Last active
August 13, 2021 11:47
-
-
Save masterdezign/c82391618bd73aa67e03988f8c4b518c to your computer and use it in GitHub Desktop.
Simple RL environment
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
import gym | |
from gym.envs.registration import register | |
from tensorforce.environments import Environment | |
from tensorforce.agents import Agent | |
if len(sys.argv) < 2: | |
print("Usage: python {} path/to/checkpoint".format(sys.argv[0])) | |
exit() | |
ckpt = sys.argv[1] | |
env_name = 'Simple-v0' | |
gym.envs.registration.register(id=env_name, entry_point="simple:SimpleEnv") | |
env = gym.make(env_name) | |
environment = Environment.create(environment=env) | |
print("Loading", ckpt) | |
agent = Agent.load(directory=ckpt, format='checkpoint', environment=environment) | |
sum_rewards = 0.0 | |
new_observation = environment.reset() | |
rewards = 0. | |
for i in range(2000): | |
actions = agent.act( | |
states=new_observation, | |
independent=True, deterministic=True | |
) | |
new_observation, done, reward = environment.execute(actions) | |
print("Action {} State {} Reward {}".format( | |
actions, new_observation, reward)) | |
rewards += reward | |
if done: | |
print("Died on {} timestep".format(i)) | |
break | |
print("Total reward of {}".format(rewards)) | |
# Close agent and environment | |
agent.close() | |
environment.close() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
gym | |
numpy | |
tensorforce==0.6.4 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Loading simple_env_checkpt | |
Action 1 State [0.35] Reward -0.15000000000000002 | |
Action 1 State [0.45] Reward -0.050000000000000044 | |
Action 1 State [0.55] Reward 0.04999999999999993 | |
Action 1 State [0.65] Reward 0.1499999999999999 | |
Action 1 State [0.75] Reward 0.2499999999999999 | |
Action 0 State [0.59634611] Reward 0.0963461147740361 | |
Action 1 State [0.69634611] Reward 0.19634611477403607 | |
Action 1 State [0.79634611] Reward 0.29634611477403605 | |
Action 0 State [0.73654598] Reward 0.23654597656387766 | |
Action 1 State [0.83654598] Reward 0.33654597656387764 | |
Action 0 State [0.71598668] Reward 0.21598668088995698 | |
Action 1 State [0.81598668] Reward 0.31598668088995696 | |
Action 0 State [0.70601773] Reward 0.2060177270885848 | |
Action 1 State [0.80601773] Reward 0.30601772708858477 | |
Action 0 State [0.76372286] Reward 0.2637228582357476 | |
Action 0 State [0.56806222] Reward 0.06806221823186098 | |
Action 1 State [0.66806222] Reward 0.16806221823186096 | |
Action 1 State [0.76806222] Reward 0.26806221823186094 | |
Action 0 State [0.76711325] Reward 0.2671132455350771 | |
Action 0 State [0.6422693] Reward 0.14226930433124751 | |
Action 1 State [0.7422693] Reward 0.2422693043312475 | |
Action 1 State [0.8422693] Reward 0.34226930433124747 | |
Action 0 State [0.74028403] Reward 0.2402840348778157 | |
Action 1 State [0.84028403] Reward 0.34028403487781567 | |
Action 0 State [0.82559155] Reward 0.32559154567112336 | |
Action 0 State [0.75058309] Reward 0.25058308935048446 | |
Action 0 State [0.71845356] Reward 0.21845355776525477 | |
Action 1 State [0.81845356] Reward 0.31845355776525475 | |
Action 0 State [0.64847235] Reward 0.14847235250533453 | |
Action 1 State [0.74847235] Reward 0.2484723525053345 | |
Action 1 State [0.84847235] Reward 0.3484723525053345 | |
Action 0 State [0.66088571] Reward 0.16088570811336023 | |
Action 1 State [0.76088571] Reward 0.2608857081133602 | |
Action 0 State [0.72650366] Reward 0.2265036567683011 | |
Action 1 State [0.82650366] Reward 0.32650365676830106 | |
Action 0 State [0.63338554] Reward 0.13338553884400584 | |
Action 1 State [0.73338554] Reward 0.2333855388440058 | |
Action 1 State [0.83338554] Reward 0.3333855388440058 | |
Action 0 State [0.70882431] Reward 0.20882430549807296 | |
Action 1 State [0.80882431] Reward 0.30882430549807294 | |
Action 0 State [0.73255205] Reward 0.23255205403520818 | |
Action 1 State [0.83255205] Reward 0.33255205403520816 | |
Action 0 State [0.68129575] Reward 0.18129575131136355 | |
Action 1 State [0.78129575] Reward 0.28129575131136353 | |
Action 0 State [0.65794974] Reward 0.1579497447674314 | |
Action 1 State [0.75794974] Reward 0.2579497447674314 | |
Action 0 State [0.60822743] Reward 0.10822743109540567 | |
Action 1 State [0.70822743] Reward 0.20822743109540565 | |
Action 1 State [0.80822743] Reward 0.3082274310954056 | |
Action 0 State [0.63578014] Reward 0.13578013636783948 | |
Action 1 State [0.73578014] Reward 0.23578013636783945 | |
Action 1 State [0.83578014] Reward 0.33578013636783943 | |
Action 0 State [0.67195065] Reward 0.1719506528834167 | |
Action 1 State [0.77195065] Reward 0.2719506528834167 | |
Action 0 State [0.61777627] Reward 0.11777627169793392 | |
Action 1 State [0.71777627] Reward 0.2177762716979339 | |
Action 1 State [0.81777627] Reward 0.3177762716979339 | |
Action 0 State [0.7919528] Reward 0.2919527974888375 | |
Action 0 State [0.70612409] Reward 0.2061240946343217 | |
Action 1 State [0.80612409] Reward 0.30612409463432166 | |
Action 0 State [0.66466288] Reward 0.164662876054808 | |
Action 1 State [0.76466288] Reward 0.264662876054808 | |
Action 0 State [0.607291] Reward 0.10729100156816307 | |
Action 1 State [0.707291] Reward 0.20729100156816305 | |
Action 1 State [0.807291] Reward 0.307291001568163 | |
Action 0 State [0.75403847] Reward 0.2540384741547701 | |
Action 0 State [0.70404004] Reward 0.20404003783161506 | |
Action 1 State [0.80404004] Reward 0.30404003783161504 | |
Action 0 State [0.6723718] Reward 0.17237179623731258 | |
Action 1 State [0.7723718] Reward 0.27237179623731256 | |
Action 0 State [0.64581742] Reward 0.14581741531035464 | |
Action 1 State [0.74581742] Reward 0.24581741531035461 | |
Action 1 State [0.84581742] Reward 0.3458174153103546 | |
Action 0 State [0.79574104] Reward 0.29574103500391724 | |
Action 0 State [0.7214759] Reward 0.2214759022077758 | |
Action 1 State [0.8214759] Reward 0.3214759022077758 | |
Action 0 State [0.79836246] Reward 0.2983624626690502 | |
Action 0 State [0.63147674] Reward 0.13147674244470775 | |
Action 1 State [0.73147674] Reward 0.23147674244470773 | |
Action 1 State [0.83147674] Reward 0.3314767424447077 | |
Action 0 State [0.64351808] Reward 0.14351808481344308 | |
Action 1 State [0.74351808] Reward 0.24351808481344306 | |
Action 1 State [0.84351808] Reward 0.34351808481344304 | |
Action 0 State [0.78502919] Reward 0.28502919407157523 | |
Action 0 State [0.634147] Reward 0.1341470004609423 | |
Action 1 State [0.734147] Reward 0.23414700046094228 | |
Action 1 State [0.834147] Reward 0.33414700046094226 | |
Action 0 State [0.77650038] Reward 0.27650037792241067 | |
Action 0 State [0.72328374] Reward 0.22328374385698657 | |
Action 1 State [0.82328374] Reward 0.32328374385698655 | |
Action 0 State [0.81304585] Reward 0.31304584764245424 | |
Action 0 State [0.79936879] Reward 0.29936878708955417 | |
Action 0 State [0.73586876] Reward 0.2358687573504905 | |
Action 1 State [0.83586876] Reward 0.3358687573504905 | |
Action 0 State [0.70110991] Reward 0.20110990948996443 | |
Action 1 State [0.80110991] Reward 0.3011099094899644 | |
Action 0 State [0.64130651] Reward 0.14130651421502383 | |
Action 1 State [0.74130651] Reward 0.2413065142150238 | |
Action 1 State [0.84130651] Reward 0.3413065142150238 | |
Action 0 State [0.7412416] Reward 0.2412416003266462 | |
Action 1 State [0.8412416] Reward 0.3412416003266462 | |
Action 0 State [0.72123981] Reward 0.22123980992094938 | |
Action 1 State [0.82123981] Reward 0.32123980992094936 | |
Action 0 State [0.68872859] Reward 0.1887285866433993 | |
Action 1 State [0.78872859] Reward 0.2887285866433993 | |
Action 0 State [0.70751166] Reward 0.2075116580731866 | |
Action 1 State [0.80751166] Reward 0.3075116580731866 | |
Action 0 State [0.6404999] Reward 0.14049990152633796 | |
Action 1 State [0.7404999] Reward 0.24049990152633793 | |
Action 1 State [0.8404999] Reward 0.3404999015263379 | |
Action 0 State [0.6812127] Reward 0.1812126988220255 | |
Action 1 State [0.7812127] Reward 0.2812126988220255 | |
Action 0 State [0.75212182] Reward 0.2521218243316289 | |
Action 0 State [0.63660372] Reward 0.13660372450373215 | |
Action 1 State [0.73660372] Reward 0.23660372450373213 | |
Action 1 State [0.83660372] Reward 0.3366037245037321 | |
Action 0 State [0.823808] Reward 0.32380799640694113 | |
Action 0 State [0.79760639] Reward 0.2976063864918692 | |
Action 0 State [0.79268757] Reward 0.29268757351382013 | |
Action 0 State [0.69403451] Reward 0.19403451189931953 | |
Action 1 State [0.79403451] Reward 0.2940345118993195 | |
Action 0 State [0.71535902] Reward 0.2153590248749283 | |
Action 1 State [0.81535902] Reward 0.3153590248749283 | |
Action 0 State [0.70059219] Reward 0.20059219391418948 | |
Action 1 State [0.80059219] Reward 0.30059219391418945 | |
Action 0 State [0.71347586] Reward 0.2134758587325707 | |
Action 1 State [0.81347586] Reward 0.31347585873257067 | |
Action 0 State [0.71021121] Reward 0.2102112114939746 | |
Action 1 State [0.81021121] Reward 0.31021121149397457 | |
Action 0 State [0.79425683] Reward 0.2942568277937886 | |
Action 0 State [0.74450552] Reward 0.24450551503935147 | |
Action 1 State [0.84450552] Reward 0.34450551503935145 | |
Action 0 State [0.73902145] Reward 0.2390214501018978 | |
Action 1 State [0.83902145] Reward 0.33902145010189777 | |
Action 0 State [0.7639155] Reward 0.26391550488567106 | |
Action 0 State [0.74744904] Reward 0.24744903689918973 | |
Action 1 State [0.84744904] Reward 0.3474490368991897 | |
Action 0 State [0.66711211] Reward 0.16711211490812872 | |
Action 1 State [0.76711211] Reward 0.2671121149081287 | |
Action 0 State [0.63441826] Reward 0.1344182607889266 | |
Action 1 State [0.73441826] Reward 0.23441826078892658 | |
Action 1 State [0.83441826] Reward 0.33441826078892656 | |
Action 0 State [0.72841629] Reward 0.22841629076552028 | |
Action 1 State [0.82841629] Reward 0.32841629076552026 | |
Action 0 State [0.65269477] Reward 0.15269477147383914 | |
Action 1 State [0.75269477] Reward 0.2526947714738391 | |
Action 0 State [0.66953841] Reward 0.16953840906204098 | |
Action 1 State [0.76953841] Reward 0.26953840906204096 | |
Action 0 State [0.64172358] Reward 0.14172357714695338 | |
Action 1 State [0.74172358] Reward 0.24172357714695336 | |
Action 1 State [0.84172358] Reward 0.34172357714695334 | |
Action 0 State [0.77184737] Reward 0.27184736765506434 | |
Action 0 State [0.65958578] Reward 0.15958577568625987 | |
Action 1 State [0.75958578] Reward 0.25958577568625985 | |
Action 0 State [0.59504145] Reward 0.09504144627191913 | |
Action 1 State [0.69504145] Reward 0.1950414462719191 | |
Action 1 State [0.79504145] Reward 0.2950414462719191 | |
Action 0 State [0.78647703] Reward 0.2864770295673079 | |
Action 0 State [0.70984436] Reward 0.20984435677143287 | |
Action 1 State [0.80984436] Reward 0.30984435677143285 | |
Action 0 State [0.7965769] Reward 0.2965768986462691 | |
Action 0 State [0.70971366] Reward 0.20971365664255004 | |
Action 1 State [0.80971366] Reward 0.30971365664255 | |
Action 0 State [0.64836908] Reward 0.14836908146343952 | |
Action 1 State [0.74836908] Reward 0.2483690814634395 | |
Action 1 State [0.84836908] Reward 0.3483690814634395 | |
Action 0 State [0.70462559] Reward 0.20462558790611962 | |
Action 1 State [0.80462559] Reward 0.3046255879061196 | |
Action 0 State [0.7725466] Reward 0.27254660248796103 | |
Action 0 State [0.74252335] Reward 0.2425233521046507 | |
Action 1 State [0.84252335] Reward 0.3425233521046507 | |
Action 0 State [0.73213108] Reward 0.2321310812761933 | |
Action 1 State [0.83213108] Reward 0.3321310812761933 | |
Action 0 State [0.77271428] Reward 0.2727142761022464 | |
Action 0 State [0.58685793] Reward 0.08685792662253733 | |
Action 1 State [0.68685793] Reward 0.1868579266225373 | |
Action 1 State [0.78685793] Reward 0.2868579266225373 | |
Action 0 State [0.7030115] Reward 0.20301150316921635 | |
Action 1 State [0.8030115] Reward 0.3030115031692163 | |
Action 0 State [0.62924867] Reward 0.129248666652799 | |
Action 1 State [0.72924867] Reward 0.22924866665279897 | |
Action 1 State [0.82924867] Reward 0.32924866665279895 | |
Action 0 State [0.68078883] Reward 0.18078883061429674 | |
Action 1 State [0.78078883] Reward 0.2807888306142967 | |
Action 0 State [0.62423068] Reward 0.12423068119403957 | |
Action 1 State [0.72423068] Reward 0.22423068119403955 | |
Action 1 State [0.82423068] Reward 0.3242306811940395 | |
Action 0 State [0.76598147] Reward 0.2659814676822866 | |
Action 0 State [0.57565967] Reward 0.07565967215639002 | |
Action 1 State [0.67565967] Reward 0.17565967215639 | |
Action 1 State [0.77565967] Reward 0.27565967215639 | |
Action 0 State [0.62385222] Reward 0.12385221776598698 | |
Action 1 State [0.72385222] Reward 0.22385221776598696 | |
Action 1 State [0.82385222] Reward 0.32385221776598694 | |
Action 0 State [0.67235545] Reward 0.17235544553881588 | |
Action 1 State [0.77235545] Reward 0.27235544553881585 | |
Action 0 State [0.64766107] Reward 0.147661066516934 | |
Action 1 State [0.74766107] Reward 0.24766106651693398 | |
Action 1 State [0.84766107] Reward 0.34766106651693396 | |
Action 0 State [0.82495859] Reward 0.3249585916233948 | |
Action 0 State [0.67001385] Reward 0.17001384501052563 | |
Action 1 State [0.77001385] Reward 0.2700138450105256 | |
Action 0 State [0.67538879] Reward 0.17538878834768012 | |
Action 1 State [0.77538879] Reward 0.2753887883476801 | |
Action 0 State [0.74001247] Reward 0.24001247387124292 | |
Action 1 State [0.84001247] Reward 0.3400124738712429 | |
Action 0 State [0.77110765] Reward 0.27110764527442166 | |
Action 0 State [0.65667475] Reward 0.1566747510919142 | |
Action 1 State [0.75667475] Reward 0.2566747510919142 | |
Action 0 State [0.6239362] Reward 0.1239361968930599 | |
Action 1 State [0.7239362] Reward 0.22393619689305988 | |
Action 1 State [0.8239362] Reward 0.32393619689305986 | |
Action 0 State [0.73445233] Reward 0.23445232965529805 | |
Action 1 State [0.83445233] Reward 0.33445232965529803 | |
Action 0 State [0.75510428] Reward 0.25510428041515487 | |
Action 0 State [0.60733445] Reward 0.1073344494245132 | |
Action 1 State [0.70733445] Reward 0.20733444942451318 | |
Action 1 State [0.80733445] Reward 0.30733444942451316 | |
Action 0 State [0.73947248] Reward 0.2394724772658563 | |
Action 1 State [0.83947248] Reward 0.3394724772658563 | |
Action 0 State [0.77755128] Reward 0.27755128488414016 | |
Action 0 State [0.62639295] Reward 0.12639295496556524 | |
Action 1 State [0.72639295] Reward 0.22639295496556522 | |
Action 1 State [0.82639295] Reward 0.3263929549655652 | |
Action 0 State [0.79688059] Reward 0.2968805905151155 | |
Action 0 State [0.66679959] Reward 0.16679959321484705 | |
Action 1 State [0.76679959] Reward 0.26679959321484703 | |
Action 0 State [0.74292894] Reward 0.2429289421351979 | |
Action 1 State [0.84292894] Reward 0.34292894213519787 | |
Action 0 State [0.7904106] Reward 0.29041060493298043 | |
Action 0 State [0.62576853] Reward 0.12576852862628185 | |
Action 1 State [0.72576853] Reward 0.22576852862628183 | |
