665890836316
e=824 episode_reward=-288.7375129370881 epsilon=0.01 avg=-281.4570417568219 independent_100_runs=-189.00676643764677
e=825 episode_reward=-157.31768209649675 epsilon=0.01 avg=-277.5162255180348 independent_100_runs=-153.52245572011034
e=826 episode_reward=-124.64467451923299 epsilon=0.01 avg=-271.41017189431955 independent_100_runs=-171.45929883243568
e=827 episode_reward=-152.76416912519346 epsilon=0.01 avg=-267.235325335341 independent_100_runs=-234.5111363782893
e=828 episode_reward=-185.9967664160098 epsilon=0.01 avg=-261.68921351160924 independent_100_runs=-215.04962770302873
e=829 episode_reward=-405.9341850721322 epsilon=0.01 avg=-262.8964898697369 independent_100_runs=-177.26330991388784
e=830 episode_reward=-487.3812961412579 epsilon=0.01 avg=-262.8893238911169 independent_100_runs=-629.54294043753
e=831 episode_reward=-345.01270400718295 epsilon=0.01 avg=-264.3129970031021 independent_100_runs=-379.6141627921365
e=832 episode_reward=-570.9312164989121 epsilon=0.01 avg=-264.1780771619339 independent_100_runs=-166.6942218479192
e=833 episode_reward=-205.94582157107465 epsilon=0.01 avg=-262.5948182047587 independent_100_runs=-475.92288691298546
e=834 episode_reward=-682.0425732149098 epsilon=0.01 avg=-263.9698424381435 independent_100_runs=-611.3617272865347
e=835 episode_reward=-438.88294439804343 epsilon=0.01 avg=-264.6579186980787 independent_100_runs=-564.9942602243567
e=836 episode_reward=-715.1370432854009 epsilon=0.01 avg=-268.2552856051292 independent_100_runs=-637.4472848302318
e=837 episode_reward=-655.0932632642839 epsilon=0.01 avg=-270.4091711135436 independent_100_runs=-594.9610801492742
e=838 episode_reward=-665.6481549411632 epsilon=0.01 avg=-271.54293760309974 independent_100_runs=-511.8860941989726
e=839 episode_reward=-344.09370330100126 epsilon=0.01 avg=-272.7626172146388 independent_100_runs=-100.1359531226372
e=840 episode_reward=-514.4043676382619 epsilon=0.01 avg=-275.6697738190223 independent_100_runs=-489.8908302208412
e=841 episode_reward=-376.03522552813 epsilon=0.01 avg=-276.9942472226061 independent_100_runs=-324.13555278692786
e=842 episode_reward=-137.4354489102232 epsilon=0.01 avg=-274.70744325140964 independent_100_runs=-110.28325080315184
e=843 episode_reward=-390.89220974286246 epsilon=0.01 avg=-275.48171545569807 independent_100_runs=-359.91959786472086
e=844 episode_reward=-251.20177068405258 epsilon=0.01 avg=-273.59423401774563 independent_100_runs=-456.3636979459029
e=845 episode_reward=-525.266765779897 epsilon=0.01 avg=-275.8709855465245 independent_100_runs=-215.3156973253188
e=846 episode_reward=-169.50609168049803 epsilon=0.01 avg=-275.3312818168373 independent_100_runs=-32.50626371671314
e=847 episode_reward=-887.7647300022323 epsilon=0.01 avg=-280.93504886807295 independent_100_runs=-228.3827956198269
e=848 episode_reward=-404.76943335437676 epsilon=0.01 avg=-281.9028000516032 independent_100_runs=-171.40948871390228
e=849 episode_reward=-95.35995988217721 epsilon=0.01 avg=-279.8593653029925 independent_100_runs=-212.79949586637858
e=850 episode_reward=-189.77006344437586 epsilon=0.01 avg=-277.639453084113 independent_100_runs=-140.58150948009765
e=851 episode_reward=-134.21749555044377 epsilon=0.01 avg=-276.7359060988722 independent_100_runs=-36.87215592436427
e=852 episode_reward=-122.71191708997117 epsilon=0.01 avg=-274.84260527427006 independent_100_runs=-50.52105404573669
e=853 episode_reward=-545.2076353410174 epsilon=0.01 avg=-277.9611895770354 independent_100_runs=-454.4795303700435
e=854 episode_reward=-563.2604164602367 epsilon=0.01 avg=-281.3688799367045 independent_100_runs=-255.14304220551122
e=855 episode_reward=-336.85463828559875 epsilon=0.01 avg=-282.60300895481555 independent_100_runs=-291.2000551537192
e=856 episode_reward=-314.5797486907593 epsilon=0.01 avg=-283.82464556383565 independent_100_runs=-314.6196010858899
e=857 episode_reward=-277.01733952271024 epsilon=0.01 avg=-284.3098059371594 independent_100_runs=-309.7716161775897
e=858 episode_reward=-311.1574512839959 epsilon=0.01 avg=-287.64863563348024 independent_100_runs=-333.387237330507
e=859 episode_reward=-605.0898928642998 epsilon=0.01 avg=-292.0416777227551 independent_100_runs=-189.92062169226688
e=860 episode_reward=-284.84604869382395 epsilon=0.01 avg=-292.43403991913584 independent_100_runs=-236.65688844445907
e=861 episode_reward=-210.53821033814467 epsilon=0.01 avg=-292.12204158729355 independent_100_runs=-161.00491884106353
e=862 episode_reward=-174.9499604018505 epsilon=0.01 avg=-290.4170353326672 independent_100_runs=-286.2379727692362
e=863 episode_reward=-136.91829831903976 epsilon=0.01 avg=-291.4574594023161 independent_100_runs=-265.74290617765683
e=864 episode_reward=-49.12666337015853 epsilon=0.01 avg=-289.53117710502937 independent_100_runs=-189.944097549301
e=865 episode_reward=-418.82577608004334 epsilon=0.01 avg=-291.3239829105321 independent_100_runs=-204.9613461050073
e=866 episode_reward=-297.1573730316463 epsilon=0.01 avg=-291.9905889509678 independent_100_runs=-216.01042180481716
e=867 episode_reward=-254.49141868951904 epsilon=0.01 avg=-292.18109261457107 independent_100_runs=-329.6146889913755
e=868 episode_reward=-154.99457172313757 epsilon=0.01 avg=-291.67094806743336 independent_100_runs=-284.9681464856713
e=869 episode_reward=-385.80617694755256 epsilon=0.01 avg=-293.612996900163 independent_100_runs=-68.27727980463472
e=870 episode_reward=-103.01690187340617 epsilon=0.01 avg=-292.4088010564104 independent_100_runs=-63.89930061808383
e=871 episode_reward=-86.22269598774844 epsilon=0.01 avg=-290.8201737181106 independent_100_runs=-19.579594535430587
e=872 episode_reward=-70.23182307003235 epsilon=0.01 avg=-289.26728734551705 independent_100_runs=-131.09811553931027
e=873 episode_reward=-452.83315185796334 epsilon=0.01 avg=-292.038697007092 independent_100_runs=-162.42240321463615
e=874 episode_reward=-26.03006503541637 epsilon=0.01 avg=-291.32798936493293 independent_100_runs=-248.5603232065713
e=875 episode_reward=-238.69866842712096 epsilon=0.01 avg=-289.9495883436299 independent_100_runs=-162.99375865688813
e=876 episode_reward=-517.1395632154873 epsilon=0.01 avg=-293.2849562731897 independent_100_runs=-165.9947095929927
e=877 episode_reward=-332.5417967206606 epsilon=0.01 avg=-294.17938697090455 independent_100_runs=-166.62339567317807
e=878 episode_reward=-295.7459146248592 epsilon=0.01 avg=-295.6152251572361 independent_100_runs=-107.13205499559199
e=879 episode_reward=-138.27953844237317 epsilon=0.01 avg=-294.7330093480354 independent_100_runs=-141.82458652524775
e=880 episode_reward=-42.5168404279046 epsilon=0.01 avg=-295.5228460483522 independent_100_runs=-25.526772184665266
e=881 episode_reward=-112.48500035444768 epsilon=0.01 avg=-295.32953786900964 independent_100_runs=-58.77421067573073
e=882 episode_reward=-160.57676424917688 epsilon=0.01 avg=-295.7773225968973 independent_100_runs=-303.65453530342376
e=883 episode_reward=-316.1638554287304 epsilon=0.01 avg=-296.04999543991437 independent_100_runs=-348.0543489941264
e=884 episode_reward=-386.7475721151588 epsilon=0.01 avg=-293.6492827648637 independent_100_runs=-192.14954087422723
e=885 episode_reward=-86.6013170984197 epsilon=0.01 avg=-293.35107497381335 independent_100_runs=-201.79482676708304
e=886 episode_reward=-150.31041795016228 epsilon=0.01 avg=-290.21176863964934 independent_100_runs=-156.89930078377623
e=887 episode_reward=136.7158883515266 epsilon=0.01 avg=-287.1284151249723 independent_100_runs=-383.53803158439985
e=888 episode_reward=-237.6870129674407 epsilon=0.01 avg=-288.62418665460643 independent_100_runs=-585.8413889744886
e=889 episode_reward=-554.1633771086608 epsilon=0.01 avg=-290.01363427983256 independent_100_runs=-669.550612335272
e=890 episode_reward=-370.05993967013217 epsilon=0.01 avg=-290.0149822030374 independent_100_runs=-175.25070963200815
e=891 episode_reward=-111.28163119990377 epsilon=0.01 avg=-286.9874968046868 independent_100_runs=-301.5081361169824
e=892 episode_reward=-390.7962379029041 epsilon=0.01 avg=-289.43900102669267 independent_100_runs=-381.07769696198636
e=893 episode_reward=-95.18792759409325 epsilon=0.01 avg=-286.71843915711133 independent_100_runs=-299.1154895115661
e=894 episode_reward=-454.92130357810714 epsilon=0.01 avg=-288.48165780423756 independent_100_runs=-419.2659243989912
e=895 episode_reward=-174.46937127654422 epsilon=0.01 avg=-289.2078197226073 independent_100_runs=-219.98118411272742
e=896 episode_reward=-371.388724399222 epsilon=0.01 avg=-291.46957116368446 independent_100_runs=-409.10088796836976
e=897 episode_reward=-470.11936489169074 epsilon=0.01 avg=-293.1172628998858 independent_100_runs=-455.3181523435775
e=898 episode_reward=-544.4421345969687 epsilon=0.01 avg=-293.0727409238332 independent_100_runs=-421.36391766574076
e=899 episode_reward=-444.5328336674198 epsilon=0.01 avg=-293.8760044143844 independent_100_runs=-569.9611109531947
e=900 episode_reward=-538.7560691533487 epsilon=0.01 avg=-294.5015787914601 independent_100_runs=-565.5775802591419
e=901 episode_reward=-241.37786434262674 epsilon=0.01 avg=-294.29997745404586 independent_100_runs=-499.49293717333705
e=902 episode_reward=-221.60519088767694 epsilon=0.01 avg=-294.22036668104147 independent_100_runs=-585.7549549013356
e=903 episode_reward=-641.9688157002004 epsilon=0.01 avg=-298.3939723186624 independent_100_runs=-679.5118541639296
e=904 episode_reward=-537.8307929105392 epsilon=0.01 avg=-302.4471162330355 independent_100_runs=-425.50740413127687
e=905 episode_reward=-373.27686754350543 epsilon=0.01 avg=-303.8108905077511 independent_100_runs=-670.1131529967971
e=906 episode_reward=-443.99078971378617 epsilon=0.01 avg=-305.5314411249339 independent_100_runs=-596.0548876362521
e=907 episode_reward=-325.2094591876446 epsilon=0.01 avg=-306.5491542123376 independent_100_runs=-626.3827827486047
e=908 episode_reward=-155.4820018964014 epsilon=0.01 avg=-305.27720975214095 independent_100_runs=-422.1021603568578
e=909 episode_reward=-640.325484411018 epsilon=0.01 avg=-309.893296281509 independent_100_runs=-634.8022766454128
e=910 episode_reward=-442.8212186529377 epsilon=0.01 avg=-312.76505873481074 independent_100_runs=-173.51109030868727
e=911 episode_reward=-499.47858820608883 epsilon=0.01 avg=-315.48083961413397 independent_100_runs=-604.9309465975034
e=912 episode_reward=-665.2457494116776 epsilon=0.01 avg=-320.63414107324763 independent_100_runs=-622.7426651927783
e=913 episode_reward=-747.1435960338031 epsilon=0.01 avg=-326.78429783584824 independent_100_runs=-725.7965849184773
e=914 episode_reward=-832.9560852271328 epsilon=0.01 avg=-333.70448281065416 independent_100_runs=-446.0345725574418
e=915 episode_reward=-345.04543173288994 epsilon=0.01 avg=-335.0797363043583 independent_100_runs=-351.9686105641701
e=916 episode_reward=-574.767669877511 epsilon=0.01 avg=-338.6468169219532 independent_100_runs=-472.4513948922296
e=917 episode_reward=-346.45264341983267 epsilon=0.01 avg=-340.2124094082339 independent_100_runs=-500.8108860614497
e=918 episode_reward=-473.3008679287193 epsilon=0.01 avg=-342.59310311148226 independent_100_runs=-482.05257418115036
e=919 episode_reward=-727.7928938701148 epsilon=0.01 avg=-345.5965865583311 independent_100_runs=-541.5919265094446
e=920 episode_reward=-234.7228229116161 epsilon=0.01 avg=-345.08331696301394 independent_100_runs=-218.15139504021593
e=921 episode_reward=-230.85283753130722 epsilon=0.01 avg=-342.8326893338929 independent_100_runs=-282.9575278602135
e=922 episode_reward=-232.99664699967968 epsilon=0.01 avg=-341.85006306534973 independent_100_runs=-401.50828103532416
e=923 episode_reward=-366.53231475828943 epsilon=0.01 avg=-343.84129369809403 independent_100_runs=-471.51471160230545
e=924 episode_reward=-364.9404405872198 epsilon=0.01 avg=-344.6033229745953 independent_100_runs=-518.3152507517162
e=925 episode_reward=-451.90085912585005 epsilon=0.01 avg=-347.5491547448889 independent_100_runs=-525.969459291136
e=926 episode_reward=-340.6685149150925 epsilon=0.01 avg=-349.7093931488474 independent_100_runs=-313.45962622463117
e=927 episode_reward=-279.1855213865906 epsilon=0.01 avg=-350.9736066714615 independent_100_runs=-639.2049441491622
e=928 episode_reward=-724.1889898361571 epsilon=0.01 avg=-356.3555289056629 independent_100_runs=-351.36171051301613
e=929 episode_reward=-453.36711556185475 epsilon=0.01 avg=-356.82985821056013 independent_100_runs=-435.31246227766286
e=930 episode_reward=-339.91571721033415 epsilon=0.01 avg=-355.35520242125085 independent_100_runs=-407.36075597950605
e=931 episode_reward=-223.0905345303721 epsilon=0.01 avg=-354.1359807264827 independent_100_runs=-412.86289699138547
e=932 episode_reward=-386.57766108550396 epsilon=0.01 avg=-352.29244517234866 independent_100_runs=-391.8035649407859
e=933 episode_reward=-454.0242157908345 epsilon=0.01 avg=-354.7732291145462 independent_100_runs=-435.6046278650062
e=934 episode_reward=-188.65022280995169 epsilon=0.01 avg=-349.8393056104966 independent_100_runs=-293.14685681024764
e=935 episode_reward=-183.49938392009926 epsilon=0.01 avg=-347.2854700057171 independent_100_runs=-540.6234510655677
e=936 episode_reward=-743.7349201591502 epsilon=0.01 avg=-347.57144877445467 independent_100_runs=-784.2316292846654
e=937 episode_reward=-797.2667414947485 epsilon=0.01 avg=-348.99318355675933 independent_100_runs=-438.7988270864346
e=938 episode_reward=-268.12018433049707 epsilon=0.01 avg=-345.0179038506527 independent_100_runs=-462.47066617167735
e=939 episode_reward=-314.8571798827619 epsilon=0.01 avg=-344.7255386164703 independent_100_runs=-688.9519385155494
e=940 episode_reward=-513.3206274648895 epsilon=0.01 avg=-344.71470121473664 independent_100_runs=-325.52143685638174
e=941 episode_reward=-586.3643964640478 epsilon=0.01 avg=-346.8179929240958 independent_100_runs=-793.7238354457701
e=942 episode_reward=-905.1523730494612 epsilon=0.01 avg=-354.4951621654881 independent_100_runs=-586.5230645018523
e=943 episode_reward=-803.8257867630284 epsilon=0.01 avg=-358.6244979356899 independent_100_runs=-651.9335151187056
e=944 episode_reward=-546.3496171154252 epsilon=0.01 avg=-361.5759764000036 independent_100_runs=-448.73943211154494
e=945 episode_reward=-454.1922710527902 epsilon=0.01 avg=-360.8652314527325 independent_100_runs=-421.7213478123057
e=946 episode_reward=-282.34563803302376 epsilon=0.01 avg=-361.9936269162577 independent_100_runs=-506.19120133526013
e=947 episode_reward=-360.0750534229166 epsilon=0.01 avg=-356.7167301504645 independent_100_runs=-602.7114753021416
e=948 episode_reward=-915.0735470871866 epsilon=0.01 avg=-361.8197712877926 independent_100_runs=-729.1431643268514
e=949 episode_reward=-177.01515963682897 epsilon=0.01 avg=-362.63632328533924 independent_100_runs=-413.42947636217315
e=950 episode_reward=-697.2066649370191 epsilon=0.01 avg=-367.71068930026564 independent_100_runs=-534.3324493520511
e=951 episode_reward=-302.31341107573303 epsilon=0.01 avg=-369.3916484555185 independent_100_runs=-322.6055859802259
e=952 episode_reward=-469.9090166013425 epsilon=0.01 avg=-372.86361945063226 independent_100_runs=-435.25876913515685
e=953 episode_reward=-451.62044172580147 epsilon=0.01 avg=-371.9277475144801 independent_100_runs=-410.2027453885758
e=954 episode_reward=-524.6639373891994 epsilon=0.01 avg=-371.5417827237697 independent_100_runs=-470.74826087046523
e=955 episode_reward=120.54648596733516 epsilon=0.01 avg=-366.96777148124033 independent_100_runs=-299.5920673228776
e=956 episode_reward=-376.8630446168183 epsilon=0.01 avg=-367.59060444050095 independent_100_runs=-189.03087999007153
e=957 episode_reward=-100.08819874130508 epsilon=0.01 avg=-365.8213130326869 independent_100_runs=-203.74660197340393
e=958 episode_reward=-394.4466494674211 epsilon=0.01 avg=-366.65420501452115 independent_100_runs=-274.8732090732654
e=959 episode_reward=-185.36946163088203 epsilon=0.01 avg=-362.4570007021869 independent_100_runs=-205.56264876169698
e=960 episode_reward=-282.4599055414233 epsilon=0.01 avg=-362.4331392706629 independent_100_runs=-241.75706431296348
e=961 episode_reward=-296.1999846753742 epsilon=0.01 avg=-363.2897570140352 independent_100_runs=-227.2225819435366
e=962 episode_reward=-178.49054297737231 epsilon=0.01 avg=-363.32516283979044 independent_100_runs=-205.13790873233972
e=963 episode_reward=-289.2824940566534 epsilon=0.01 avg=-364.8488047971665 independent_100_runs=-301.0274374135022
e=964 episode_reward=-313.97003605125315 epsilon=0.01 avg=-367.49723852397756 independent_100_runs=-316.83157358360904
e=965 episode_reward=-292.6269758983676 epsilon=0.01 avg=-366.2352505221608 independent_100_runs=-239.9363046145328
e=966 episode_reward=-389.33641673836826 epsilon=0.01 avg=-367.157040959228 independent_100_runs=-324.41314117836964
e=967 episode_reward=-276.2056433099363 epsilon=0.01 avg=-367.3741832054322 independent_100_runs=-357.3205739733945
e=968 episode_reward=-318.8782095680996 epsilon=0.01 avg=-369.0130195838819 independent_100_runs=-354.11947880067487
e=969 episode_reward=-326.6579169177174 epsilon=0.01 avg=-368.4215369835835 independent_100_runs=-352.540507968775
e=970 episode_reward=-258.61562803245516 epsilon=0.01 avg=-369.97752424517404 independent_100_runs=-238.2583645480164
e=971 episode_reward=-260.7104188460853 epsilon=0.01 avg=-371.7224014737574 independent_100_runs=-284.8249711567555
e=972 episode_reward=-262.7387985047248 epsilon=0.01 avg=-373.64747122810434 independent_100_runs=-296.12510813823826
e=973 episode_reward=-410.6802918867649 epsilon=0.01 avg=-373.2259426283922 independent_100_runs=-249.119426698318
e=974 episode_reward=-219.37655357206478 epsilon=0.01 avg=-375.15940751375877 independent_100_runs=-325.05804394714295
e=975 episode_reward=-383.265575034707 epsilon=0.01 avg=-376.6050765798345 independent_100_runs=-401.20964160669797
e=976 episode_reward=-354.0666799424584 epsilon=0.01 avg=-374.9743477471043 independent_100_runs=-428.2204771677075
e=977 episode_reward=-305.61971926181513 epsilon=0.01 avg=-374.7051269725158 independent_100_runs=-310.34596570503896
e=978 episode_reward=-287.57417555201255 epsilon=0.01 avg=-374.62340958178737 independent_100_runs=-232.7503183403244
e=979 episode_reward=-250.05826286051683 epsilon=0.01 avg=-375.7411968259688 independent_100_runs=-304.6265922526555
e=980 episode_reward=-227.6977388116921 epsilon=0.01 avg=-377.5930058098067 independent_100_runs=-202.90505409880453
e=981 episode_reward=-570.9070926159426 epsilon=0.01 avg=-382.1772267324217 independent_100_runs=-296.6671490514385
e=982 episode_reward=-235.52826945578997 epsilon=0.01 avg=-382.92674178448783 independent_100_runs=-245.16570250754867
e=983 episode_reward=-271.5754687619652 epsilon=0.01 avg=-382.4808579178201 independent_100_runs=-261.99491489310117
e=984 episode_reward=-414.93049834311427 epsilon=0.01 avg=-382.76268718009965 independent_100_runs=-229.0936908152268
e=985 episode_reward=-253.63835607947004 epsilon=0.01 avg=-384.43305756991026 independent_100_runs=-217.36722349893964
e=986 episode_reward=-261.4942695721297 epsilon=0.01 avg=-385.5448960861299 independent_100_runs=-205.42934164731233
e=987 episode_reward=-309.40984128842575 epsilon=0.01 avg=-390.0061533825294 independent_100_runs=-251.34087201835217
e=988 episode_reward=-264.5364000146999 epsilon=0.01 avg=-390.27464725300206 independent_100_runs=-249.0402009963123
e=989 episode_reward=-236.9870628945472 epsilon=0.01 avg=-387.102884110861 independent_100_runs=-243.52463203098708
e=990 episode_reward=-227.51648563032342 epsilon=0.01 avg=-385.67744957046284 independent_100_runs=-238.27255482403842
e=991 episode_reward=-212.89220444303407 epsilon=0.01 avg=-386.6935553028941 independent_100_runs=-237.1857884963561
e=992 episode_reward=-90.01187432919606 epsilon=0.01 avg=-383.6857116671571 independent_100_runs=-193.3144426169708
e=993 episode_reward=-282.8617044414832 epsilon=0.01 avg=-385.5624494356309 independent_100_runs=-188.22298526329476
e=994 episode_reward=-279.82392122989125 epsilon=0.01 avg=-383.8114756121488 independent_100_runs=-232.8436393175958
e=995 episode_reward=-81.42784269248891 epsilon=0.01 avg=-382.8810603263082 independent_100_runs=-223.3332254281102
e=996 episode_reward=-226.32230088214476 epsilon=0.01 avg=-381.4303960911374 independent_100_runs=-163.19281416421137
e=997 episode_reward=-225.11344531725007 epsilon=0.01 avg=-378.98033689539295 independent_100_runs=-226.3543961108432
e=998 episode_reward=-156.81721726365953 epsilon=0.01 avg=-375.10408772205983 independent_100_runs=-233.57849888141286
e=999 episode_reward=-217.384253204635 epsilon=0.01 avg=-372.83260191743204 independent_100_runs=-213.02249582929093
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment