Tiredsheep commited on
Commit
c2787b8
·
verified ·
1 Parent(s): de0962e

Upload folder using huggingface_hub

Browse files
Files changed (41) hide show
  1. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/env.csv +0 -0
  2. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/env_sv.csv +0 -0
  3. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/eval.csv +31 -0
  4. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/eval_sv.csv +31 -0
  5. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/flags.json +1 -0
  6. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/offline_agent.csv +201 -0
  7. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/offline_agent_sv.csv +201 -0
  8. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/online_agent.csv +101 -0
  9. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/online_agent_sv.csv +101 -0
  10. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_100000.pkl +3 -0
  11. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1000000.pkl +3 -0
  12. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1050000.pkl +3 -0
  13. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1100000.pkl +3 -0
  14. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1150000.pkl +3 -0
  15. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1200000.pkl +3 -0
  16. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1250000.pkl +3 -0
  17. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1300000.pkl +3 -0
  18. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1350000.pkl +3 -0
  19. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1400000.pkl +3 -0
  20. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1450000.pkl +3 -0
  21. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_150000.pkl +3 -0
  22. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1500000.pkl +3 -0
  23. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_200000.pkl +3 -0
  24. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_250000.pkl +3 -0
  25. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_300000.pkl +3 -0
  26. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_350000.pkl +3 -0
  27. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_400000.pkl +3 -0
  28. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_450000.pkl +3 -0
  29. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_50000.pkl +3 -0
  30. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_500000.pkl +3 -0
  31. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_550000.pkl +3 -0
  32. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_600000.pkl +3 -0
  33. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_650000.pkl +3 -0
  34. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_700000.pkl +3 -0
  35. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_750000.pkl +3 -0
  36. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_800000.pkl +3 -0
  37. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_850000.pkl +3 -0
  38. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_900000.pkl +3 -0
  39. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_950000.pkl +3 -0
  40. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/progress.tk +1 -0
  41. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/token.tk +1 -0
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/eval.csv ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ avg_gripper_contact_length,num_gripper_contacts,prev_button_states,button_states,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
2
+ 0.0,0.0,0.4955555555555556,0.4955555555555556,-0.1823109644076872,-0.0036113110565380393,-0.1821995095362422,-0.0002950079957824076,34.7317559366667,25.24999999999688,0.0,12750.0,-4.54,-2400.08,500.0,2.0032492685317993,50000
3
+ 0.0,0.0,0.5266666666666666,0.5266666666666666,-0.1861315420525029,-0.006390609348580372,-0.1859993075061297,-0.0011404158181836438,34.98027793199072,25.24999999999688,0.0,38750.0,-4.26,-2287.78,500.0,1.9496320247650147,100000
4
+ 0.0,0.0,0.49333333333333335,0.49333333333333335,-0.18467900462840647,-0.0061529206026806164,-0.18494134398443735,-0.008504042647443186,34.591228082061676,25.24999999999688,0.0,64750.0,-4.56,-2395.94,500.0,1.8557483911514283,150000
5
+ 0.0,0.0,0.5333333333333333,0.5333333333333333,-0.17783258684858627,-0.0034593449702788543,-0.1776408822626174,-0.0016423401539120083,34.83602059462565,25.24999999999688,0.0,90750.0,-4.2,-2237.48,500.0,1.8456436014175415,200000
6
+ 0.0,0.0,0.56,0.56,-0.18385401413929203,-0.0009274375692699297,-0.18433298693316488,-0.01080434735265958,34.17743639985424,25.24999999999688,0.0,116750.0,-3.96,-2209.22,500.0,1.833575210571289,250000
7
+ 0.0,0.0,0.5222222222222223,0.5222222222222223,-0.1836431985020944,-0.01760466241243687,-0.18446224547680343,-0.01541908179960404,35.053879393750904,25.24999999999688,0.0,142750.0,-4.3,-2230.78,500.0,1.841410231590271,300000
8
+ 0.0,0.0,0.5088888888888888,0.5088888888888888,-0.17874734086600585,0.008332041238222229,-0.17835931586890358,0.005545649613876157,34.79775966000895,25.24999999999688,0.0,168750.0,-4.42,-2274.8,500.0,1.834565019607544,350000
9
+ 0.0,0.0,0.54,0.5466666666666666,-0.18093694572670604,-0.005362031310912227,-0.18099588587506302,-0.004631900477367766,34.78539902569179,25.24999999999688,0.0,194750.0,-4.08,-2167.46,500.0,1.8486171674728393,400000
10
+ 0.0,0.0,0.5555555555555556,0.5555555555555556,-0.18090161355742007,-0.005077748061196984,-0.18079786355174687,-0.00023352420308134307,35.39153219535701,25.24999999999688,0.0,220750.0,-4.0,-2216.76,500.0,1.8741959953308105,450000
11
+ 0.0,0.0,0.5377777777777778,0.5311111111111111,-0.18604454573823698,-0.0050515823306754104,-0.18622804107275184,-0.0067799446265664354,34.915649190237765,25.24999999999688,0.0,246750.0,-4.22,-2257.28,500.0,1.8635986852645874,500000
12
+ 0.0,0.0,0.48,0.4866666666666667,-0.1797991774443072,0.00305232716106351,-0.17973198207851515,-0.0009797525297443588,34.909333765764856,25.24999999999688,0.0,272750.0,-4.62,-2221.06,500.0,1.88084942817688,550000
13
+ 0.0,0.0,0.4866666666666667,0.4866666666666667,-0.17906999649107122,-0.0039002174673395456,-0.17909068118808721,-0.0020512840248978694,35.24290674707944,25.24999999999688,0.0,298750.0,-4.62,-2208.9,500.0,1.868926887512207,600000
14
+ 0.0,0.0,0.5444444444444444,0.5422222222222223,-0.1843901109777063,-0.004029381732842184,-0.184656244038894,-0.00679648043317533,34.807703692051675,25.103999999996958,0.02,324618.6,-4.12,-2179.68,497.08,1.9669628572463989,650000
15
+ 0.0,0.0,0.54,0.5444444444444444,-0.1818899193081661,-0.005006720437254989,-0.18236189315925863,-0.008763543178333806,34.686123712699484,25.24999999999688,0.0,350604.0,-4.1,-2173.24,500.0,2.004435029029846,700000
16
+ 0.0,0.0,0.5422222222222223,0.5422222222222223,-0.18655353496183308,-0.0007565637102712423,-0.1864783951699033,-0.0023664913563967074,34.27218344245478,25.24999999999688,0.0,376604.0,-4.12,-2219.9,500.0,1.9953720664978027,750000
17
+ 0.0,0.0,0.5333333333333333,0.5422222222222223,-0.1804904840078951,0.005053082533988238,-0.18021153791884895,0.0033839706538472685,35.03379145799669,25.09299999999697,0.02,402569.46,-4.12,-2192.4,496.86,1.9864367961883544,800000
18
+ 0.0,0.0,0.4866666666666667,0.4866666666666667,-0.18991256881353222,-0.005218513515423203,-0.1903276949288042,-0.00808407925234294,34.77748258933813,25.24999999999688,0.0,428447.0,-4.62,-2244.94,500.0,2.015931601524353,850000
19
+ 0.0,0.0,0.5377777777777778,0.56,-0.17790264093045505,0.002958963277321043,-0.17788747257664517,5.70358999897902e-05,35.12935194412666,25.079999999996975,0.04,454439.4,-3.96,-2233.3,496.6,1.9902378416061401,900000
20
+ 0.0,0.0,0.5111111111111111,0.49777777777777776,-0.18680984653990154,0.00025280579343610023,-0.18619652051699004,0.010358871596982042,35.00973827649558,25.24999999999688,0.0,480277.0,-4.52,-2254.08,500.0,2.0462763023376467,950000
21
+ 0.0,0.0,0.5044444444444445,0.5177777777777778,-0.18212048414064735,-0.012847055241202715,-0.18264239796579917,-0.011093026856148179,35.12241803456497,25.179999999996916,0.02,506207.0,-4.34,-2285.26,498.6,1.9781414556503296,1000000
22
+ 0.0,0.0,0.4866666666666667,0.4955555555555556,-0.18097304082101856,0.00588178032139505,-0.18058594689884072,0.005544512246383352,35.22828638342973,25.09199999999697,0.02,532131.16,-4.54,-2253.84,496.84,1.8403616762161255,1050000
23
+ 0.0,0.0,0.5711111111111111,0.5777777777777777,-0.18122268359615223,0.0012912510322031295,-0.18104960310225302,0.0004639438618360747,35.0653874179727,25.033999999996972,0.02,558031.72,-3.8,-2181.12,495.68,1.8333583068847656,1100000
24
+ 0.0,0.0,0.5288888888888889,0.5333333333333333,-0.1792619518833928,0.002241662731721289,-0.1789301388602482,0.0028699533717915066,34.16118311654266,25.219999999996897,0.02,583824.0,-4.2,-2171.7,499.4,1.9683964157104492,1150000
25
+ 0.0,0.0,0.4888888888888889,0.4888888888888889,-0.18270155304653554,0.0037775947369773116,-0.18236959679604925,0.004409884351722563,35.29253495071921,25.048999999996994,0.04,609608.5,-4.6,-2279.32,495.98,1.9690742826461791,1200000
26
+ 0.0,0.0,0.5377777777777778,0.5444444444444444,-0.18310194259693158,-0.009857166926274235,-0.18353930642000513,-0.008911167648525753,34.73889441762448,25.24999999999688,0.02,635602.0,-4.1,-2188.38,500.0,1.972101149559021,1250000
27
+ 0.0,0.0,0.5222222222222223,0.5222222222222223,-0.18496752445762676,-0.001770918612516882,-0.18501375003029022,-0.0029805591902508912,35.13033509774581,25.24999999999688,0.0,661602.0,-4.3,-2283.2,500.0,1.8592963647842407,1300000
28
+ 0.0,0.0,0.5088888888888888,0.5155555555555555,-0.18146749024466485,0.003385147988947521,-0.1812260703748377,0.004234727534794259,35.159928765862816,25.215999999996903,0.02,687595.2,-4.36,-2284.76,499.32,1.8659902238845825,1350000
29
+ 0.0,0.0,0.5422222222222223,0.5422222222222223,-0.18497787622863804,-0.005437390095135063,-0.18484754374987145,-0.0003171149524950721,34.890281376907694,25.24999999999688,0.0,713568.0,-4.12,-2241.2,500.0,1.9039997816085816,1400000
30
+ 0.0,0.0,0.5044444444444445,0.4955555555555556,-0.18436679719877203,-0.0003351147577858547,-0.18424711897109902,0.0018907131370187562,35.25442576378246,25.24999999999688,0.0,739568.0,-4.54,-2212.4,500.0,1.9824689197540284,1450000
31
+ 0.0,0.0,0.52,0.5266666666666666,-0.17899205292582193,-0.0079788896444535,-0.17936812978683175,-0.007260662317695672,35.34086319206154,25.07499999999698,0.02,765459.5,-4.26,-2161.52,496.5,1.972663278579712,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/eval_sv.csv ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ avg_gripper_contact_length,num_gripper_contacts,prev_button_states,button_states,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
2
+ 0.0,0.0,0.4955555555555556,0.4955555555555556,-0.1823109644076872,-0.0036113110565380393,-0.1821995095362422,-0.0002950079957824076,34.7317559366667,25.24999999999688,0.0,12750.0,-4.54,-2400.08,500.0,2.0032492685317993,50000
3
+ 0.0,0.0,0.5266666666666666,0.5266666666666666,-0.1861315420525029,-0.006390609348580372,-0.1859993075061297,-0.0011404158181836438,34.98027793199072,25.24999999999688,0.0,38750.0,-4.26,-2287.78,500.0,1.9496320247650147,100000
4
+ 0.0,0.0,0.49333333333333335,0.49333333333333335,-0.18467900462840647,-0.0061529206026806164,-0.18494134398443735,-0.008504042647443186,34.591228082061676,25.24999999999688,0.0,64750.0,-4.56,-2395.94,500.0,1.8557483911514283,150000
5
+ 0.0,0.0,0.5333333333333333,0.5333333333333333,-0.17783258684858627,-0.0034593449702788543,-0.1776408822626174,-0.0016423401539120083,34.83602059462565,25.24999999999688,0.0,90750.0,-4.2,-2237.48,500.0,1.8456436014175415,200000
6
+ 0.0,0.0,0.56,0.56,-0.18385401413929203,-0.0009274375692699297,-0.18433298693316488,-0.01080434735265958,34.17743639985424,25.24999999999688,0.0,116750.0,-3.96,-2209.22,500.0,1.833575210571289,250000
7
+ 0.0,0.0,0.5222222222222223,0.5222222222222223,-0.1836431985020944,-0.01760466241243687,-0.18446224547680343,-0.01541908179960404,35.053879393750904,25.24999999999688,0.0,142750.0,-4.3,-2230.78,500.0,1.841410231590271,300000
8
+ 0.0,0.0,0.5088888888888888,0.5088888888888888,-0.17874734086600585,0.008332041238222229,-0.17835931586890358,0.005545649613876157,34.79775966000895,25.24999999999688,0.0,168750.0,-4.42,-2274.8,500.0,1.834565019607544,350000
9
+ 0.0,0.0,0.54,0.5466666666666666,-0.18093694572670604,-0.005362031310912227,-0.18099588587506302,-0.004631900477367766,34.78539902569179,25.24999999999688,0.0,194750.0,-4.08,-2167.46,500.0,1.8486171674728393,400000
10
+ 0.0,0.0,0.5555555555555556,0.5555555555555556,-0.18090161355742007,-0.005077748061196984,-0.18079786355174687,-0.00023352420308134307,35.39153219535701,25.24999999999688,0.0,220750.0,-4.0,-2216.76,500.0,1.8741959953308105,450000
11
+ 0.0,0.0,0.5377777777777778,0.5311111111111111,-0.18604454573823698,-0.0050515823306754104,-0.18622804107275184,-0.0067799446265664354,34.915649190237765,25.24999999999688,0.0,246750.0,-4.22,-2257.28,500.0,1.8635986852645874,500000
12
+ 0.0,0.0,0.48,0.4866666666666667,-0.1797991774443072,0.00305232716106351,-0.17973198207851515,-0.0009797525297443588,34.909333765764856,25.24999999999688,0.0,272750.0,-4.62,-2221.06,500.0,1.88084942817688,550000
13
+ 0.0,0.0,0.4866666666666667,0.4866666666666667,-0.17906999649107122,-0.0039002174673395456,-0.17909068118808721,-0.0020512840248978694,35.24290674707944,25.24999999999688,0.0,298750.0,-4.62,-2208.9,500.0,1.868926887512207,600000
14
+ 0.0,0.0,0.5444444444444444,0.5422222222222223,-0.1843901109777063,-0.004029381732842184,-0.184656244038894,-0.00679648043317533,34.807703692051675,25.103999999996958,0.02,324618.6,-4.12,-2179.68,497.08,1.9669628572463989,650000
15
+ 0.0,0.0,0.54,0.5444444444444444,-0.1818899193081661,-0.005006720437254989,-0.18236189315925863,-0.008763543178333806,34.686123712699484,25.24999999999688,0.0,350604.0,-4.1,-2173.24,500.0,2.004435029029846,700000
16
+ 0.0,0.0,0.5422222222222223,0.5422222222222223,-0.18655353496183308,-0.0007565637102712423,-0.1864783951699033,-0.0023664913563967074,34.27218344245478,25.24999999999688,0.0,376604.0,-4.12,-2219.9,500.0,1.9953720664978027,750000
17
+ 0.0,0.0,0.5333333333333333,0.5422222222222223,-0.1804904840078951,0.005053082533988238,-0.18021153791884895,0.0033839706538472685,35.03379145799669,25.09299999999697,0.02,402569.46,-4.12,-2192.4,496.86,1.9864367961883544,800000
18
+ 0.0,0.0,0.4866666666666667,0.4866666666666667,-0.18991256881353222,-0.005218513515423203,-0.1903276949288042,-0.00808407925234294,34.77748258933813,25.24999999999688,0.0,428447.0,-4.62,-2244.94,500.0,2.015931601524353,850000
19
+ 0.0,0.0,0.5377777777777778,0.56,-0.17790264093045505,0.002958963277321043,-0.17788747257664517,5.70358999897902e-05,35.12935194412666,25.079999999996975,0.04,454439.4,-3.96,-2233.3,496.6,1.9902378416061401,900000
20
+ 0.0,0.0,0.5111111111111111,0.49777777777777776,-0.18680984653990154,0.00025280579343610023,-0.18619652051699004,0.010358871596982042,35.00973827649558,25.24999999999688,0.0,480277.0,-4.52,-2254.08,500.0,2.0462763023376467,950000
21
+ 0.0,0.0,0.5044444444444445,0.5177777777777778,-0.18212048414064735,-0.012847055241202715,-0.18264239796579917,-0.011093026856148179,35.12241803456497,25.179999999996916,0.02,506207.0,-4.34,-2285.26,498.6,1.9781414556503296,1000000
22
+ 0.0,0.0,0.4866666666666667,0.4955555555555556,-0.18097304082101856,0.00588178032139505,-0.18058594689884072,0.005544512246383352,35.22828638342973,25.09199999999697,0.02,532131.16,-4.54,-2253.84,496.84,1.8403616762161255,1050000
23
+ 0.0,0.0,0.5711111111111111,0.5777777777777777,-0.18122268359615223,0.0012912510322031295,-0.18104960310225302,0.0004639438618360747,35.0653874179727,25.033999999996972,0.02,558031.72,-3.8,-2181.12,495.68,1.8333583068847656,1100000
24
+ 0.0,0.0,0.5288888888888889,0.5333333333333333,-0.1792619518833928,0.002241662731721289,-0.1789301388602482,0.0028699533717915066,34.16118311654266,25.219999999996897,0.02,583824.0,-4.2,-2171.7,499.4,1.9683964157104492,1150000
25
+ 0.0,0.0,0.4888888888888889,0.4888888888888889,-0.18270155304653554,0.0037775947369773116,-0.18236959679604925,0.004409884351722563,35.29253495071921,25.048999999996994,0.04,609608.5,-4.6,-2279.32,495.98,1.9690742826461791,1200000
26
+ 0.0,0.0,0.5377777777777778,0.5444444444444444,-0.18310194259693158,-0.009857166926274235,-0.18353930642000513,-0.008911167648525753,34.73889441762448,25.24999999999688,0.02,635602.0,-4.1,-2188.38,500.0,1.972101149559021,1250000
27
+ 0.0,0.0,0.5222222222222223,0.5222222222222223,-0.18496752445762676,-0.001770918612516882,-0.18501375003029022,-0.0029805591902508912,35.13033509774581,25.24999999999688,0.0,661602.0,-4.3,-2283.2,500.0,1.8592963647842407,1300000
28
+ 0.0,0.0,0.5088888888888888,0.5155555555555555,-0.18146749024466485,0.003385147988947521,-0.1812260703748377,0.004234727534794259,35.159928765862816,25.215999999996903,0.02,687595.2,-4.36,-2284.76,499.32,1.8659902238845825,1350000
29
+ 0.0,0.0,0.5422222222222223,0.5422222222222223,-0.18497787622863804,-0.005437390095135063,-0.18484754374987145,-0.0003171149524950721,34.890281376907694,25.24999999999688,0.0,713568.0,-4.12,-2241.2,500.0,1.9039997816085816,1400000
30
+ 0.0,0.0,0.5044444444444445,0.4955555555555556,-0.18436679719877203,-0.0003351147577858547,-0.18424711897109902,0.0018907131370187562,35.25442576378246,25.24999999999688,0.0,739568.0,-4.54,-2212.4,500.0,1.9824689197540284,1450000
31
+ 0.0,0.0,0.52,0.5266666666666666,-0.17899205292582193,-0.0079788896444535,-0.17936812978683175,-0.007260662317695672,35.34086319206154,25.07499999999698,0.02,765459.5,-4.26,-2161.52,496.5,1.972663278579712,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"logtostderr": false, "alsologtostderr": false, "log_dir": "", "v": 0, "verbosity": 0, "logger_levels": {}, "stderrthreshold": "fatal", "showprefixforinfo": true, "run_with_pdb": false, "pdb_post_mortem": false, "pdb": false, "run_with_profiling": false, "profile_file": null, "use_cprofile_for_profiling": true, "only_check_args": false, "pymjcf_debug": false, "pymjcf_debug_full_dump_dir": "", "pymjcf_log_xml": false, "timeout": true, "chex_n_cpu_devices": 1, "chex_assert_multiple_cpu_devices": false, "test_srcdir": "", "test_tmpdir": "/tmp/absl_testing", "test_random_seed": 301, "test_randomize_ordering_seed": "", "xml_output_file": "", "chex_skip_pmap_variant_if_single_device": true, "run_group": "main-experiments", "tags": "FAWAC", "seed": 10001, "env_name": "puzzle-3x3-play-singletask-task4-v0", "save_dir": "exp/qam-reproduce/main-experiments/puzzle-3x3-play-singletask-task4-v0/20260308_141107", "offline_steps": 1000000, "online_steps": 500000, "buffer_size": 1000000, "log_interval": 5000, "eval_interval": 50000, "save_interval": 50000, "start_training": 5000, "utd_ratio": 1, "eval_episodes": 50, "video_episodes": 2, "video_frame_skip": 3, "agent": {"ac_action_dim": 25, "action_chunking": true, "action_dim": 5, "actor_hidden_dims": [512, 512, 512, 512], "actor_layer_norm": false, "agent_name": "fawac", "batch_size": 256, "best_of_n": 1, "discount": 0.99, "flow_steps": 10, "horizon_length": 5, "inv_temp": 0.8, "lr": 0.0003, "num_qs": 10, "ob_dims": [55], "rho": 0.5, "tau": 0.005, "value_hidden_dims": [512, 512, 512, 512], "value_layer_norm": true}, "dataset_proportion": 1.0, "dataset_replace_interval": 1000, "ogbench_dataset_dir": null, "horizon_length": 5, "sparse": true, "save_all_online_states": false, "save_last_checkpoint": false, "save_replay_buffer": false, "balanced_sampling": false, "?": false, "help": false, "helpshort": false, "helpfull": false, "helpxml": false}
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/offline_agent.csv ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,critic/value_loss,grad/max,grad/min,grad/norm,step
2
+ 0.115540415,18.77205,-73.80803,-75.69133,-75.80335,0.003366718,0.06988833,-0.14721154,7.576399,5000
3
+ 0.25290036,1.1149992,-43.617916,-94.76918,-95.486946,0.03737503,6.335382,-6.4655666,100.07944,10000
4
+ 0.3779252,0.49680445,-88.759,-100.99047,-101.68877,0.02471619,0.3517061,-0.20656186,22.65007,15000
5
+ 0.3061837,0.31726307,-0.3807384,-102.31548,-104.170395,0.053845514,0.2240226,-0.31388137,15.487057,20000
6
+ 0.26091284,0.011727537,0.08710304,-102.82782,-103.53233,0.007286181,0.08635192,-0.033824697,3.6474416,25000
7
+ 0.28292555,0.06730841,-98.40343,-103.45326,-104.028145,0.13507043,0.1643811,-0.053109497,7.7025084,30000
8
+ 0.2149696,0.16047768,-0.22232223,-102.61609,-103.317696,0.07352119,0.64551485,-0.69563985,10.616798,35000
9
+ 0.30237496,0.8415882,-99.56935,-102.2476,-102.587006,0.03362368,0.24204859,-0.66677654,16.631441,40000
10
+ 0.2358851,0.02618273,-97.28751,-102.21511,-102.409805,0.037117798,0.17324038,-0.06658696,6.2354593,45000
11
+ 0.22886232,0.085374236,-0.21570209,-101.6305,-102.40136,0.06228729,0.13768992,-0.17911616,9.331837,50000
12
+ 0.22992794,0.06397193,-93.68237,-101.907326,-102.27688,0.030866787,0.06593228,-0.06415962,4.9773874,55000
13
+ 0.25256538,0.083970845,0.48268515,-101.44397,-102.37995,0.043460835,0.4801869,-0.20692748,13.231135,60000
14
+ 0.24700752,0.18971701,-89.302704,-101.9626,-102.31043,0.1077945,0.1855909,-0.4376136,13.281654,65000
15
+ 0.26320294,6.778486,0.30486643,-100.66872,-102.21684,3.1901453,6.341703,-8.844065,147.45123,70000
16
+ 0.34315318,6.4636483,-41.126846,-101.48792,-102.05954,12.334414,1.0402722,-1.6089591,82.40053,75000
17
+ 0.20272142,0.025911963,-98.98992,-101.42564,-101.87388,0.06477165,0.045217466,-0.072586045,4.7406654,80000
18
+ 0.2609416,0.8276453,-56.407856,-101.21665,-101.55251,0.39606768,8.737747,-6.0382385,116.82756,85000
19
+ 0.23211935,0.023752576,-96.24682,-101.11224,-101.65932,0.014498203,0.16131599,-0.16802102,7.218813,90000
20
+ 0.3112764,1.0492939,-74.05478,-100.776634,-101.2748,1.3547997,0.8479719,-0.82640076,43.31848,95000
21
+ 0.2756429,0.13587749,-0.38764143,-100.43736,-101.41557,0.06756749,0.28990766,-0.64481044,12.733299,100000
22
+ 0.27860045,0.09325719,-79.63735,-100.7333,-101.962555,0.32758787,0.19488434,-0.20109302,14.046765,105000
23
+ 0.24698414,1.2659097,-90.572784,-100.76091,-101.41109,0.15375823,0.33004528,-0.17565346,15.448582,110000
24
+ 0.18343832,0.07689959,-1.7316551,-100.47629,-101.34044,0.068440385,0.49067202,-0.20995331,10.763243,115000
25
+ 0.2336121,0.3924977,0.24815032,-100.346344,-101.202126,0.2850714,0.86962754,-0.73331976,28.021713,120000
26
+ 0.23221171,0.43321034,0.51447946,-100.415924,-101.35866,0.22174482,0.41969335,-0.66226226,18.518711,125000
27
+ 0.6650834,0.43978664,-3.636214,-100.37766,-101.088234,6.8801317,45.757565,-51.372307,1115.7535,130000
28
+ 0.25542653,3.4893365,0.4508555,-100.0767,-101.207214,0.22105284,3.2054658,-2.9116175,90.81673,135000
29
+ 0.22453591,1.6032562,0.4669857,-100.11322,-101.515396,0.28733924,0.2366283,-0.29326257,16.724274,140000
30
+ 0.4659013,1.0919783,0.36769378,-100.07789,-101.61082,0.32842848,0.1969239,-0.29683,26.860416,145000
31
+ 0.17003167,12.18307,-2.048141,-100.454254,-101.31355,0.6093159,0.6660909,-0.8381134,49.937458,150000
32
+ 0.2403077,7.2541385,-1.2366557,-100.09849,-101.1339,0.47000661,0.49237,-0.50344485,42.634254,155000
33
+ 0.18543074,0.1401987,-92.169685,-100.88802,-101.50689,0.24457793,0.4392179,-0.21940345,16.435913,160000
34
+ 0.2198374,0.0939626,-10.68817,-100.52316,-101.308655,0.3413899,0.48961776,-0.22475182,14.59041,165000
35
+ 0.2445609,0.10693157,-93.3237,-100.77631,-101.15113,0.07628318,0.13681135,-0.06179312,7.3527336,170000
36
+ 0.2708445,0.42822763,-73.7641,-100.55801,-101.34317,2.1945832,0.39439273,-0.3490316,22.272621,175000
37
+ 0.2380516,0.34342813,-6.728455,-100.30798,-101.2524,0.22735214,0.29232228,-0.17016333,16.273897,180000
38
+ 0.3315048,11.622565,-56.269073,-100.45227,-101.01305,0.7291837,1.8921052,-1.9226043,75.45816,185000
39
+ 0.2726216,0.3674917,-76.53105,-100.73354,-101.217186,0.14824629,0.09611399,-0.16458853,9.716139,190000
40
+ 0.25616065,0.3636475,2.077018,-100.19668,-101.055466,0.22407222,0.112004615,-0.2029684,13.315961,195000
41
+ 0.5057868,8.007448,-26.310984,-100.34588,-101.14538,2.9811962,3.302088,-3.6147504,137.9446,200000
42
+ 0.28584725,9.767978,0.08705963,-99.55639,-100.948494,1.5744547,4.459319,-6.445695,152.67435,205000
43
+ 0.45897686,0.9817589,0.07463494,-99.93108,-101.12207,0.9362506,0.40720576,-0.6043406,32.37635,210000
44
+ 0.18044347,0.26216772,-85.08917,-100.64482,-101.100876,0.27132007,0.91205364,-0.47453922,31.481997,215000
45
+ 0.29071495,0.04965577,-80.54141,-100.54223,-101.084595,0.35320428,0.19199938,-0.22250111,13.416677,220000
46
+ 0.21906236,0.4224023,-2.520843,-100.12729,-101.004425,0.26730818,0.3114289,-0.1712817,14.351221,225000
47
+ 0.4971079,0.11681416,-70.33,-100.487076,-100.99884,0.26051077,0.33194643,-0.3713237,16.544956,230000
48
+ 0.20078585,0.59601897,0.27120668,-99.87432,-101.08394,0.32049033,0.277836,-0.4061582,19.35922,235000
49
+ 0.3639936,2.0007591,-83.66632,-100.38052,-101.12757,17.318623,25.962252,-23.708956,555.53467,240000
50
+ 0.4107006,0.14509551,0.6543379,-99.79753,-101.05482,0.11738119,0.2849669,-0.5363231,15.388834,245000
51
+ 0.21721154,0.2381033,0.17362975,-100.207985,-101.06614,0.07926039,0.20892003,-0.22085735,11.147051,250000
52
+ 0.20546892,0.14417818,-1.2073487,-100.123924,-101.189705,0.14486006,0.47863775,-0.21523273,14.964552,255000
53
+ 0.32482323,10.129238,0.3307088,-100.002396,-101.11811,0.8077375,0.617138,-0.6485465,45.846565,260000
54
+ 0.19285831,0.9601361,-79.77692,-100.4875,-101.119736,0.6485451,0.35935417,-0.619354,25.914795,265000
55
+ 0.3029385,0.1777914,-15.028319,-100.024,-100.9289,0.41438913,0.22505751,-0.1959271,16.17265,270000
56
+ 0.45712495,1.1741623,0.3022747,-99.86296,-101.05323,0.6375449,0.23258565,-0.3474617,21.767769,275000
57
+ 0.23725918,0.42247364,-0.3295239,-99.97524,-100.88143,0.2925882,0.17251226,-0.42767817,17.139069,280000
58
+ 0.22221252,0.2540567,-78.16197,-100.5559,-101.08102,0.11907438,0.513087,-0.57103896,15.735911,285000
59
+ 0.3371608,0.7159322,-19.758472,-99.97973,-100.90503,2.821888,1.981438,-2.0766466,96.77292,290000
60
+ 0.23062044,0.631133,-88.77759,-100.35425,-100.86838,0.3822351,0.28213215,-0.31227183,22.01784,295000
61
+ 0.15873426,0.1593468,-0.46473706,-100.00747,-100.886314,0.1367429,0.48595455,-0.25764552,12.888859,300000
62
+ 0.2739727,2.5741181,-69.79533,-100.14436,-100.96599,0.35300156,0.51293385,-0.6720872,26.0718,305000
63
+ 0.21385136,0.27192482,-85.79416,-100.30785,-100.791275,0.36835495,0.19105402,-0.16734344,15.334282,310000
64
+ 0.17844453,3.5538907,-67.41752,-100.28579,-100.96607,0.11141427,0.2913221,-0.14377615,14.183277,315000
65
+ 0.23126413,0.7522397,-26.55983,-99.985,-100.990265,0.18431807,0.28015387,-0.2102393,16.464287,320000
66
+ 0.17666802,0.0510346,-1.8990211,-100.135315,-100.96789,0.45480165,0.70536214,-0.5313505,14.908633,325000
67
+ 0.2769337,0.5064916,-86.497955,-100.26916,-100.83334,0.62061507,0.603966,-1.0442107,28.820208,330000
68
+ 0.50607127,2.7196236,-75.244095,-100.358925,-100.96449,2.1635776,4.3757205,-5.6585455,173.70279,335000
69
+ 0.23592652,1.4351767,-84.574326,-100.26501,-100.89992,0.7550901,0.64166355,-0.38321173,29.099697,340000
70
+ 1.1257796,2.5076082,-9.745365,-99.741264,-100.99077,0.59209424,0.6449474,-1.1586493,45.33512,345000
71
+ 0.21076083,0.30180016,2.5175152,-100.09497,-100.98088,0.12683974,0.24680476,-0.22052854,8.171984,350000
72
+ 0.20972256,0.46007806,0.09206113,-99.935646,-101.13166,0.117180996,0.46157175,-0.21136624,13.713152,355000
73
+ 0.22968204,1.2975453,0.2938956,-99.707886,-101.02507,0.45007214,0.79540324,-0.8646804,28.70092,360000
74
+ 0.32090807,0.71173185,-71.74523,-100.0991,-100.91919,0.66176325,0.6059648,-0.79316485,31.330215,365000
75
+ 0.23091425,1.4721136,-81.262955,-100.37158,-101.0197,0.2640246,0.22125797,-0.40832528,16.409592,370000
76
+ 0.42481858,0.3190488,0.06872007,-99.47865,-100.98945,1.2189348,0.84045684,-0.7427862,31.643347,375000
77
+ 0.20523617,0.8314009,0.23811156,-99.541115,-100.89094,0.5389969,0.7393609,-0.77224064,39.569244,380000
78
+ 0.21416776,0.44021875,0.16997033,-99.856834,-100.8926,0.16708532,0.10235281,-0.060170814,9.236446,385000
79
+ 0.25788367,14.241304,0.29091108,-99.8082,-101.022995,0.9351082,0.8006637,-1.2207036,57.74623,390000
80
+ 0.2685551,3.337539,-73.77215,-100.21327,-101.17484,0.40944448,0.2957667,-0.42585823,31.103086,395000
81
+ 0.17374691,0.13219799,-82.240845,-100.3374,-101.173134,0.27551743,0.78149873,-1.0671475,21.72985,400000
82
+ 0.2275764,0.11006913,0.50799567,-99.8084,-101.02269,0.21162434,0.22061652,-0.267406,12.4430485,405000
83
+ 0.30137572,0.14325221,-84.92573,-100.3084,-100.96812,0.64485615,0.8208621,-0.61848485,19.110275,410000
84
+ 0.25883704,1.4766392,-72.11086,-100.025215,-100.89401,0.33256122,0.4214474,-0.5026648,24.788464,415000
85
+ 0.24546495,0.6704742,0.4305534,-99.51209,-101.02947,0.45398936,0.9450612,-1.1245114,35.264492,420000
86
+ 0.19830024,0.8217463,-74.9556,-100.313614,-101.131645,0.2165176,0.13135418,-0.26904854,14.180977,425000
87
+ 0.33047193,1.0660051,0.5133637,-99.66532,-100.93846,0.37195653,0.28194958,-0.8122812,19.89638,430000
88
+ 0.20798367,2.087362,-74.15748,-100.30198,-101.047325,0.2806898,0.9790543,-0.49685788,25.273804,435000
89
+ 0.18738988,0.11185815,-8.073764,-100.08879,-100.95187,5.4203796,36.272,-34.837475,1035.9828,440000
90
+ 0.18746911,0.1453195,-85.497055,-100.51228,-101.01153,0.11858573,0.98116314,-0.3964311,16.292048,445000
91
+ 0.31585097,0.48638716,0.09022999,-100.018326,-101.18553,0.21660462,0.3285753,-0.9849614,20.7284,450000
92
+ 0.21171016,0.7209562,-1.8603373,-99.84124,-101.000984,0.24298075,0.15491559,-0.16599776,12.259846,455000
93
+ 0.20554829,8.293859,0.0063835084,-99.96777,-100.96805,0.08021608,0.5758436,-0.685656,32.19394,460000
94
+ 0.32227874,0.52884674,0.5303297,-99.321976,-100.98093,0.95001715,1.7462629,-1.3047522,56.28937,465000
95
+ 0.25665173,0.2672539,-81.61102,-100.18575,-100.80193,0.79790366,0.38173115,-0.6120523,25.42994,470000
96
+ 0.22029687,3.523634,-68.61729,-100.124916,-100.84302,0.21512671,0.73566175,-0.43612784,24.154415,475000
97
+ 0.40917578,3.7071826,0.31399596,-99.366714,-100.78951,2.6465783,1.3586758,-1.763167,81.95957,480000
98
+ 0.30331033,0.095215924,-91.65438,-100.29248,-100.859116,0.2939578,0.28364006,-0.6062681,14.597069,485000
99
+ 0.53340334,0.7904257,-9.868786,-99.99535,-101.01815,0.3045543,0.66035026,-0.9780648,26.183718,490000
100
+ 0.21845809,0.14932275,0.27592787,-99.97366,-101.09759,0.2537888,0.6589999,-0.37433815,16.284185,495000
101
+ 0.2514034,0.14629701,-1.2839239,-100.01986,-100.91238,0.147602,0.33212793,-0.8958198,12.884441,500000
102
+ 0.2103116,0.64488286,0.17661452,-99.88354,-100.952835,0.19986117,0.16491637,-0.32236844,10.356983,505000
103
+ 0.20382458,0.0576819,-92.718,-100.34119,-100.913414,0.054176193,0.23396687,-0.079161316,7.7624874,510000
104
+ 0.29096127,0.24659215,0.07438961,-99.83965,-100.921165,0.31357798,0.28237012,-0.13588937,10.261234,515000
105
+ 0.20207672,2.7457879,-0.86304986,-99.64939,-100.96197,2.306154,1.7187761,-1.6423886,71.85309,520000
106
+ 0.25199932,24.907297,-78.18836,-99.946236,-100.87517,0.85926497,0.7521163,-0.72936,53.305347,525000
107
+ 0.21238065,10.665584,-2.096865,-99.99887,-100.92805,0.3000675,0.3308906,-0.26788965,22.633125,530000
108
+ 0.2063928,0.1475433,-76.15193,-100.06061,-100.91208,0.37026635,0.27565593,-0.5989175,16.011753,535000
109
+ 0.29245982,0.120379165,0.104290724,-99.870766,-101.12038,0.12239789,0.18781482,-0.518643,14.094328,540000
110
+ 0.25149503,12.483705,-75.42358,-100.13641,-100.84107,0.083959155,0.15374744,-0.22398801,12.472567,545000
111
+ 0.22946851,0.46818596,0.19480851,-99.82867,-100.7029,0.16856177,0.2100572,-0.28329977,15.173485,550000
112
+ 0.25396788,3.3392198,0.06102869,-99.44649,-100.80498,3.7868047,1.9990531,-2.2457004,99.179474,555000
113
+ 0.2372072,0.3671922,0.13524044,-99.80748,-100.91327,0.58936584,0.53665817,-0.9036026,19.570328,560000
114
+ 0.23895109,0.30537325,-90.20395,-100.3799,-100.829285,0.5249668,0.5205529,-1.1591876,20.038963,565000
115
+ 0.27211633,0.51882833,-22.611877,-100.049,-100.96416,0.6360037,1.9990433,-1.7728972,95.06458,570000
116
+ 0.2287849,2.8155038,0.27259532,-99.87101,-100.84773,0.308018,0.2070972,-0.17943965,14.933926,575000
117
+ 0.19314511,0.22708564,-0.057533264,-99.93312,-100.83253,0.25886843,0.4158726,-1.0535126,17.208038,580000
118
+ 0.18086654,1.2255799,-66.15179,-100.13556,-100.96815,0.20622063,1.1597998,-0.45624983,28.264841,585000
119
+ 0.16137186,0.29401508,0.39305454,-99.74908,-100.94342,0.06584373,0.07471207,-0.15200162,6.2048664,590000
120
+ 0.17670926,0.029530073,-82.45222,-100.408134,-100.88731,0.13859224,0.40738615,-0.16253944,10.544317,595000
121
+ 0.30993593,0.09500466,-74.85822,-100.19993,-100.793076,0.30735707,0.42644614,-0.3691037,19.632017,600000
122
+ 0.19792676,0.23793165,-91.19676,-100.38015,-100.79336,0.05125962,0.091167815,-0.034594234,5.4308214,605000
123
+ 0.18659273,0.30181175,0.2074894,-99.34298,-100.8367,0.21026932,0.22248116,-0.25158754,12.802622,610000
124
+ 0.25326622,0.12102971,0.18576792,-99.49166,-100.86903,0.33417803,0.2351017,-0.50301063,15.253417,615000
125
+ 0.16949694,0.35422167,-81.79811,-100.32998,-100.900116,0.19939081,0.13936287,-0.15867507,9.907725,620000
126
+ 0.27809197,0.3993218,-15.108309,-99.75783,-100.728294,0.6112494,0.65855503,-0.7864785,27.016787,625000
127
+ 0.20637417,0.34324947,-75.462074,-100.37359,-102.32112,0.05893693,0.40213448,-0.14671963,8.746129,630000
128
+ 0.23729862,0.5072116,-0.40248007,-99.7803,-100.89215,0.36912856,0.365312,-0.5402901,19.33196,635000
129
+ 0.17952096,2.2967021,0.12972301,-99.91609,-100.96024,0.27744445,0.26197425,-0.21687008,16.383028,640000
130
+ 0.2671109,0.63676935,-79.06018,-100.22953,-100.730934,0.12259271,0.17212299,-0.34193832,11.815531,645000
131
+ 0.18625215,0.11821487,-85.78768,-100.30681,-101.0433,0.107077055,0.11752571,-0.061383057,4.1137996,650000
132
+ 0.2140835,0.13866362,0.10867527,-99.08849,-100.81569,0.16594067,0.2419428,-0.3705828,13.209004,655000
133
+ 0.29637867,7.3535857,-81.34565,-100.141106,-100.77187,0.33142337,0.24278158,-0.23391545,18.981861,660000
134
+ 0.25292563,0.4841257,0.20456451,-99.71026,-100.74051,0.105357625,0.28778103,-0.671314,10.027105,665000
135
+ 0.21563154,0.30687898,-16.906153,-99.942604,-100.71481,0.07929269,0.3589295,-0.1763953,11.133225,670000
136
+ 0.1965871,0.17106313,-81.57942,-100.17335,-100.74024,0.23263502,0.6136447,-0.33925626,17.236916,675000
137
+ 0.17138359,0.39145997,-82.74516,-100.22075,-100.80901,0.06503244,0.61652976,-0.24764976,11.707111,680000
138
+ 0.19428125,12.328954,-76.32411,-100.28701,-100.767815,0.20890939,0.33907464,-0.220883,25.837807,685000
139
+ 0.19230829,0.22146049,-89.22778,-100.432915,-100.818535,0.1310761,0.12554732,-0.25592282,9.87409,690000
140
+ 0.19110379,0.112042226,-86.53295,-100.34521,-100.81989,0.03532011,0.12258612,-0.08090302,3.6329138,695000
141
+ 0.26839608,15.101239,0.21077523,-99.50091,-100.64534,0.23271827,0.3911237,-0.91251963,22.902884,700000
142
+ 0.19694069,0.26756468,-0.0667454,-99.610214,-100.867294,0.0681687,0.22934441,-0.11710673,6.4230585,705000
143
+ 0.17313826,0.54790175,0.19991252,-99.79639,-100.679375,0.09843191,0.60772765,-0.25377348,12.423157,710000
144
+ 0.19994277,11.866543,0.1923376,-99.25211,-100.81197,0.40185854,0.6760674,-0.61655617,33.847305,715000
145
+ 0.2617077,0.23573005,-82.059,-100.023544,-100.753075,0.16158424,0.31171972,-0.7506311,17.214928,720000
146
+ 0.16123174,2.207276,-19.328388,-99.84143,-100.90834,0.27794537,0.9265824,-0.3773012,25.38166,725000
147
+ 0.3246886,0.10882389,-11.6073475,-99.998535,-100.89197,0.20254035,0.67571783,-0.42940152,24.922646,730000
148
+ 0.237901,3.6202333,0.29410768,-99.59179,-101.476364,0.1681573,0.6483996,-0.87948626,31.038017,735000
149
+ 0.19806421,0.2691302,0.2850823,-99.803566,-100.69748,0.37927148,0.26380008,-0.5323889,15.391335,740000
150
+ 0.20123641,0.2767619,0.34712955,-99.82154,-100.844,0.06709682,0.07533969,-0.13750677,6.2106256,745000
151
+ 0.16571857,0.058999646,-12.712109,-99.910484,-100.711105,0.058097918,0.19875938,-0.09250298,6.263979,750000
152
+ 0.20331472,1.0743359,0.067183286,-99.475975,-100.75324,0.355511,0.7673763,-0.54023904,27.014362,755000
153
+ 0.27558428,0.5710838,-0.06918126,-99.41244,-100.634575,0.27391377,0.2963184,-0.38405216,16.805775,760000
154
+ 0.18770234,3.441246,-70.47877,-100.09123,-100.740486,0.19984983,0.5540973,-0.5120669,27.759377,765000
155
+ 0.19771615,0.10117866,-90.33486,-100.27997,-100.6531,0.13659273,0.74580383,-0.26218992,11.396174,770000
156
+ 0.183188,0.35604545,0.43779036,-99.82137,-100.72706,0.07495928,0.11123456,-0.0707181,5.273358,775000
157
+ 0.34611726,2.2829094,0.22576454,-99.59225,-100.807,2.1132631,0.8625061,-1.205832,51.18,780000
158
+ 0.28994533,0.69555146,0.49003437,-99.55749,-100.73265,0.24046493,0.23924708,-0.47517562,18.454659,785000
159
+ 0.23202097,0.14866781,-6.3773174,-99.83957,-100.837975,0.40446758,0.53041387,-1.1350788,25.8567,790000
160
+ 0.18001376,0.10981517,0.4289724,-99.80767,-100.79513,0.08815017,0.10846114,-0.058325715,3.9709249,795000
161
+ 0.23783621,0.039988074,-96.47916,-100.40272,-100.740654,0.0760754,0.19402082,-0.38973084,5.496591,800000
162
+ 0.20502365,1.2546706,-79.84188,-100.0566,-100.81358,0.1717389,0.1445698,-0.12368154,12.692157,805000
163
+ 0.21469477,0.13846886,-1.1590291,-100.11758,-100.95987,19.955572,2.4520104,-1.8562543,84.03417,810000
164
+ 0.22962457,0.05563218,-0.41654554,-99.84928,-100.845764,0.20631276,0.2285886,-0.46185002,12.679518,815000
165
+ 0.16333032,0.28369927,-16.867344,-100.075935,-100.82006,0.06313594,0.099090695,-0.24206555,7.8359566,820000
166
+ 0.19282612,22.432402,0.1830239,-99.78326,-100.66634,0.1552718,0.5157861,-0.40197265,29.24088,825000
167
+ 0.24765009,0.21813552,-82.21643,-100.159004,-100.84182,0.24878941,0.4318395,-0.32500717,15.599607,830000
168
+ 0.2075671,0.2594096,-80.42325,-100.14308,-100.75853,0.0424422,0.18855911,-0.069686696,6.836266,835000
169
+ 0.16133839,0.0577128,0.30058217,-99.995865,-100.82831,0.037096184,0.25003132,-0.099688575,4.7330327,840000
170
+ 0.1931781,0.121452406,-80.73546,-100.18199,-100.70252,0.07913082,0.71630013,-0.3114454,12.494635,845000
171
+ 0.21394677,0.12977341,-81.70693,-100.12697,-100.756226,0.105671264,0.300032,-0.6829814,12.132485,850000
172
+ 0.18160713,0.49381104,-3.1657145,-99.50201,-100.75695,0.36954376,0.7058332,-0.36248294,20.663204,855000
173
+ 0.27878657,11.000727,-62.30198,-99.96006,-100.7241,0.2907489,0.56022614,-0.61790967,36.762634,860000
174
+ 0.1998902,0.26038963,0.15823156,-99.44677,-100.810936,0.260839,0.33570012,-0.6198244,14.740345,865000
175
+ 0.15713158,0.39351034,-78.53953,-100.09133,-100.97739,0.13793902,0.30627388,-0.6455342,14.896187,870000
176
+ 0.18284205,15.36779,-84.84266,-100.29601,-100.918785,0.2710248,0.30339876,-0.26992455,20.973143,875000
177
+ 0.17347395,0.08828722,-87.95916,-100.30929,-100.762024,0.045684565,0.12766874,-0.2630027,4.8909235,880000
178
+ 0.19798902,0.05740228,-81.04703,-100.29976,-101.09033,0.29569942,0.17426628,-0.28532577,11.4477,885000
179
+ 0.17071299,2.0906909,-15.744319,-99.8424,-100.85173,0.17522731,0.6617784,-0.3140673,16.201405,890000
180
+ 0.22184063,0.20771806,-88.50115,-100.225174,-100.96973,0.27170098,0.5489736,-0.5030859,16.560513,895000
181
+ 0.1891011,0.11667366,-86.7876,-100.31628,-100.83644,0.041959617,0.066769645,-0.12544438,4.343469,900000
182
+ 0.16307724,0.26889774,0.0670729,-99.90982,-100.81736,0.06708904,0.19574,-0.10032371,5.562188,905000
183
+ 0.19288081,0.2814314,-5.976229,-99.958694,-100.89314,0.033585545,0.3774087,-0.1738782,5.374654,910000
184
+ 0.17859852,0.07318339,0.42951593,-99.83303,-100.72643,0.04421122,0.20352706,-0.069120035,4.15868,915000
185
+ 0.2449526,0.925082,-82.44861,-100.12782,-100.58277,0.2446404,0.60635203,-1.2861335,23.531286,920000
186
+ 0.1785632,0.052573223,-90.340576,-100.35158,-100.82143,0.06304245,0.068139896,-0.13259774,5.520061,925000
187
+ 0.20971283,0.40381575,-84.982834,-100.12861,-100.79197,0.069452524,0.14929149,-0.35799456,7.075247,930000
188
+ 0.17746982,2.064792,-94.077,-100.33059,-100.78886,0.45292607,0.49607736,-0.78594816,24.511803,935000
189
+ 0.18469019,0.51451045,-0.059998482,-99.80294,-100.92067,0.19005176,0.39681113,-0.9590275,19.399744,940000
190
+ 0.20256314,1.5692996,0.30178317,-99.40687,-100.86361,0.21258862,0.5672147,-0.28276604,19.021545,945000
191
+ 0.20590691,0.062438842,-2.7467802,-99.745384,-100.58286,0.04405596,0.33890083,-0.74567294,11.040033,950000
192
+ 0.1830896,0.13441156,0.2531456,-99.39999,-100.59019,0.06891879,0.18133102,-0.20118201,5.772876,955000
193
+ 0.25475237,5.157911,-10.4426155,-99.724075,-100.75119,0.3419428,0.22025953,-0.2721977,18.036224,960000
194
+ 0.19445863,1.4359354,-82.61858,-100.12812,-100.692696,0.10832138,0.28692847,-0.2592953,10.779348,965000
195
+ 0.19633351,2.7896786,-3.0418236,-99.63619,-100.82519,0.32609934,0.31753525,-0.4300772,28.507206,970000
196
+ 0.36091113,1.0729495,0.10778287,-99.33503,-100.74539,0.1344466,0.411665,-0.9125227,18.865469,975000
197
+ 0.19609651,0.23653975,-85.54065,-100.24403,-100.72906,0.101253234,0.1315724,-0.19006056,6.5097303,980000
198
+ 0.20511201,0.08802792,-89.688705,-100.36806,-100.80725,0.2182765,0.14952528,-0.28853452,10.367322,985000
199
+ 0.179744,0.55193084,-6.605167,-99.802124,-100.7644,0.11702309,0.105583854,-0.13483387,8.177393,990000
200
+ 0.20466864,0.031106636,-86.13422,-100.24232,-100.72789,0.0800535,0.18204492,-0.15052699,6.441738,995000
201
+ 0.17044032,0.3596142,0.1694071,-99.68297,-100.638794,0.09254839,0.4579007,-1.010879,15.257434,1000000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/offline_agent_sv.csv ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,critic/value_loss,grad/max,grad/min,grad/norm,step
2
+ 0.115540415,18.77205,-73.80803,-75.69133,-75.80335,0.003366718,0.06988833,-0.14721154,7.576399,5000
3
+ 0.25290036,1.1149992,-43.617916,-94.76918,-95.486946,0.03737503,6.335382,-6.4655666,100.07944,10000
4
+ 0.3779252,0.49680445,-88.759,-100.99047,-101.68877,0.02471619,0.3517061,-0.20656186,22.65007,15000
5
+ 0.3061837,0.31726307,-0.3807384,-102.31548,-104.170395,0.053845514,0.2240226,-0.31388137,15.487057,20000
6
+ 0.26091284,0.011727537,0.08710304,-102.82782,-103.53233,0.007286181,0.08635192,-0.033824697,3.6474416,25000
7
+ 0.28292555,0.06730841,-98.40343,-103.45326,-104.028145,0.13507043,0.1643811,-0.053109497,7.7025084,30000
8
+ 0.2149696,0.16047768,-0.22232223,-102.61609,-103.317696,0.07352119,0.64551485,-0.69563985,10.616798,35000
9
+ 0.30237496,0.8415882,-99.56935,-102.2476,-102.587006,0.03362368,0.24204859,-0.66677654,16.631441,40000
10
+ 0.2358851,0.02618273,-97.28751,-102.21511,-102.409805,0.037117798,0.17324038,-0.06658696,6.2354593,45000
11
+ 0.22886232,0.085374236,-0.21570209,-101.6305,-102.40136,0.06228729,0.13768992,-0.17911616,9.331837,50000
12
+ 0.22992794,0.06397193,-93.68237,-101.907326,-102.27688,0.030866787,0.06593228,-0.06415962,4.9773874,55000
13
+ 0.25256538,0.083970845,0.48268515,-101.44397,-102.37995,0.043460835,0.4801869,-0.20692748,13.231135,60000
14
+ 0.24700752,0.18971701,-89.302704,-101.9626,-102.31043,0.1077945,0.1855909,-0.4376136,13.281654,65000
15
+ 0.26320294,6.778486,0.30486643,-100.66872,-102.21684,3.1901453,6.341703,-8.844065,147.45123,70000
16
+ 0.34315318,6.4636483,-41.126846,-101.48792,-102.05954,12.334414,1.0402722,-1.6089591,82.40053,75000
17
+ 0.20272142,0.025911963,-98.98992,-101.42564,-101.87388,0.06477165,0.045217466,-0.072586045,4.7406654,80000
18
+ 0.2609416,0.8276453,-56.407856,-101.21665,-101.55251,0.39606768,8.737747,-6.0382385,116.82756,85000
19
+ 0.23211935,0.023752576,-96.24682,-101.11224,-101.65932,0.014498203,0.16131599,-0.16802102,7.218813,90000
20
+ 0.3112764,1.0492939,-74.05478,-100.776634,-101.2748,1.3547997,0.8479719,-0.82640076,43.31848,95000
21
+ 0.2756429,0.13587749,-0.38764143,-100.43736,-101.41557,0.06756749,0.28990766,-0.64481044,12.733299,100000
22
+ 0.27860045,0.09325719,-79.63735,-100.7333,-101.962555,0.32758787,0.19488434,-0.20109302,14.046765,105000
23
+ 0.24698414,1.2659097,-90.572784,-100.76091,-101.41109,0.15375823,0.33004528,-0.17565346,15.448582,110000
24
+ 0.18343832,0.07689959,-1.7316551,-100.47629,-101.34044,0.068440385,0.49067202,-0.20995331,10.763243,115000
25
+ 0.2336121,0.3924977,0.24815032,-100.346344,-101.202126,0.2850714,0.86962754,-0.73331976,28.021713,120000
26
+ 0.23221171,0.43321034,0.51447946,-100.415924,-101.35866,0.22174482,0.41969335,-0.66226226,18.518711,125000
27
+ 0.6650834,0.43978664,-3.636214,-100.37766,-101.088234,6.8801317,45.757565,-51.372307,1115.7535,130000
28
+ 0.25542653,3.4893365,0.4508555,-100.0767,-101.207214,0.22105284,3.2054658,-2.9116175,90.81673,135000
29
+ 0.22453591,1.6032562,0.4669857,-100.11322,-101.515396,0.28733924,0.2366283,-0.29326257,16.724274,140000
30
+ 0.4659013,1.0919783,0.36769378,-100.07789,-101.61082,0.32842848,0.1969239,-0.29683,26.860416,145000
31
+ 0.17003167,12.18307,-2.048141,-100.454254,-101.31355,0.6093159,0.6660909,-0.8381134,49.937458,150000
32
+ 0.2403077,7.2541385,-1.2366557,-100.09849,-101.1339,0.47000661,0.49237,-0.50344485,42.634254,155000
33
+ 0.18543074,0.1401987,-92.169685,-100.88802,-101.50689,0.24457793,0.4392179,-0.21940345,16.435913,160000
34
+ 0.2198374,0.0939626,-10.68817,-100.52316,-101.308655,0.3413899,0.48961776,-0.22475182,14.59041,165000
35
+ 0.2445609,0.10693157,-93.3237,-100.77631,-101.15113,0.07628318,0.13681135,-0.06179312,7.3527336,170000
36
+ 0.2708445,0.42822763,-73.7641,-100.55801,-101.34317,2.1945832,0.39439273,-0.3490316,22.272621,175000
37
+ 0.2380516,0.34342813,-6.728455,-100.30798,-101.2524,0.22735214,0.29232228,-0.17016333,16.273897,180000
38
+ 0.3315048,11.622565,-56.269073,-100.45227,-101.01305,0.7291837,1.8921052,-1.9226043,75.45816,185000
39
+ 0.2726216,0.3674917,-76.53105,-100.73354,-101.217186,0.14824629,0.09611399,-0.16458853,9.716139,190000
40
+ 0.25616065,0.3636475,2.077018,-100.19668,-101.055466,0.22407222,0.112004615,-0.2029684,13.315961,195000
41
+ 0.5057868,8.007448,-26.310984,-100.34588,-101.14538,2.9811962,3.302088,-3.6147504,137.9446,200000
42
+ 0.28584725,9.767978,0.08705963,-99.55639,-100.948494,1.5744547,4.459319,-6.445695,152.67435,205000
43
+ 0.45897686,0.9817589,0.07463494,-99.93108,-101.12207,0.9362506,0.40720576,-0.6043406,32.37635,210000
44
+ 0.18044347,0.26216772,-85.08917,-100.64482,-101.100876,0.27132007,0.91205364,-0.47453922,31.481997,215000
45
+ 0.29071495,0.04965577,-80.54141,-100.54223,-101.084595,0.35320428,0.19199938,-0.22250111,13.416677,220000
46
+ 0.21906236,0.4224023,-2.520843,-100.12729,-101.004425,0.26730818,0.3114289,-0.1712817,14.351221,225000
47
+ 0.4971079,0.11681416,-70.33,-100.487076,-100.99884,0.26051077,0.33194643,-0.3713237,16.544956,230000
48
+ 0.20078585,0.59601897,0.27120668,-99.87432,-101.08394,0.32049033,0.277836,-0.4061582,19.35922,235000
49
+ 0.3639936,2.0007591,-83.66632,-100.38052,-101.12757,17.318623,25.962252,-23.708956,555.53467,240000
50
+ 0.4107006,0.14509551,0.6543379,-99.79753,-101.05482,0.11738119,0.2849669,-0.5363231,15.388834,245000
51
+ 0.21721154,0.2381033,0.17362975,-100.207985,-101.06614,0.07926039,0.20892003,-0.22085735,11.147051,250000
52
+ 0.20546892,0.14417818,-1.2073487,-100.123924,-101.189705,0.14486006,0.47863775,-0.21523273,14.964552,255000
53
+ 0.32482323,10.129238,0.3307088,-100.002396,-101.11811,0.8077375,0.617138,-0.6485465,45.846565,260000
54
+ 0.19285831,0.9601361,-79.77692,-100.4875,-101.119736,0.6485451,0.35935417,-0.619354,25.914795,265000
55
+ 0.3029385,0.1777914,-15.028319,-100.024,-100.9289,0.41438913,0.22505751,-0.1959271,16.17265,270000
56
+ 0.45712495,1.1741623,0.3022747,-99.86296,-101.05323,0.6375449,0.23258565,-0.3474617,21.767769,275000
57
+ 0.23725918,0.42247364,-0.3295239,-99.97524,-100.88143,0.2925882,0.17251226,-0.42767817,17.139069,280000
58
+ 0.22221252,0.2540567,-78.16197,-100.5559,-101.08102,0.11907438,0.513087,-0.57103896,15.735911,285000
59
+ 0.3371608,0.7159322,-19.758472,-99.97973,-100.90503,2.821888,1.981438,-2.0766466,96.77292,290000
60
+ 0.23062044,0.631133,-88.77759,-100.35425,-100.86838,0.3822351,0.28213215,-0.31227183,22.01784,295000
61
+ 0.15873426,0.1593468,-0.46473706,-100.00747,-100.886314,0.1367429,0.48595455,-0.25764552,12.888859,300000
62
+ 0.2739727,2.5741181,-69.79533,-100.14436,-100.96599,0.35300156,0.51293385,-0.6720872,26.0718,305000
63
+ 0.21385136,0.27192482,-85.79416,-100.30785,-100.791275,0.36835495,0.19105402,-0.16734344,15.334282,310000
64
+ 0.17844453,3.5538907,-67.41752,-100.28579,-100.96607,0.11141427,0.2913221,-0.14377615,14.183277,315000
65
+ 0.23126413,0.7522397,-26.55983,-99.985,-100.990265,0.18431807,0.28015387,-0.2102393,16.464287,320000
66
+ 0.17666802,0.0510346,-1.8990211,-100.135315,-100.96789,0.45480165,0.70536214,-0.5313505,14.908633,325000
67
+ 0.2769337,0.5064916,-86.497955,-100.26916,-100.83334,0.62061507,0.603966,-1.0442107,28.820208,330000
68
+ 0.50607127,2.7196236,-75.244095,-100.358925,-100.96449,2.1635776,4.3757205,-5.6585455,173.70279,335000
69
+ 0.23592652,1.4351767,-84.574326,-100.26501,-100.89992,0.7550901,0.64166355,-0.38321173,29.099697,340000
70
+ 1.1257796,2.5076082,-9.745365,-99.741264,-100.99077,0.59209424,0.6449474,-1.1586493,45.33512,345000
71
+ 0.21076083,0.30180016,2.5175152,-100.09497,-100.98088,0.12683974,0.24680476,-0.22052854,8.171984,350000
72
+ 0.20972256,0.46007806,0.09206113,-99.935646,-101.13166,0.117180996,0.46157175,-0.21136624,13.713152,355000
73
+ 0.22968204,1.2975453,0.2938956,-99.707886,-101.02507,0.45007214,0.79540324,-0.8646804,28.70092,360000
74
+ 0.32090807,0.71173185,-71.74523,-100.0991,-100.91919,0.66176325,0.6059648,-0.79316485,31.330215,365000
75
+ 0.23091425,1.4721136,-81.262955,-100.37158,-101.0197,0.2640246,0.22125797,-0.40832528,16.409592,370000
76
+ 0.42481858,0.3190488,0.06872007,-99.47865,-100.98945,1.2189348,0.84045684,-0.7427862,31.643347,375000
77
+ 0.20523617,0.8314009,0.23811156,-99.541115,-100.89094,0.5389969,0.7393609,-0.77224064,39.569244,380000
78
+ 0.21416776,0.44021875,0.16997033,-99.856834,-100.8926,0.16708532,0.10235281,-0.060170814,9.236446,385000
79
+ 0.25788367,14.241304,0.29091108,-99.8082,-101.022995,0.9351082,0.8006637,-1.2207036,57.74623,390000
80
+ 0.2685551,3.337539,-73.77215,-100.21327,-101.17484,0.40944448,0.2957667,-0.42585823,31.103086,395000
81
+ 0.17374691,0.13219799,-82.240845,-100.3374,-101.173134,0.27551743,0.78149873,-1.0671475,21.72985,400000
82
+ 0.2275764,0.11006913,0.50799567,-99.8084,-101.02269,0.21162434,0.22061652,-0.267406,12.4430485,405000
83
+ 0.30137572,0.14325221,-84.92573,-100.3084,-100.96812,0.64485615,0.8208621,-0.61848485,19.110275,410000
84
+ 0.25883704,1.4766392,-72.11086,-100.025215,-100.89401,0.33256122,0.4214474,-0.5026648,24.788464,415000
85
+ 0.24546495,0.6704742,0.4305534,-99.51209,-101.02947,0.45398936,0.9450612,-1.1245114,35.264492,420000
86
+ 0.19830024,0.8217463,-74.9556,-100.313614,-101.131645,0.2165176,0.13135418,-0.26904854,14.180977,425000
87
+ 0.33047193,1.0660051,0.5133637,-99.66532,-100.93846,0.37195653,0.28194958,-0.8122812,19.89638,430000
88
+ 0.20798367,2.087362,-74.15748,-100.30198,-101.047325,0.2806898,0.9790543,-0.49685788,25.273804,435000
89
+ 0.18738988,0.11185815,-8.073764,-100.08879,-100.95187,5.4203796,36.272,-34.837475,1035.9828,440000
90
+ 0.18746911,0.1453195,-85.497055,-100.51228,-101.01153,0.11858573,0.98116314,-0.3964311,16.292048,445000
91
+ 0.31585097,0.48638716,0.09022999,-100.018326,-101.18553,0.21660462,0.3285753,-0.9849614,20.7284,450000
92
+ 0.21171016,0.7209562,-1.8603373,-99.84124,-101.000984,0.24298075,0.15491559,-0.16599776,12.259846,455000
93
+ 0.20554829,8.293859,0.0063835084,-99.96777,-100.96805,0.08021608,0.5758436,-0.685656,32.19394,460000
94
+ 0.32227874,0.52884674,0.5303297,-99.321976,-100.98093,0.95001715,1.7462629,-1.3047522,56.28937,465000
95
+ 0.25665173,0.2672539,-81.61102,-100.18575,-100.80193,0.79790366,0.38173115,-0.6120523,25.42994,470000
96
+ 0.22029687,3.523634,-68.61729,-100.124916,-100.84302,0.21512671,0.73566175,-0.43612784,24.154415,475000
97
+ 0.40917578,3.7071826,0.31399596,-99.366714,-100.78951,2.6465783,1.3586758,-1.763167,81.95957,480000
98
+ 0.30331033,0.095215924,-91.65438,-100.29248,-100.859116,0.2939578,0.28364006,-0.6062681,14.597069,485000
99
+ 0.53340334,0.7904257,-9.868786,-99.99535,-101.01815,0.3045543,0.66035026,-0.9780648,26.183718,490000
100
+ 0.21845809,0.14932275,0.27592787,-99.97366,-101.09759,0.2537888,0.6589999,-0.37433815,16.284185,495000
101
+ 0.2514034,0.14629701,-1.2839239,-100.01986,-100.91238,0.147602,0.33212793,-0.8958198,12.884441,500000
102
+ 0.2103116,0.64488286,0.17661452,-99.88354,-100.952835,0.19986117,0.16491637,-0.32236844,10.356983,505000
103
+ 0.20382458,0.0576819,-92.718,-100.34119,-100.913414,0.054176193,0.23396687,-0.079161316,7.7624874,510000
104
+ 0.29096127,0.24659215,0.07438961,-99.83965,-100.921165,0.31357798,0.28237012,-0.13588937,10.261234,515000
105
+ 0.20207672,2.7457879,-0.86304986,-99.64939,-100.96197,2.306154,1.7187761,-1.6423886,71.85309,520000
106
+ 0.25199932,24.907297,-78.18836,-99.946236,-100.87517,0.85926497,0.7521163,-0.72936,53.305347,525000
107
+ 0.21238065,10.665584,-2.096865,-99.99887,-100.92805,0.3000675,0.3308906,-0.26788965,22.633125,530000
108
+ 0.2063928,0.1475433,-76.15193,-100.06061,-100.91208,0.37026635,0.27565593,-0.5989175,16.011753,535000
109
+ 0.29245982,0.120379165,0.104290724,-99.870766,-101.12038,0.12239789,0.18781482,-0.518643,14.094328,540000
110
+ 0.25149503,12.483705,-75.42358,-100.13641,-100.84107,0.083959155,0.15374744,-0.22398801,12.472567,545000
111
+ 0.22946851,0.46818596,0.19480851,-99.82867,-100.7029,0.16856177,0.2100572,-0.28329977,15.173485,550000
112
+ 0.25396788,3.3392198,0.06102869,-99.44649,-100.80498,3.7868047,1.9990531,-2.2457004,99.179474,555000
113
+ 0.2372072,0.3671922,0.13524044,-99.80748,-100.91327,0.58936584,0.53665817,-0.9036026,19.570328,560000
114
+ 0.23895109,0.30537325,-90.20395,-100.3799,-100.829285,0.5249668,0.5205529,-1.1591876,20.038963,565000
115
+ 0.27211633,0.51882833,-22.611877,-100.049,-100.96416,0.6360037,1.9990433,-1.7728972,95.06458,570000
116
+ 0.2287849,2.8155038,0.27259532,-99.87101,-100.84773,0.308018,0.2070972,-0.17943965,14.933926,575000
117
+ 0.19314511,0.22708564,-0.057533264,-99.93312,-100.83253,0.25886843,0.4158726,-1.0535126,17.208038,580000
118
+ 0.18086654,1.2255799,-66.15179,-100.13556,-100.96815,0.20622063,1.1597998,-0.45624983,28.264841,585000
119
+ 0.16137186,0.29401508,0.39305454,-99.74908,-100.94342,0.06584373,0.07471207,-0.15200162,6.2048664,590000
120
+ 0.17670926,0.029530073,-82.45222,-100.408134,-100.88731,0.13859224,0.40738615,-0.16253944,10.544317,595000
121
+ 0.30993593,0.09500466,-74.85822,-100.19993,-100.793076,0.30735707,0.42644614,-0.3691037,19.632017,600000
122
+ 0.19792676,0.23793165,-91.19676,-100.38015,-100.79336,0.05125962,0.091167815,-0.034594234,5.4308214,605000
123
+ 0.18659273,0.30181175,0.2074894,-99.34298,-100.8367,0.21026932,0.22248116,-0.25158754,12.802622,610000
124
+ 0.25326622,0.12102971,0.18576792,-99.49166,-100.86903,0.33417803,0.2351017,-0.50301063,15.253417,615000
125
+ 0.16949694,0.35422167,-81.79811,-100.32998,-100.900116,0.19939081,0.13936287,-0.15867507,9.907725,620000
126
+ 0.27809197,0.3993218,-15.108309,-99.75783,-100.728294,0.6112494,0.65855503,-0.7864785,27.016787,625000
127
+ 0.20637417,0.34324947,-75.462074,-100.37359,-102.32112,0.05893693,0.40213448,-0.14671963,8.746129,630000
128
+ 0.23729862,0.5072116,-0.40248007,-99.7803,-100.89215,0.36912856,0.365312,-0.5402901,19.33196,635000
129
+ 0.17952096,2.2967021,0.12972301,-99.91609,-100.96024,0.27744445,0.26197425,-0.21687008,16.383028,640000
130
+ 0.2671109,0.63676935,-79.06018,-100.22953,-100.730934,0.12259271,0.17212299,-0.34193832,11.815531,645000
131
+ 0.18625215,0.11821487,-85.78768,-100.30681,-101.0433,0.107077055,0.11752571,-0.061383057,4.1137996,650000
132
+ 0.2140835,0.13866362,0.10867527,-99.08849,-100.81569,0.16594067,0.2419428,-0.3705828,13.209004,655000
133
+ 0.29637867,7.3535857,-81.34565,-100.141106,-100.77187,0.33142337,0.24278158,-0.23391545,18.981861,660000
134
+ 0.25292563,0.4841257,0.20456451,-99.71026,-100.74051,0.105357625,0.28778103,-0.671314,10.027105,665000
135
+ 0.21563154,0.30687898,-16.906153,-99.942604,-100.71481,0.07929269,0.3589295,-0.1763953,11.133225,670000
136
+ 0.1965871,0.17106313,-81.57942,-100.17335,-100.74024,0.23263502,0.6136447,-0.33925626,17.236916,675000
137
+ 0.17138359,0.39145997,-82.74516,-100.22075,-100.80901,0.06503244,0.61652976,-0.24764976,11.707111,680000
138
+ 0.19428125,12.328954,-76.32411,-100.28701,-100.767815,0.20890939,0.33907464,-0.220883,25.837807,685000
139
+ 0.19230829,0.22146049,-89.22778,-100.432915,-100.818535,0.1310761,0.12554732,-0.25592282,9.87409,690000
140
+ 0.19110379,0.112042226,-86.53295,-100.34521,-100.81989,0.03532011,0.12258612,-0.08090302,3.6329138,695000
141
+ 0.26839608,15.101239,0.21077523,-99.50091,-100.64534,0.23271827,0.3911237,-0.91251963,22.902884,700000
142
+ 0.19694069,0.26756468,-0.0667454,-99.610214,-100.867294,0.0681687,0.22934441,-0.11710673,6.4230585,705000
143
+ 0.17313826,0.54790175,0.19991252,-99.79639,-100.679375,0.09843191,0.60772765,-0.25377348,12.423157,710000
144
+ 0.19994277,11.866543,0.1923376,-99.25211,-100.81197,0.40185854,0.6760674,-0.61655617,33.847305,715000
145
+ 0.2617077,0.23573005,-82.059,-100.023544,-100.753075,0.16158424,0.31171972,-0.7506311,17.214928,720000
146
+ 0.16123174,2.207276,-19.328388,-99.84143,-100.90834,0.27794537,0.9265824,-0.3773012,25.38166,725000
147
+ 0.3246886,0.10882389,-11.6073475,-99.998535,-100.89197,0.20254035,0.67571783,-0.42940152,24.922646,730000
148
+ 0.237901,3.6202333,0.29410768,-99.59179,-101.476364,0.1681573,0.6483996,-0.87948626,31.038017,735000
149
+ 0.19806421,0.2691302,0.2850823,-99.803566,-100.69748,0.37927148,0.26380008,-0.5323889,15.391335,740000
150
+ 0.20123641,0.2767619,0.34712955,-99.82154,-100.844,0.06709682,0.07533969,-0.13750677,6.2106256,745000
151
+ 0.16571857,0.058999646,-12.712109,-99.910484,-100.711105,0.058097918,0.19875938,-0.09250298,6.263979,750000
152
+ 0.20331472,1.0743359,0.067183286,-99.475975,-100.75324,0.355511,0.7673763,-0.54023904,27.014362,755000
153
+ 0.27558428,0.5710838,-0.06918126,-99.41244,-100.634575,0.27391377,0.2963184,-0.38405216,16.805775,760000
154
+ 0.18770234,3.441246,-70.47877,-100.09123,-100.740486,0.19984983,0.5540973,-0.5120669,27.759377,765000
155
+ 0.19771615,0.10117866,-90.33486,-100.27997,-100.6531,0.13659273,0.74580383,-0.26218992,11.396174,770000
156
+ 0.183188,0.35604545,0.43779036,-99.82137,-100.72706,0.07495928,0.11123456,-0.0707181,5.273358,775000
157
+ 0.34611726,2.2829094,0.22576454,-99.59225,-100.807,2.1132631,0.8625061,-1.205832,51.18,780000
158
+ 0.28994533,0.69555146,0.49003437,-99.55749,-100.73265,0.24046493,0.23924708,-0.47517562,18.454659,785000
159
+ 0.23202097,0.14866781,-6.3773174,-99.83957,-100.837975,0.40446758,0.53041387,-1.1350788,25.8567,790000
160
+ 0.18001376,0.10981517,0.4289724,-99.80767,-100.79513,0.08815017,0.10846114,-0.058325715,3.9709249,795000
161
+ 0.23783621,0.039988074,-96.47916,-100.40272,-100.740654,0.0760754,0.19402082,-0.38973084,5.496591,800000
162
+ 0.20502365,1.2546706,-79.84188,-100.0566,-100.81358,0.1717389,0.1445698,-0.12368154,12.692157,805000
163
+ 0.21469477,0.13846886,-1.1590291,-100.11758,-100.95987,19.955572,2.4520104,-1.8562543,84.03417,810000
164
+ 0.22962457,0.05563218,-0.41654554,-99.84928,-100.845764,0.20631276,0.2285886,-0.46185002,12.679518,815000
165
+ 0.16333032,0.28369927,-16.867344,-100.075935,-100.82006,0.06313594,0.099090695,-0.24206555,7.8359566,820000
166
+ 0.19282612,22.432402,0.1830239,-99.78326,-100.66634,0.1552718,0.5157861,-0.40197265,29.24088,825000
167
+ 0.24765009,0.21813552,-82.21643,-100.159004,-100.84182,0.24878941,0.4318395,-0.32500717,15.599607,830000
168
+ 0.2075671,0.2594096,-80.42325,-100.14308,-100.75853,0.0424422,0.18855911,-0.069686696,6.836266,835000
169
+ 0.16133839,0.0577128,0.30058217,-99.995865,-100.82831,0.037096184,0.25003132,-0.099688575,4.7330327,840000
170
+ 0.1931781,0.121452406,-80.73546,-100.18199,-100.70252,0.07913082,0.71630013,-0.3114454,12.494635,845000
171
+ 0.21394677,0.12977341,-81.70693,-100.12697,-100.756226,0.105671264,0.300032,-0.6829814,12.132485,850000
172
+ 0.18160713,0.49381104,-3.1657145,-99.50201,-100.75695,0.36954376,0.7058332,-0.36248294,20.663204,855000
173
+ 0.27878657,11.000727,-62.30198,-99.96006,-100.7241,0.2907489,0.56022614,-0.61790967,36.762634,860000
174
+ 0.1998902,0.26038963,0.15823156,-99.44677,-100.810936,0.260839,0.33570012,-0.6198244,14.740345,865000
175
+ 0.15713158,0.39351034,-78.53953,-100.09133,-100.97739,0.13793902,0.30627388,-0.6455342,14.896187,870000
176
+ 0.18284205,15.36779,-84.84266,-100.29601,-100.918785,0.2710248,0.30339876,-0.26992455,20.973143,875000
177
+ 0.17347395,0.08828722,-87.95916,-100.30929,-100.762024,0.045684565,0.12766874,-0.2630027,4.8909235,880000
178
+ 0.19798902,0.05740228,-81.04703,-100.29976,-101.09033,0.29569942,0.17426628,-0.28532577,11.4477,885000
179
+ 0.17071299,2.0906909,-15.744319,-99.8424,-100.85173,0.17522731,0.6617784,-0.3140673,16.201405,890000
180
+ 0.22184063,0.20771806,-88.50115,-100.225174,-100.96973,0.27170098,0.5489736,-0.5030859,16.560513,895000
181
+ 0.1891011,0.11667366,-86.7876,-100.31628,-100.83644,0.041959617,0.066769645,-0.12544438,4.343469,900000
182
+ 0.16307724,0.26889774,0.0670729,-99.90982,-100.81736,0.06708904,0.19574,-0.10032371,5.562188,905000
183
+ 0.19288081,0.2814314,-5.976229,-99.958694,-100.89314,0.033585545,0.3774087,-0.1738782,5.374654,910000
184
+ 0.17859852,0.07318339,0.42951593,-99.83303,-100.72643,0.04421122,0.20352706,-0.069120035,4.15868,915000
185
+ 0.2449526,0.925082,-82.44861,-100.12782,-100.58277,0.2446404,0.60635203,-1.2861335,23.531286,920000
186
+ 0.1785632,0.052573223,-90.340576,-100.35158,-100.82143,0.06304245,0.068139896,-0.13259774,5.520061,925000
187
+ 0.20971283,0.40381575,-84.982834,-100.12861,-100.79197,0.069452524,0.14929149,-0.35799456,7.075247,930000
188
+ 0.17746982,2.064792,-94.077,-100.33059,-100.78886,0.45292607,0.49607736,-0.78594816,24.511803,935000
189
+ 0.18469019,0.51451045,-0.059998482,-99.80294,-100.92067,0.19005176,0.39681113,-0.9590275,19.399744,940000
190
+ 0.20256314,1.5692996,0.30178317,-99.40687,-100.86361,0.21258862,0.5672147,-0.28276604,19.021545,945000
191
+ 0.20590691,0.062438842,-2.7467802,-99.745384,-100.58286,0.04405596,0.33890083,-0.74567294,11.040033,950000
192
+ 0.1830896,0.13441156,0.2531456,-99.39999,-100.59019,0.06891879,0.18133102,-0.20118201,5.772876,955000
193
+ 0.25475237,5.157911,-10.4426155,-99.724075,-100.75119,0.3419428,0.22025953,-0.2721977,18.036224,960000
194
+ 0.19445863,1.4359354,-82.61858,-100.12812,-100.692696,0.10832138,0.28692847,-0.2592953,10.779348,965000
195
+ 0.19633351,2.7896786,-3.0418236,-99.63619,-100.82519,0.32609934,0.31753525,-0.4300772,28.507206,970000
196
+ 0.36091113,1.0729495,0.10778287,-99.33503,-100.74539,0.1344466,0.411665,-0.9125227,18.865469,975000
197
+ 0.19609651,0.23653975,-85.54065,-100.24403,-100.72906,0.101253234,0.1315724,-0.19006056,6.5097303,980000
198
+ 0.20511201,0.08802792,-89.688705,-100.36806,-100.80725,0.2182765,0.14952528,-0.28853452,10.367322,985000
199
+ 0.179744,0.55193084,-6.605167,-99.802124,-100.7644,0.11702309,0.105583854,-0.13483387,8.177393,990000
200
+ 0.20466864,0.031106636,-86.13422,-100.24232,-100.72789,0.0800535,0.18204492,-0.15052699,6.441738,995000
201
+ 0.17044032,0.3596142,0.1694071,-99.68297,-100.638794,0.09254839,0.4579007,-1.010879,15.257434,1000000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,critic/value_loss,grad/max,grad/min,grad/norm,step
2
+ 0.18768835,0.09134745,-81.35456,-100.10657,-100.69836,0.046444837,0.22641602,-0.11820134,5.377088,1005000
3
+ 0.18959102,0.8001544,-2.1180587,-99.40464,-100.66217,0.084856465,0.19296026,-0.45685777,12.238469,1010000
4
+ 0.17323738,0.031234836,-0.010850221,-99.948364,-100.74427,0.10231266,0.23432507,-0.49583757,6.1740317,1015000
5
+ 0.21360493,1.2108244,-3.4438605,-99.7636,-100.73472,0.18339132,0.14564978,-0.103390984,10.372396,1020000
6
+ 0.18424219,0.10282203,-13.680149,-99.94629,-100.76613,0.14077373,0.2639478,-0.23743267,10.373459,1025000
7
+ 0.20109639,15.606928,-83.46211,-100.20523,-100.68811,0.12598814,0.30123273,-0.3004239,24.702065,1030000
8
+ 0.20047064,0.69664437,-3.5296645,-99.88196,-100.64751,0.13021243,0.30175877,-0.3302073,13.915092,1035000
9
+ 0.14050622,12.707795,-85.7594,-100.24656,-100.767624,0.08920359,0.21173464,-0.26065344,18.418695,1040000
10
+ 0.18952814,0.7576336,0.52932525,-99.8963,-100.66767,0.06853577,0.14343488,-0.14493653,7.8183746,1045000
11
+ 0.20787191,1.1953893,-7.1778026,-99.91464,-100.77508,0.37425265,0.27106148,-0.61055,21.305779,1050000
12
+ 0.18742537,0.10520468,-7.9034896,-99.724724,-100.68835,0.10004437,0.06728807,-0.14032187,6.1661243,1055000
13
+ 0.18812716,0.16505535,0.22004563,-99.68578,-100.58723,0.1608262,0.20038985,-0.16985506,9.379223,1060000
14
+ 0.17825001,0.13091877,-70.822205,-100.126816,-100.74939,0.07971448,0.19911274,-0.4347616,10.007163,1065000
15
+ 0.20393723,0.055244338,-82.330315,-100.24187,-100.75057,0.051563382,0.16613144,-0.0894955,6.1620097,1070000
16
+ 0.20618097,4.2754803,-7.447969,-99.767525,-100.621704,0.14043233,0.22141336,-0.13865013,13.677859,1075000
17
+ 0.26609784,0.15401728,-1.6446027,-99.916725,-100.7277,0.30799612,0.25422013,-0.28487203,15.242995,1080000
18
+ 0.20422328,2.9983993,-13.4096775,-99.91967,-100.58542,0.0828132,1.014887,-1.5700327,61.08101,1085000
19
+ 0.21155089,0.32314858,-35.446728,-99.89916,-100.811646,0.14281945,0.20920117,-0.17242141,12.327435,1090000
20
+ 0.1909797,0.4028941,-85.827774,-100.12478,-100.598274,0.16183014,0.23197475,-0.16038668,11.633423,1095000
21
+ 0.1982997,0.5896541,-91.29394,-100.22401,-100.660225,0.10487254,0.19172195,-0.40468398,11.60808,1100000
22
+ 0.17524832,2.2540474,-3.240529,-99.63857,-100.74553,0.42862082,0.592464,-0.6824983,29.410301,1105000
23
+ 0.21556115,0.58752865,0.26935378,-99.61708,-100.57809,0.16101429,0.22422373,-0.29086053,13.164018,1110000
24
+ 0.1646298,0.28300837,-87.958626,-100.23917,-100.91821,0.08933005,0.11947683,-0.2592392,6.478447,1115000
25
+ 0.19032833,0.108518176,-4.2475653,-99.196,-100.64749,0.17980304,0.5490432,-0.26493716,11.305365,1120000
26
+ 0.21902466,1.122633,-83.55025,-100.11734,-100.71083,0.10176104,0.29603165,-0.5951922,11.918346,1125000
27
+ 0.19502352,0.736931,-0.55136895,-99.763824,-100.77275,0.11731117,0.09693681,-0.10179228,10.104057,1130000
28
+ 0.18845978,0.019936843,-87.54437,-100.378586,-100.719635,0.07884538,0.2930892,-0.30880827,8.5104065,1135000
29
+ 0.19772722,0.22942562,-81.809204,-100.028885,-100.55735,0.06193478,0.28592247,-0.14620104,7.439246,1140000
30
+ 0.21269983,0.7816989,0.31948322,-99.61786,-100.76116,0.8037769,2.0880206,-4.8273664,85.83455,1145000
31
+ 0.15721972,0.10989926,-87.40582,-100.16735,-100.73699,0.05100562,0.5841391,-0.25484556,6.719847,1150000
32
+ 0.19116358,0.3378856,0.263353,-99.74538,-100.74967,0.05869899,0.44856888,-0.20846105,7.4776115,1155000
33
+ 0.20146063,2.1037292,0.12160167,-99.8585,-100.81388,0.063379884,0.13760397,-0.15236796,6.057087,1160000
34
+ 0.20779891,0.18580644,-75.59162,-100.191696,-100.69809,0.023909796,0.1371074,-0.081145026,3.9543295,1165000
35
+ 0.1555449,0.23442374,-93.95224,-100.221275,-100.69289,0.08803379,0.10399017,-0.24584575,6.4099283,1170000
36
+ 0.15706888,0.3592895,-84.66987,-100.15713,-100.702385,0.2656455,0.2815569,-0.2231923,13.608355,1175000
37
+ 0.23172863,0.42895386,-81.59129,-100.193474,-100.72204,0.09302679,0.21743476,-0.12787586,6.484741,1180000
38
+ 0.2199735,0.085995935,0.32116684,-99.779396,-100.56306,0.055174183,0.29468566,-0.11567326,7.3271875,1185000
39
+ 0.18150723,0.53324413,-79.39246,-100.19346,-100.84584,0.06919559,0.15184617,-0.13545679,6.698231,1190000
40
+ 0.29646805,0.80211276,0.24750999,-99.79947,-100.811165,0.46379018,0.47572994,-0.3405564,19.975376,1195000
41
+ 0.20760229,0.43006697,-79.5314,-100.16708,-100.80566,0.2317638,0.27771637,-0.3778391,8.678116,1200000
42
+ 0.17794377,0.37374577,-6.3621655,-99.880684,-100.69483,0.10939115,0.12739109,-0.26794243,7.744462,1205000
43
+ 0.19616428,0.21129714,-82.77471,-100.13567,-100.77831,0.07928045,0.07956755,-0.1502769,4.760145,1210000
44
+ 0.20803934,1.792857,0.23118195,-99.62402,-100.700874,0.44469023,0.6048523,-1.2528483,23.914423,1215000
45
+ 0.21411851,0.12196108,-19.30349,-99.92655,-100.59377,0.18330011,0.4443022,-0.21150796,13.43561,1220000
46
+ 0.2595706,0.12721387,0.17898181,-99.47082,-100.670654,0.10822647,0.21166658,-0.49662364,10.382397,1225000
47
+ 0.1919941,0.03298604,-78.62514,-100.23498,-100.621765,0.024240011,0.1225741,-0.24532656,3.6714346,1230000
48
+ 0.21763176,0.026102452,-90.59143,-100.31142,-100.7373,0.03093527,0.19179922,-0.42021245,5.6815295,1235000
49
+ 0.15891823,6.2400465,0.4680497,-99.90387,-100.866776,0.03453016,0.63776624,-0.43150976,18.119991,1240000
50
+ 0.17472498,0.052240282,-8.085847,-99.810776,-100.650955,0.054674357,0.058514386,-0.13840102,5.041067,1245000
51
+ 0.17192847,0.048703358,-85.42341,-100.24457,-100.65993,0.063972525,0.17971212,-0.079292454,4.9879904,1250000
52
+ 0.19195232,0.20185857,-18.83325,-99.961,-100.6752,0.29393393,0.38953757,-0.6746025,12.775431,1255000
53
+ 0.18246387,0.19049187,-78.967285,-100.165726,-100.718025,0.10214589,1.0661603,-0.53598994,18.366259,1260000
54
+ 0.18586095,2.6662443,-71.047935,-100.03352,-100.647194,0.19105232,0.40024,-0.17184812,13.139351,1265000
55
+ 0.2077958,17.559483,-17.298035,-99.53446,-100.79584,5.886781,7.141426,-8.012062,185.57187,1270000
56
+ 0.27100006,0.43608484,-78.82675,-99.89302,-100.6118,0.16935024,0.54494584,-0.19102609,14.712485,1275000
57
+ 0.22428489,2.5887773,-77.74074,-100.01736,-100.573364,0.11017417,0.44897062,-0.2057113,18.425072,1280000
58
+ 0.16559173,5.362787,-77.24238,-99.95022,-100.74702,0.39963952,0.6410105,-0.28533584,19.508442,1285000
59
+ 0.18261907,0.13992964,-86.54729,-100.21559,-100.65793,0.31690398,0.31781542,-0.5775595,12.761013,1290000
60
+ 0.19240244,0.1585139,-88.283295,-100.151566,-100.70001,0.22500978,0.6197836,-0.2705717,11.559721,1295000
61
+ 0.19685052,0.062248565,0.29929984,-99.88731,-100.63257,0.04561893,0.6594243,-0.31620997,7.209624,1300000
62
+ 0.17490715,0.48709813,0.3094315,-99.74651,-100.70213,0.04242217,0.29188442,-0.20104997,6.1635556,1305000
63
+ 0.2631651,0.3237667,0.2979293,-99.84533,-100.82654,0.22177027,0.25260353,-0.53135216,19.576942,1310000
64
+ 0.2170724,0.18937202,0.3163641,-99.659134,-100.66622,0.3035308,0.9079729,-2.0178943,27.717415,1315000
65
+ 0.18298826,0.0828088,-90.29267,-100.29477,-100.67185,0.041697722,0.16319641,-0.35436746,4.711298,1320000
66
+ 0.22768581,16.5524,0.10247791,-99.318375,-100.72185,0.34184447,0.21412183,-0.31723055,26.008709,1325000
67
+ 0.21101318,0.2814055,-16.300156,-99.88971,-100.686226,0.15858226,0.71343046,-0.455078,21.001637,1330000
68
+ 0.20751497,0.2777161,-84.26554,-100.138084,-100.654045,0.1284947,0.23793833,-0.17373562,7.964709,1335000
69
+ 0.17469832,0.19957191,-84.86773,-100.274864,-100.735405,0.030940045,0.14640701,-0.23214763,5.0728393,1340000
70
+ 0.18152311,12.798668,-17.425947,-99.638,-100.88979,0.08952748,0.6587549,-0.43530643,17.302027,1345000
71
+ 0.21702424,0.16461666,-95.05125,-100.267525,-100.6535,0.09793711,0.1680904,-0.38616207,6.108566,1350000
72
+ 0.3744908,3.7229073,-0.73889965,-99.51569,-100.79961,0.90207016,1.6442214,-1.0719402,89.9722,1355000
73
+ 0.2983997,2.606963,-74.70267,-99.78005,-100.44472,0.2795317,0.7983165,-1.8487693,33.877914,1360000
74
+ 0.17659545,3.8392732,-56.610928,-99.92091,-100.904686,0.18841699,0.24457675,-0.28608802,22.012157,1365000
75
+ 0.20858222,0.07169901,-84.78757,-100.1036,-100.52169,0.03951617,0.7417075,-0.32746804,11.169391,1370000
76
+ 0.59200627,0.16265707,-6.7455664,-99.783516,-100.851204,0.44110075,0.46940866,-1.4951991,28.953842,1375000
77
+ 0.15318039,0.037680782,-87.037506,-100.30327,-100.70184,0.04028678,0.18172759,-0.42963165,6.1836705,1380000
78
+ 0.15533817,0.94434404,0.26093435,-99.32165,-100.68244,0.11200478,1.1287441,-0.4990221,16.14668,1385000
79
+ 0.17549396,1.5908704,-78.47187,-99.82592,-100.67132,0.61427176,0.60984784,-0.6545186,26.617245,1390000
80
+ 0.1922754,4.253064,-3.1060967,-99.48698,-100.692276,0.14297724,0.24862657,-0.20584945,18.05276,1395000
81
+ 0.17538226,0.08018374,-93.451256,-100.278275,-100.67742,0.05742104,0.15384002,-0.2370138,7.3800044,1400000
82
+ 0.14713117,1.6031449,0.27465868,-99.751724,-100.79538,0.24774623,0.2934614,-0.34352833,15.755978,1405000
83
+ 0.19370817,0.3200923,-75.91314,-100.09207,-100.628746,0.10515566,0.32960805,-0.6476952,13.119924,1410000
84
+ 0.17400587,0.2878234,-96.74975,-100.41378,-100.8568,0.046826705,0.15051773,-0.35484752,5.8813887,1415000
85
+ 0.18567628,0.05385405,-92.62262,-100.20376,-100.55768,0.077063344,0.24501508,-0.108897746,5.392752,1420000
86
+ 0.20867081,0.94297427,-79.59917,-100.15807,-100.6888,0.07815657,0.23069315,-0.5222229,9.935865,1425000
87
+ 0.25859267,1.0395586,-73.030365,-99.980125,-100.7472,1.6541103,0.51698554,-1.3027943,25.102829,1430000
88
+ 0.23742743,0.7311471,0.30768013,-99.406624,-100.60409,0.2812731,0.50204587,-0.42076316,15.998825,1435000
89
+ 0.17986968,0.25819555,-1.604712,-99.67904,-100.61643,0.19548513,0.18695591,-0.2248121,10.755932,1440000
90
+ 0.18374959,0.15275818,-81.351326,-100.169914,-100.65571,0.13442805,0.5095174,-0.23012531,7.777879,1445000
91
+ 0.17081869,9.176837,-5.4742513,-99.708466,-100.6025,0.10459886,0.2547719,-0.3065585,20.063194,1450000
92
+ 0.16041292,0.06390389,0.33355367,-99.726456,-100.65371,0.057288963,0.09856665,-0.05058684,3.9600716,1455000
93
+ 0.15464643,0.08791048,-84.05471,-100.160225,-100.67836,0.0653148,0.36606032,-0.15067837,6.339777,1460000
94
+ 0.2958951,0.61081016,-7.158073,-99.500656,-100.68184,0.17496245,0.25037482,-0.33931547,10.987275,1465000
95
+ 0.21227334,18.384092,-3.8788257,-99.67482,-100.58649,0.21523695,0.53318405,-0.33667696,25.13873,1470000
96
+ 0.18111108,0.7429684,-9.686788,-99.60729,-100.557625,0.18672553,0.37406415,-0.24422063,15.588162,1475000
97
+ 0.17310101,0.08201449,-97.8893,-100.33542,-100.821846,0.018560922,0.34705558,-0.7978407,6.618712,1480000
98
+ 0.15676948,1.7854458,-76.67466,-100.10866,-100.64816,0.2311294,0.27933565,-0.41627902,17.625528,1485000
99
+ 0.16663109,0.58016264,-83.46835,-100.10345,-100.56737,0.03888115,0.3595741,-0.15662692,8.496969,1490000
100
+ 0.14068173,0.2872227,-86.88316,-100.407196,-100.93784,0.066297,0.86425155,-0.37798995,13.638732,1495000
101
+ 0.18961802,0.16899791,-79.41721,-100.120285,-100.64149,0.055443104,0.42574215,-0.18635342,7.2354975,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,critic/value_loss,grad/max,grad/min,grad/norm,step
2
+ 0.18768835,0.09134745,-81.35456,-100.10657,-100.69836,0.046444837,0.22641602,-0.11820134,5.377088,1005000
3
+ 0.18959102,0.8001544,-2.1180587,-99.40464,-100.66217,0.084856465,0.19296026,-0.45685777,12.238469,1010000
4
+ 0.17323738,0.031234836,-0.010850221,-99.948364,-100.74427,0.10231266,0.23432507,-0.49583757,6.1740317,1015000
5
+ 0.21360493,1.2108244,-3.4438605,-99.7636,-100.73472,0.18339132,0.14564978,-0.103390984,10.372396,1020000
6
+ 0.18424219,0.10282203,-13.680149,-99.94629,-100.76613,0.14077373,0.2639478,-0.23743267,10.373459,1025000
7
+ 0.20109639,15.606928,-83.46211,-100.20523,-100.68811,0.12598814,0.30123273,-0.3004239,24.702065,1030000
8
+ 0.20047064,0.69664437,-3.5296645,-99.88196,-100.64751,0.13021243,0.30175877,-0.3302073,13.915092,1035000
9
+ 0.14050622,12.707795,-85.7594,-100.24656,-100.767624,0.08920359,0.21173464,-0.26065344,18.418695,1040000
10
+ 0.18952814,0.7576336,0.52932525,-99.8963,-100.66767,0.06853577,0.14343488,-0.14493653,7.8183746,1045000
11
+ 0.20787191,1.1953893,-7.1778026,-99.91464,-100.77508,0.37425265,0.27106148,-0.61055,21.305779,1050000
12
+ 0.18742537,0.10520468,-7.9034896,-99.724724,-100.68835,0.10004437,0.06728807,-0.14032187,6.1661243,1055000
13
+ 0.18812716,0.16505535,0.22004563,-99.68578,-100.58723,0.1608262,0.20038985,-0.16985506,9.379223,1060000
14
+ 0.17825001,0.13091877,-70.822205,-100.126816,-100.74939,0.07971448,0.19911274,-0.4347616,10.007163,1065000
15
+ 0.20393723,0.055244338,-82.330315,-100.24187,-100.75057,0.051563382,0.16613144,-0.0894955,6.1620097,1070000
16
+ 0.20618097,4.2754803,-7.447969,-99.767525,-100.621704,0.14043233,0.22141336,-0.13865013,13.677859,1075000
17
+ 0.26609784,0.15401728,-1.6446027,-99.916725,-100.7277,0.30799612,0.25422013,-0.28487203,15.242995,1080000
18
+ 0.20422328,2.9983993,-13.4096775,-99.91967,-100.58542,0.0828132,1.014887,-1.5700327,61.08101,1085000
19
+ 0.21155089,0.32314858,-35.446728,-99.89916,-100.811646,0.14281945,0.20920117,-0.17242141,12.327435,1090000
20
+ 0.1909797,0.4028941,-85.827774,-100.12478,-100.598274,0.16183014,0.23197475,-0.16038668,11.633423,1095000
21
+ 0.1982997,0.5896541,-91.29394,-100.22401,-100.660225,0.10487254,0.19172195,-0.40468398,11.60808,1100000
22
+ 0.17524832,2.2540474,-3.240529,-99.63857,-100.74553,0.42862082,0.592464,-0.6824983,29.410301,1105000
23
+ 0.21556115,0.58752865,0.26935378,-99.61708,-100.57809,0.16101429,0.22422373,-0.29086053,13.164018,1110000
24
+ 0.1646298,0.28300837,-87.958626,-100.23917,-100.91821,0.08933005,0.11947683,-0.2592392,6.478447,1115000
25
+ 0.19032833,0.108518176,-4.2475653,-99.196,-100.64749,0.17980304,0.5490432,-0.26493716,11.305365,1120000
26
+ 0.21902466,1.122633,-83.55025,-100.11734,-100.71083,0.10176104,0.29603165,-0.5951922,11.918346,1125000
27
+ 0.19502352,0.736931,-0.55136895,-99.763824,-100.77275,0.11731117,0.09693681,-0.10179228,10.104057,1130000
28
+ 0.18845978,0.019936843,-87.54437,-100.378586,-100.719635,0.07884538,0.2930892,-0.30880827,8.5104065,1135000
29
+ 0.19772722,0.22942562,-81.809204,-100.028885,-100.55735,0.06193478,0.28592247,-0.14620104,7.439246,1140000
30
+ 0.21269983,0.7816989,0.31948322,-99.61786,-100.76116,0.8037769,2.0880206,-4.8273664,85.83455,1145000
31
+ 0.15721972,0.10989926,-87.40582,-100.16735,-100.73699,0.05100562,0.5841391,-0.25484556,6.719847,1150000
32
+ 0.19116358,0.3378856,0.263353,-99.74538,-100.74967,0.05869899,0.44856888,-0.20846105,7.4776115,1155000
33
+ 0.20146063,2.1037292,0.12160167,-99.8585,-100.81388,0.063379884,0.13760397,-0.15236796,6.057087,1160000
34
+ 0.20779891,0.18580644,-75.59162,-100.191696,-100.69809,0.023909796,0.1371074,-0.081145026,3.9543295,1165000
35
+ 0.1555449,0.23442374,-93.95224,-100.221275,-100.69289,0.08803379,0.10399017,-0.24584575,6.4099283,1170000
36
+ 0.15706888,0.3592895,-84.66987,-100.15713,-100.702385,0.2656455,0.2815569,-0.2231923,13.608355,1175000
37
+ 0.23172863,0.42895386,-81.59129,-100.193474,-100.72204,0.09302679,0.21743476,-0.12787586,6.484741,1180000
38
+ 0.2199735,0.085995935,0.32116684,-99.779396,-100.56306,0.055174183,0.29468566,-0.11567326,7.3271875,1185000
39
+ 0.18150723,0.53324413,-79.39246,-100.19346,-100.84584,0.06919559,0.15184617,-0.13545679,6.698231,1190000
40
+ 0.29646805,0.80211276,0.24750999,-99.79947,-100.811165,0.46379018,0.47572994,-0.3405564,19.975376,1195000
41
+ 0.20760229,0.43006697,-79.5314,-100.16708,-100.80566,0.2317638,0.27771637,-0.3778391,8.678116,1200000
42
+ 0.17794377,0.37374577,-6.3621655,-99.880684,-100.69483,0.10939115,0.12739109,-0.26794243,7.744462,1205000
43
+ 0.19616428,0.21129714,-82.77471,-100.13567,-100.77831,0.07928045,0.07956755,-0.1502769,4.760145,1210000
44
+ 0.20803934,1.792857,0.23118195,-99.62402,-100.700874,0.44469023,0.6048523,-1.2528483,23.914423,1215000
45
+ 0.21411851,0.12196108,-19.30349,-99.92655,-100.59377,0.18330011,0.4443022,-0.21150796,13.43561,1220000
46
+ 0.2595706,0.12721387,0.17898181,-99.47082,-100.670654,0.10822647,0.21166658,-0.49662364,10.382397,1225000
47
+ 0.1919941,0.03298604,-78.62514,-100.23498,-100.621765,0.024240011,0.1225741,-0.24532656,3.6714346,1230000
48
+ 0.21763176,0.026102452,-90.59143,-100.31142,-100.7373,0.03093527,0.19179922,-0.42021245,5.6815295,1235000
49
+ 0.15891823,6.2400465,0.4680497,-99.90387,-100.866776,0.03453016,0.63776624,-0.43150976,18.119991,1240000
50
+ 0.17472498,0.052240282,-8.085847,-99.810776,-100.650955,0.054674357,0.058514386,-0.13840102,5.041067,1245000
51
+ 0.17192847,0.048703358,-85.42341,-100.24457,-100.65993,0.063972525,0.17971212,-0.079292454,4.9879904,1250000
52
+ 0.19195232,0.20185857,-18.83325,-99.961,-100.6752,0.29393393,0.38953757,-0.6746025,12.775431,1255000
53
+ 0.18246387,0.19049187,-78.967285,-100.165726,-100.718025,0.10214589,1.0661603,-0.53598994,18.366259,1260000
54
+ 0.18586095,2.6662443,-71.047935,-100.03352,-100.647194,0.19105232,0.40024,-0.17184812,13.139351,1265000
55
+ 0.2077958,17.559483,-17.298035,-99.53446,-100.79584,5.886781,7.141426,-8.012062,185.57187,1270000
56
+ 0.27100006,0.43608484,-78.82675,-99.89302,-100.6118,0.16935024,0.54494584,-0.19102609,14.712485,1275000
57
+ 0.22428489,2.5887773,-77.74074,-100.01736,-100.573364,0.11017417,0.44897062,-0.2057113,18.425072,1280000
58
+ 0.16559173,5.362787,-77.24238,-99.95022,-100.74702,0.39963952,0.6410105,-0.28533584,19.508442,1285000
59
+ 0.18261907,0.13992964,-86.54729,-100.21559,-100.65793,0.31690398,0.31781542,-0.5775595,12.761013,1290000
60
+ 0.19240244,0.1585139,-88.283295,-100.151566,-100.70001,0.22500978,0.6197836,-0.2705717,11.559721,1295000
61
+ 0.19685052,0.062248565,0.29929984,-99.88731,-100.63257,0.04561893,0.6594243,-0.31620997,7.209624,1300000
62
+ 0.17490715,0.48709813,0.3094315,-99.74651,-100.70213,0.04242217,0.29188442,-0.20104997,6.1635556,1305000
63
+ 0.2631651,0.3237667,0.2979293,-99.84533,-100.82654,0.22177027,0.25260353,-0.53135216,19.576942,1310000
64
+ 0.2170724,0.18937202,0.3163641,-99.659134,-100.66622,0.3035308,0.9079729,-2.0178943,27.717415,1315000
65
+ 0.18298826,0.0828088,-90.29267,-100.29477,-100.67185,0.041697722,0.16319641,-0.35436746,4.711298,1320000
66
+ 0.22768581,16.5524,0.10247791,-99.318375,-100.72185,0.34184447,0.21412183,-0.31723055,26.008709,1325000
67
+ 0.21101318,0.2814055,-16.300156,-99.88971,-100.686226,0.15858226,0.71343046,-0.455078,21.001637,1330000
68
+ 0.20751497,0.2777161,-84.26554,-100.138084,-100.654045,0.1284947,0.23793833,-0.17373562,7.964709,1335000
69
+ 0.17469832,0.19957191,-84.86773,-100.274864,-100.735405,0.030940045,0.14640701,-0.23214763,5.0728393,1340000
70
+ 0.18152311,12.798668,-17.425947,-99.638,-100.88979,0.08952748,0.6587549,-0.43530643,17.302027,1345000
71
+ 0.21702424,0.16461666,-95.05125,-100.267525,-100.6535,0.09793711,0.1680904,-0.38616207,6.108566,1350000
72
+ 0.3744908,3.7229073,-0.73889965,-99.51569,-100.79961,0.90207016,1.6442214,-1.0719402,89.9722,1355000
73
+ 0.2983997,2.606963,-74.70267,-99.78005,-100.44472,0.2795317,0.7983165,-1.8487693,33.877914,1360000
74
+ 0.17659545,3.8392732,-56.610928,-99.92091,-100.904686,0.18841699,0.24457675,-0.28608802,22.012157,1365000
75
+ 0.20858222,0.07169901,-84.78757,-100.1036,-100.52169,0.03951617,0.7417075,-0.32746804,11.169391,1370000
76
+ 0.59200627,0.16265707,-6.7455664,-99.783516,-100.851204,0.44110075,0.46940866,-1.4951991,28.953842,1375000
77
+ 0.15318039,0.037680782,-87.037506,-100.30327,-100.70184,0.04028678,0.18172759,-0.42963165,6.1836705,1380000
78
+ 0.15533817,0.94434404,0.26093435,-99.32165,-100.68244,0.11200478,1.1287441,-0.4990221,16.14668,1385000
79
+ 0.17549396,1.5908704,-78.47187,-99.82592,-100.67132,0.61427176,0.60984784,-0.6545186,26.617245,1390000
80
+ 0.1922754,4.253064,-3.1060967,-99.48698,-100.692276,0.14297724,0.24862657,-0.20584945,18.05276,1395000
81
+ 0.17538226,0.08018374,-93.451256,-100.278275,-100.67742,0.05742104,0.15384002,-0.2370138,7.3800044,1400000
82
+ 0.14713117,1.6031449,0.27465868,-99.751724,-100.79538,0.24774623,0.2934614,-0.34352833,15.755978,1405000
83
+ 0.19370817,0.3200923,-75.91314,-100.09207,-100.628746,0.10515566,0.32960805,-0.6476952,13.119924,1410000
84
+ 0.17400587,0.2878234,-96.74975,-100.41378,-100.8568,0.046826705,0.15051773,-0.35484752,5.8813887,1415000
85
+ 0.18567628,0.05385405,-92.62262,-100.20376,-100.55768,0.077063344,0.24501508,-0.108897746,5.392752,1420000
86
+ 0.20867081,0.94297427,-79.59917,-100.15807,-100.6888,0.07815657,0.23069315,-0.5222229,9.935865,1425000
87
+ 0.25859267,1.0395586,-73.030365,-99.980125,-100.7472,1.6541103,0.51698554,-1.3027943,25.102829,1430000
88
+ 0.23742743,0.7311471,0.30768013,-99.406624,-100.60409,0.2812731,0.50204587,-0.42076316,15.998825,1435000
89
+ 0.17986968,0.25819555,-1.604712,-99.67904,-100.61643,0.19548513,0.18695591,-0.2248121,10.755932,1440000
90
+ 0.18374959,0.15275818,-81.351326,-100.169914,-100.65571,0.13442805,0.5095174,-0.23012531,7.777879,1445000
91
+ 0.17081869,9.176837,-5.4742513,-99.708466,-100.6025,0.10459886,0.2547719,-0.3065585,20.063194,1450000
92
+ 0.16041292,0.06390389,0.33355367,-99.726456,-100.65371,0.057288963,0.09856665,-0.05058684,3.9600716,1455000
93
+ 0.15464643,0.08791048,-84.05471,-100.160225,-100.67836,0.0653148,0.36606032,-0.15067837,6.339777,1460000
94
+ 0.2958951,0.61081016,-7.158073,-99.500656,-100.68184,0.17496245,0.25037482,-0.33931547,10.987275,1465000
95
+ 0.21227334,18.384092,-3.8788257,-99.67482,-100.58649,0.21523695,0.53318405,-0.33667696,25.13873,1470000
96
+ 0.18111108,0.7429684,-9.686788,-99.60729,-100.557625,0.18672553,0.37406415,-0.24422063,15.588162,1475000
97
+ 0.17310101,0.08201449,-97.8893,-100.33542,-100.821846,0.018560922,0.34705558,-0.7978407,6.618712,1480000
98
+ 0.15676948,1.7854458,-76.67466,-100.10866,-100.64816,0.2311294,0.27933565,-0.41627902,17.625528,1485000
99
+ 0.16663109,0.58016264,-83.46835,-100.10345,-100.56737,0.03888115,0.3595741,-0.15662692,8.496969,1490000
100
+ 0.14068173,0.2872227,-86.88316,-100.407196,-100.93784,0.066297,0.86425155,-0.37798995,13.638732,1495000
101
+ 0.18961802,0.16899791,-79.41721,-100.120285,-100.64149,0.055443104,0.42574215,-0.18635342,7.2354975,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d72632da5a7905836c1b149a70ca138b00a942b724bff636b9e1998d2307366
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a7eb3db8e1c8b56c41ab8a5c7732e2a35f19a99b2de388ec117b031a7bba77
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0d2b440c524ca851191fba79e6f8beeaf43402b148bc03d557acf028f67757
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae2a912df6ed366880077e363beeb8892bb6086853082fe41d0c50bc6f2bb7d
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc755fc55d6961ba3ccb52d3c9685abcfd673b332e0c2e6ea147812e767c1eb
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca810c7c628ef50a8c21a406181b17f89044ee3079aaf402e4a01433dcc41480
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d919a4b06058d86bcb884f421594afd018a54facf9cdbff453dd4a489a4817
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18dcb4bb1adb29012e2df66ac6f1c9c9a532456cbafab7334ae5a28dd3a8fc1f
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa94f1faf59cc89c7d720b443bb3c95a44d393d2903277b112c65ab93d920d2
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208914a47ff2f846af54c7b7d68c8de02d5da58e2dea1e2c47807cb776d70fd9
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f60fa5023795468556154bc6fa85eda837e0d44be9d67303211669f66f611348
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3dd73cc37e0a151e08e399cf9ed093c7f82c59e6a22d17afe918ce628dcc39
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_1500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3493c43c6c02ab34cd3d800b0decc679dca1d8807be869fb6c4175065cd143ea
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9756d51f578846267e43e34d44bc4d928e8e73e62f8725098824251f3cb336
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d7a2e3d3d07b5e102e0e7b0b1698383c939f84e266b59e88aceaacbbf32e6cb
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd625fb94b50bc12cf42538f944f7b1e6870fa8749065a080d05cb938844ad3e
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30e817ef43cf54b6e1cc1cba8823a64b49acbc97d14301e898385dd49478799
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d72eca564a36e52537948d3fc13e40ea0588cb3a5bc47b9af7d52ff90bdd868
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa688d0f1fba99371f55aa77ce0c1fbe121c8ba83a692b7a51f7a46f22bf1624
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_50000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:180ea526ba4998b132ff3f417fd9e146a6c32c75a16f312e902f586d8a5c9d1c
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c40f2ab33adae8eef8eeb81018f3a4d8914419155f9bc72a63e41d243950fb78
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b0583586509f99f30bfc5d4946602c13737de420ffa2aec03d876b07a49793
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a0db712eef8629c3ef3fbe9d6c65642b030fb603fff1a391aafbaab911f9e7
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef77c557802cbc3ca5556c675676dc89367098049e965e2bf0b9c7c356c4ae7
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def9ab5213dbcd2c545d25b1a382aa1126db147cf194a2b11dae8524de7982b4
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44bc3aee9bc1ec149aa2fb12b5aacd7e88074fefb55144cebefa85d34241c7ac
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529a988a8bd1888c1e2365516d5aa67391c0f942e47037ea1857b56b1254c74a
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b0260a87be3e49f4be3337347ed610e19db08feeee741a70c94a9b8c20c4ec
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb0d16d769c78fd6f0d05f9cd292b42903e9a183b01180737daac6a7499ec58
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90d4d3158b88030b6db74a0bfde00190d00cc7d3728cc1b42909d7ee3ae726c
3
+ size 220151418
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_141107/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-reproduce/runs/4e7i9mdt