Action 1 State [0.82576853] Reward 0.3257685286262818 | |
Action 0 State [0.72236276] Reward 0.2223627637803075 | |
Action 1 State [0.82236276] Reward 0.3223627637803075 | |
Action 0 State [0.77470198] Reward 0.27470198251769473 | |
Action 0 State [0.6452678] Reward 0.14526779513157884 | |
Action 1 State [0.7452678] Reward 0.24526779513157881 | |
Action 1 State [0.8452678] Reward 0.3452677951315788 | |
Action 0 State [0.76894176] Reward 0.26894175719401137 | |
Action 0 State [0.63173871] Reward 0.13173871213866795 | |
Action 1 State [0.73173871] Reward 0.23173871213866792 | |
Action 1 State [0.83173871] Reward 0.3317387121386679 | |
Action 0 State [0.71678284] Reward 0.21678284417446503 | |
Action 1 State [0.81678284] Reward 0.316782844174465 | |
Action 0 State [0.63118798] Reward 0.1311879787646576 | |
Action 1 State [0.73118798] Reward 0.23118797876465758 | |
Action 1 State [0.83118798] Reward 0.33118797876465755 | |
Action 0 State [0.63163669] Reward 0.13163669331689976 | |
Action 1 State [0.73163669] Reward 0.23163669331689973 | |
Action 1 State [0.83163669] Reward 0.3316366933168997 | |
Action 0 State [0.73473784] Reward 0.23473783570329976 | |
Action 1 State [0.83473784] Reward 0.33473783570329974 | |
Action 0 State [0.76841749] Reward 0.26841748613219263 | |
Action 0 State [0.74233409] Reward 0.24233408620777364 | |
Action 1 State [0.84233409] Reward 0.3423340862077736 | |
Action 0 State [0.8232741] Reward 0.32327410176413074 | |
Action 0 State [0.74680284] Reward 0.2468028429388024 | |
Action 1 State [0.84680284] Reward 0.34680284293880237 | |
Action 0 State [0.75724098] Reward 0.257240981744273 | |
Action 0 State [0.68641512] Reward 0.18641511600541916 | |
Action 1 State [0.78641512] Reward 0.28641511600541913 | |
Action 0 State [0.66529183] Reward 0.16529182596498893 | |
Action 1 State [0.76529183] Reward 0.2652918259649889 | |
Action 0 State [0.63664248] Reward 0.13664248235322873 | |
Action 1 State [0.73664248] Reward 0.2366424823532287 | |
Action 1 State [0.83664248] Reward 0.3366424823532287 | |
Action 0 State [0.64679735] Reward 0.14679734999636562 | |
Action 1 State [0.74679735] Reward 0.2467973499963656 | |
Action 1 State [0.84679735] Reward 0.3467973499963656 | |
Action 0 State [0.83197827] Reward 0.3319782673564484 | |
Action 0 State [0.72381482] Reward 0.22381481695731342 | |
Action 1 State [0.82381482] Reward 0.3238148169573134 | |
Action 0 State [0.72452907] Reward 0.22452907466723393 | |
Action 1 State [0.82452907] Reward 0.3245290746672339 | |
Action 0 State [0.80473357] Reward 0.3047335705437577 | |
Action 0 State [0.70929933] Reward 0.2092993298945065 | |
Action 1 State [0.80929933] Reward 0.3092993298945065 | |
Action 0 State [0.76353009] Reward 0.26353009287501516 | |
Action 0 State [0.71297309] Reward 0.21297309024754474 | |
Action 1 State [0.81297309] Reward 0.3129730902475447 | |
Action 0 State [0.70705315] Reward 0.20705315363017174 | |
Action 1 State [0.80705315] Reward 0.3070531536301717 | |
Action 0 State [0.79718586] Reward 0.29718585960269905 | |
Action 0 State [0.76146937] Reward 0.26146937206206355 | |
Action 0 State [0.57808132] Reward 0.07808131735107249 | |
Action 1 State [0.67808132] Reward 0.17808131735107247 | |
Action 1 State [0.77808132] Reward 0.27808131735107244 | |
Action 0 State [0.71459088] Reward 0.21459088263405368 | |
Action 1 State [0.81459088] Reward 0.31459088263405366 | |
Action 0 State [0.74110014] Reward 0.2411001418709804 | |
Action 1 State [0.84110014] Reward 0.34110014187098037 | |
Action 0 State [0.67993655] Reward 0.1799365519599725 | |
Action 1 State [0.77993655] Reward 0.27993655195997247 | |
Action 0 State [0.7197629] Reward 0.21976289893201895 | |
Action 1 State [0.8197629] Reward 0.3197628989320189 | |
Action 0 State [0.73077333] Reward 0.23077333011038148 | |
Action 1 State [0.83077333] Reward 0.33077333011038146 | |
Action 0 State [0.66472215] Reward 0.1647221474516879 | |
Action 1 State [0.76472215] Reward 0.2647221474516879 | |
Action 0 State [0.7180028] Reward 0.2180027999542955 | |
Action 1 State [0.8180028] Reward 0.3180027999542955 | |
Action 0 State [0.74703595] Reward 0.24703595473696416 | |
Action 1 State [0.84703595] Reward 0.34703595473696414 | |
Action 0 State [0.80590048] Reward 0.3059004817569497 | |
Action 0 State [0.6444199] Reward 0.14441989603862404 | |
Action 1 State [0.7444199] Reward 0.24441989603862402 | |
Action 1 State [0.8444199] Reward 0.344419896038624 | |
Action 0 State [0.7936941] Reward 0.2936940998187425 | |
Action 0 State [0.75666938] Reward 0.2566693810302203 | |
Action 0 State [0.56955032] Reward 0.06955031838183012 | |
Action 1 State [0.66955032] Reward 0.1695503183818301 | |
Action 1 State [0.76955032] Reward 0.2695503183818301 | |
Action 0 State [0.66594527] Reward 0.1659452668250787 | |
Action 1 State [0.76594527] Reward 0.2659452668250787 | |
Action 0 State [0.74092669] Reward 0.24092669381717968 | |
Action 1 State [0.84092669] Reward 0.34092669381717966 | |
Action 0 State [0.74329449] Reward 0.24329448527041697 | |
Action 1 State [0.84329449] Reward 0.34329448527041695 | |
Action 0 State [0.72701795] Reward 0.22701794978721412 | |
Action 1 State [0.82701795] Reward 0.3270179497872141 | |
Action 0 State [0.75317868] Reward 0.25317867658104265 | |
Action 0 State [0.59589613] Reward 0.09589613174592793 | |
Action 1 State [0.69589613] Reward 0.1958961317459279 | |
Action 1 State [0.79589613] Reward 0.2958961317459279 | |
Action 0 State [0.78518458] Reward 0.28518458029016847 | |
Action 0 State [0.62127196] Reward 0.12127196379813188 | |
Action 1 State [0.72127196] Reward 0.22127196379813185 | |
Action 1 State [0.82127196] Reward 0.32127196379813183 | |
Action 0 State [0.80004879] Reward 0.3000487865192841 | |
Action 0 State [0.79186144] Reward 0.2918614410979167 | |
Action 0 State [0.64130623] Reward 0.1413062281423647 | |
Action 1 State [0.74130623] Reward 0.2413062281423647 | |
Action 1 State [0.84130623] Reward 0.34130622814236466 | |
Action 0 State [0.74151476] Reward 0.24151476420206386 | |
Action 1 State [0.84151476] Reward 0.34151476420206384 | |
Action 0 State [0.76350026] Reward 0.26350025558859946 | |
Action 0 State [0.68422057] Reward 0.1842205748059792 | |
Action 1 State [0.78422057] Reward 0.2842205748059792 | |
Action 0 State [0.78126831] Reward 0.2812683075446407 | |
Action 0 State [0.6347286] Reward 0.1347285989124377 | |
Action 1 State [0.7347286] Reward 0.2347285989124377 | |
Action 1 State [0.8347286] Reward 0.33472859891243767 | |
Action 0 State [0.69437987] Reward 0.19437987215063557 | |
Action 1 State [0.79437987] Reward 0.29437987215063555 | |
Action 0 State [0.78952] Reward 0.28952000072736195 | |
Action 0 State [0.70286118] Reward 0.20286117809745208 | |
Action 1 State [0.80286118] Reward 0.30286117809745206 | |
Action 0 State [0.76653498] Reward 0.26653498264323816 | |
Action 0 State [0.69520425] Reward 0.1952042545178636 | |
Action 1 State [0.79520425] Reward 0.2952042545178636 | |
Action 0 State [0.73057067] Reward 0.23057067117835317 | |
Action 1 State [0.83057067] Reward 0.33057067117835315 | |
Action 0 State [0.72243869] Reward 0.22243868815546697 | |
Action 1 State [0.82243869] Reward 0.32243868815546695 | |
Action 0 State [0.70760645] Reward 0.20760644879756596 | |
Action 1 State [0.80760645] Reward 0.30760644879756593 | |
Action 0 State [0.7673547] Reward 0.26735470459782074 | |
Action 0 State [0.688825] Reward 0.18882499753938942 | |
Action 1 State [0.788825] Reward 0.2888249975393894 | |
Action 0 State [0.7410381] Reward 0.2410381027407983 | |
Action 1 State [0.8410381] Reward 0.34103810274079827 | |
Action 0 State [0.69568232] Reward 0.19568231576152395 | |
Action 1 State [0.79568232] Reward 0.29568231576152393 | |
Action 0 State [0.6477365] Reward 0.14773649997125782 | |
Action 1 State [0.7477365] Reward 0.2477364999712578 | |
Action 1 State [0.8477365] Reward 0.3477364999712578 | |
Action 0 State [0.75787126] Reward 0.25787126430441065 | |
Action 0 State [0.67278545] Reward 0.17278545200216977 | |
Action 1 State [0.77278545] Reward 0.27278545200216975 | |
Action 0 State [0.73375606] Reward 0.23375605887337436 | |
Action 1 State [0.83375606] Reward 0.33375605887337434 | |
Action 0 State [0.71292334] Reward 0.21292333573329314 | |
Action 1 State [0.81292334] Reward 0.3129233357332931 | |
Action 0 State [0.78467352] Reward 0.28467351780098604 | |
Action 0 State [0.6559423] Reward 0.15594230402978337 | |
Action 1 State [0.7559423] Reward 0.25594230402978335 | |
Action 0 State [0.61308749] Reward 0.1130874855560342 | |
Action 1 State [0.71308749] Reward 0.21308748555603418 | |
Action 1 State [0.81308749] Reward 0.31308748555603416 | |
Action 0 State [0.79365717] Reward 0.2936571659087359 | |
Action 0 State [0.67295558] Reward 0.1729555779723948 | |
Action 1 State [0.77295558] Reward 0.2729555779723948 | |
Action 0 State [0.57354387] Reward 0.0735438695372661 | |
Action 1 State [0.67354387] Reward 0.17354386953726608 | |
Action 1 State [0.77354387] Reward 0.27354386953726606 | |
Action 0 State [0.72330611] Reward 0.22330610591071376 | |
Action 1 State [0.82330611] Reward 0.32330610591071374 | |
Action 0 State [0.77557673] Reward 0.27557673494906676 | |
Action 0 State [0.70711969] Reward 0.2071196922647146 | |
Action 1 State [0.80711969] Reward 0.3071196922647146 | |
Action 0 State [0.73811293] Reward 0.23811293463588634 | |
Action 1 State [0.83811293] Reward 0.3381129346358863 | |
Action 0 State [0.83265575] Reward 0.3326557508315039 | |
Action 0 State [0.66349469] Reward 0.163494686372314 | |
Action 1 State [0.76349469] Reward 0.263494686372314 | |
Action 0 State [0.6141917] Reward 0.11419169505660554 | |
Action 1 State [0.7141917] Reward 0.2141916950566055 | |
Action 1 State [0.8141917] Reward 0.3141916950566055 | |
Action 0 State [0.70215203] Reward 0.20215203190448172 | |
Action 1 State [0.80215203] Reward 0.3021520319044817 | |
Action 0 State [0.66885881] Reward 0.168858809615392 | |
Action 1 State [0.76885881] Reward 0.268858809615392 | |
Action 0 State [0.66464417] Reward 0.16464417074240134 | |
Action 1 State [0.76464417] Reward 0.2646441707424013 | |
Action 0 State [0.70458372] Reward 0.20458371920469598 | |
Action 1 State [0.80458372] Reward 0.30458371920469596 | |
Action 0 State [0.78876862] Reward 0.2887686207526886 | |
Action 0 State [0.73239139] Reward 0.23239139179244916 | |
Action 1 State [0.83239139] Reward 0.33239139179244914 | |
Action 0 State [0.81162168] Reward 0.3116216780265768 | |
Action 0 State [0.7056752] Reward 0.20567520066076472 | |
Action 1 State [0.8056752] Reward 0.3056752006607647 | |
Action 0 State [0.72065964] Reward 0.22065964444786457 | |
Action 1 State [0.82065964] Reward 0.32065964444786454 | |
Action 0 State [0.66814976] Reward 0.16814975816781963 | |
Action 1 State [0.76814976] Reward 0.2681497581678196 | |
Action 0 State [0.76143079] Reward 0.2614307947528215 | |
Action 0 State [0.68997332] Reward 0.18997332130994793 | |
Action 1 State [0.78997332] Reward 0.2899733213099479 | |
Action 0 State [0.77550973] Reward 0.27550973421856384 | |
Action 0 State [0.70052753] Reward 0.20052753379406763 | |
Action 1 State [0.80052753] Reward 0.3005275337940676 | |
Action 0 State [0.66264359] Reward 0.16264359333264378 | |
Action 1 State [0.76264359] Reward 0.26264359333264375 | |
Action 0 State [0.72296848] Reward 0.2229684770225041 | |
Action 1 State [0.82296848] Reward 0.3229684770225041 | |
Action 0 State [0.62424326] Reward 0.124243263416834 | |
Action 1 State [0.72424326] Reward 0.22424326341683398 | |
Action 1 State [0.82424326] Reward 0.32424326341683396 | |
Action 0 State [0.75138184] Reward 0.25138183961771077 | |
Action 0 State [0.70734095] Reward 0.20734095261308072 | |
Action 1 State [0.80734095] Reward 0.3073409526130807 | |
Action 0 State [0.62226019] Reward 0.12226019447954561 | |
Action 1 State [0.72226019] Reward 0.2222601944795456 | |
Action 1 State [0.82226019] Reward 0.32226019447954557 | |
Action 0 State [0.65505108] Reward 0.1550510763042836 | |
Action 1 State [0.75505108] Reward 0.2550510763042836 | |
Action 0 State [0.66027535] Reward 0.160275354229082 | |
Action 1 State [0.76027535] Reward 0.260275354229082 | |
Action 0 State [0.67151959] Reward 0.1715195887754748 | |
Action 1 State [0.77151959] Reward 0.2715195887754748 | |
Action 0 State [0.60981664] Reward 0.10981663987908674 | |
Action 1 State [0.70981664] Reward 0.20981663987908672 | |
Action 1 State [0.80981664] Reward 0.3098166398790867 | |
Action 0 State [0.76971363] Reward 0.26971362748902006 | |
Action 0 State [0.74980811] Reward 0.2498081050587896 | |
Action 0 State [0.62551508] Reward 0.1255150798077389 | |
Action 1 State [0.72551508] Reward 0.22551507980773888 | |
Action 1 State [0.82551508] Reward 0.32551507980773886 | |
Action 0 State [0.69050734] Reward 0.19050734007797698 | |
Action 1 State [0.79050734] Reward 0.29050734007797696 | |
Action 0 State [0.72475479] Reward 0.22475478911495494 | |
Action 1 State [0.82475479] Reward 0.3247547891149549 | |
Action 0 State [0.75633915] Reward 0.2563391453491357 | |
Action 0 State [0.64763218] Reward 0.14763218138463907 | |
Action 1 State [0.74763218] Reward 0.24763218138463905 | |
Action 1 State [0.84763218] Reward 0.347632181384639 | |
Action 0 State [0.68548052] Reward 0.18548051985181746 | |
Action 1 State [0.78548052] Reward 0.28548051985181744 | |
Action 0 State [0.6811389] Reward 0.18113889590705 | |
Action 1 State [0.7811389] Reward 0.28113889590705 | |
Action 0 State [0.73846145] Reward 0.23846144869098806 | |
Action 1 State [0.83846145] Reward 0.33846144869098804 | |
Action 0 State [0.74700814] Reward 0.24700813952569 | |
Action 1 State [0.84700814] Reward 0.34700813952569 | |
Action 0 State [0.79829225] Reward 0.29829225371974366 | |
Action 0 State [0.77739008] Reward 0.27739008250363417 | |
Action 0 State [0.74418326] Reward 0.24418326025991877 | |
Action 1 State [0.84418326] Reward 0.34418326025991874 | |
Action 0 State [0.72798612] Reward 0.22798611748980457 | |
Action 1 State [0.82798612] Reward 0.32798611748980455 | |
Action 0 State [0.82542997] Reward 0.32542996688220027 | |
Action 0 State [0.72593368] Reward 0.22593368289647298 | |
Action 1 State [0.82593368] Reward 0.32593368289647295 | |
Action 0 State [0.78591719] Reward 0.28591718554585 | |
Action 0 State [0.70467075] Reward 0.2046707466825266 | |
Action 1 State [0.80467075] Reward 0.3046707466825266 | |
Action 0 State [0.69588551] Reward 0.19588550908858315 | |
Action 1 State [0.79588551] Reward 0.29588550908858313 | |
Action 0 State [0.64555094] Reward 0.1455509406919565 | |
Action 1 State [0.74555094] Reward 0.2455509406919565 | |
Action 1 State [0.84555094] Reward 0.34555094069195647 | |
Action 0 State [0.74426161] Reward 0.24426161253691103 | |
Action 1 State [0.84426161] Reward 0.344261612536911 | |
Action 0 State [0.69649977] Reward 0.19649976796223068 | |
Action 1 State [0.79649977] Reward 0.29649976796223065 | |
Action 0 State [0.66077592] Reward 0.16077592497296245 | |
Action 1 State [0.76077592] Reward 0.2607759249729624 | |
Action 0 State [0.57904555] Reward 0.07904555405854397 | |
Action 1 State [0.67904555] Reward 0.17904555405854394 | |
Action 1 State [0.77904555] Reward 0.2790455540585439 | |
Action 0 State [0.63487185] Reward 0.13487184914277783 | |
Action 1 State [0.73487185] Reward 0.2348718491427778 | |
Action 1 State [0.83487185] Reward 0.3348718491427778 | |
Action 0 State [0.76131154] Reward 0.2613115354672577 | |
Action 0 State [0.73379117] Reward 0.23379116627789365 | |
Action 1 State [0.83379117] Reward 0.3337911662778936 | |
Action 0 State [0.65986031] Reward 0.15986030729891254 | |
Action 1 State [0.75986031] Reward 0.2598603072989125 | |
Action 0 State [0.59646033] Reward 0.09646033190289949 | |
Action 1 State [0.69646033] Reward 0.19646033190289947 | |
Action 1 State [0.79646033] Reward 0.29646033190289944 | |
Action 0 State [0.6751461] Reward 0.17514610021342714 | |
Action 1 State [0.7751461] Reward 0.2751461002134271 | |
Action 0 State [0.73369859] Reward 0.2336985917372877 | |
Action 1 State [0.83369859] Reward 0.33369859173728766 | |
Action 0 State [0.75741337] Reward 0.257413372743577 | |
Action 0 State [0.69616859] Reward 0.19616859443347878 | |
Action 1 State [0.79616859] Reward 0.29616859443347876 | |
Action 0 State [0.63851593] Reward 0.13851592919819966 | |
Action 1 State [0.73851593] Reward 0.23851592919819964 | |
Action 1 State [0.83851593] Reward 0.3385159291981996 | |
Action 0 State [0.77350886] Reward 0.27350886044069533 | |
Action 0 State [0.69907795] Reward 0.19907795049480703 | |
Action 1 State [0.79907795] Reward 0.299077950494807 | |
Action 0 State [0.68248426] Reward 0.1824842587806137 | |
Action 1 State [0.78248426] Reward 0.2824842587806137 | |
Action 0 State [0.63980571] Reward 0.1398057065808035 | |
Action 1 State [0.73980571] Reward 0.23980570658080347 | |
Action 1 State [0.83980571] Reward 0.33980570658080345 | |
Action 0 State [0.78738948] Reward 0.28738948059251523 | |
Action 0 State [0.65830505] Reward 0.15830505206128132 | |
Action 1 State [0.75830505] Reward 0.2583050520612813 | |
Action 0 State [0.57461245] Reward 0.07461244606495387 | |
Action 1 State [0.67461245] Reward 0.17461244606495385 | |
Action 1 State [0.77461245] Reward 0.27461244606495383 | |
Action 0 State [0.6227951] Reward 0.1227950970703342 | |
Action 1 State [0.7227951] Reward 0.22279509707033418 | |
Action 1 State [0.8227951] Reward 0.32279509707033416 | |
Action 0 State [0.71883507] Reward 0.21883507324073714 | |
Action 1 State [0.81883507] Reward 0.3188350732407371 | |
Action 0 State [0.71829082] Reward 0.21829082038925662 | |
Action 1 State [0.81829082] Reward 0.3182908203892566 | |
Action 0 State [0.81694198] Reward 0.3169419777633097 | |
Action 0 State [0.76506377] Reward 0.26506377214237664 | |
Action 0 State [0.67167858] Reward 0.17167858368806677 | |
Action 1 State [0.77167858] Reward 0.27167858368806674 | |
Action 0 State [0.60720026] Reward 0.10720025951567835 | |
Action 1 State [0.70720026] Reward 0.20720025951567833 | |
Action 1 State [0.80720026] Reward 0.3072002595156783 | |
Action 0 State [0.64188182] Reward 0.14188181567171876 | |
Action 1 State [0.74188182] Reward 0.24188181567171874 | |
Action 1 State [0.84188182] Reward 0.3418818156717187 | |
Action 0 State [0.70106515] Reward 0.20106514832314104 | |
Action 1 State [0.80106515] Reward 0.301065148323141 | |
Action 0 State [0.66809845] Reward 0.16809844971247445 | |
Action 1 State [0.76809845] Reward 0.26809844971247443 | |
Action 0 State [0.74954468] Reward 0.2495446802161766 | |
Action 1 State [0.84954468] Reward 0.3495446802161766 | |
Action 0 State [0.69221786] Reward 0.19221786440846156 | |
Action 1 State [0.79221786] Reward 0.29221786440846154 | |
Action 0 State [0.66562633] Reward 0.16562633492288592 | |
Action 1 State [0.76562633] Reward 0.2656263349228859 | |
Action 0 State [0.69110056] Reward 0.19110056087026728 | |
Action 1 State [0.79110056] Reward 0.29110056087026726 | |
Action 0 State [0.75869984] Reward 0.2586998371083199 | |
Action 0 State [0.70430069] Reward 0.20430069131528583 | |
Action 1 State [0.80430069] Reward 0.3043006913152858 | |
Action 0 State [0.66010391] Reward 0.16010391067994012 | |
Action 1 State [0.76010391] Reward 0.2601039106799401 | |
Action 0 State [0.58788978] Reward 0.0878897826619709 | |
Action 1 State [0.68788978] Reward 0.18788978266197087 | |
Action 1 State [0.78788978] Reward 0.28788978266197085 | |
Action 0 State [0.67245612] Reward 0.1724561186547482 | |
Action 1 State [0.77245612] Reward 0.27245611865474817 | |
Action 0 State [0.62658501] Reward 0.1265850104155175 | |
Action 1 State [0.72658501] Reward 0.22658501041551748 | |
Action 1 State [0.82658501] Reward 0.32658501041551746 | |
Action 0 State [0.66011229] Reward 0.16011229234905222 | |
Action 1 State [0.76011229] Reward 0.2601122923490522 | |
Action 0 State [0.59517632] Reward 0.09517631544303662 | |
Action 1 State [0.69517632] Reward 0.1951763154430366 | |
Action 1 State [0.79517632] Reward 0.2951763154430366 | |
Action 0 State [0.7845625] Reward 0.2845624964141933 | |
Action 0 State [0.74191628] Reward 0.2419162795899139 | |
Action 1 State [0.84191628] Reward 0.3419162795899139 | |
Action 0 State [0.70401458] Reward 0.20401457997954187 | |
Action 1 State [0.80401458] Reward 0.30401457997954184 | |
Action 0 State [0.62001144] Reward 0.12001143576367035 | |
Action 1 State [0.72001144] Reward 0.22001143576367033 | |
Action 1 State [0.82001144] Reward 0.3200114357636703 | |
Action 0 State [0.79063033] Reward 0.29063033290561124 | |
Action 0 State [0.68445484] Reward 0.18445483846728827 | |
Action 1 State [0.78445484] Reward 0.28445483846728825 | |
Action 0 State [0.63064088] Reward 0.13064087510339517 | |
Action 1 State [0.73064088] Reward 0.23064087510339515 | |
Action 1 State [0.83064088] Reward 0.3306408751033951 | |
Action 0 State [0.80868316] Reward 0.3086831645822883 | |
Action 0 State [0.6690617] Reward 0.16906169919338643 | |
Action 1 State [0.7690617] Reward 0.2690616991933864 | |
Action 0 State [0.71879391] Reward 0.2187939086805769 | |
Action 1 State [0.81879391] Reward 0.3187939086805769 | |
Action 0 State [0.64434983] Reward 0.14434983097408516 | |
Action 1 State [0.74434983] Reward 0.24434983097408514 | |
Action 1 State [0.84434983] Reward 0.3443498309740851 | |
Action 0 State [0.66124478] Reward 0.16124478472830828 | |
Action 1 State [0.76124478] Reward 0.26124478472830825 | |
Action 0 State [0.71904911] Reward 0.2190491073721973 | |
Action 1 State [0.81904911] Reward 0.31904910737219727 | |
Action 0 State [0.61945867] Reward 0.11945867059977533 | |
Action 1 State [0.71945867] Reward 0.2194586705997753 | |
Action 1 State [0.81945867] Reward 0.3194586705997753 | |
Action 0 State [0.67468185] Reward 0.1746818545737655 | |
Action 1 State [0.77468185] Reward 0.2746818545737655 | |
Action 0 State [0.71061997] Reward 0.2106199656272958 | |
Action 1 State [0.81061997] Reward 0.31061996562729577 | |
Action 0 State [0.61971581] Reward 0.11971580736651144 | |
Action 1 State [0.71971581] Reward 0.21971580736651142 | |
Action 1 State [0.81971581] Reward 0.3197158073665114 | |
Action 0 State [0.75172278] Reward 0.2517227848742307 | |
Action 0 State [0.56603782] Reward 0.0660378209108261 | |
Action 1 State [0.66603782] Reward 0.16603782091082608 | |
Action 1 State [0.76603782] Reward 0.26603782091082606 | |
Action 0 State [0.61710694] Reward 0.1171069411921909 | |
Action 1 State [0.71710694] Reward 0.21710694119219087 | |
Action 1 State [0.81710694] Reward 0.31710694119219085 | |
Action 0 State [0.67519841] Reward 0.17519840910451157 | |
Action 1 State [0.77519841] Reward 0.27519840910451154 | |
Action 0 State [0.7481774] Reward 0.24817740331229232 | |
Action 1 State [0.8481774] Reward 0.3481774033122923 | |
Action 0 State [0.6895983] Reward 0.18959829513686355 | |
Action 1 State [0.7895983] Reward 0.2895982951368635 | |
Action 0 State [0.69386389] Reward 0.19386389125884884 | |
Action 1 State [0.79386389] Reward 0.2938638912588488 | |
Action 0 State [0.64280802] Reward 0.1428080176556379 | |
Action 1 State [0.74280802] Reward 0.24280801765563786 | |
Action 1 State [0.84280802] Reward 0.34280801765563784 | |
Action 0 State [0.65443505] Reward 0.1544350520725266 | |
Action 1 State [0.75443505] Reward 0.2544350520725266 | |
Action 0 State [0.66063145] Reward 0.16063144573869947 | |
Action 1 State [0.76063145] Reward 0.26063144573869945 | |
Action 0 State [0.62776999] Reward 0.12776998596611722 | |
Action 1 State [0.72776999] Reward 0.2277699859661172 | |
Action 1 State [0.82776999] Reward 0.32776998596611717 | |
Action 0 State [0.76327876] Reward 0.2632787619117698 | |
Action 0 State [0.66243233] Reward 0.16243232562015442 | |
Action 1 State [0.76243233] Reward 0.2624323256201544 | |
Action 0 State [0.75787793] Reward 0.2578779306734851 | |
Action 0 State [0.68640505] Reward 0.18640504793236978 | |
Action 1 State [0.78640505] Reward 0.28640504793236976 | |
Action 0 State [0.68247342] Reward 0.18247341731653421 | |
Action 1 State [0.78247342] Reward 0.2824734173165342 | |
Action 0 State [0.75084753] Reward 0.25084752585470094 | |
Action 0 State [0.70342331] Reward 0.20342330576035317 | |
Action 1 State [0.80342331] Reward 0.30342330576035315 | |
Action 0 State [0.60828748] Reward 0.10828747782923598 | |
Action 1 State [0.70828748] Reward 0.20828747782923596 | |
Action 1 State [0.80828748] Reward 0.30828747782923593 | |
Action 0 State [0.64331806] Reward 0.14331806029330685 | |
Action 1 State [0.74331806] Reward 0.24331806029330683 | |
Action 1 State [0.84331806] Reward 0.3433180602933068 | |
Action 0 State [0.72252478] Reward 0.2225247798848231 | |
Action 1 State [0.82252478] Reward 0.3225247798848231 | |
Action 0 State [0.7146207] Reward 0.21462069851060805 | |
Action 1 State [0.8146207] Reward 0.31462069851060803 | |
Action 0 State [0.81104993] Reward 0.3110499292618212 | |
Action 0 State [0.77714882] Reward 0.27714882281627073 | |
Action 0 State [0.71773821] Reward 0.2177382126378844 | |
Action 1 State [0.81773821] Reward 0.3177382126378844 | |
Action 0 State [0.81121294] Reward 0.3112129376266676 | |
Action 0 State [0.7916781] Reward 0.29167809606899 | |
Action 0 State [0.72473345] Reward 0.2247334494535782 | |
Action 1 State [0.82473345] Reward 0.3247334494535782 | |
Action 0 State [0.78765181] Reward 0.28765181351156155 | |
Action 0 State [0.70502581] Reward 0.20502581078902538 | |
Action 1 State [0.80502581] Reward 0.30502581078902535 | |
Action 0 State [0.75936187] Reward 0.2593618722426312 | |
Action 0 State [0.70781043] Reward 0.2078104349460641 | |
Action 1 State [0.80781043] Reward 0.3078104349460641 | |
Action 0 State [0.6321349] Reward 0.13213489847349424 | |
Action 1 State [0.7321349] Reward 0.23213489847349422 | |
Action 1 State [0.8321349] Reward 0.3321348984734942 | |
Action 0 State [0.72404479] Reward 0.22404478896845992 | |
Action 1 State [0.82404479] Reward 0.3240447889684599 | |
Action 0 State [0.63729887] Reward 0.13729886830338978 | |
Action 1 State [0.73729887] Reward 0.23729886830338975 | |
Action 1 State [0.83729887] Reward 0.33729886830338973 | |
Action 0 State [0.69318843] Reward 0.19318842989808482 | |
Action 1 State [0.79318843] Reward 0.2931884298980848 | |
Action 0 State [0.66170862] Reward 0.1617086213325245 | |
Action 1 State [0.76170862] Reward 0.2617086213325245 | |
Action 0 State [0.5738239] Reward 0.07382390215693801 | |
Action 1 State [0.6738239] Reward 0.173823902156938 | |
Action 1 State [0.7738239] Reward 0.27382390215693797 | |
Action 0 State [0.7735302] Reward 0.27353020437676623 | |
Action 0 State [0.70416973] Reward 0.20416973457013143 | |
Action 1 State [0.80416973] Reward 0.3041697345701314 | |
Action 0 State [0.67736303] Reward 0.17736303326688407 | |
Action 1 State [0.77736303] Reward 0.27736303326688405 | |
Action 0 State [0.58972453] Reward 0.08972453493816768 | |
Action 1 State [0.68972453] Reward 0.18972453493816765 | |
Action 1 State [0.78972453] Reward 0.28972453493816763 | |
Action 0 State [0.69301696] Reward 0.1930169566671952 | |
Action 1 State [0.79301696] Reward 0.2930169566671952 | |
Action 0 State [0.77628574] Reward 0.2762857420388237 | |
Action 0 State [0.7335214] Reward 0.2335214002254956 | |
Action 1 State [0.8335214] Reward 0.3335214002254956 | |
Action 0 State [0.67041769] Reward 0.17041768595678297 | |
Action 1 State [0.77041769] Reward 0.27041768595678295 | |
Action 0 State [0.68743061] Reward 0.187430610657908 | |
Action 1 State [0.78743061] Reward 0.287430610657908 | |
Action 0 State [0.59573097] Reward 0.09573097365404748 | |
Action 1 State [0.69573097] Reward 0.19573097365404746 | |
Action 1 State [0.79573097] Reward 0.29573097365404744 | |
Action 0 State [0.63079286] Reward 0.1307928621711535 | |
Action 1 State [0.73079286] Reward 0.23079286217115347 | |
Action 1 State [0.83079286] Reward 0.33079286217115345 | |
Action 0 State [0.74328571] Reward 0.2432857087311785 | |
Action 1 State [0.84328571] Reward 0.3432857087311785 | |
Action 0 State [0.70352164] Reward 0.2035216376139597 | |
Action 1 State [0.80352164] Reward 0.30352163761395967 | |
Action 0 State [0.62891787] Reward 0.12891787445354774 | |
Action 1 State [0.72891787] Reward 0.22891787445354772 | |
Action 1 State [0.82891787] Reward 0.3289178744535477 | |
Action 0 State [0.68588524] Reward 0.18588523518842448 | |
Action 1 State [0.78588524] Reward 0.28588523518842446 | |
Action 0 State [0.64025525] Reward 0.1402552464566691 | |
Action 1 State [0.74025525] Reward 0.24025524645666907 | |
Action 1 State [0.84025525] Reward 0.34025524645666905 | |
Action 0 State [0.69610934] Reward 0.1961093386694157 | |
Action 1 State [0.79610934] Reward 0.2961093386694157 | |
Action 0 State [0.75839031] Reward 0.2583903145212957 | |
Action 0 State [0.73074954] Reward 0.2307495383533964 | |
Action 1 State [0.83074954] Reward 0.3307495383533964 | |
Action 0 State [0.67025136] Reward 0.1702513617939676 | |
Action 1 State [0.77025136] Reward 0.2702513617939676 | |
Action 0 State [0.58978012] Reward 0.08978011801624852 | |
Action 1 State [0.68978012] Reward 0.1897801180162485 | |
Action 1 State [0.78978012] Reward 0.2897801180162485 | |
Action 0 State [0.6768525] Reward 0.17685249793333757 | |
Action 1 State [0.7768525] Reward 0.27685249793333755 | |
Action 0 State [0.72216576] Reward 0.2221657613633553 | |
Action 1 State [0.82216576] Reward 0.3221657613633553 | |
Action 0 State [0.64948023] Reward 0.14948023403695987 | |
Action 1 State [0.74948023] Reward 0.24948023403695985 | |
Action 1 State [0.84948023] Reward 0.3494802340369598 | |
Action 0 State [0.70819522] Reward 0.20819521628957172 | |
Action 1 State [0.80819522] Reward 0.3081952162895717 | |
Action 0 State [0.62238668] Reward 0.12238668275020337 | |
Action 1 State [0.72238668] Reward 0.22238668275020335 | |
Action 1 State [0.82238668] Reward 0.3223866827502033 | |
Action 0 State [0.76930504] Reward 0.2693050444240135 | |
Action 0 State [0.61715123] Reward 0.11715122609858564 | |
Action 1 State [0.71715123] Reward 0.21715122609858561 | |
Action 1 State [0.81715123] Reward 0.3171512260985856 | |
Action 0 State [0.81398294] Reward 0.3139829374647981 | |
Action 0 State [0.67747418] Reward 0.17747417551824385 | |
Action 1 State [0.77747418] Reward 0.2774741755182438 | |
Action 0 State [0.76345937] Reward 0.263459374136535 | |
Action 0 State [0.59575646] Reward 0.09575646233872481 | |
Action 1 State [0.69575646] Reward 0.1957564623387248 | |
Action 1 State [0.79575646] Reward 0.29575646233872477 | |
Action 0 State [0.76299287] Reward 0.26299287498068413 | |
Action 0 State [0.57306208] Reward 0.07306207894102701 | |
Action 1 State [0.67306208] Reward 0.173062078941027 | |
Action 1 State [0.77306208] Reward 0.27306207894102696 | |
Action 0 State [0.62214107] Reward 0.12214107324793011 | |
Action 1 State [0.72214107] Reward 0.2221410732479301 | |
Action 1 State [0.82214107] Reward 0.32214107324793007 | |
Action 0 State [0.76632764] Reward 0.2663276390996 | |
Action 0 State [0.60125042] Reward 0.10125041713751204 | |
Action 1 State [0.70125042] Reward 0.20125041713751202 | |
Action 1 State [0.80125042] Reward 0.301250417137512 | |
Action 0 State [0.74720586] Reward 0.24720585803004924 | |
Action 1 State [0.84720586] Reward 0.3472058580300492 | |
Action 0 State [0.6741194] Reward 0.17411940322341457 | |
Action 1 State [0.7741194] Reward 0.27411940322341455 | |
Action 0 State [0.66760954] Reward 0.1676095353656899 | |
Action 1 State [0.76760954] Reward 0.2676095353656899 | |
Action 0 State [0.68351361] Reward 0.18351360537026729 | |
Action 1 State [0.78351361] Reward 0.28351360537026726 | |
Action 0 State [0.76167082] Reward 0.26167082244064077 | |
Action 0 State [0.75785939] Reward 0.25785938759010285 | |
Action 0 State [0.66814515] Reward 0.16814515251313444 | |
Action 1 State [0.76814515] Reward 0.2681451525131344 | |
Action 0 State [0.60072686] Reward 0.10072686208971526 | |
Action 1 State [0.70072686] Reward 0.20072686208971524 | |
Action 1 State [0.80072686] Reward 0.3007268620897152 | |
Action 0 State [0.66194095] Reward 0.16194094524810176 | |
Action 1 State [0.76194095] Reward 0.26194094524810174 | |
Action 0 State [0.56916617] Reward 0.06916616837564071 | |
Action 1 State [0.66916617] Reward 0.1691661683756407 | |
Action 1 State [0.76916617] Reward 0.26916616837564067 | |
Action 0 State [0.75772103] Reward 0.2577210288258076 | |
Action 0 State [0.57137418] Reward 0.07137417867037232 | |
Action 1 State [0.67137418] Reward 0.1713741786703723 | |
Action 1 State [0.77137418] Reward 0.2713741786703723 | |
Action 0 State [0.57730004] Reward 0.07730004123367384 | |
Action 1 State [0.67730004] Reward 0.17730004123367382 | |
Action 1 State [0.77730004] Reward 0.2773000412336738 | |
Action 0 State [0.77611563] Reward 0.2761156349684746 | |
Action 0 State [0.62372009] Reward 0.1237200895410897 | |
Action 1 State [0.72372009] Reward 0.22372008954108968 | |
Action 1 State [0.82372009] Reward 0.32372008954108966 | |
Action 0 State [0.63826386] Reward 0.13826385762184001 | |
Action 1 State [0.73826386] Reward 0.23826385762184 | |
Action 1 State [0.83826386] Reward 0.33826385762183997 | |
Action 0 State [0.73495772] Reward 0.23495771756888728 | |
Action 1 State [0.83495772] Reward 0.33495771756888726 | |
Action 0 State [0.63587434] Reward 0.13587433785483305 | |
Action 1 State [0.73587434] Reward 0.23587433785483303 | |
Action 1 State [0.83587434] Reward 0.335874337854833 | |
Action 0 State [0.64045007] Reward 0.14045006614520683 | |
Action 1 State [0.74045007] Reward 0.2404500661452068 | |
Action 1 State [0.84045007] Reward 0.3404500661452068 | |
Action 0 State [0.73202505] Reward 0.2320250525954065 | |
Action 1 State [0.83202505] Reward 0.3320250525954065 | |
Action 0 State [0.70500961] Reward 0.2050096073613712 | |
Action 1 State [0.80500961] Reward 0.30500960736137117 | |
Action 0 State [0.70792548] Reward 0.20792548335606864 | |
Action 1 State [0.80792548] Reward 0.3079254833560686 | |
Action 0 State [0.70999435] Reward 0.20999434902419645 | |
Action 1 State [0.80999435] Reward 0.3099943490241964 | |
Action 0 State [0.7487345] Reward 0.24873449789403723 | |
Action 1 State [0.8487345] Reward 0.3487344978940372 | |
Action 0 State [0.82958042] Reward 0.3295804150199111 | |
Action 0 State [0.74344316] Reward 0.24344316459501458 | |
Action 1 State [0.84344316] Reward 0.34344316459501456 | |
Action 0 State [0.8134487] Reward 0.31344870258375246 | |
Action 0 State [0.74897361] Reward 0.24897360560029103 | |
Action 1 State [0.84897361] Reward 0.348973605600291 | |
Action 0 State [0.74400032] Reward 0.2440003218358231 | |
Action 1 State [0.84400032] Reward 0.3440003218358231 | |
Action 0 State [0.82019658] Reward 0.32019657825428294 | |
Action 0 State [0.79311874] Reward 0.29311874288676 | |
Action 0 State [0.76482599] Reward 0.26482598887139164 | |
Action 0 State [0.69010272] Reward 0.190102715917167 | |
Action 1 State [0.79010272] Reward 0.29010271591716696 | |
Action 0 State [0.63555474] Reward 0.13555473786562244 | |
Action 1 State [0.73555474] Reward 0.23555473786562242 | |
Action 1 State [0.83555474] Reward 0.3355547378656224 | |
Action 0 State [0.65898042] Reward 0.15898042132279866 | |
Action 1 State [0.75898042] Reward 0.25898042132279864 | |
Action 0 State [0.70344657] Reward 0.20344656973764363 | |
Action 1 State [0.80344657] Reward 0.3034465697376436 | |
Action 0 State [0.71721727] Reward 0.21721726854916146 | |
Action 1 State [0.81721727] Reward 0.31721726854916144 | |
Action 0 State [0.70413083] Reward 0.20413083107077323 | |
Action 1 State [0.80413083] Reward 0.3041308310707732 | |
Action 0 State [0.6679639] Reward 0.16796390209744683 | |
Action 1 State [0.7679639] Reward 0.2679639020974468 | |
Action 0 State [0.60120799] Reward 0.10120798595967373 | |
Action 1 State [0.70120799] Reward 0.2012079859596737 | |
Action 1 State [0.80120799] Reward 0.3012079859596737 | |
Action 0 State [0.60834305] Reward 0.10834304643780379 | |
Action 1 State [0.70834305] Reward 0.20834304643780377 | |
Action 1 State [0.80834305] Reward 0.30834304643780375 | |
Action 0 State [0.65035034] Reward 0.15035034008824633 | |
Action 1 State [0.75035034] Reward 0.2503503400882463 | |
Action 0 State [0.56347318] Reward 0.06347318438540994 | |
Action 1 State [0.66347318] Reward 0.16347318438540992 | |
Action 1 State [0.76347318] Reward 0.2634731843854099 | |
Action 0 State [0.71879727] Reward 0.21879727389929404 | |
Action 1 State [0.81879727] Reward 0.318797273899294 | |
Action 0 State [0.74208416] Reward 0.24208415991724253 | |
Action 1 State [0.84208416] Reward 0.3420841599172425 | |
Action 0 State [0.74492256] Reward 0.2449225647484009 | |
Action 1 State [0.84492256] Reward 0.3449225647484009 | |
Action 0 State [0.80104783] Reward 0.301047830533295 | |
Action 0 State [0.79461073] Reward 0.2946107317693678 | |
Action 0 State [0.64013008] Reward 0.1401300846185599 | |
Action 1 State [0.74013008] Reward 0.2401300846185599 | |
Action 1 State [0.84013008] Reward 0.34013008461855987 | |
Action 0 State [0.78313176] Reward 0.2831317550451561 | |
Action 0 State [0.60265268] Reward 0.10265268096479963 | |
Action 1 State [0.70265268] Reward 0.2026526809647996 | |
Action 1 State [0.80265268] Reward 0.3026526809647996 | |
Action 0 State [0.66189897] Reward 0.16189897237146944 | |
Action 1 State [0.76189897] Reward 0.2618989723714694 | |
Action 0 State [0.5960428] Reward 0.09604279771702551 | |
Action 1 State [0.6960428] Reward 0.19604279771702549 | |
Action 1 State [0.7960428] Reward 0.29604279771702546 | |
Action 0 State [0.75917895] Reward 0.2591789544121482 | |
Action 0 State [0.56469614] Reward 0.06469613898095161 | |
Action 1 State [0.66469614] Reward 0.1646961389809516 | |
Action 1 State [0.76469614] Reward 0.26469613898095157 | |
Action 0 State [0.60398577] Reward 0.10398576869310427 | |
Action 1 State [0.70398577] Reward 0.20398576869310425 | |
Action 1 State [0.80398577] Reward 0.30398576869310423 | |
Action 0 State [0.70640832] Reward 0.2064083234110572 | |
Action 1 State [0.80640832] Reward 0.30640832341105717 | |
Action 0 State [0.7770651] Reward 0.2770651003630803 | |
Action 0 State [0.64420899] Reward 0.14420899354161743 | |
Action 1 State [0.74420899] Reward 0.2442089935416174 | |
Action 1 State [0.84420899] Reward 0.3442089935416174 | |
Action 0 State [0.76357627] Reward 0.26357627265890826 | |
Action 0 State [0.65527365] Reward 0.15527364594769066 | |
Action 1 State [0.75527365] Reward 0.25527364594769064 | |
Action 0 State [0.64679327] Reward 0.14679327424300348 | |
Action 1 State [0.74679327] Reward 0.24679327424300346 | |
Action 1 State [0.84679327] Reward 0.34679327424300344 | |
Action 0 State [0.66586791] Reward 0.16586791331688167 | |
Action 1 State [0.76586791] Reward 0.26586791331688164 | |
Action 0 State [0.74540667] Reward 0.24540667086162127 | |
Action 1 State [0.84540667] Reward 0.34540667086162125 | |
Action 0 State [0.81241124] Reward 0.3124112351696585 | |
Action 0 State [0.74189377] Reward 0.24189377466017237 | |
Action 1 State [0.84189377] Reward 0.34189377466017234 | |
Action 0 State [0.65249108] Reward 0.15249108389400268 | |
Action 1 State [0.75249108] Reward 0.25249108389400265 | |
Action 0 State [0.70300702] Reward 0.2030070158617142 | |
Action 1 State [0.80300702] Reward 0.3030070158617142 | |
Action 0 State [0.6829568] Reward 0.18295679706010903 | |
Action 1 State [0.7829568] Reward 0.282956797060109 | |
Action 0 State [0.59967734] Reward 0.09967734295110542 | |
Action 1 State [0.69967734] Reward 0.1996773429511054 | |
Action 1 State [0.79967734] Reward 0.2996773429511054 | |
Action 0 State [0.67116412] Reward 0.171164119072733 | |
Action 1 State [0.77116412] Reward 0.27116411907273297 | |
Action 0 State [0.75811345] Reward 0.25811344815932036 | |
Action 0 State [0.68260592] Reward 0.18260591522935354 | |
Action 1 State [0.78260592] Reward 0.2826059152293535 | |
Action 0 State [0.63383106] Reward 0.13383105891032654 | |
Action 1 State [0.73383106] Reward 0.23383105891032652 | |
Action 1 State [0.83383106] Reward 0.3338310589103265 | |
Action 0 State [0.80854176] Reward 0.30854175639200443 | |
Action 0 State [0.80321093] Reward 0.30321092738560684 | |
Action 0 State [0.63351625] Reward 0.1335162476019376 | |
Action 1 State [0.73351625] Reward 0.23351624760193757 | |
Action 1 State [0.83351625] Reward 0.33351624760193754 | |
Action 0 State [0.64865782] Reward 0.1486578215996509 | |
Action 1 State [0.74865782] Reward 0.24865782159965089 | |
Action 1 State [0.84865782] Reward 0.34865782159965086 | |
Action 0 State [0.69361161] Reward 0.19361160714043257 | |
Action 1 State [0.79361161] Reward 0.29361160714043255 | |
Action 0 State [0.65965716] Reward 0.15965716341928737 | |
Action 1 State [0.75965716] Reward 0.25965716341928735 | |
Action 0 State [0.68632989] Reward 0.1863298949573421 | |
Action 1 State [0.78632989] Reward 0.28632989495734207 | |
Action 0 State [0.65973908] Reward 0.15973908495329425 | |
Action 1 State [0.75973908] Reward 0.25973908495329423 | |
Action 0 State [0.70372297] Reward 0.20372297346937152 | |
Action 1 State [0.80372297] Reward 0.3037229734693715 | |
Action 0 State [0.62416804] Reward 0.12416804474001641 | |
Action 1 State [0.72416804] Reward 0.2241680447400164 | |
Action 1 State [0.82416804] Reward 0.32416804474001637 | |
Action 0 State [0.65818146] Reward 0.15818145768829617 | |
Action 1 State [0.75818146] Reward 0.25818145768829615 | |
Action 0 State [0.69462606] Reward 0.194626059462786 | |
Action 1 State [0.79462606] Reward 0.29462605946278597 | |
Action 0 State [0.62574628] Reward 0.12574627701638796 | |
Action 1 State [0.72574628] Reward 0.22574627701638794 | |
Action 1 State [0.82574628] Reward 0.3257462770163879 | |
Action 0 State [0.63067983] Reward 0.1306798251070337 | |
Action 1 State [0.73067983] Reward 0.23067982510703366 | |
Action 1 State [0.83067983] Reward 0.33067982510703364 | |
Action 0 State [0.81736391] Reward 0.31736390796588265 | |
Action 0 State [0.77349115] Reward 0.27349115429860227 | |
Action 0 State [0.59280482] Reward 0.09280481707027666 | |
Action 1 State [0.69280482] Reward 0.19280481707027664 | |
Action 1 State [0.79280482] Reward 0.2928048170702766 | |
Action 0 State [0.65919172] Reward 0.1591917191217198 | |
Action 1 State [0.75919172] Reward 0.2591917191217198 | |
Action 0 State [0.59676066] Reward 0.09676066162496766 | |
Action 1 State [0.69676066] Reward 0.19676066162496764 | |
Action 1 State [0.79676066] Reward 0.2967606616249676 | |
Action 0 State [0.61255782] Reward 0.11255781569226353 | |
Action 1 State [0.71255782] Reward 0.2125578156922635 | |
Action 1 State [0.81255782] Reward 0.3125578156922635 | |
Action 0 State [0.64023409] Reward 0.14023408733159248 | |
Action 1 State [0.74023409] Reward 0.24023408733159246 | |
Action 1 State [0.84023409] Reward 0.34023408733159244 | |
Action 0 State [0.65001509] Reward 0.1500150905808011 | |
Action 1 State [0.75001509] Reward 0.25001509058080107 | |
Action 0 State [0.72904419] Reward 0.22904418722207176 | |
Action 1 State [0.82904419] Reward 0.32904418722207174 | |
Action 0 State [0.68234946] Reward 0.18234945785444578 | |
Action 1 State [0.78234946] Reward 0.28234945785444576 | |
Action 0 State [0.72197946] Reward 0.22197945543282616 | |
Action 1 State [0.82197946] Reward 0.32197945543282613 | |
Action 0 State [0.77623784] Reward 0.2762378354536861 | |
Action 0 State [0.65778528] Reward 0.1577852779497172 | |
Action 1 State [0.75778528] Reward 0.2577852779497172 | |
Action 0 State [0.57873693] Reward 0.07873693000006976 | |
Action 1 State [0.67873693] Reward 0.17873693000006974 | |
Action 1 State [0.77873693] Reward 0.2787369300000697 | |
Action 0 State [0.75058028] Reward 0.2505802782766229 | |
Action 0 State [0.68211519] Reward 0.18211518981754737 | |
Action 1 State [0.78211519] Reward 0.28211518981754735 | |
Action 0 State [0.68476083] Reward 0.18476083345298866 | |
Action 1 State [0.78476083] Reward 0.28476083345298864 | |
Action 0 State [0.72894813] Reward 0.228948132460833 | |
Action 1 State [0.82894813] Reward 0.328948132460833 | |
Action 0 State [0.70079462] Reward 0.20079462153259797 | |
Action 1 State [0.80079462] Reward 0.30079462153259795 | |
Action 0 State [0.69774803] Reward 0.19774802820631088 | |
Action 1 State [0.79774803] Reward 0.29774802820631086 | |
Action 0 State [0.76156451] Reward 0.2615645149885911 | |
Action 0 State [0.68403745] Reward 0.18403745106049907 | |
Action 1 State [0.78403745] Reward 0.28403745106049905 | |
Action 0 State [0.77626505] Reward 0.276265052737911 | |
Action 0 State [0.65265756] Reward 0.1526575594755213 | |
Action 1 State [0.75265756] Reward 0.25265755947552127 | |
Action 0 State [0.73187876] Reward 0.23187875670543634 | |
Action 1 State [0.83187876] Reward 0.3318787567054363 | |
Action 0 State [0.7320505] Reward 0.23205049503949748 | |
Action 1 State [0.8320505] Reward 0.33205049503949746 | |
Action 0 State [0.67610024] Reward 0.1761002366923018 | |
Action 1 State [0.77610024] Reward 0.27610023669230177 | |
Action 0 State [0.75647269] Reward 0.2564726853215721 | |
Action 0 State [0.57270868] Reward 0.07270868028545296 | |
Action 1 State [0.67270868] Reward 0.17270868028545294 | |
Action 1 State [0.77270868] Reward 0.2727086802854529 | |
Action 0 State [0.58107461] Reward 0.08107461352556367 | |
Action 1 State [0.68107461] Reward 0.18107461352556364 | |
Action 1 State [0.78107461] Reward 0.2810746135255636 | |
Action 0 State [0.64583416] Reward 0.1458341568723921 | |
Action 1 State [0.74583416] Reward 0.24583415687239207 | |
Action 1 State [0.84583416] Reward 0.34583415687239205 | |
Action 0 State [0.66467031] Reward 0.16467031171955038 | |
Action 1 State [0.76467031] Reward 0.26467031171955036 | |
Action 0 State [0.68652265] Reward 0.18652265043161076 | |
Action 1 State [0.78652265] Reward 0.28652265043161074 | |
Action 0 State [0.78243737] Reward 0.282437372499878 | |
Action 0 State [0.61939025] Reward 0.11939024702554024 | |
Action 1 State [0.71939025] Reward 0.21939024702554022 | |
Action 1 State [0.81939025] Reward 0.3193902470255402 | |
Action 0 State [0.79974881] Reward 0.29974880832739437 | |
Action 0 State [0.70040854] Reward 0.2004085421977253 | |
Action 1 State [0.80040854] Reward 0.3004085421977253 | |
Action 0 State [0.75658328] Reward 0.25658327743004194 | |
Action 0 State [0.60824443] Reward 0.10824442767117592 | |
Action 1 State [0.70824443] Reward 0.2082444276711759 | |
Action 1 State [0.80824443] Reward 0.3082444276711759 | |
Action 0 State [0.71156308] Reward 0.21156307755717252 | |
Action 1 State [0.81156308] Reward 0.3115630775571725 | |
Action 0 State [0.77450083] Reward 0.2745008326857932 | |
Action 0 State [0.6331778] Reward 0.13317780235928978 | |
Action 1 State [0.7331778] Reward 0.23317780235928975 | |
Action 1 State [0.8331778] Reward 0.33317780235928973 | |
Action 0 State [0.65855203] Reward 0.158552032717709 | |
Action 1 State [0.75855203] Reward 0.258552032717709 | |
Action 0 State [0.59892952] Reward 0.09892952232032703 | |
Action 1 State [0.69892952] Reward 0.198929522320327 | |
Action 1 State [0.79892952] Reward 0.298929522320327 | |
Action 0 State [0.66713222] Reward 0.16713222128314786 | |
Action 1 State [0.76713222] Reward 0.26713222128314784 | |
Action 0 State [0.75737107] Reward 0.2573710687123596 | |
Action 0 State [0.73673281] Reward 0.2367328060968047 | |
Action 1 State [0.83673281] Reward 0.33673280609680467 | |
Action 0 State [0.739705] Reward 0.2397049986533547 | |
Action 1 State [0.839705] Reward 0.3397049986533547 | |
Action 0 State [0.65357742] Reward 0.15357742138393127 | |
Action 1 State [0.75357742] Reward 0.25357742138393125 | |
Action 0 State [0.55912152] Reward 0.0591215229661588 | |
Action 1 State [0.65912152] Reward 0.15912152296615878 | |
Action 1 State [0.75912152] Reward 0.25912152296615876 | |
Action 0 State [0.74165665] Reward 0.24165665208688647 | |
Action 1 State [0.84165665] Reward 0.34165665208688645 | |
Action 0 State [0.70558269] Reward 0.2055826865797027 | |
Action 1 State [0.80558269] Reward 0.30558268657970267 | |
Action 0 State [0.60686051] Reward 0.10686050611140319 | |
Action 1 State [0.70686051] Reward 0.20686050611140316 | |
Action 1 State [0.80686051] Reward 0.30686050611140314 | |
Action 0 State [0.63607115] Reward 0.1360711503497103 | |
Action 1 State [0.73607115] Reward 0.23607115034971027 | |
Action 1 State [0.83607115] Reward 0.33607115034971025 | |
Action 0 State [0.75506662] Reward 0.25506662447479933 | |
Action 0 State [0.66915478] Reward 0.16915478478294588 | |
Action 1 State [0.76915478] Reward 0.26915478478294586 | |
Action 0 State [0.76067139] Reward 0.26067139321335786 | |
Action 0 State [0.66327922] Reward 0.16327922291641406 | |
Action 1 State [0.76327922] Reward 0.26327922291641404 | |
Action 0 State [0.74282997] Reward 0.24282997060903744 | |
Action 1 State [0.84282997] Reward 0.3428299706090374 | |
Action 0 State [0.72092786] Reward 0.22092786467875158 | |
Action 1 State [0.82092786] Reward 0.32092786467875156 | |
Action 0 State [0.64479509] Reward 0.14479508959087906 | |
Action 1 State [0.74479509] Reward 0.24479508959087903 | |
Action 1 State [0.84479509] Reward 0.344795089590879 | |
Action 0 State [0.75230762] Reward 0.2523076227337505 | |
Action 0 State [0.55912337] Reward 0.0591233734564367 | |
Action 1 State [0.65912337] Reward 0.15912337345643668 | |
Action 1 State [0.75912337] Reward 0.25912337345643666 | |
Action 0 State [0.62711808] Reward 0.12711807617789472 | |
Action 1 State [0.72711808] Reward 0.2271180761778947 | |
Action 1 State [0.82711808] Reward 0.3271180761778947 | |
Action 0 State [0.75942163] Reward 0.25942162557711024 | |
Action 0 State [0.61592584] Reward 0.11592583678053248 | |
Action 1 State [0.71592584] Reward 0.21592583678053245 | |
Action 1 State [0.81592584] Reward 0.31592583678053243 | |
Action 0 State [0.68602882] Reward 0.18602881822562933 | |
Action 1 State [0.78602882] Reward 0.2860288182256293 | |
Action 0 State [0.68973291] Reward 0.1897329096756708 | |
Action 1 State [0.78973291] Reward 0.2897329096756708 | |
Action 0 State [0.63562] Reward 0.13561999941232572 | |
Action 1 State [0.73562] Reward 0.2356199994123257 | |
Action 1 State [0.83562] Reward 0.3356199994123257 | |
Action 0 State [0.8034591] Reward 0.3034590983061721 | |
Action 0 State [0.7339166] Reward 0.23391660169471218 | |
Action 1 State [0.8339166] Reward 0.33391660169471216 | |
Action 0 State [0.73537512] Reward 0.23537512494579338 | |
Action 1 State [0.83537512] Reward 0.33537512494579336 | |
Action 0 State [0.79036006] Reward 0.29036005841537704 | |
Action 0 State [0.60549295] Reward 0.10549295160742467 | |
Action 1 State [0.70549295] Reward 0.20549295160742465 | |
Action 1 State [0.80549295] Reward 0.3054929516074246 | |
Action 0 State [0.71520956] Reward 0.2152095643034 | |
Action 1 State [0.81520956] Reward 0.31520956430339997 | |
Action 0 State [0.74372272] Reward 0.24372271762360198 | |
Action 1 State [0.84372272] Reward 0.34372271762360196 | |
Action 0 State [0.82450733] Reward 0.3245073277113597 | |
Action 0 State [0.77757727] Reward 0.2775772695360931 | |
Action 0 State [0.74521211] Reward 0.24521211365045636 | |
Action 1 State [0.84521211] Reward 0.34521211365045634 | |
Action 0 State [0.74466554] Reward 0.24466553777759392 | |
Action 1 State [0.84466554] Reward 0.3446655377775939 | |
Action 0 State [0.77197828] Reward 0.2719782836444683 | |
Action 0 State [0.76356807] Reward 0.263568072878932 | |
Action 0 State [0.7186635] Reward 0.2186634962214431 | |
Action 1 State [0.8186635] Reward 0.3186634962214431 | |
Action 0 State [0.7215992] Reward 0.22159920047300286 | |
Action 1 State [0.8215992] Reward 0.32159920047300283 | |
Action 0 State [0.79019055] Reward 0.2901905514890283 | |
Action 0 State [0.78207547] Reward 0.2820754728808772 | |
Action 0 State [0.77179504] Reward 0.27179504261136045 | |
Action 0 State [0.76393086] Reward 0.2639308588552114 | |
Action 0 State [0.63742174] Reward 0.13742173766647292 | |
Action 1 State [0.73742174] Reward 0.2374217376664729 | |
Action 1 State [0.83742174] Reward 0.3374217376664729 | |
Action 0 State [0.67343646] Reward 0.17343646059637907 | |
Action 1 State [0.77343646] Reward 0.27343646059637905 | |
Action 0 State [0.61502438] Reward 0.11502437760433393 | |
Action 1 State [0.71502438] Reward 0.2150243776043339 | |
Action 1 State [0.81502438] Reward 0.3150243776043339 | |
Action 0 State [0.76390269] Reward 0.263902685776051 | |
Action 0 State [0.74482637] Reward 0.2448263676838235 | |
Action 1 State [0.84482637] Reward 0.34482636768382346 | |
Action 0 State [0.7694649] Reward 0.26946489944826535 | |
Action 0 State [0.76248757] Reward 0.2624875664015007 | |
Action 0 State [0.70465201] Reward 0.20465200723946853 | |
Action 1 State [0.80465201] Reward 0.3046520072394685 | |
Action 0 State [0.62209974] Reward 0.12209973546306085 | |
Action 1 State [0.72209974] Reward 0.22209973546306083 | |
Action 1 State [0.82209974] Reward 0.3220997354630608 | |
Action 0 State [0.66599251] Reward 0.16599251473026921 | |
Action 1 State [0.76599251] Reward 0.2659925147302692 | |
Action 0 State [0.59487794] Reward 0.09487793974870073 | |
Action 1 State [0.69487794] Reward 0.1948779397487007 | |
Action 1 State [0.79487794] Reward 0.2948779397487007 | |
Action 0 State [0.72296613] Reward 0.22296612917186553 | |
Action 1 State [0.82296613] Reward 0.3229661291718655 | |
Action 0 State [0.74269961] Reward 0.24269961137126472 | |
Action 1 State [0.84269961] Reward 0.3426996113712647 | |
Action 0 State [0.69819564] Reward 0.19819563739597923 | |
Action 1 State [0.79819564] Reward 0.2981956373959792 | |
Action 0 State [0.74750402] Reward 0.2475040151330289 | |
Action 1 State [0.84750402] Reward 0.34750401513302887 | |
Action 0 State [0.70445079] Reward 0.20445078922757376 | |
Action 1 State [0.80445079] Reward 0.30445078922757374 | |
Action 0 State [0.68957738] Reward 0.18957737755059934 | |
Action 1 State [0.78957738] Reward 0.2895773775505993 | |
Action 0 State [0.76424432] Reward 0.26424431860535613 | |
Action 0 State [0.64449101] Reward 0.14449101350654647 | |
Action 1 State [0.74449101] Reward 0.24449101350654645 | |
Action 1 State [0.84449101] Reward 0.34449101350654643 | |
Action 0 State [0.83039887] Reward 0.3303988732718234 | |
Action 0 State [0.63234062] Reward 0.13234061793757534 | |
Action 1 State [0.73234062] Reward 0.23234061793757532 | |
Action 1 State [0.83234062] Reward 0.3323406179375753 | |
Action 0 State [0.77755134] Reward 0.277551337122927 | |
Action 0 State [0.67871488] Reward 0.1787148768990402 | |
Action 1 State [0.77871488] Reward 0.2787148768990402 | |
Action 0 State [0.69402793] Reward 0.194027932858303 | |
Action 1 State [0.79402793] Reward 0.294027932858303 | |
Action 0 State [0.63860907] Reward 0.13860906854033284 | |
Action 1 State [0.73860907] Reward 0.2386090685403328 | |
Action 1 State [0.83860907] Reward 0.3386090685403328 | |
Action 0 State [0.76880385] Reward 0.2688038450187863 | |
Action 0 State [0.76279602] Reward 0.26279602497388777 | |
Action 0 State [0.7110586] Reward 0.2110586005928381 | |
Action 1 State [0.8110586] Reward 0.3110586005928381 | |
Action 0 State [0.65660392] Reward 0.1566039216868318 | |
Action 1 State [0.75660392] Reward 0.25660392168683177 | |
Action 0 State [0.6566265] Reward 0.1566264971873832 | |
Action 1 State [0.7566265] Reward 0.2566264971873832 | |
Action 0 State [0.5976312] Reward 0.09763119552645638 | |
Action 1 State [0.6976312] Reward 0.19763119552645636 | |
Action 1 State [0.7976312] Reward 0.29763119552645634 | |
Action 0 State [0.60209751] Reward 0.10209751202662343 | |
Action 1 State [0.70209751] Reward 0.2020975120266234 | |
Action 1 State [0.80209751] Reward 0.3020975120266234 | |
Action 0 State [0.78687783] Reward 0.28687783081943385 | |
Action 0 State [0.69569688] Reward 0.19569687773849154 | |
Action 1 State [0.79569688] Reward 0.2956968777384915 | |
Action 0 State [0.77805605] Reward 0.27805605293064595 | |
Action 0 State [0.74946055] Reward 0.24946055481031648 | |
Action 1 State [0.84946055] Reward 0.34946055481031646 | |
Action 0 State [0.78363049] Reward 0.2836304866365993 | |
Action 0 State [0.58663497] Reward 0.08663497394513342 | |
Action 1 State [0.68663497] Reward 0.1866349739451334 | |
Action 1 State [0.78663497] Reward 0.2866349739451334 | |
Action 0 State [0.64691416] Reward 0.14691416186602257 | |
Action 1 State [0.74691416] Reward 0.24691416186602255 | |
Action 1 State [0.84691416] Reward 0.34691416186602253 | |
Action 0 State [0.7197872] Reward 0.21978719961987303 | |
Action 1 State [0.8197872] Reward 0.319787199619873 | |
Action 0 State [0.8176314] Reward 0.31763140316041616 | |
Action 0 State [0.64105288] Reward 0.14105287574330994 | |
Action 1 State [0.74105288] Reward 0.2410528757433099 | |
Action 1 State [0.84105288] Reward 0.3410528757433099 | |
Action 0 State [0.78341891] Reward 0.28341891419889154 | |
Action 0 State [0.61604621] Reward 0.11604621490440603 | |
Action 1 State [0.71604621] Reward 0.216046214904406 | |
Action 1 State [0.81604621] Reward 0.316046214904406 | |
Action 0 State [0.64645841] Reward 0.14645841167577678 | |
Action 1 State [0.74645841] Reward 0.24645841167577676 | |
Action 1 State [0.84645841] Reward 0.34645841167577673 | |
Action 0 State [0.79742505] Reward 0.2974250547352948 | |
Action 0 State [0.66298624] Reward 0.1629862356402232 | |
Action 1 State [0.76298624] Reward 0.26298623564022316 | |
Action 0 State [0.59941591] Reward 0.0994159050093173 | |
Action 1 State [0.69941591] Reward 0.19941590500931727 | |
Action 1 State [0.79941591] Reward 0.29941590500931725 | |
Action 0 State [0.60545482] Reward 0.10545481811172952 | |
Action 1 State [0.70545482] Reward 0.2054548181117295 | |
Action 1 State [0.80545482] Reward 0.3054548181117295 | |
Action 0 State [0.76599005] Reward 0.26599004657511005 | |
Action 0 State [0.62281956] Reward 0.12281955741753137 | |
Action 1 State [0.72281956] Reward 0.22281955741753134 | |
Action 1 State [0.82281956] Reward 0.3228195574175313 | |
Action 0 State [0.72848317] Reward 0.22848316900083687 | |
Action 1 State [0.82848317] Reward 0.32848316900083685 | |
Action 0 State [0.65133052] Reward 0.1513305228297268 | |
Action 1 State [0.75133052] Reward 0.2513305228297268 | |
Action 0 State [0.66934941] Reward 0.16934941008308801 | |
Action 1 State [0.76934941] Reward 0.269349410083088 | |
Action 0 State [0.69324105] Reward 0.19324104686292998 | |
Action 1 State [0.79324105] Reward 0.29324104686292995 | |
Action 0 State [0.60668239] Reward 0.10668238719153911 | |
Action 1 State [0.70668239] Reward 0.20668238719153909 | |
Action 1 State [0.80668239] Reward 0.30668238719153906 | |
Action 0 State [0.759887] Reward 0.2598870004120536 | |
Action 0 State [0.61625197] Reward 0.11625197215732719 | |
Action 1 State [0.71625197] Reward 0.21625197215732717 | |
Action 1 State [0.81625197] Reward 0.31625197215732714 | |
Action 0 State [0.7917149] Reward 0.2917149010076957 | |
Action 0 State [0.76913503] Reward 0.2691350278212542 | |
Action 0 State [0.60034678] Reward 0.10034678408426279 | |
Action 1 State [0.70034678] Reward 0.20034678408426276 | |
Action 1 State [0.80034678] Reward 0.30034678408426274 | |
Action 0 State [0.65874086] Reward 0.15874086499624063 | |
Action 1 State [0.75874086] Reward 0.2587408649962406 | |
Action 0 State [0.72953765] Reward 0.22953765403224358 | |
Action 1 State [0.82953765] Reward 0.32953765403224355 | |
Action 0 State [0.78581922] Reward 0.2858192209419831 | |
Action 0 State [0.69648975] Reward 0.1964897457869451 | |
Action 1 State [0.79648975] Reward 0.2964897457869451 | |
Action 0 State [0.78601989] Reward 0.2860198940562707 | |
Action 0 State [0.77031811] Reward 0.27031811482700574 | |
Action 0 State [0.72557381] Reward 0.22557380642736835 | |
Action 1 State [0.82557381] Reward 0.32557380642736833 | |
Action 0 State [0.7718456] Reward 0.2718456048119152 | |
Action 0 State [0.62409335] Reward 0.12409334857342591 | |
Action 1 State [0.72409335] Reward 0.2240933485734259 | |
Action 1 State [0.82409335] Reward 0.32409334857342587 | |
Action 0 State [0.63501442] Reward 0.13501442281908216 | |
Action 1 State [0.73501442] Reward 0.23501442281908214 | |
Action 1 State [0.83501442] Reward 0.3350144228190821 | |
Action 0 State [0.66950075] Reward 0.1695007493584596 | |
Action 1 State [0.76950075] Reward 0.2695007493584596 | |
Action 0 State [0.62524331] Reward 0.12524331164277602 | |
Action 1 State [0.72524331] Reward 0.225243311642776 | |
Action 1 State [0.82524331] Reward 0.325243311642776 | |
Action 0 State [0.7835306] Reward 0.28353060025310917 | |
Action 0 State [0.77064464] Reward 0.2706446390481225 | |
Action 0 State [0.64523141] Reward 0.1452314078426291 | |
Action 1 State [0.74523141] Reward 0.2452314078426291 | |
Action 1 State [0.84523141] Reward 0.34523140784262907 | |
Action 0 State [0.77064501] Reward 0.27064501399522667 | |
Action 0 State [0.58251104] Reward 0.08251104170559698 | |
Action 1 State [0.68251104] Reward 0.18251104170559695 | |
Action 1 State [0.78251104] Reward 0.28251104170559693 | |
Action 0 State [0.7001603] Reward 0.2001602969983325 | |
Action 1 State [0.8001603] Reward 0.30016029699833247 | |
Action 0 State [0.67928401] Reward 0.1792840086881642 | |
Action 1 State [0.77928401] Reward 0.27928400868816416 | |
Action 0 State [0.74054076] Reward 0.24054075542193853 | |
Action 1 State [0.84054076] Reward 0.3405407554219385 | |
Action 0 State [0.77773768] Reward 0.27773767757737244 | |
Action 0 State [0.77262643] Reward 0.2726264252411854 | |
Action 0 State [0.57975971] Reward 0.0797597054580419 | |
Action 1 State [0.67975971] Reward 0.17975970545804187 | |
Action 1 State [0.77975971] Reward 0.27975970545804185 | |
Action 0 State [0.75186623] Reward 0.2518662254953451 | |
Action 0 State [0.60429055] Reward 0.10429055047645486 | |
Action 1 State [0.70429055] Reward 0.20429055047645484 | |
Action 1 State [0.80429055] Reward 0.3042905504764548 | |
Action 0 State [0.67945978] Reward 0.1794597774853488 | |
Action 1 State [0.77945978] Reward 0.2794597774853488 | |
Action 0 State [0.66148784] Reward 0.16148783812633882 | |
Action 1 State [0.76148784] Reward 0.2614878381263388 | |
Action 0 State [0.60020359] Reward 0.100203585014352 | |
Action 1 State [0.70020359] Reward 0.20020358501435198 | |
Action 1 State [0.80020359] Reward 0.30020358501435196 | |
Action 0 State [0.63239776] Reward 0.13239776251663837 | |
Action 1 State [0.73239776] Reward 0.23239776251663835 | |
Action 1 State [0.83239776] Reward 0.33239776251663833 | |
Action 0 State [0.79539238] Reward 0.2953923808359583 | |
Action 0 State [0.77206462] Reward 0.27206461564387674 | |
Action 0 State [0.57784174] Reward 0.07784174331833948 | |
Action 1 State [0.67784174] Reward 0.17784174331833946 | |
Action 1 State [0.77784174] Reward 0.27784174331833944 | |
Action 0 State [0.65452758] Reward 0.15452758007818979 | |
Action 1 State [0.75452758] Reward 0.25452758007818976 | |
Action 0 State [0.65728195] Reward 0.15728195254028732 | |
Action 1 State [0.75728195] Reward 0.2572819525402873 | |
Action 0 State [0.72068513] Reward 0.22068512663048478 | |
Action 1 State [0.82068513] Reward 0.32068512663048476 | |
Action 0 State [0.67291509] Reward 0.17291509088103618 | |
Action 1 State [0.77291509] Reward 0.27291509088103616 | |
Action 0 State [0.64786491] Reward 0.14786491389505307 | |
Action 1 State [0.74786491] Reward 0.24786491389505305 | |
Action 1 State [0.84786491] Reward 0.34786491389505303 | |
Action 0 State [0.76417418] Reward 0.26417417832934487 | |
Action 0 State [0.59691022] Reward 0.09691022188948595 | |
Action 1 State [0.69691022] Reward 0.19691022188948593 | |
Action 1 State [0.79691022] Reward 0.2969102218894859 | |
Action 0 State [0.63610308] Reward 0.13610307706570002 | |
Action 1 State [0.73610308] Reward 0.2361030770657 | |
Action 1 State [0.83610308] Reward 0.3361030770657 | |
Action 0 State [0.68571641] Reward 0.18571640601137596 | |
Action 1 State [0.78571641] Reward 0.28571640601137593 | |
Action 0 State [0.68297713] Reward 0.18297713046925257 | |
Action 1 State [0.78297713] Reward 0.28297713046925255 | |
Action 0 State [0.61415451] Reward 0.11415451409389166 | |
Action 1 State [0.71415451] Reward 0.21415451409389163 | |
Action 1 State [0.81415451] Reward 0.3141545140938916 | |
Action 0 State [0.63779327] Reward 0.13779326550580395 | |
Action 1 State [0.73779327] Reward 0.23779326550580393 | |
Action 1 State [0.83779327] Reward 0.3377932655058039 | |
Action 0 State [0.80228724] Reward 0.3022872410800078 | |
Action 0 State [0.69914868] Reward 0.1991486830147431 | |
Action 1 State [0.79914868] Reward 0.29914868301474307 | |
Action 0 State [0.73817608] Reward 0.2381760786318352 | |
Action 1 State [0.83817608] Reward 0.3381760786318352 | |
Action 0 State [0.78708013] Reward 0.2870801285282275 | |
Action 0 State [0.78343082] Reward 0.2834308229532473 | |
Action 0 State [0.67108462] Reward 0.17108461894208138 | |
Action 1 State [0.77108462] Reward 0.27108461894208136 | |
Action 0 State [0.76808877] Reward 0.26808876705456697 | |
Action 0 State [0.57308352] Reward 0.07308351941737057 | |
Action 1 State [0.67308352] Reward 0.17308351941737055 | |
Action 1 State [0.77308352] Reward 0.2730835194173705 | |
Action 0 State [0.58924372] Reward 0.08924372319405438 | |
Action 1 State [0.68924372] Reward 0.18924372319405436 | |
Action 1 State [0.78924372] Reward 0.28924372319405434 | |
Action 0 State [0.71989641] Reward 0.21989641063765397 | |
Action 1 State [0.81989641] Reward 0.31989641063765395 | |
Action 0 State [0.70739995] Reward 0.2073999452800177 | |
Action 1 State [0.80739995] Reward 0.3073999452800177 | |
Action 0 State [0.71492123] Reward 0.21492123486319126 | |
Action 1 State [0.81492123] Reward 0.31492123486319124 | |
Action 0 State [0.7208332] Reward 0.22083320114435556 | |
Action 1 State [0.8208332] Reward 0.32083320114435554 | |
Action 0 State [0.73656006] Reward 0.2365600559001183 | |
Action 1 State [0.83656006] Reward 0.3365600559001183 | |
Action 0 State [0.67842659] Reward 0.17842658693111169 | |
Action 1 State [0.77842659] Reward 0.27842658693111166 | |
Action 0 State [0.70517271] Reward 0.20517270518639974 | |
Action 1 State [0.80517271] Reward 0.3051727051863997 | |
Action 0 State [0.70777001] Reward 0.20777001429161956 | |
Action 1 State [0.80777001] Reward 0.30777001429161954 | |
Action 0 State [0.75255359] Reward 0.25255358824925445 | |
Action 0 State [0.68203504] Reward 0.18203504226533795 | |
Action 1 State [0.78203504] Reward 0.28203504226533793 | |
Action 0 State [0.75983258] Reward 0.2598325817087307 | |
Action 0 State [0.56878298] Reward 0.06878298309524045 | |
Action 1 State [0.66878298] Reward 0.16878298309524042 | |
Action 1 State [0.76878298] Reward 0.2687829830952404 | |
Action 0 State [0.57158365] Reward 0.07158365414621526 | |
Action 1 State [0.67158365] Reward 0.17158365414621524 | |
Action 1 State [0.77158365] Reward 0.2715836541462152 | |
Action 0 State [0.62425177] Reward 0.12425177183785674 | |
Action 1 State [0.72425177] Reward 0.22425177183785672 | |
Action 1 State [0.82425177] Reward 0.3242517718378567 | |
Action 0 State [0.80638919] Reward 0.3063891864741314 | |
Action 0 State [0.76580616] Reward 0.26580615950371045 | |
Action 0 State [0.75506123] Reward 0.25506122731998593 | |
Action 0 State [0.74252135] Reward 0.2425213476275484 | |
Action 1 State [0.84252135] Reward 0.3425213476275484 | |
Action 0 State [0.64462109] Reward 0.1446210891524654 | |
Action 1 State [0.74462109] Reward 0.2446210891524654 | |
Action 1 State [0.84462109] Reward 0.34462108915246537 | |
Action 0 State [0.67509679] Reward 0.17509678695012143 | |
Action 1 State [0.77509679] Reward 0.2750967869501214 | |
Action 0 State [0.67916322] Reward 0.17916322474240354 | |
Action 1 State [0.77916322] Reward 0.2791632247424035 | |
Action 0 State [0.62464596] Reward 0.12464595725485428 | |
Action 1 State [0.72464596] Reward 0.22464595725485426 | |
Action 1 State [0.82464596] Reward 0.32464595725485423 | |
Action 0 State [0.80960646] Reward 0.30960645630830397 | |
Action 0 State [0.70819575] Reward 0.2081957540452225 | |
Action 1 State [0.80819575] Reward 0.3081957540452225 | |
Action 0 State [0.79125045] Reward 0.2912504490258595 | |
Action 0 State [0.6869114] Reward 0.18691139599136675 | |
Action 1 State [0.7869114] Reward 0.2869113959913667 | |
Action 0 State [0.67594193] Reward 0.17594192984728296 | |
Action 1 State [0.77594193] Reward 0.27594192984728294 | |
Action 0 State [0.57780343] Reward 0.0778034299273187 | |
Action 1 State [0.67780343] Reward 0.17780342992731868 | |
Action 1 State [0.77780343] Reward 0.27780342992731866 | |
Action 0 State [0.75673699] Reward 0.256736986238021 | |
Action 0 State [0.65355736] Reward 0.1535573580896823 | |
Action 1 State [0.75355736] Reward 0.25355735808968227 | |
Action 0 State [0.68318918] Reward 0.1831891839777402 | |
Action 1 State [0.78318918] Reward 0.2831891839777402 | |
Action 0 State [0.62874634] Reward 0.1287463395006151 | |
Action 1 State [0.72874634] Reward 0.22874633950061507 | |
Action 1 State [0.82874634] Reward 0.32874633950061505 | |
Action 0 State [0.71115291] Reward 0.21115290641162587 | |
Action 1 State [0.81115291] Reward 0.31115290641162585 | |
Action 0 State [0.70787851] Reward 0.20787851431502513 | |
Action 1 State [0.80787851] Reward 0.3078785143150251 | |
Action 0 State [0.67139348] Reward 0.17139347668236238 | |
Action 1 State [0.77139348] Reward 0.27139347668236236 | |
Action 0 State [0.7479216] Reward 0.2479216039924238 | |
Action 1 State [0.8479216] Reward 0.3479216039924238 | |
Action 0 State [0.82446528] Reward 0.3244652803299658 | |
Action 0 State [0.69185627] Reward 0.19185627220946755 | |
Action 1 State [0.79185627] Reward 0.2918562722094675 | |
Action 0 State [0.73032033] Reward 0.2303203323554136 | |
Action 1 State [0.83032033] Reward 0.3303203323554136 | |
Action 0 State [0.7778348] Reward 0.2778348047505347 | |
Action 0 State [0.65081735] Reward 0.1508173511177301 | |
Action 1 State [0.75081735] Reward 0.25081735111773007 | |
Action 0 State [0.55385446] Reward 0.053854455692431524 | |
Action 1 State [0.65385446] Reward 0.1538544556924315 | |
Action 1 State [0.75385446] Reward 0.2538544556924315 | |
Action 0 State [0.66879359] Reward 0.1687935920410727 | |
Action 1 State [0.76879359] Reward 0.26879359204107267 | |
Action 0 State [0.74185867] Reward 0.24185867477650091 | |
Action 1 State [0.84185867] Reward 0.3418586747765009 | |
Action 0 State [0.80809882] Reward 0.3080988238753726 | |
Action 0 State [0.78538135] Reward 0.2853813493131625 | |
Action 0 State [0.62547143] Reward 0.1254714279188731 | |
Action 1 State [0.72547143] Reward 0.2254714279188731 | |
Action 1 State [0.82547143] Reward 0.32547142791887307 | |
Action 0 State [0.78045401] Reward 0.2804540089704012 | |
Action 0 State [0.77070044] Reward 0.27070043545820544 | |
Action 0 State [0.62378727] Reward 0.12378726870096668 | |
Action 1 State [0.72378727] Reward 0.22378726870096666 | |
Action 1 State [0.82378727] Reward 0.32378726870096664 | |
Action 0 State [0.80547995] Reward 0.3054799523575976 | |
Action 0 State [0.60905849] Reward 0.10905848872711887 | |
Action 1 State [0.70905849] Reward 0.20905848872711885 | |
Action 1 State [0.80905849] Reward 0.30905848872711883 | |
Action 0 State [0.72463157] Reward 0.22463157229397435 | |
Action 1 State [0.82463157] Reward 0.3246315722939743 | |
Action 0 State [0.67409303] Reward 0.17409302782484593 | |
Action 1 State [0.77409303] Reward 0.2740930278248459 | |
Action 0 State [0.75112361] Reward 0.2511236136489978 | |
Action 0 State [0.66436726] Reward 0.16436726339908025 | |
Action 1 State [0.76436726] Reward 0.26436726339908023 | |
Action 0 State [0.58929247] Reward 0.08929247017009334 | |
Action 1 State [0.68929247] Reward 0.18929247017009332 | |
Action 1 State [0.78929247] Reward 0.2892924701700933 | |
Action 0 State [0.64027402] Reward 0.14027401927029515 | |
Action 1 State [0.74027402] Reward 0.24027401927029512 | |
Action 1 State [0.84027402] Reward 0.3402740192702951 | |
Action 0 State [0.76334615] Reward 0.26334614762827513 | |
Action 0 State [0.71093648] Reward 0.21093647688642914 | |
Action 1 State [0.81093648] Reward 0.3109364768864291 | |
Action 0 State [0.68228485] Reward 0.18228485358058455 | |
Action 1 State [0.78228485] Reward 0.2822848535805845 | |
Action 0 State [0.73474235] Reward 0.2347423458091642 | |
Action 1 State [0.83474235] Reward 0.3347423458091642 | |
Action 0 State [0.72508075] Reward 0.22508074554938617 | |
Action 1 State [0.82508075] Reward 0.32508074554938615 | |
Action 0 State [0.78227064] Reward 0.28227063792105056 | |
Action 0 State [0.66172522] Reward 0.1617252154621367 | |
Action 1 State [0.76172522] Reward 0.2617252154621367 | |
Action 0 State [0.57410572] Reward 0.07410571869982607 | |
Action 1 State [0.67410572] Reward 0.17410571869982605 | |
Action 1 State [0.77410572] Reward 0.27410571869982603 | |
Action 0 State [0.76306586] Reward 0.2630658604070333 | |
Action 0 State [0.57463985] Reward 0.07463984622470188 | |
Action 1 State [0.67463985] Reward 0.17463984622470186 | |
Action 1 State [0.77463985] Reward 0.27463984622470183 | |
Action 0 State [0.73098796] Reward 0.23098795876082656 | |
Action 1 State [0.83098796] Reward 0.33098795876082654 | |
Action 0 State [0.75247509] Reward 0.252475090480182 | |
Action 0 State [0.67420384] Reward 0.17420383946558227 | |
Action 1 State [0.77420384] Reward 0.27420383946558224 | |
Action 0 State [0.73465302] Reward 0.23465302117778686 | |
Action 1 State [0.83465302] Reward 0.33465302117778684 | |
Action 0 State [0.66991208] Reward 0.16991207665603092 | |
Action 1 State [0.76991208] Reward 0.2699120766560309 | |
Action 0 State [0.62056932] Reward 0.1205693163625865 | |
Action 1 State [0.72056932] Reward 0.22056931636258648 | |
Action 1 State [0.82056932] Reward 0.32056931636258645 | |
Action 0 State [0.68742829] Reward 0.18742828877014117 | |
Action 1 State [0.78742829] Reward 0.28742828877014115 | |
Action 0 State [0.70238511] Reward 0.20238510681360555 | |
Action 1 State [0.80238511] Reward 0.30238510681360553 | |
Action 0 State [0.70674316] Reward 0.20674316398151227 | |
Action 1 State [0.80674316] Reward 0.30674316398151225 | |
Action 0 State [0.65799562] Reward 0.15799562407383583 | |
Action 1 State [0.75799562] Reward 0.2579956240738358 | |
Action 0 State [0.65855147] Reward 0.15855146929218678 | |
Action 1 State [0.75855147] Reward 0.25855146929218675 | |
Action 0 State [0.72682602] Reward 0.22682602379951422 | |
Action 1 State [0.82682602] Reward 0.3268260237995142 | |
Action 0 State [0.7146195] Reward 0.21461949575126904 | |
Action 1 State [0.8146195] Reward 0.314619495751269 | |
Action 0 State [0.80957282] Reward 0.30957282225426797 | |
Action 0 State [0.621736] Reward 0.12173600377926563 | |
Action 1 State [0.721736] Reward 0.2217360037792656 | |
Action 1 State [0.821736] Reward 0.3217360037792656 | |
Action 0 State [0.68889579] Reward 0.18889579327304518 | |
Action 1 State [0.78889579] Reward 0.28889579327304515 | |
Action 0 State [0.77742912] Reward 0.27742911798269865 | |
Action 0 State [0.68706695] Reward 0.187066949138752 | |
Action 1 State [0.78706695] Reward 0.28706694913875197 | |
Action 0 State [0.71619754] Reward 0.21619754411813896 | |
Action 1 State [0.81619754] Reward 0.31619754411813894 | |
Action 0 State [0.80256883] Reward 0.3025688317595693 | |
Action 0 State [0.61514274] Reward 0.11514273639127981 | |
Action 1 State [0.71514274] Reward 0.2151427363912798 | |
Action 1 State [0.81514274] Reward 0.31514273639127977 | |
Action 0 State [0.64667637] Reward 0.14667637095156327 | |
Action 1 State [0.74667637] Reward 0.24667637095156325 | |
Action 1 State [0.84667637] Reward 0.34667637095156323 | |
Action 0 State [0.66494921] Reward 0.16494920512961309 | |
Action 1 State [0.76494921] Reward 0.26494920512961306 | |
Action 0 State [0.67275931] Reward 0.17275931007485856 | |
Action 1 State [0.77275931] Reward 0.27275931007485854 | |
Action 0 State [0.59983375] Reward 0.09983374689371582 | |
Action 1 State [0.69983375] Reward 0.1998337468937158 | |
Action 1 State [0.79983375] Reward 0.2998337468937158 | |
Action 0 State [0.6207587] Reward 0.12075869767283587 | |
Action 1 State [0.7207587] Reward 0.22075869767283585 | |
Action 1 State [0.8207587] Reward 0.3207586976728358 | |
Action 0 State [0.64091746] Reward 0.14091745949270829 | |
Action 1 State [0.74091746] Reward 0.24091745949270826 | |
Action 1 State [0.84091746] Reward 0.34091745949270824 | |
Action 0 State [0.69942941] Reward 0.19942940530660203 | |
Action 1 State [0.79942941] Reward 0.299429405306602 | |
Action 0 State [0.77082119] Reward 0.2708211909803532 | |
Action 0 State [0.66031672] Reward 0.1603167185937333 | |
Action 1 State [0.76031672] Reward 0.2603167185937333 | |
Action 0 State [0.74201627] Reward 0.2420162665544775 | |
Action 1 State [0.84201627] Reward 0.3420162665544775 | |
Action 0 State [0.69258463] Reward 0.19258462867826043 | |
Action 1 State [0.79258463] Reward 0.2925846286782604 | |
Action 0 State [0.76141329] Reward 0.2614132919524056 | |
Action 0 State [0.73071756] Reward 0.23071755728888466 | |
Action 1 State [0.83071756] Reward 0.33071755728888463 | |
Action 0 State [0.74874859] Reward 0.24874859101482094 | |
Action 1 State [0.84874859] Reward 0.3487485910148209 | |
Action 0 State [0.73779813] Reward 0.23779813470949884 | |
Action 1 State [0.83779813] Reward 0.3377981347094988 | |
Action 0 State [0.68472066] Reward 0.18472065568608897 | |
Action 1 State [0.78472066] Reward 0.28472065568608895 | |
Action 0 State [0.74746208] Reward 0.24746207604663129 | |
Action 1 State [0.84746208] Reward 0.34746207604663126 | |
Action 0 State [0.8353785] Reward 0.3353785049404743 | |
Action 0 State [0.73302643] Reward 0.23302642740651813 | |
Action 1 State [0.83302643] Reward 0.3330264274065181 | |
Action 0 State [0.77410276] Reward 0.27410276024920177 | |
Action 0 State [0.6803996] Reward 0.18039959550094398 | |
Action 1 State [0.7803996] Reward 0.28039959550094395 | |
Action 0 State [0.74494007] Reward 0.24494006550803193 | |
Action 1 State [0.84494007] Reward 0.3449400655080319 | |
Action 0 State [0.75207474] Reward 0.2520747434552115 | |
Action 0 State [0.56760866] Reward 0.06760865729748133 | |
Action 1 State [0.66760866] Reward 0.1676086572974813 | |
Action 1 State [0.76760866] Reward 0.2676086572974813 | |
Action 0 State [0.57957247] Reward 0.07957247040514026 | |
Action 1 State [0.67957247] Reward 0.17957247040514024 | |
Action 1 State [0.77957247] Reward 0.2795724704051402 | |
Action 0 State [0.70595136] Reward 0.20595135522223185 | |
Action 1 State [0.80595136] Reward 0.3059513552222318 | |
Action 0 State [0.6182761] Reward 0.11827609514485438 | |
Action 1 State [0.7182761] Reward 0.21827609514485435 | |
Action 1 State [0.8182761] Reward 0.31827609514485433 | |
Action 0 State [0.7803817] Reward 0.2803816988886437 | |
Action 0 State [0.77483277] Reward 0.2748327660452915 | |
Action 0 State [0.73545587] Reward 0.23545587047819072 | |
Action 1 State [0.83545587] Reward 0.3354558704781907 | |
Action 0 State [0.80758891] Reward 0.3075889114474033 | |
Action 0 State [0.66587833] Reward 0.165878326934631 | |
Action 1 State [0.76587833] Reward 0.265878326934631 | |
Action 0 State [0.69368045] Reward 0.1936804516831644 | |
Action 1 State [0.79368045] Reward 0.29368045168316437 | |
Action 0 State [0.7345456] Reward 0.2345455996021999 | |
Action 1 State [0.8345456] Reward 0.3345455996021999 | |
Action 0 State [0.76444697] Reward 0.26444697463445843 | |
Action 0 State [0.66500668] Reward 0.16500667877729325 | |
Action 1 State [0.76500668] Reward 0.2650066787772932 | |
Action 0 State [0.6286822] Reward 0.1286822003970286 | |
Action 1 State [0.7286822] Reward 0.22868220039702858 | |
Action 1 State [0.8286822] Reward 0.32868220039702856 | |
Action 0 State [0.75756881] Reward 0.2575688057255101 | |
Action 0 State [0.61713174] Reward 0.11713173848108349 | |
Action 1 State [0.71713174] Reward 0.21713173848108347 | |
Action 1 State [0.81713174] Reward 0.31713173848108345 | |
Action 0 State [0.74593941] Reward 0.24593941099248529 | |
Action 1 State [0.84593941] Reward 0.34593941099248526 | |
Action 0 State [0.64656107] Reward 0.14656107460857692 | |
Action 1 State [0.74656107] Reward 0.2465610746085769 | |
Action 1 State [0.84656107] Reward 0.3465610746085769 | |
Action 0 State [0.84025467] Reward 0.34025466639003143 | |
Action 0 State [0.78041958] Reward 0.2804195833027938 | |
Action 0 State [0.64669545] Reward 0.1466954520908761 | |
Action 1 State [0.74669545] Reward 0.24669545209087607 | |
Action 1 State [0.84669545] Reward 0.34669545209087604 | |
Action 0 State [0.64856965] Reward 0.14856964939140527 | |
Action 1 State [0.74856965] Reward 0.24856964939140525 | |
Action 1 State [0.84856965] Reward 0.3485696493914052 | |
Action 0 State [0.6598422] Reward 0.15984219593958748 | |
Action 1 State [0.7598422] Reward 0.25984219593958746 | |
Action 0 State [0.70040146] Reward 0.20040145971452072 | |
Action 1 State [0.80040146] Reward 0.3004014597145207 | |
Action 0 State [0.75216158] Reward 0.25216158496086005 | |
Action 0 State [0.6099928] Reward 0.10999279543973539 | |
Action 1 State [0.7099928] Reward 0.20999279543973537 | |
Action 1 State [0.8099928] Reward 0.30999279543973535 | |
Action 0 State [0.65720068] Reward 0.15720067854385622 | |
Action 1 State [0.75720068] Reward 0.2572006785438562 | |
Action 0 State [0.64713272] Reward 0.14713271642588632 | |
Action 1 State [0.74713272] Reward 0.2471327164258863 | |
Action 1 State [0.84713272] Reward 0.3471327164258863 | |
Action 0 State [0.78864907] Reward 0.2886490746733873 | |
Action 0 State [0.66612909] Reward 0.16612908866629905 | |
Action 1 State [0.76612909] Reward 0.26612908866629903 | |
Action 0 State [0.70955343] Reward 0.2095534306955955 | |
Action 1 State [0.80955343] Reward 0.3095534306955955 | |
Action 0 State [0.7270909] Reward 0.227090898488313 | |
Action 1 State [0.8270909] Reward 0.32709089848831296 | |
Action 0 State [0.63864752] Reward 0.13864752222658538 | |
Action 1 State [0.73864752] Reward 0.23864752222658536 | |
Action 1 State [0.83864752] Reward 0.33864752222658534 | |
Action 0 State [0.81515674] Reward 0.31515673871264627 | |
Action 0 State [0.69963506] Reward 0.1996350605705094 | |
Action 1 State [0.79963506] Reward 0.29963506057050937 | |
Action 0 State [0.62650109] Reward 0.12650108697331353 | |
Action 1 State [0.72650109] Reward 0.2265010869733135 | |
Action 1 State [0.82650109] Reward 0.3265010869733135 | |
Action 0 State [0.71428396] Reward 0.21428395687782742 | |
Action 1 State [0.81428396] Reward 0.3142839568778274 | |
Action 0 State [0.77936048] Reward 0.2793604795253861 | |
Action 0 State [0.67372934] Reward 0.1737293368279894 | |
Action 1 State [0.77372934] Reward 0.2737293368279894 | |
Action 0 State [0.71635653] Reward 0.21635653074567862 | |
Action 1 State [0.81635653] Reward 0.3163565307456786 | |
Action 0 State [0.75334403] Reward 0.25334402586149096 | |
Action 0 State [0.66223021] Reward 0.16223020973305158 | |
Action 1 State [0.76223021] Reward 0.26223020973305156 | |
Action 0 State [0.68324227] Reward 0.1832422684551438 | |
Action 1 State [0.78324227] Reward 0.2832422684551438 | |
Action 0 State [0.7177348] Reward 0.21773479622741632 | |
Action 1 State [0.8177348] Reward 0.3177347962274163 | |
Action 0 State [0.6674623] Reward 0.16746230471869716 | |
Action 1 State [0.7674623] Reward 0.26746230471869714 | |
Action 0 State [0.74446201] Reward 0.244462009128961 | |
Action 1 State [0.84446201] Reward 0.34446200912896097 | |
Action 0 State [0.78137699] Reward 0.28137698870857575 | |
Action 0 State [0.6265855] Reward 0.12658549603422165 | |
Action 1 State [0.7265855] Reward 0.22658549603422162 | |
Action 1 State [0.8265855] Reward 0.3265854960342216 | |
Action 0 State [0.67940679] Reward 0.17940678676331712 | |
Action 1 State [0.77940679] Reward 0.2794067867633171 | |
Action 0 State [0.63000407] Reward 0.13000406573873846 | |
Action 1 State [0.73000407] Reward 0.23000406573873844 | |
Action 1 State [0.83000407] Reward 0.3300040657387384 | |
Action 0 State [0.63041229] Reward 0.1304122853946903 | |
Action 1 State [0.73041229] Reward 0.23041228539469027 | |
Action 1 State [0.83041229] Reward 0.33041228539469025 | |
Action 0 State [0.71467914] Reward 0.21467913925170146 | |
Action 1 State [0.81467914] Reward 0.31467913925170143 | |
Action 0 State [0.6695319] Reward 0.16953190116493788 | |
Action 1 State [0.7695319] Reward 0.26953190116493786 | |
Action 0 State [0.72239825] Reward 0.22239824932652685 | |
Action 1 State [0.82239825] Reward 0.32239824932652683 | |
Action 0 State [0.71385959] Reward 0.21385959031541601 | |
Action 1 State [0.81385959] Reward 0.313859590315416 | |
Action 0 State [0.79100008] Reward 0.29100008493876384 | |
Action 0 State [0.61517092] Reward 0.11517092012334551 | |
Action 1 State [0.71517092] Reward 0.2151709201233455 | |
Action 1 State [0.81517092] Reward 0.31517092012334547 | |
Action 0 State [0.81300149] Reward 0.31300148954354257 | |
Action 0 State [0.79855327] Reward 0.2985532719812152 | |
Action 0 State [0.63595489] Reward 0.13595488955997703 | |
Action 1 State [0.73595489] Reward 0.235954889559977 | |
Action 1 State [0.83595489] Reward 0.335954889559977 | |
Action 0 State [0.66094394] Reward 0.1609439382510086 | |
Action 1 State [0.76094394] Reward 0.2609439382510086 | |
Action 0 State [0.61085586] Reward 0.1108558572207049 | |
Action 1 State [0.71085586] Reward 0.21085585722070488 | |
Action 1 State [0.81085586] Reward 0.31085585722070486 | |
Action 0 State [0.74149916] Reward 0.241499157166721 | |
Action 1 State [0.84149916] Reward 0.34149915716672097 | |
Action 0 State [0.69142675] Reward 0.1914267528574145 | |
Action 1 State [0.79142675] Reward 0.2914267528574145 | |
Action 0 State [0.66787569] Reward 0.16787569411104064 | |
Action 1 State [0.76787569] Reward 0.2678756941110406 | |
Action 0 State [0.69620287] Reward 0.19620286594169722 | |
Action 1 State [0.79620287] Reward 0.2962028659416972 | |
Action 0 State [0.63796516] Reward 0.13796515824379796 | |
Action 1 State [0.73796516] Reward 0.23796515824379794 | |
Action 1 State [0.83796516] Reward 0.3379651582437979 | |
Action 0 State [0.71683369] Reward 0.2168336934524524 | |
Action 1 State [0.81683369] Reward 0.3168336934524524 | |
Action 0 State [0.76329179] Reward 0.26329179357798094 | |
Action 0 State [0.62817627] Reward 0.12817627074958426 | |
Action 1 State [0.72817627] Reward 0.22817627074958424 | |
Action 1 State [0.82817627] Reward 0.3281762707495842 | |
Action 0 State [0.63123974] Reward 0.13123973646243825 | |
Action 1 State [0.73123974] Reward 0.23123973646243823 | |
Action 1 State [0.83123974] Reward 0.3312397364624382 | |
Action 0 State [0.7234603] Reward 0.22346030300899866 | |
Action 1 State [0.8234603] Reward 0.32346030300899864 | |
Action 0 State [0.70843534] Reward 0.20843534478474113 | |
Action 1 State [0.80843534] Reward 0.3084353447847411 | |
Action 0 State [0.61713832] Reward 0.1171383164926274 | |
Action 1 State [0.71713832] Reward 0.21713831649262738 | |
Action 1 State [0.81713832] Reward 0.31713831649262736 | |
Action 0 State [0.81413899] Reward 0.314138990783154 | |
Action 0 State [0.78964803] Reward 0.2896480282587316 | |
Action 0 State [0.65590881] Reward 0.15590880921816086 | |
Action 1 State [0.75590881] Reward 0.25590880921816084 | |
Action 0 State [0.71112599] Reward 0.21112598640405367 | |
Action 1 State [0.81112599] Reward 0.31112598640405364 | |
Action 0 State [0.66598067] Reward 0.16598067354587276 | |
Action 1 State [0.76598067] Reward 0.26598067354587274 | |
Action 0 State [0.74613369] Reward 0.24613369407386887 | |
Action 1 State [0.84613369] Reward 0.34613369407386885 | |
Action 0 State [0.72136837] Reward 0.22136837007283994 | |
Action 1 State [0.82136837] Reward 0.3213683700728399 | |
Action 0 State [0.79118933] Reward 0.2911893296263406 | |
Action 0 State [0.73432545] Reward 0.23432545274022631 | |
Action 1 State [0.83432545] Reward 0.3343254527402263 | |
Action 0 State [0.71436973] Reward 0.21436973428438777 | |
Action 1 State [0.81436973] Reward 0.31436973428438775 | |
Action 0 State [0.81303577] Reward 0.31303577129421345 | |
Action 0 State [0.77715529] Reward 0.27715528798448186 | |
Action 0 State [0.70272024] Reward 0.20272023976192888 | |
Action 1 State [0.80272024] Reward 0.30272023976192886 | |
Action 0 State [0.61355028] Reward 0.11355028152223545 | |
Action 1 State [0.71355028] Reward 0.21355028152223543 | |
Action 1 State [0.81355028] Reward 0.3135502815222354 | |
Action 0 State [0.6396827] Reward 0.13968270475425482 | |
Action 1 State [0.7396827] Reward 0.2396827047542548 | |
Action 1 State [0.8396827] Reward 0.33968270475425477 | |
Action 0 State [0.64140073] Reward 0.1414007343436029 | |
Action 1 State [0.74140073] Reward 0.24140073434360287 | |
Action 1 State [0.84140073] Reward 0.34140073434360285 | |
Action 0 State [0.72746745] Reward 0.2274674506300508 | |
Action 1 State [0.82746745] Reward 0.3274674506300508 | |
Action 0 State [0.75107377] Reward 0.251073770047499 | |
Action 0 State [0.59394325] Reward 0.09394324560488299 | |
Action 1 State [0.69394325] Reward 0.19394324560488296 | |
Action 1 State [0.79394325] Reward 0.29394324560488294 | |
Action 0 State [0.63207342] Reward 0.1320734217992814 | |
Action 1 State [0.73207342] Reward 0.23207342179928137 | |
Action 1 State [0.83207342] Reward 0.33207342179928134 | |
Action 0 State [0.64270673] Reward 0.14270672718788902 | |
Action 1 State [0.74270673] Reward 0.242706727187889 | |
Action 1 State [0.84270673] Reward 0.34270672718788897 | |
Action 0 State [0.80451652] Reward 0.30451652226690074 | |
Action 0 State [0.79481363] Reward 0.29481363115316583 | |
Action 0 State [0.63519037] Reward 0.13519036941908036 | |
Action 1 State [0.73519037] Reward 0.23519036941908034 | |
Action 1 State [0.83519037] Reward 0.3351903694190803 | |
Action 0 State [0.66645939] Reward 0.1664593923247497 | |
Action 1 State [0.76645939] Reward 0.2664593923247497 | |
Action 0 State [0.73230717] Reward 0.23230717437957338 | |
Action 1 State [0.83230717] Reward 0.33230717437957336 | |
Action 0 State [0.78806715] Reward 0.2880671514558515 | |
Action 0 State [0.75033484] Reward 0.25033484413428897 | |
Action 0 State [0.70932888] Reward 0.20932888186247067 | |
Action 1 State [0.80932888] Reward 0.30932888186247065 | |
Action 0 State [0.65254725] Reward 0.1525472549192669 | |
Action 1 State [0.75254725] Reward 0.2525472549192669 | |
Action 0 State [0.71405756] Reward 0.21405756177209323 | |
Action 1 State [0.81405756] Reward 0.3140575617720932 | |
Action 0 State [0.69663198] Reward 0.1966319795462136 | |
Action 1 State [0.79663198] Reward 0.29663197954621356 | |
Action 0 State [0.7287813] Reward 0.2287812978775564 | |
Action 1 State [0.8287813] Reward 0.3287812978775564 | |
Action 0 State [0.8061611] Reward 0.3061611026035538 | |
Action 0 State [0.65587864] Reward 0.15587863949758152 | |
Action 1 State [0.75587864] Reward 0.2558786394975815 | |
Action 0 State [0.63605527] Reward 0.13605527107255622 | |
Action 1 State [0.73605527] Reward 0.2360552710725562 | |
Action 1 State [0.83605527] Reward 0.33605527107255617 | |
Action 0 State [0.65025092] Reward 0.15025092076308066 | |
Action 1 State [0.75025092] Reward 0.25025092076308064 | |
Action 0 State [0.65859394] Reward 0.15859394145172556 | |
Action 1 State [0.75859394] Reward 0.25859394145172554 | |
Action 0 State [0.73192544] Reward 0.23192543925742426 | |
Action 1 State [0.83192544] Reward 0.33192543925742424 | |
Action 0 State [0.75048257] Reward 0.2504825689410275 | |
Action 0 State [0.5624701] Reward 0.062470102922775994 | |
Action 1 State [0.6624701] Reward 0.16247010292277597 | |
Action 1 State [0.7624701] Reward 0.26247010292277595 | |
Action 0 State [0.64506922] Reward 0.14506922312236903 | |
Action 1 State [0.74506922] Reward 0.245069223122369 | |
Action 1 State [0.84506922] Reward 0.345069223122369 | |
Action 0 State [0.81088167] Reward 0.3108816676392657 | |
Action 0 State [0.71113545] Reward 0.21113544732578904 | |
Action 1 State [0.81113545] Reward 0.311135447325789 | |
Action 0 State [0.65191817] Reward 0.15191816756541632 | |
Action 1 State [0.75191817] Reward 0.2519181675654163 | |
Action 0 State [0.5652702] Reward 0.06527019511780974 | |
Action 1 State [0.6652702] Reward 0.16527019511780972 | |
Action 1 State [0.7652702] Reward 0.2652701951178097 | |
Action 0 State [0.64661989] Reward 0.1466198870737231 | |
Action 1 State [0.74661989] Reward 0.24661988707372307 | |
Action 1 State [0.84661989] Reward 0.34661988707372304 | |
Action 0 State [0.84325371] Reward 0.34325371130619065 | |
Action 0 State [0.73348071] Reward 0.2334807106335267 | |
Action 1 State [0.83348071] Reward 0.3334807106335267 | |
Action 0 State [0.82358504] Reward 0.323585044402666 | |
Action 0 State [0.81176681] Reward 0.3117668107259789 | |
Action 0 State [0.62037061] Reward 0.12037061162723084 | |
Action 1 State [0.72037061] Reward 0.22037061162723082 | |
Action 1 State [0.82037061] Reward 0.3203706116272308 | |
Action 0 State [0.70408748] Reward 0.20408747555321116 | |
Action 1 State [0.80408748] Reward 0.30408747555321114 | |
Action 0 State [0.79411947] Reward 0.29411946507301623 | |
Action 0 State [0.6776043] Reward 0.17760429634098251 | |
Action 1 State [0.7776043] Reward 0.2776042963409825 | |
Action 0 State [0.7037659] Reward 0.20376590266351224 | |
Action 1 State [0.8037659] Reward 0.3037659026635122 | |
Action 0 State [0.76826342] Reward 0.2682634220752045 | |
Action 0 State [0.75545594] Reward 0.25545594347794964 | |
Action 0 State [0.74851772] Reward 0.24851772330475153 | |
Action 1 State [0.84851772] Reward 0.3485177233047515 | |
Action 0 State [0.65205992] Reward 0.15205992404483315 | |
Action 1 State [0.75205992] Reward 0.25205992404483313 | |
Action 0 State [0.63376603] Reward 0.13376603440545443 | |
Action 1 State [0.73376603] Reward 0.2337660344054544 | |
Action 1 State [0.83376603] Reward 0.3337660344054544 | |
Action 0 State [0.75123527] Reward 0.25123527303039805 | |
Action 0 State [0.60961483] Reward 0.10961483236660463 | |
Action 1 State [0.70961483] Reward 0.2096148323666046 | |
Action 1 State [0.80961483] Reward 0.3096148323666046 | |
Action 0 State [0.72579307] Reward 0.22579306964157597 | |
Action 1 State [0.82579307] Reward 0.32579306964157595 | |
Action 0 State [0.74126743] Reward 0.24126743106064485 | |
Action 1 State [0.84126743] Reward 0.34126743106064483 | |
Action 0 State [0.74485368] Reward 0.2448536765421443 | |
Action 1 State [0.84485368] Reward 0.34485367654214427 | |
Action 0 State [0.69875943] Reward 0.1987594295798082 | |
Action 1 State [0.79875943] Reward 0.29875942957980817 | |
Action 0 State [0.65615043] Reward 0.15615043379296967 | |
Action 1 State [0.75615043] Reward 0.25615043379296965 | |
Action 0 State [0.59317464] Reward 0.09317463726524355 | |
Action 1 State [0.69317464] Reward 0.19317463726524353 | |
Action 1 State [0.79317464] Reward 0.2931746372652435 | |
Action 0 State [0.71243801] Reward 0.21243800810800362 | |
Action 1 State [0.81243801] Reward 0.3124380081080036 | |
Action 0 State [0.67763939] Reward 0.1776393860855905 | |
Action 1 State [0.77763939] Reward 0.27763938608559047 | |
Action 0 State [0.69197307] Reward 0.19197306846307616 | |
Action 1 State [0.79197307] Reward 0.29197306846307614 | |
Action 0 State [0.61207679] Reward 0.11207678531658094 | |
Action 1 State [0.71207679] Reward 0.21207678531658092 | |
Action 1 State [0.81207679] Reward 0.3120767853165809 | |
Action 0 State [0.80043456] Reward 0.3004345594047729 | |
Action 0 State [0.7389397] Reward 0.23893970435866763 | |
Action 1 State [0.8389397] Reward 0.3389397043586676 | |
Action 0 State [0.78197583] Reward 0.28197583146141325 | |
Action 0 State [0.70033651] Reward 0.20033651312704692 | |
Action 1 State [0.80033651] Reward 0.3003365131270469 | |
Action 0 State [0.77017756] Reward 0.2701775579712288 | |
Action 0 State [0.76008187] Reward 0.2600818710700058 | |
Action 0 State [0.56822006] Reward 0.06822005970454703 | |
Action 1 State [0.66822006] Reward 0.168220059704547 | |
Action 1 State [0.76822006] Reward 0.268220059704547 | |
Action 0 State [0.74454461] Reward 0.2445446129014318 | |
Action 1 State [0.84454461] Reward 0.3445446129014318 | |
Action 0 State [0.82475292] Reward 0.32475292021340896 | |
Action 0 State [0.66389463] Reward 0.16389463466014897 | |
Action 1 State [0.76389463] Reward 0.26389463466014895 | |
Action 0 State [0.59054932] Reward 0.09054932084413003 | |
Action 1 State [0.69054932] Reward 0.19054932084413 | |
Action 1 State [0.79054932] Reward 0.29054932084413 | |
Action 0 State [0.73932466] Reward 0.2393246556610672 | |
Action 1 State [0.83932466] Reward 0.3393246556610672 | |
Action 0 State [0.74248334] Reward 0.242483343027595 | |
Action 1 State [0.84248334] Reward 0.342483343027595 | |
Action 0 State [0.65600819] Reward 0.15600818500766045 | |
Action 1 State [0.75600819] Reward 0.2560081850076604 | |
Action 0 State [0.74845312] Reward 0.2484531150185869 | |
Action 1 State [0.84845312] Reward 0.3484531150185869 | |
Action 0 State [0.72046415] Reward 0.22046415217098525 | |
Action 1 State [0.82046415] Reward 0.32046415217098523 | |
Action 0 State [0.6299719] Reward 0.1299719002470533 | |
Action 1 State [0.7299719] Reward 0.22997190024705327 | |
Action 1 State [0.8299719] Reward 0.32997190024705325 | |
Action 0 State [0.67703358] Reward 0.1770335790955594 | |
Action 1 State [0.77703358] Reward 0.27703357909555937 | |
Action 0 State [0.60892285] Reward 0.10892284558209953 | |
Action 1 State [0.70892285] Reward 0.2089228455820995 | |
Action 1 State [0.80892285] Reward 0.3089228455820995 | |
Action 0 State [0.67964796] Reward 0.1796479601112293 | |
Action 1 State [0.77964796] Reward 0.2796479601112293 | |
Action 0 State [0.75364818] Reward 0.2536481841310033 | |
Action 0 State [0.60517672] Reward 0.10517672300557601 | |
Action 1 State [0.70517672] Reward 0.205176723005576 | |
Action 1 State [0.80517672] Reward 0.30517672300557597 | |
Action 0 State [0.78854465] Reward 0.2885446477236615 | |
Action 0 State [0.73224835] Reward 0.23224834568221187 | |
Action 1 State [0.83224835] Reward 0.33224834568221184 | |
Action 0 State [0.76938783] Reward 0.26938782847641296 | |
Action 0 State [0.62910735] Reward 0.1291073487540868 | |
Action 1 State [0.72910735] Reward 0.22910734875408678 | |
Action 1 State [0.82910735] Reward 0.32910734875408676 | |
Action 0 State [0.71854258] Reward 0.2185425831602379 | |
Action 1 State [0.81854258] Reward 0.31854258316023787 | |
Action 0 State [0.79748261] Reward 0.29748260690493256 | |
Action 0 State [0.67852378] Reward 0.1785237793664256 | |
Action 1 State [0.77852378] Reward 0.2785237793664256 | |
Action 0 State [0.681629] Reward 0.18162900468687426 | |
Action 1 State [0.781629] Reward 0.28162900468687424 | |
Action 0 State [0.73196901] Reward 0.2319690136173853 | |
Action 1 State [0.83196901] Reward 0.3319690136173853 | |
Action 0 State [0.74428338] Reward 0.24428337771005137 | |
Action 1 State [0.84428338] Reward 0.34428337771005135 | |
Action 0 State [0.75434341] Reward 0.25434341265325155 | |
Action 0 State [0.74805241] Reward 0.2480524078164975 | |
Action 1 State [0.84805241] Reward 0.3480524078164975 | |
Action 0 State [0.74034994] Reward 0.24034994237935647 | |
Action 1 State [0.84034994] Reward 0.34034994237935645 | |
Action 0 State [0.75129961] Reward 0.2512996109893443 | |
Action 0 State [0.58398732] Reward 0.08398731892885825 | |
Action 1 State [0.68398732] Reward 0.18398731892885822 | |
Action 1 State [0.78398732] Reward 0.2839873189288582 | |
Action 0 State [0.70414004] Reward 0.20414004395244634 | |
Action 1 State [0.80414004] Reward 0.3041400439524463 | |
Action 0 State [0.68868274] Reward 0.18868274154903386 | |
Action 1 State [0.78868274] Reward 0.28868274154903384 | |
Action 0 State [0.69945061] Reward 0.1994506074263267 | |
Action 1 State [0.79945061] Reward 0.2994506074263267 | |
Action 0 State [0.68674963] Reward 0.18674962569945497 | |
Action 1 State [0.78674963] Reward 0.28674962569945495 | |
Action 0 State [0.6800384] Reward 0.18003840479746014 | |
Action 1 State [0.7800384] Reward 0.2800384047974601 | |
Action 0 State [0.76513716] Reward 0.26513716143563526 | |
Action 0 State [0.57105678] Reward 0.07105678189968712 | |
Action 1 State [0.67105678] Reward 0.1710567818996871 | |
Action 1 State [0.77105678] Reward 0.27105678189968707 | |
Action 0 State [0.61450033] Reward 0.11450032627387485 | |
Action 1 State [0.71450033] Reward 0.21450032627387483 | |
Action 1 State [0.81450033] Reward 0.3145003262738748 | |
Action 0 State [0.69766513] Reward 0.19766512523698976 | |
Action 1 State [0.79766513] Reward 0.29766512523698974 | |
Action 0 State [0.63055087] Reward 0.1305508685411375 | |
Action 1 State [0.73055087] Reward 0.2305508685411375 | |
Action 1 State [0.83055087] Reward 0.33055086854113747 | |
Action 0 State [0.73077009] Reward 0.23077008869705484 | |
Action 1 State [0.83077009] Reward 0.3307700886970548 | |
Action 0 State [0.6709701] Reward 0.17097010458487927 | |
Action 1 State [0.7709701] Reward 0.27097010458487925 | |
Action 0 State [0.68218903] Reward 0.18218903360853056 | |
Action 1 State [0.78218903] Reward 0.28218903360853054 | |
Action 0 State [0.60395608] Reward 0.10395607778466531 | |
Action 1 State [0.70395608] Reward 0.2039560777846653 | |
Action 1 State [0.80395608] Reward 0.30395607778466527 | |
Action 0 State [0.68425412] Reward 0.18425411876525455 | |
Action 1 State [0.78425412] Reward 0.2842541187652545 | |
Action 0 State [0.77403849] Reward 0.27403849085644205 | |
Action 0 State [0.63824916] Reward 0.13824915819173578 | |
Action 1 State [0.73824916] Reward 0.23824915819173575 | |
Action 1 State [0.83824916] Reward 0.33824915819173573 | |
Action 0 State [0.79201706] Reward 0.29201705769758857 | |
Action 0 State [0.69508841] Reward 0.1950884128389293 | |
Action 1 State [0.79508841] Reward 0.2950884128389293 | |
Action 0 State [0.63393406] Reward 0.13393405526215263 | |
Action 1 State [0.73393406] Reward 0.2339340552621526 | |
Action 1 State [0.83393406] Reward 0.3339340552621526 | |
Action 0 State [0.67377633] Reward 0.1737763268562137 | |
Action 1 State [0.77377633] Reward 0.27377632685621367 | |
Action 0 State [0.70556594] Reward 0.20556594124148875 | |
Action 1 State [0.80556594] Reward 0.3055659412414887 | |
Action 0 State [0.62945854] Reward 0.12945854127868528 | |
Action 1 State [0.72945854] Reward 0.22945854127868526 | |
Action 1 State [0.82945854] Reward 0.32945854127868524 | |
Action 0 State [0.73930125] Reward 0.23930124550261345 | |
Action 1 State [0.83930125] Reward 0.3393012455026134 | |
Action 0 State [0.7082294] Reward 0.20822940031021853 | |
Action 1 State [0.8082294] Reward 0.3082294003102185 | |
Action 0 State [0.75407934] Reward 0.2540793363378583 | |
Action 0 State [0.6457498] Reward 0.1457497953393201 | |
Action 1 State [0.7457498] Reward 0.24574979533932007 | |
Action 1 State [0.8457498] Reward 0.34574979533932004 | |
Action 0 State [0.71657859] Reward 0.21657859497512866 | |
Action 1 State [0.81657859] Reward 0.31657859497512864 | |
Action 0 State [0.8021899] Reward 0.30218990086725717 | |
Action 0 State [0.69829778] Reward 0.1982977813928194 | |
Action 1 State [0.79829778] Reward 0.29829778139281937 | |
Action 0 State [0.78083275] Reward 0.2808327494176228 | |
Action 0 State [0.66362502] Reward 0.16362502136667634 | |
Action 1 State [0.76362502] Reward 0.2636250213666763 | |
Action 0 State [0.58137424] Reward 0.0813742369220587 | |
Action 1 State [0.68137424] Reward 0.18137423692205867 | |
Total reward of 482.43006715246787 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import gym | |
from gym.envs.registration import register | |
from tensorforce.environments import Environment | |
from tensorforce.agents import Agent | |
from tensorforce.execution import Runner | |
env_name = 'Simple-v0' | |
gym.envs.registration.register(id=env_name, entry_point="simple:SimpleEnv") | |
def main(): | |
environment = Environment.create( | |
environment='gym', level=env_name, max_episode_timesteps=2000 | |
) | |
agent = Agent.create( | |
agent='tensorforce', environment=environment, update=100, | |
optimizer=dict(optimizer='adam', learning_rate=1e-3), | |
objective='policy_gradient', reward_estimation=dict(horizon=10), | |
saver=dict(directory='simple_env_checkpt', frequency=25, | |
max_checkpoints=20), | |
) | |
runner = Runner( | |
agent=agent, | |
environment=environment | |
) | |
runner.run(num_episodes=1000) | |
runner.run(num_episodes=100, evaluation=True) | |
runner.close() | |
agent.close() | |
if __name__ == '__main__': | |
main() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from random import random | |
import gym | |
from gym import spaces | |
import numpy as np | |
class SimpleEnv(gym.Env): | |
def __init__(self): | |
self.action_space = spaces.Discrete(2) | |
self.observation_space = spaces.Box(np.array([-0.2]), | |
np.array([1.08]), dtype=np.float32) | |
self.reset() | |
def _take_action(self, action): | |
assert self.action_space.contains(action) | |
if action == 1: | |
self.state += 0.1 | |
else: | |
self.state -= random() * 0.2 | |
def step(self, action): | |
self._take_action(action) | |
self._reward = self.state - 0.5 | |
ob = self.get_state() | |
done = False | |
# Game over | |
if self.state > 0.98 or self.state < 0.: | |
done = True | |
self._reward = 0. | |
return ob, self._reward, done, {} | |
def get_state(self): | |
return np.array([self.state]) | |
def reset(self): | |
self.state = 0.25 | |
self._reward = 0. | |
return self.get_state() | |
def render(self, mode = "human"): | |
print("{:.2f}, Reward: {:.2f}".format( | |
self.state, | |
self._reward | |
)) | |
def seed(self, seed = 1): | |
random.seed(seed) | |
np.random.seed(seed) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment