Tiredsheep commited on
Commit
de0962e
·
verified ·
1 Parent(s): 6f46584

Upload folder using huggingface_hub

Browse files
Files changed (41) hide show
  1. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/env.csv +0 -0
  2. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/env_sv.csv +0 -0
  3. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/eval.csv +31 -0
  4. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/eval_sv.csv +31 -0
  5. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/flags.json +1 -0
  6. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/offline_agent.csv +201 -0
  7. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/offline_agent_sv.csv +201 -0
  8. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/online_agent.csv +101 -0
  9. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/online_agent_sv.csv +101 -0
  10. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_100000.pkl +3 -0
  11. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1000000.pkl +3 -0
  12. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1050000.pkl +3 -0
  13. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1100000.pkl +3 -0
  14. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1150000.pkl +3 -0
  15. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1200000.pkl +3 -0
  16. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1250000.pkl +3 -0
  17. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1300000.pkl +3 -0
  18. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1350000.pkl +3 -0
  19. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1400000.pkl +3 -0
  20. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1450000.pkl +3 -0
  21. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_150000.pkl +3 -0
  22. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1500000.pkl +3 -0
  23. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_200000.pkl +3 -0
  24. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_250000.pkl +3 -0
  25. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_300000.pkl +3 -0
  26. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_350000.pkl +3 -0
  27. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_400000.pkl +3 -0
  28. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_450000.pkl +3 -0
  29. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_50000.pkl +3 -0
  30. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_500000.pkl +3 -0
  31. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_550000.pkl +3 -0
  32. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_600000.pkl +3 -0
  33. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_650000.pkl +3 -0
  34. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_700000.pkl +3 -0
  35. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_750000.pkl +3 -0
  36. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_800000.pkl +3 -0
  37. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_850000.pkl +3 -0
  38. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_900000.pkl +3 -0
  39. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_950000.pkl +3 -0
  40. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/progress.tk +1 -0
  41. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/token.tk +1 -0
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/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_113045/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_113045/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
+ 0.0,0.0,0.6688888888888889,0.6688888888888889,-0.19691510193733736,-0.0026645878276253592,-0.19752861725715604,-0.012061732503429266,33.86503519590016,25.24999999999688,0.0,12750.0,-2.98,-2095.98,500.0,1.8211109399795533,50000
3
+ 0.0,0.0,0.56,0.6222222222222222,-0.1813342058881092,0.005436982600713472,-0.18118769581767763,0.002571477750097156,34.81541402475816,24.77099999999715,0.18,38522.14,-3.4,-2179.5,490.42,1.7815654182434082,100000
4
+ 0.0,0.0,0.5733333333333334,0.8555555555555555,-0.18460106619068015,-0.004305860074038781,-0.1846446837576921,0.0011559588055688895,35.09596890382728,21.460999999998943,0.66,62002.5,-1.3,-1844.46,424.22,1.5602857065200806,150000
5
+ 0.0,0.0,0.6355555555555555,0.9911111111111112,-0.18178005008233633,-0.0026477575303508185,-0.18187604986227981,0.0007447891771651176,35.27315445321268,18.475000000000264,0.98,82683.3,-0.08,-1516.34,364.5,1.333532419204712,200000
6
+ 0.0,0.0,0.6488888888888888,0.9866666666666667,-0.1876756788565474,-0.009772384372240506,-0.18821876530693954,-0.008306404285844731,34.914648743371245,17.191000000000855,0.96,100778.2,-0.12,-1493.78,338.82,1.2365639734268188,250000
7
+ 0.0,0.0,0.6311111111111111,1.0,-0.18170404423911102,-0.004047473626439653,-0.1820632277813686,-0.0036844326139314856,35.20204972584724,16.6330000000009,1.0,117956.42,0.0,-1373.24,327.66,1.19135675907135,300000
8
+ 0.0,0.0,0.64,1.0,-0.1829510809586485,-0.004213016104107537,-0.18344552173021814,-0.003984793070216794,34.90249542086447,16.24700000000109,1.0,134987.4,0.0,-1391.7,319.94,1.1691679286956786,350000
9
+ 0.0,0.0,0.6355555555555555,1.0,-0.18624896235498653,-0.005668628991892512,-0.18691605947148426,-0.005440879766551492,34.97219382277929,15.633000000001255,1.0,151309.78,0.0,-1329.48,307.66,1.1259048414230346,400000
10
+ 0.0,0.0,0.6288888888888889,1.0,-0.18002673267806443,-0.005993783579420944,-0.18035488792762397,-0.0035883442435268097,35.06498568638053,15.641000000001284,1.0,167220.68,0.0,-1349.88,307.82,1.1644256448745727,450000
11
+ 0.0,0.0,0.6422222222222222,1.0,-0.1789557719005772,-0.007900594394576764,-0.17941521558184464,-0.004951661454118848,34.979218273756345,15.188000000001379,1.0,182989.56,0.0,-1280.82,298.76,1.134086980819702,500000
12
+ 0.0,0.0,0.6311111111111111,1.0,-0.17799027916045407,-0.004697964807676401,-0.1783461817805346,-0.0033194173056449194,35.223063397622774,16.122000000001236,1.0,198942.76,0.0,-1389.36,317.44,1.1629466009140015,550000
13
+ 0.0,0.0,0.6377777777777778,1.0,-0.18002766609324983,-0.006063080090332967,-0.18019892659139308,-0.0007219451092086739,34.89550973718934,15.345000000001118,1.0,215463.12,0.0,-1311.08,301.9,1.1043927478790283,600000
14
+ 0.0,0.0,0.6333333333333333,1.0,-0.18510471027417447,-0.011729136759613396,-0.18581770215803958,-0.009828389176609309,34.817913303410066,15.180000000001174,1.0,231089.8,0.0,-1323.24,298.6,1.0907486009597778,650000
15
+ 0.0,0.0,0.6355555555555555,1.0,-0.18235309915337328,-0.005683052218596222,-0.18301206043244317,-0.0068639411721991535,35.00869918165872,16.031000000001175,1.0,246784.22,0.0,-1371.58,315.62,1.15701247215271,700000
16
+ 0.0,0.0,0.6488888888888888,1.0,-0.17852740582663634,-0.009351285441263119,-0.17913434642762038,-0.007491767698452915,35.0967859770837,15.466000000001298,1.0,262959.82,0.0,-1292.5,304.32,1.1161862707138062,750000
17
+ 0.0,0.0,0.6422222222222222,1.0,-0.17729964558315936,-0.008919560295532317,-0.1779184968665721,-0.006072136905818945,35.01666940501616,16.051000000000936,1.0,279086.08,0.0,-1352.98,316.02,1.1490920400619506,800000
18
+ 0.0,0.0,0.6244444444444445,1.0,-0.17958925743346205,-0.004293850383152812,-0.1799500211174268,-0.004057112000637643,35.07856682138788,15.202000000001295,1.0,295166.66,0.0,-1305.88,299.04,1.099862937927246,850000
19
+ 0.0,0.0,0.6333333333333333,1.0,-0.17501989275805316,-0.0012818354260895916,-0.17512041858922558,0.001026949099995425,35.29315784243551,15.685000000001098,1.0,310806.3,0.0,-1300.88,308.7,1.13539559841156,900000
20
+ 0.0,0.0,0.6488888888888888,1.0,-0.1825018763095996,-0.010344307001687912,-0.18314643575735487,-0.00679393100215268,34.97668198029096,15.329000000001082,1.0,326864.4,0.0,-1280.98,301.58,1.096357879638672,950000
21
+ 0.0,0.0,0.6422222222222222,0.9933333333333333,-0.18504981008756752,-0.011067511874417556,-0.18578617431983246,-0.009332859300329541,35.00438787272922,15.189000000001055,0.98,342549.9,-0.06,-1292.14,298.78,1.1045069360733033,1000000
22
+ 0.0,0.0,0.6466666666666666,1.0,-0.1768771511125647,-0.0016273435597593344,-0.17714848662120408,-0.0016876953875084879,35.1146360097117,15.33500000000141,1.0,357966.26,0.0,-1315.88,301.7,1.1149995231628418,1050000
23
+ 0.0,0.0,0.6355555555555555,1.0,-0.1791995813068301,-0.00530960571492019,-0.1797471881056381,-0.004539601437687006,34.88903489624965,14.313000000001296,1.0,373232.68,0.0,-1230.78,281.26,1.0349890184402466,1100000
24
+ 0.0,0.0,0.6488888888888888,1.0,-0.1801138560921088,-0.004328451060384341,-0.18056994714321387,-0.0029326704106852593,34.94130236819594,14.70900000000136,1.0,387933.52,0.0,-1243.54,289.18,1.0658512353897094,1150000
25
+ 0.0,0.0,0.64,1.0,-0.18315240838994823,-0.005734552685949903,-0.18353683296548656,-0.0028218965850095672,35.18514685058983,14.443000000001362,1.0,402861.4,0.0,-1259.1,283.86,1.0500581407546996,1200000
26
+ 0.0,0.0,0.6555555555555556,1.0,-0.18002671167698078,-0.0011821763989330017,-0.1804833093123117,-0.003847188325115361,35.236939026775765,14.093000000001211,1.0,417493.48,0.0,-1148.62,276.86,1.0233480787277223,1250000
27
+ 0.0,0.0,0.6377777777777778,1.0,-0.17880194235997668,-0.006965311684213381,-0.17932052968632572,-0.004424238133356792,35.15302802710362,13.690000000001216,1.0,431593.58,0.0,-1168.4,268.8,0.990675368309021,1300000
28
+ 0.0,0.0,0.6466666666666666,1.0,-0.17935320527941978,-0.0044744640187476675,-0.17992149509053304,-0.004675993589519461,35.17109965936634,13.746000000001223,1.0,445530.18,0.0,-1186.52,269.92,1.05004629611969,1350000
29
+ 0.0,0.0,0.6533333333333333,1.0,-0.18623667721908904,-0.01048017353099955,-0.18705157390375837,-0.009588340480766242,35.25336698318077,13.260000000001094,1.0,459367.94,0.0,-1122.54,260.2,1.0274169540405274,1400000
30
+ 0.0,0.0,0.6555555555555556,0.9933333333333333,-0.18634500011449917,-0.0038635406430638643,-0.1869578823139095,-0.006637463732921699,35.10366558920742,13.801000000000952,0.98,473145.92,-0.06,-1162.56,271.02,1.0688276863098145,1450000
31
+ 0.0,0.0,0.66,1.0,-0.17477752279366962,-0.0013221297462161854,-0.17509347292369878,-0.00021989234754104956,35.04741896220112,12.807000000000931,1.0,486716.86,0.0,-1056.62,251.14,0.9981927251815796,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/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
+ 0.0,0.0,0.6688888888888889,0.6688888888888889,-0.19691510193733736,-0.0026645878276253592,-0.19752861725715604,-0.012061732503429266,33.86503519590016,25.24999999999688,0.0,12750.0,-2.98,-2095.98,500.0,1.8211109399795533,50000
3
+ 0.0,0.0,0.56,0.6222222222222222,-0.1813342058881092,0.005436982600713472,-0.18118769581767763,0.002571477750097156,34.81541402475816,24.77099999999715,0.18,38522.14,-3.4,-2179.5,490.42,1.7815654182434082,100000
4
+ 0.0,0.0,0.5733333333333334,0.8555555555555555,-0.18460106619068015,-0.004305860074038781,-0.1846446837576921,0.0011559588055688895,35.09596890382728,21.460999999998943,0.66,62002.5,-1.3,-1844.46,424.22,1.5602857065200806,150000
5
+ 0.0,0.0,0.6355555555555555,0.9911111111111112,-0.18178005008233633,-0.0026477575303508185,-0.18187604986227981,0.0007447891771651176,35.27315445321268,18.475000000000264,0.98,82683.3,-0.08,-1516.34,364.5,1.333532419204712,200000
6
+ 0.0,0.0,0.6488888888888888,0.9866666666666667,-0.1876756788565474,-0.009772384372240506,-0.18821876530693954,-0.008306404285844731,34.914648743371245,17.191000000000855,0.96,100778.2,-0.12,-1493.78,338.82,1.2365639734268188,250000
7
+ 0.0,0.0,0.6311111111111111,1.0,-0.18170404423911102,-0.004047473626439653,-0.1820632277813686,-0.0036844326139314856,35.20204972584724,16.6330000000009,1.0,117956.42,0.0,-1373.24,327.66,1.19135675907135,300000
8
+ 0.0,0.0,0.64,1.0,-0.1829510809586485,-0.004213016104107537,-0.18344552173021814,-0.003984793070216794,34.90249542086447,16.24700000000109,1.0,134987.4,0.0,-1391.7,319.94,1.1691679286956786,350000
9
+ 0.0,0.0,0.6355555555555555,1.0,-0.18624896235498653,-0.005668628991892512,-0.18691605947148426,-0.005440879766551492,34.97219382277929,15.633000000001255,1.0,151309.78,0.0,-1329.48,307.66,1.1259048414230346,400000
10
+ 0.0,0.0,0.6288888888888889,1.0,-0.18002673267806443,-0.005993783579420944,-0.18035488792762397,-0.0035883442435268097,35.06498568638053,15.641000000001284,1.0,167220.68,0.0,-1349.88,307.82,1.1644256448745727,450000
11
+ 0.0,0.0,0.6422222222222222,1.0,-0.1789557719005772,-0.007900594394576764,-0.17941521558184464,-0.004951661454118848,34.979218273756345,15.188000000001379,1.0,182989.56,0.0,-1280.82,298.76,1.134086980819702,500000
12
+ 0.0,0.0,0.6311111111111111,1.0,-0.17799027916045407,-0.004697964807676401,-0.1783461817805346,-0.0033194173056449194,35.223063397622774,16.122000000001236,1.0,198942.76,0.0,-1389.36,317.44,1.1629466009140015,550000
13
+ 0.0,0.0,0.6377777777777778,1.0,-0.18002766609324983,-0.006063080090332967,-0.18019892659139308,-0.0007219451092086739,34.89550973718934,15.345000000001118,1.0,215463.12,0.0,-1311.08,301.9,1.1043927478790283,600000
14
+ 0.0,0.0,0.6333333333333333,1.0,-0.18510471027417447,-0.011729136759613396,-0.18581770215803958,-0.009828389176609309,34.817913303410066,15.180000000001174,1.0,231089.8,0.0,-1323.24,298.6,1.0907486009597778,650000
15
+ 0.0,0.0,0.6355555555555555,1.0,-0.18235309915337328,-0.005683052218596222,-0.18301206043244317,-0.0068639411721991535,35.00869918165872,16.031000000001175,1.0,246784.22,0.0,-1371.58,315.62,1.15701247215271,700000
16
+ 0.0,0.0,0.6488888888888888,1.0,-0.17852740582663634,-0.009351285441263119,-0.17913434642762038,-0.007491767698452915,35.0967859770837,15.466000000001298,1.0,262959.82,0.0,-1292.5,304.32,1.1161862707138062,750000
17
+ 0.0,0.0,0.6422222222222222,1.0,-0.17729964558315936,-0.008919560295532317,-0.1779184968665721,-0.006072136905818945,35.01666940501616,16.051000000000936,1.0,279086.08,0.0,-1352.98,316.02,1.1490920400619506,800000
18
+ 0.0,0.0,0.6244444444444445,1.0,-0.17958925743346205,-0.004293850383152812,-0.1799500211174268,-0.004057112000637643,35.07856682138788,15.202000000001295,1.0,295166.66,0.0,-1305.88,299.04,1.099862937927246,850000
19
+ 0.0,0.0,0.6333333333333333,1.0,-0.17501989275805316,-0.0012818354260895916,-0.17512041858922558,0.001026949099995425,35.29315784243551,15.685000000001098,1.0,310806.3,0.0,-1300.88,308.7,1.13539559841156,900000
20
+ 0.0,0.0,0.6488888888888888,1.0,-0.1825018763095996,-0.010344307001687912,-0.18314643575735487,-0.00679393100215268,34.97668198029096,15.329000000001082,1.0,326864.4,0.0,-1280.98,301.58,1.096357879638672,950000
21
+ 0.0,0.0,0.6422222222222222,0.9933333333333333,-0.18504981008756752,-0.011067511874417556,-0.18578617431983246,-0.009332859300329541,35.00438787272922,15.189000000001055,0.98,342549.9,-0.06,-1292.14,298.78,1.1045069360733033,1000000
22
+ 0.0,0.0,0.6466666666666666,1.0,-0.1768771511125647,-0.0016273435597593344,-0.17714848662120408,-0.0016876953875084879,35.1146360097117,15.33500000000141,1.0,357966.26,0.0,-1315.88,301.7,1.1149995231628418,1050000
23
+ 0.0,0.0,0.6355555555555555,1.0,-0.1791995813068301,-0.00530960571492019,-0.1797471881056381,-0.004539601437687006,34.88903489624965,14.313000000001296,1.0,373232.68,0.0,-1230.78,281.26,1.0349890184402466,1100000
24
+ 0.0,0.0,0.6488888888888888,1.0,-0.1801138560921088,-0.004328451060384341,-0.18056994714321387,-0.0029326704106852593,34.94130236819594,14.70900000000136,1.0,387933.52,0.0,-1243.54,289.18,1.0658512353897094,1150000
25
+ 0.0,0.0,0.64,1.0,-0.18315240838994823,-0.005734552685949903,-0.18353683296548656,-0.0028218965850095672,35.18514685058983,14.443000000001362,1.0,402861.4,0.0,-1259.1,283.86,1.0500581407546996,1200000
26
+ 0.0,0.0,0.6555555555555556,1.0,-0.18002671167698078,-0.0011821763989330017,-0.1804833093123117,-0.003847188325115361,35.236939026775765,14.093000000001211,1.0,417493.48,0.0,-1148.62,276.86,1.0233480787277223,1250000
27
+ 0.0,0.0,0.6377777777777778,1.0,-0.17880194235997668,-0.006965311684213381,-0.17932052968632572,-0.004424238133356792,35.15302802710362,13.690000000001216,1.0,431593.58,0.0,-1168.4,268.8,0.990675368309021,1300000
28
+ 0.0,0.0,0.6466666666666666,1.0,-0.17935320527941978,-0.0044744640187476675,-0.17992149509053304,-0.004675993589519461,35.17109965936634,13.746000000001223,1.0,445530.18,0.0,-1186.52,269.92,1.05004629611969,1350000
29
+ 0.0,0.0,0.6533333333333333,1.0,-0.18623667721908904,-0.01048017353099955,-0.18705157390375837,-0.009588340480766242,35.25336698318077,13.260000000001094,1.0,459367.94,0.0,-1122.54,260.2,1.0274169540405274,1400000
30
+ 0.0,0.0,0.6555555555555556,0.9933333333333333,-0.18634500011449917,-0.0038635406430638643,-0.1869578823139095,-0.006637463732921699,35.10366558920742,13.801000000000952,0.98,473145.92,-0.06,-1162.56,271.02,1.0688276863098145,1450000
31
+ 0.0,0.0,0.66,1.0,-0.17477752279366962,-0.0013221297462161854,-0.17509347292369878,-0.00021989234754104956,35.04741896220112,12.807000000000931,1.0,486716.86,0.0,-1056.62,251.14,0.9981927251815796,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/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": "FQL", "seed": 10001, "env_name": "puzzle-3x3-play-singletask-task4-v0", "save_dir": "exp/qam-reproduce/main-experiments/puzzle-3x3-play-singletask-task4-v0/20260308_113045", "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": {"action_chunking": true, "action_dim": 5, "actor_hidden_dims": [512, 512, 512, 512], "actor_layer_norm": false, "agent_name": "fql", "alpha": 300.0, "batch_size": 256, "best_of_n": 1, "discount": 0.99, "flow_steps": 10, "horizon_length": 5, "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_113045/offline_agent.csv ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 78.15827,0.25252324,0.0062490753,11.648656,-71.8434,-76.0323,-76.30153,1.6244917,-1.4825938,57.2396,5000
3
+ 96.69877,0.22133787,0.0045914743,0.049432404,-86.27315,-95.10056,-95.26914,1.130741,-1.7780235,41.19323,10000
4
+ 101.56074,0.20500015,0.0031556056,0.42920747,-88.41905,-100.40065,-101.066635,0.6306942,-1.1966522,44.878353,15000
5
+ 103.26981,0.22581206,0.003923249,3.1660304,-0.28564614,-101.86659,-103.56707,1.4963536,-1.395691,47.94576,20000
6
+ 103.41898,0.19874,0.0029625962,0.017975837,0.089640975,-102.33111,-103.1964,0.99890184,-0.99355125,28.021053,25000
7
+ 104.25602,0.2293864,0.004081701,0.02694652,-98.87507,-102.80392,-103.19628,1.7469289,-1.7024238,42.176636,30000
8
+ 103.150085,0.18881918,0.0025878507,0.13608234,-0.30981448,-102.1758,-102.88292,0.63450336,-0.7053414,20.835058,35000
9
+ 102.124504,0.19698289,0.0033728117,16.91205,-28.167429,-101.2362,-102.72504,0.71411765,-0.78273267,54.596497,40000
10
+ 94.88151,0.18617857,0.004812117,11.348956,-55.690575,-94.40215,-100.13645,1.699997,-2.1735847,110.428696,45000
11
+ 72.336395,0.20827319,0.00889275,10.230922,0.33254248,-72.5377,-95.34479,1.1311781,-1.4011451,91.04277,50000
12
+ 73.845505,0.20679094,0.0074740383,9.856421,-29.271252,-73.24451,-88.213875,4.371046,-2.9336944,125.579765,55000
13
+ 74.5171,0.18092726,0.0052757333,9.369583,0.11106341,-74.440285,-94.301025,0.6381474,-0.8656107,101.88274,60000
14
+ 71.48838,0.20484468,0.008006058,11.441542,-18.669754,-71.151245,-98.32179,2.4517891,-1.9047257,96.83018,65000
15
+ 68.11875,0.21853992,0.0056881355,5.8774676,0.5465531,-68.18792,-88.53344,1.2172731,-1.3029826,75.51163,70000
16
+ 71.86238,0.1885004,0.006958225,7.088661,-16.502752,-71.32357,-104.41736,1.8877206,-1.8298616,87.02083,75000
17
+ 82.539894,0.16264462,0.004119135,5.91208,-25.395706,-82.328,-106.95554,0.90879667,-0.6443383,66.350876,80000
18
+ 80.892784,0.21309832,0.0066764983,4.760598,-20.966267,-80.76686,-102.38116,1.2178833,-0.9415711,67.88518,85000
19
+ 81.003815,0.19689189,0.0050244904,4.111577,-25.931076,-80.42852,-101.28113,1.2011509,-0.840341,53.964485,90000
20
+ 79.76796,0.17272408,0.0060202093,3.0363412,-17.337633,-78.99896,-104.45085,2.2802904,-2.6792362,76.02612,95000
21
+ 77.700356,0.20144698,0.006348907,3.360543,0.4298413,-77.292984,-103.50953,1.7390137,-1.7587819,61.721825,100000
22
+ 79.39805,0.18202755,0.004524323,2.9039946,-20.130241,-79.11537,-98.96357,0.534623,-0.6416044,38.506382,105000
23
+ 77.22644,0.19747123,0.0064491234,3.7273457,-21.766233,-76.72568,-102.90418,1.2160665,-1.366221,62.1032,110000
24
+ 77.24084,0.1720927,0.006651279,3.9213548,-2.168902,-76.47384,-99.24639,2.106081,-2.9178512,71.65243,115000
25
+ 77.12722,0.19502532,0.0052628624,2.1294012,0.5030185,-76.62762,-100.586365,2.0235338,-1.3448353,49.26047,120000
26
+ 78.38424,0.16272399,0.005857253,2.5632489,0.5342769,-77.94562,-99.98948,2.8954902,-1.9484856,52.0312,125000
27
+ 77.24164,0.18248852,0.00630942,2.1816843,-1.0165021,-76.80746,-99.12085,2.5983384,-1.6892734,55.406578,130000
28
+ 74.35725,0.18101716,0.00555966,2.3058724,0.31062347,-74.12703,-103.143486,1.4437603,-1.3913438,44.993816,135000
29
+ 76.938576,0.17317107,0.0064001023,2.221908,0.34663457,-76.49121,-98.0546,1.5817747,-2.0129375,51.3035,140000
30
+ 76.38402,0.19888881,0.0056449124,1.9109976,0.22116552,-75.970535,-102.090965,1.5882404,-1.9159769,42.628345,145000
31
+ 77.383545,0.16260833,0.005187883,2.422255,-2.0494413,-77.27189,-102.83604,1.2579393,-1.7685035,47.25456,150000
32
+ 77.617035,0.175862,0.005661975,2.4657285,-1.2883797,-77.302124,-99.76395,1.0905925,-0.91049004,36.102074,155000
33
+ 76.94384,0.16725367,0.0062866714,1.5539024,-22.89983,-76.1099,-102.549614,3.1249037,-2.1204336,51.82777,160000
34
+ 77.63227,0.18444963,0.0058740983,2.5271394,-8.280749,-77.55994,-102.16063,1.0700579,-0.6973089,44.792133,165000
35
+ 78.006805,0.20496418,0.008272176,1.6449387,-19.148865,-76.96126,-98.62408,2.8862727,-2.868558,67.02903,170000
36
+ 75.64218,0.2069559,0.005512578,3.7398822,-17.932533,-75.24028,-98.98129,1.3014909,-1.8303775,52.646343,175000
37
+ 77.02021,0.17786202,0.0037866756,1.7274071,-6.0418444,-76.697105,-98.46414,1.2279521,-0.97068274,46.16211,180000
38
+ 76.69549,0.19819224,0.0064077494,2.523336,-16.064238,-76.00024,-97.53907,1.4536471,-1.0020003,51.910843,185000
39
+ 77.902,0.18074523,0.004822532,1.7524239,-25.731476,-77.68838,-96.85266,0.939348,-0.97958624,36.530857,190000
40
+ 76.296234,0.18097639,0.0060020676,2.2885046,1.1782258,-75.65967,-99.61043,1.8898833,-2.3041003,48.740646,195000
41
+ 76.431404,0.19020489,0.0058103227,1.6813313,-14.40282,-76.2029,-102.68396,0.88719493,-1.0133408,36.66073,200000
42
+ 76.2254,0.14664549,0.0052676443,1.9613644,0.20509315,-76.15358,-97.941574,1.0804591,-1.5978905,37.90914,205000
43
+ 74.89461,0.19407731,0.00479939,2.3088987,0.6356549,-74.72834,-102.087006,0.6814829,-1.110879,39.61379,210000
44
+ 77.45161,0.15592492,0.0040686103,1.47089,-18.93134,-77.718864,-98.01572,0.9403197,-0.7853578,32.98108,215000
45
+ 76.60794,0.16176258,0.007327168,2.0562325,-23.448843,-76.10768,-98.27493,1.7406915,-2.11767,50.631783,220000
46
+ 75.57723,0.17836136,0.003828575,1.0356218,-3.73337,-75.17562,-98.77495,2.4402785,-1.65527,35.74743,225000
47
+ 77.34104,0.1846462,0.00590966,1.504649,-16.099943,-76.63088,-98.87723,1.1683842,-1.6805925,45.220203,230000
48
+ 75.042984,0.15683074,0.0048102974,2.9200675,0.24404092,-75.087036,-102.4756,0.6823147,-0.55980355,33.634163,235000
49
+ 74.68202,0.16078526,0.004936166,1.39412,-22.45233,-74.41791,-97.79944,1.0981388,-1.0261918,35.77555,240000
50
+ 77.083244,0.22672728,0.005728909,1.7626861,0.47397757,-77.23269,-102.46788,0.978258,-1.1548026,45.936768,245000
51
+ 75.90976,0.16654515,0.004947837,2.0294242,0.34883228,-76.0427,-98.31647,0.88665974,-1.006761,38.2959,250000
52
+ 76.40913,0.17786731,0.006218659,1.6540269,-1.2010063,-75.72695,-97.52742,1.9257333,-1.4256239,44.836,255000
53
+ 75.08829,0.18117917,0.0054390035,1.8167664,0.307954,-74.53155,-97.31621,2.3610346,-2.2749236,50.180107,260000
54
+ 76.026825,0.17139682,0.0040719695,1.4531225,-19.83563,-76.30934,-102.05237,1.2529833,-1.8719404,32.9635,265000
55
+ 74.77372,0.18047485,0.0044323364,2.3024945,-11.396775,-75.06883,-101.676025,1.0639316,-1.0191063,40.38408,270000
56
+ 73.09954,0.15808026,0.0036689756,1.9635518,0.27597043,-73.01959,-102.48114,0.66417575,-0.84510994,29.559021,275000
57
+ 75.19111,0.17124107,0.004868494,1.7819299,-0.62978095,-75.285645,-99.14807,1.7506199,-2.0601566,39.48151,280000
58
+ 75.84048,0.17282382,0.004762089,1.5640644,-23.696651,-75.63659,-98.72948,1.5653584,-1.641871,39.182503,285000
59
+ 77.1267,0.1614841,0.004564368,1.4720147,-13.019262,-76.88633,-102.22384,0.74960685,-0.61746114,32.94783,290000
60
+ 75.76544,0.17141815,0.0055178343,1.7398165,-16.988184,-75.65664,-101.69015,1.2736738,-1.4554514,41.83953,295000
61
+ 76.635864,0.14744607,0.005023851,1.5743563,-0.584782,-76.39994,-101.90229,1.5239582,-1.8938174,41.32884,300000
62
+ 77.46129,0.17412998,0.004638228,1.342059,-17.788645,-77.03768,-101.77634,0.71829426,-0.6693668,28.695896,305000
63
+ 76.72466,0.1545318,0.0052122613,1.4519883,-21.120298,-76.466225,-98.03576,3.03425,-2.0781636,43.598404,310000
64
+ 75.57037,0.15360549,0.004760652,2.0210125,-19.025454,-75.6536,-96.292786,1.1050506,-1.2073326,41.807243,315000
65
+ 76.31088,0.1821932,0.0042684413,1.3110604,-17.572075,-76.52542,-102.03983,0.9774876,-1.460553,31.604212,320000
66
+ 76.17009,0.14577934,0.005094931,2.4602258,-2.1448374,-76.423,-97.53712,0.64021033,-0.9244,41.700413,325000
67
+ 76.66805,0.18013442,0.0058151293,3.123761,-26.975504,-76.38656,-96.855644,1.8342547,-1.649639,52.216095,330000
68
+ 74.90637,0.19552393,0.0059114364,2.4776518,-20.453072,-74.876785,-96.81951,1.292372,-1.9047073,48.198963,335000
69
+ 75.246086,0.19444835,0.0047489903,1.7694546,-14.899084,-75.08736,-98.05685,1.0610402,-1.3883247,36.45848,340000
70
+ 75.33349,0.185812,0.004568144,1.7257446,-6.5969887,-75.15841,-97.740746,1.34811,-1.2092075,33.351326,345000
71
+ 74.234184,0.18144253,0.005558216,1.7388906,-2.0370588,-74.393486,-97.86261,1.1890099,-1.7553425,60.510056,350000
72
+ 76.92294,0.1716701,0.006939624,1.4936583,0.076892614,-76.374504,-101.781044,2.419923,-1.9424751,49.45552,355000
73
+ 75.48788,0.17435421,0.004126694,1.5934633,0.23749383,-75.32942,-101.3781,1.3588176,-0.8966497,32.65947,360000
74
+ 76.950066,0.18016252,0.0046826857,1.5454744,-19.47968,-76.51261,-97.68133,1.2713382,-1.8522775,39.081287,365000
75
+ 75.42786,0.17308336,0.0051156497,1.4410604,-22.344875,-75.394325,-101.47568,1.5186299,-0.9948284,37.567787,370000
76
+ 75.962975,0.18844849,0.004737594,1.0808581,0.32529652,-75.692276,-97.868515,1.0187595,-0.92260826,30.759777,375000
77
+ 75.29101,0.15229289,0.0049530375,1.473623,0.33619958,-75.070366,-101.72031,1.8707107,-1.2107817,35.63174,380000
78
+ 74.72637,0.17323826,0.005709443,1.3168677,0.22778554,-75.16097,-97.219734,0.6782044,-0.9725463,34.25811,385000
79
+ 75.37696,0.16917092,0.004589432,1.5415841,0.14245959,-75.5144,-98.02363,0.59247607,-0.85387176,29.144514,390000
80
+ 76.250725,0.14337382,0.0042458833,1.2326432,-19.325338,-75.85329,-95.877365,2.7647905,-2.059146,38.37526,395000
81
+ 74.7082,0.17752124,0.0048935134,2.54518,-19.987322,-74.50051,-96.687935,0.9433161,-1.2911152,45.41589,400000
82
+ 76.39416,0.19338073,0.0049577868,1.094451,0.64653534,-76.24535,-101.71774,2.4373226,-2.7447891,35.72,405000
83
+ 75.07018,0.16953117,0.0041138125,2.5702212,-20.740398,-75.1319,-98.580826,0.75422263,-0.94406277,40.691124,410000
84
+ 75.61592,0.1759266,0.005491163,3.4071655,-21.634539,-75.59425,-97.16908,0.92388153,-1.2802472,41.223553,415000
85
+ 75.75282,0.17467783,0.0049461345,1.0449281,0.2638137,-75.52799,-97.75592,0.86754423,-0.7389014,26.490812,420000
86
+ 73.68726,0.17190686,0.0052392734,2.433223,-20.926434,-73.85778,-96.37313,0.7914797,-0.83607787,43.65374,425000
87
+ 74.03972,0.1924868,0.0046745013,1.2936076,0.36832836,-73.70046,-96.76571,1.1836165,-1.3070586,32.442142,430000
88
+ 74.82335,0.17456877,0.004966453,2.2684267,-21.290958,-74.94164,-97.29043,1.4627148,-1.004403,43.938034,435000
89
+ 75.093346,0.1597744,0.0054786047,1.378706,-6.6391125,-74.80169,-98.00499,1.1929238,-1.820936,37.713352,440000
90
+ 77.98258,0.17010978,0.0041302727,1.3982849,-19.406956,-78.032524,-97.75484,0.65974754,-0.6045755,28.2713,445000
91
+ 75.67687,0.19741555,0.0037483405,1.2665154,0.31787091,-75.50506,-97.29696,1.1651934,-2.1025684,32.40206,450000
92
+ 74.56232,0.16952422,0.0046710786,1.6054896,-2.1074126,-74.60201,-101.67597,0.96987534,-1.4829328,42.343292,455000
93
+ 75.37016,0.182322,0.003414574,1.1523014,0.26419675,-75.39504,-96.87724,1.6380284,-1.347887,34.537567,460000
94
+ 76.665215,0.17066343,0.005689806,1.5634272,0.37115115,-76.1993,-101.59394,1.4158288,-0.9835697,38.527283,465000
95
+ 76.2903,0.17334127,0.004649342,1.6899681,-26.172422,-76.24584,-97.886734,3.0308273,-2.0281084,42.643265,470000
96
+ 75.151764,0.18791184,0.0041087638,1.4039841,-20.343409,-74.94998,-97.903305,0.48188308,-0.63385934,25.261377,475000
97
+ 75.02468,0.17096841,0.006478723,1.6735966,0.24995549,-74.80974,-97.55365,2.0562503,-1.3984257,46.07125,480000
98
+ 75.13382,0.17736739,0.005332587,1.2870245,-20.61262,-75.11178,-101.43302,1.7296222,-1.3538662,32.863335,485000
99
+ 75.02145,0.17423227,0.004837034,1.1749878,-7.1569514,-74.79845,-98.19856,0.95705783,-0.65792775,29.315418,490000
100
+ 75.66866,0.20524089,0.005581051,1.4041283,0.19554365,-75.65673,-96.55677,1.9852715,-2.9618545,44.763477,495000
101
+ 77.577614,0.20422369,0.0044557364,1.1933196,-1.5598726,-77.31036,-96.625,2.7646153,-2.3027408,46.922905,500000
102
+ 75.8367,0.17823684,0.0049195355,1.064473,0.32334077,-75.53043,-97.68338,1.3742455,-1.6622494,34.36856,505000
103
+ 77.622826,0.1687201,0.004556067,1.2587925,-23.592281,-77.73319,-102.01577,1.0660472,-1.0647624,30.731285,510000
104
+ 72.729065,0.18495716,0.004488415,2.3433583,0.17506869,-72.71803,-96.62697,1.1740006,-0.77658606,34.7482,515000
105
+ 75.86679,0.15806198,0.0044836663,1.2693106,-2.1657894,-75.51011,-98.057076,1.0225015,-1.5072714,31.5662,520000
106
+ 74.28365,0.17893408,0.005342712,1.2161417,-20.207506,-74.05796,-101.59788,1.8941941,-1.0960438,40.20432,525000
107
+ 76.51851,0.19438621,0.0045921695,1.872508,-3.1509225,-76.02405,-101.80412,1.3759342,-1.1742843,32.558693,530000
108
+ 76.03665,0.16887376,0.004579156,1.4817342,-22.10802,-75.67431,-96.442314,1.3262295,-1.9314198,37.90918,535000
109
+ 76.55369,0.1976506,0.0041317856,1.7356589,0.16111319,-76.46612,-98.3129,0.79691833,-0.96724296,38.00096,540000
110
+ 75.86556,0.19179785,0.005499938,1.0984099,-21.449697,-75.82567,-96.3963,1.2493943,-1.3886977,32.354187,545000
111
+ 76.75013,0.18198681,0.0043019555,0.9724776,0.2862062,-76.41713,-101.76533,1.1463327,-0.77158034,35.20337,550000
112
+ 73.79603,0.16335925,0.0067097316,1.3114116,0.28863078,-73.55068,-95.82879,2.2645822,-2.559294,45.127335,555000
113
+ 75.63264,0.183028,0.004818101,1.5328597,0.5273471,-75.79341,-97.32752,1.1523343,-1.0505443,34.684322,560000
114
+ 75.97444,0.18357235,0.004941107,1.155509,-20.282076,-75.94936,-96.78773,1.8100413,-2.0778418,33.659477,565000
115
+ 74.09864,0.17769143,0.005955529,1.4292096,-18.774115,-74.11126,-96.04309,0.89332813,-0.6728712,34.323746,570000
116
+ 76.17451,0.15643927,0.004241138,0.75153655,0.2645715,-76.21808,-97.074844,1.3721644,-0.86275345,29.849247,575000
117
+ 75.18709,0.15798394,0.005364648,1.9840983,0.1568968,-74.77712,-96.68171,1.1730024,-1.6282007,46.715164,580000
118
+ 75.62283,0.14912751,0.003965403,1.5025504,-20.506687,-75.59527,-101.24512,1.3451264,-0.9970324,31.28887,585000
119
+ 77.22659,0.14390975,0.0061498415,0.9274155,0.26735866,-76.92323,-101.595924,1.6437824,-1.8301972,38.51088,590000
120
+ 75.911995,0.16202618,0.0059885154,0.99498314,-20.095053,-75.67121,-101.4624,1.3185859,-1.2237123,32.00398,595000
121
+ 76.109406,0.17481062,0.0042910003,1.632726,-19.521341,-75.84548,-98.673584,1.6929867,-1.1494046,34.76237,600000
122
+ 76.57238,0.17299065,0.004826917,0.9549036,-18.624517,-76.194176,-101.32232,2.1013381,-1.9072344,42.925934,605000
123
+ 73.33107,0.15891996,0.0050505055,1.742223,0.37571555,-73.047646,-97.04718,1.7087833,-2.82282,43.39171,610000
124
+ 74.6475,0.1480969,0.004080294,2.3980186,0.2424563,-74.50436,-96.93484,1.2021698,-0.84332776,34.482296,615000
125
+ 74.25369,0.15972726,0.0054270755,1.5177301,-20.347647,-73.922905,-96.427124,1.9225743,-1.322736,45.74662,620000
126
+ 75.164894,0.20482457,0.004940849,1.1357363,-13.573316,-75.02468,-97.057724,1.1228409,-0.94821817,29.056866,625000
127
+ 75.18466,0.19275524,0.0050667166,1.9164097,-25.841799,-75.25306,-95.71918,1.6673809,-1.7416581,45.370384,630000
128
+ 74.64077,0.15625282,0.0038956064,0.86831915,-0.8222786,-74.778114,-96.316765,0.92967653,-1.0539528,28.057964,635000
129
+ 74.17575,0.17668682,0.0035360295,2.7713406,0.16459262,-74.0321,-96.60988,1.0919652,-0.7160236,39.362083,640000
130
+ 75.46635,0.19402799,0.0046281293,1.2963392,-24.213758,-75.2751,-101.3454,1.6544627,-1.9869485,36.359634,645000
131
+ 76.76012,0.15460062,0.0046516038,1.1020612,-21.117216,-76.53741,-101.083305,1.3878562,-1.702896,34.280247,650000
132
+ 74.73183,0.17413944,0.0047424803,1.3791819,0.4147437,-74.28755,-98.8556,0.9577234,-1.3379883,33.475044,655000
133
+ 75.295265,0.16010445,0.004362417,1.0407797,-21.316692,-75.31548,-98.02495,1.4378425,-1.1940886,30.841196,660000
134
+ 75.63472,0.214109,0.0057792612,0.9966404,0.118358016,-75.27886,-96.68982,4.7801323,-3.3096912,45.717667,665000
135
+ 77.14607,0.17637122,0.0038743552,0.88797295,-19.48035,-76.92078,-101.59282,0.93629986,-1.1499717,27.440792,670000
136
+ 76.758804,0.17612012,0.0052758777,0.9747308,-28.602879,-76.239174,-101.36825,2.036011,-2.1750312,38.260296,675000
137
+ 76.34906,0.15126765,0.0041373926,1.432854,-23.409822,-76.23927,-97.13292,0.9203272,-1.3813795,29.283045,680000
138
+ 75.31418,0.17608604,0.006000129,1.3054342,-23.531946,-75.10659,-101.2092,1.5457667,-1.081536,36.563744,685000
139
+ 75.402504,0.1718119,0.005498322,1.3741586,-23.498104,-75.53974,-96.72335,1.2025307,-1.2197068,37.069454,690000
140
+ 78.04995,0.1820319,0.0050498536,1.075796,-23.847477,-77.67838,-97.80198,2.3304496,-1.8070223,38.57952,695000
141
+ 76.022606,0.18020788,0.0052392804,1.5017928,0.33611274,-75.939476,-101.3166,0.7149729,-0.96128106,36.594833,700000
142
+ 76.5636,0.18621278,0.0050809914,1.1728699,0.3777874,-76.03124,-97.907585,1.1915258,-1.4652637,34.08281,705000
143
+ 76.342964,0.15121986,0.005594195,2.3566895,0.39034152,-76.19023,-101.368385,2.7018971,-1.7829386,39.646255,710000
144
+ 75.84576,0.17290777,0.004775529,1.8570198,0.13152882,-75.74737,-101.22012,0.82715696,-1.2483065,33.994175,715000
145
+ 74.55044,0.19714662,0.0049432414,1.7479203,-25.150705,-74.9435,-96.28591,1.169524,-0.9507088,35.087635,720000
146
+ 76.07154,0.1585091,0.0054789516,1.2461065,-14.58271,-75.862595,-96.59674,1.8196176,-2.08573,37.94564,725000
147
+ 75.75108,0.2012005,0.005098285,1.2111591,-11.421995,-75.28674,-101.42281,2.5849056,-1.8092581,36.609104,730000
148
+ 74.45454,0.19097184,0.0052967207,1.5703819,0.28306985,-74.04869,-96.55998,1.1513989,-0.9023597,35.937027,735000
149
+ 75.395134,0.16419303,0.0035823935,1.3814119,0.2632022,-75.174515,-101.5835,1.2536503,-0.82750875,28.285887,740000
150
+ 75.86152,0.1861294,0.004833187,1.0017896,0.35835934,-75.88998,-101.04848,1.1092004,-1.3661014,31.578373,745000
151
+ 75.65282,0.1445001,0.005149479,1.062216,-10.552686,-75.43957,-96.87069,0.88214636,-1.3177147,27.105944,750000
152
+ 75.95728,0.17227386,0.005279597,1.1940678,0.33327836,-75.77239,-101.72672,4.346109,-2.8753054,38.89309,755000
153
+ 76.34322,0.20352022,0.0052872133,1.4840506,0.08406684,-75.92916,-97.93582,1.7543421,-1.5530118,38.284397,760000
154
+ 74.776245,0.16879088,0.006055579,1.9930108,-18.118435,-74.50281,-96.315384,2.1695287,-1.5933053,39.25368,765000
155
+ 74.96042,0.16813184,0.004113454,1.7584981,-19.613008,-75.00067,-101.71237,2.2839077,-2.9016442,40.302307,770000
156
+ 74.76333,0.16388899,0.004661346,2.7022786,0.47091004,-75.046646,-97.41351,0.66217196,-1.013584,40.34371,775000
157
+ 74.229294,0.19343126,0.006416703,2.4692082,0.33039516,-73.99806,-97.643585,1.0967736,-1.3321517,43.79091,780000
158
+ 75.416565,0.17425908,0.003668086,1.2698287,0.27987155,-75.6334,-97.289635,1.2957095,-1.4262235,33.954594,785000
159
+ 75.60081,0.16530967,0.0048706895,1.0255699,-6.378746,-75.42797,-101.255325,0.81995666,-1.204587,28.656792,790000
160
+ 74.27994,0.15375671,0.0044320463,1.3771288,0.18815202,-74.48191,-101.191536,2.2490957,-3.2724397,36.4419,795000
161
+ 76.53047,0.20952666,0.0053747473,1.6565043,-20.14599,-76.14369,-96.69442,1.4412935,-2.137904,43.262424,800000
162
+ 74.74387,0.17462245,0.0042906655,1.024825,-21.382315,-74.42066,-97.94988,1.4545403,-1.2457149,35.34482,805000
163
+ 75.19392,0.19354492,0.00433874,0.7274132,-1.4038337,-75.14135,-101.175,1.1306188,-1.5599542,28.208237,810000
164
+ 76.85801,0.16164333,0.004835102,0.66700864,-0.43471622,-76.441124,-101.4944,1.3087367,-1.7230564,31.091316,815000
165
+ 76.13767,0.1495384,0.005115637,0.77401924,-13.2893715,-75.80816,-101.39482,1.0689455,-1.345804,32.70932,820000
166
+ 75.305336,0.17231992,0.0046419594,1.8398697,0.07112831,-75.10143,-101.83293,1.7046297,-1.9716846,43.568092,825000
167
+ 76.567,0.16811752,0.0042868285,1.8700479,-20.745094,-76.645775,-101.57513,0.8532408,-1.2450385,32.630898,830000
168
+ 74.98773,0.18563534,0.004596862,1.0514606,-24.817944,-74.87571,-97.505516,1.1090465,-1.5541327,39.011997,835000
169
+ 76.65766,0.15365115,0.0044383756,1.0770682,0.16945618,-76.42318,-101.57287,1.8027943,-1.3828552,34.077106,840000
170
+ 76.753296,0.18956298,0.0046936367,1.2757796,-19.810596,-76.54563,-96.14814,1.3825455,-0.95745087,35.4794,845000
171
+ 75.32889,0.16963507,0.00487956,2.2739956,-26.32384,-74.960075,-97.077156,0.7361405,-0.72397846,31.089184,850000
172
+ 76.06996,0.18771152,0.004026072,1.8504876,-3.4618168,-75.98891,-96.105934,3.0536225,-1.6104592,36.549843,855000
173
+ 75.126816,0.17626423,0.0043246187,1.489765,-19.507706,-75.14366,-95.99117,0.93258244,-1.2939022,39.209633,860000
174
+ 75.848076,0.17239864,0.0041343165,0.9271634,0.38492677,-75.79543,-101.46111,1.334087,-1.777232,25.82861,865000
175
+ 73.58442,0.1435147,0.004269824,1.431054,-12.949872,-73.72012,-101.3762,0.6934712,-0.48794258,26.571844,870000
176
+ 76.609886,0.1789439,0.0046311216,2.0374365,-21.425507,-76.66947,-97.79672,2.6083088,-1.7171334,39.92,875000
177
+ 76.43827,0.16038644,0.0036243938,1.3946714,-28.67662,-76.52769,-101.47805,1.2798417,-0.972273,29.449665,880000
178
+ 77.32072,0.1834678,0.0052103004,0.8481247,-20.370623,-76.93149,-101.181244,2.1862345,-1.4643611,34.43634,885000
179
+ 74.64918,0.16398865,0.0057309736,0.86438894,-14.237996,-74.432884,-96.28079,3.3748736,-4.9247165,35.93019,890000
180
+ 75.241356,0.15792677,0.006021562,0.7474045,-17.398434,-74.691185,-101.29628,3.362061,-2.6674244,42.045433,895000
181
+ 75.1891,0.17378382,0.0039311624,2.1367555,-20.925356,-75.55729,-96.7508,0.5497845,-0.9676573,30.355785,900000
182
+ 74.939384,0.1611451,0.004972481,0.85965014,0.0906544,-74.86405,-97.27378,1.1559445,-1.5694656,34.369614,905000
183
+ 74.73301,0.17388165,0.004927955,0.88456005,-5.940154,-74.78566,-100.94554,1.0977875,-0.779979,29.93733,910000
184
+ 75.896675,0.17708212,0.004735496,1.4323133,0.40118182,-76.049576,-101.07997,1.3092159,-1.7512333,32.813366,915000
185
+ 75.66502,0.17910153,0.0043902365,1.2272388,-21.443998,-75.83447,-96.67472,1.9156238,-1.1107328,33.460148,920000
186
+ 76.59495,0.1715689,0.0046270606,0.7929449,-34.936596,-76.41819,-96.07402,0.64440584,-0.95501745,28.655613,925000
187
+ 77.83263,0.17525661,0.0044367095,0.9189544,-21.172878,-77.720474,-96.5556,1.0489366,-1.3395783,31.711956,930000
188
+ 74.87873,0.16394076,0.005333377,1.3866163,-22.47118,-75.07471,-96.90521,1.4301957,-1.37533,34.181454,935000
189
+ 74.10323,0.17577523,0.00389915,1.1433057,0.117569625,-74.13269,-96.91331,1.2640636,-0.8261167,32.052288,940000
190
+ 76.72264,0.17515744,0.0041117696,1.2000575,0.6090778,-76.68017,-101.52979,0.62847143,-0.97695756,28.394001,945000
191
+ 76.410164,0.1602318,0.0042320415,1.1298815,-2.8916104,-76.53768,-101.40273,0.8277605,-0.93684524,32.620735,950000
192
+ 74.6888,0.15865418,0.0040520574,0.6838961,0.24761921,-74.93841,-96.74585,0.89912945,-1.0255773,25.55064,955000
193
+ 74.54725,0.19397737,0.0048750266,1.5283365,-10.155268,-74.145874,-97.01991,1.5597275,-1.1662862,35.46494,960000
194
+ 77.305145,0.17689988,0.0039670593,1.3137199,-18.339096,-77.36779,-101.25177,1.7575223,-2.0613444,37.217613,965000
195
+ 75.57466,0.16691267,0.0054320977,1.1250635,-3.30761,-75.30769,-101.4545,4.113034,-2.8020792,41.144695,970000
196
+ 74.72609,0.16404471,0.005326437,0.7725903,0.20911905,-74.417534,-97.30491,2.14773,-1.5918101,37.701744,975000
197
+ 74.19884,0.18076734,0.003427993,1.6985329,-22.363611,-74.45788,-96.998924,0.86337954,-0.8368983,27.986837,980000
198
+ 76.48462,0.18099578,0.0033192176,1.4642502,-19.611706,-76.37711,-96.18432,2.4622948,-1.6884967,43.56331,985000
199
+ 74.24717,0.16511388,0.004551563,1.0075752,-6.672037,-74.17889,-96.87541,1.5024356,-1.793747,32.19753,990000
200
+ 75.664925,0.18640126,0.0045123636,1.4152069,-25.62262,-75.72377,-101.19276,1.1727759,-1.1715971,27.572561,995000
201
+ 75.05076,0.13989237,0.004350882,1.3810663,0.16375077,-74.93033,-101.369774,2.6451163,-1.7721817,47.582085,1000000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/offline_agent_sv.csv ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 78.15827,0.25252324,0.0062490753,11.648656,-71.8434,-76.0323,-76.30153,1.6244917,-1.4825938,57.2396,5000
3
+ 96.69877,0.22133787,0.0045914743,0.049432404,-86.27315,-95.10056,-95.26914,1.130741,-1.7780235,41.19323,10000
4
+ 101.56074,0.20500015,0.0031556056,0.42920747,-88.41905,-100.40065,-101.066635,0.6306942,-1.1966522,44.878353,15000
5
+ 103.26981,0.22581206,0.003923249,3.1660304,-0.28564614,-101.86659,-103.56707,1.4963536,-1.395691,47.94576,20000
6
+ 103.41898,0.19874,0.0029625962,0.017975837,0.089640975,-102.33111,-103.1964,0.99890184,-0.99355125,28.021053,25000
7
+ 104.25602,0.2293864,0.004081701,0.02694652,-98.87507,-102.80392,-103.19628,1.7469289,-1.7024238,42.176636,30000
8
+ 103.150085,0.18881918,0.0025878507,0.13608234,-0.30981448,-102.1758,-102.88292,0.63450336,-0.7053414,20.835058,35000
9
+ 102.124504,0.19698289,0.0033728117,16.91205,-28.167429,-101.2362,-102.72504,0.71411765,-0.78273267,54.596497,40000
10
+ 94.88151,0.18617857,0.004812117,11.348956,-55.690575,-94.40215,-100.13645,1.699997,-2.1735847,110.428696,45000
11
+ 72.336395,0.20827319,0.00889275,10.230922,0.33254248,-72.5377,-95.34479,1.1311781,-1.4011451,91.04277,50000
12
+ 73.845505,0.20679094,0.0074740383,9.856421,-29.271252,-73.24451,-88.213875,4.371046,-2.9336944,125.579765,55000
13
+ 74.5171,0.18092726,0.0052757333,9.369583,0.11106341,-74.440285,-94.301025,0.6381474,-0.8656107,101.88274,60000
14
+ 71.48838,0.20484468,0.008006058,11.441542,-18.669754,-71.151245,-98.32179,2.4517891,-1.9047257,96.83018,65000
15
+ 68.11875,0.21853992,0.0056881355,5.8774676,0.5465531,-68.18792,-88.53344,1.2172731,-1.3029826,75.51163,70000
16
+ 71.86238,0.1885004,0.006958225,7.088661,-16.502752,-71.32357,-104.41736,1.8877206,-1.8298616,87.02083,75000
17
+ 82.539894,0.16264462,0.004119135,5.91208,-25.395706,-82.328,-106.95554,0.90879667,-0.6443383,66.350876,80000
18
+ 80.892784,0.21309832,0.0066764983,4.760598,-20.966267,-80.76686,-102.38116,1.2178833,-0.9415711,67.88518,85000
19
+ 81.003815,0.19689189,0.0050244904,4.111577,-25.931076,-80.42852,-101.28113,1.2011509,-0.840341,53.964485,90000
20
+ 79.76796,0.17272408,0.0060202093,3.0363412,-17.337633,-78.99896,-104.45085,2.2802904,-2.6792362,76.02612,95000
21
+ 77.700356,0.20144698,0.006348907,3.360543,0.4298413,-77.292984,-103.50953,1.7390137,-1.7587819,61.721825,100000
22
+ 79.39805,0.18202755,0.004524323,2.9039946,-20.130241,-79.11537,-98.96357,0.534623,-0.6416044,38.506382,105000
23
+ 77.22644,0.19747123,0.0064491234,3.7273457,-21.766233,-76.72568,-102.90418,1.2160665,-1.366221,62.1032,110000
24
+ 77.24084,0.1720927,0.006651279,3.9213548,-2.168902,-76.47384,-99.24639,2.106081,-2.9178512,71.65243,115000
25
+ 77.12722,0.19502532,0.0052628624,2.1294012,0.5030185,-76.62762,-100.586365,2.0235338,-1.3448353,49.26047,120000
26
+ 78.38424,0.16272399,0.005857253,2.5632489,0.5342769,-77.94562,-99.98948,2.8954902,-1.9484856,52.0312,125000
27
+ 77.24164,0.18248852,0.00630942,2.1816843,-1.0165021,-76.80746,-99.12085,2.5983384,-1.6892734,55.406578,130000
28
+ 74.35725,0.18101716,0.00555966,2.3058724,0.31062347,-74.12703,-103.143486,1.4437603,-1.3913438,44.993816,135000
29
+ 76.938576,0.17317107,0.0064001023,2.221908,0.34663457,-76.49121,-98.0546,1.5817747,-2.0129375,51.3035,140000
30
+ 76.38402,0.19888881,0.0056449124,1.9109976,0.22116552,-75.970535,-102.090965,1.5882404,-1.9159769,42.628345,145000
31
+ 77.383545,0.16260833,0.005187883,2.422255,-2.0494413,-77.27189,-102.83604,1.2579393,-1.7685035,47.25456,150000
32
+ 77.617035,0.175862,0.005661975,2.4657285,-1.2883797,-77.302124,-99.76395,1.0905925,-0.91049004,36.102074,155000
33
+ 76.94384,0.16725367,0.0062866714,1.5539024,-22.89983,-76.1099,-102.549614,3.1249037,-2.1204336,51.82777,160000
34
+ 77.63227,0.18444963,0.0058740983,2.5271394,-8.280749,-77.55994,-102.16063,1.0700579,-0.6973089,44.792133,165000
35
+ 78.006805,0.20496418,0.008272176,1.6449387,-19.148865,-76.96126,-98.62408,2.8862727,-2.868558,67.02903,170000
36
+ 75.64218,0.2069559,0.005512578,3.7398822,-17.932533,-75.24028,-98.98129,1.3014909,-1.8303775,52.646343,175000
37
+ 77.02021,0.17786202,0.0037866756,1.7274071,-6.0418444,-76.697105,-98.46414,1.2279521,-0.97068274,46.16211,180000
38
+ 76.69549,0.19819224,0.0064077494,2.523336,-16.064238,-76.00024,-97.53907,1.4536471,-1.0020003,51.910843,185000
39
+ 77.902,0.18074523,0.004822532,1.7524239,-25.731476,-77.68838,-96.85266,0.939348,-0.97958624,36.530857,190000
40
+ 76.296234,0.18097639,0.0060020676,2.2885046,1.1782258,-75.65967,-99.61043,1.8898833,-2.3041003,48.740646,195000
41
+ 76.431404,0.19020489,0.0058103227,1.6813313,-14.40282,-76.2029,-102.68396,0.88719493,-1.0133408,36.66073,200000
42
+ 76.2254,0.14664549,0.0052676443,1.9613644,0.20509315,-76.15358,-97.941574,1.0804591,-1.5978905,37.90914,205000
43
+ 74.89461,0.19407731,0.00479939,2.3088987,0.6356549,-74.72834,-102.087006,0.6814829,-1.110879,39.61379,210000
44
+ 77.45161,0.15592492,0.0040686103,1.47089,-18.93134,-77.718864,-98.01572,0.9403197,-0.7853578,32.98108,215000
45
+ 76.60794,0.16176258,0.007327168,2.0562325,-23.448843,-76.10768,-98.27493,1.7406915,-2.11767,50.631783,220000
46
+ 75.57723,0.17836136,0.003828575,1.0356218,-3.73337,-75.17562,-98.77495,2.4402785,-1.65527,35.74743,225000
47
+ 77.34104,0.1846462,0.00590966,1.504649,-16.099943,-76.63088,-98.87723,1.1683842,-1.6805925,45.220203,230000
48
+ 75.042984,0.15683074,0.0048102974,2.9200675,0.24404092,-75.087036,-102.4756,0.6823147,-0.55980355,33.634163,235000
49
+ 74.68202,0.16078526,0.004936166,1.39412,-22.45233,-74.41791,-97.79944,1.0981388,-1.0261918,35.77555,240000
50
+ 77.083244,0.22672728,0.005728909,1.7626861,0.47397757,-77.23269,-102.46788,0.978258,-1.1548026,45.936768,245000
51
+ 75.90976,0.16654515,0.004947837,2.0294242,0.34883228,-76.0427,-98.31647,0.88665974,-1.006761,38.2959,250000
52
+ 76.40913,0.17786731,0.006218659,1.6540269,-1.2010063,-75.72695,-97.52742,1.9257333,-1.4256239,44.836,255000
53
+ 75.08829,0.18117917,0.0054390035,1.8167664,0.307954,-74.53155,-97.31621,2.3610346,-2.2749236,50.180107,260000
54
+ 76.026825,0.17139682,0.0040719695,1.4531225,-19.83563,-76.30934,-102.05237,1.2529833,-1.8719404,32.9635,265000
55
+ 74.77372,0.18047485,0.0044323364,2.3024945,-11.396775,-75.06883,-101.676025,1.0639316,-1.0191063,40.38408,270000
56
+ 73.09954,0.15808026,0.0036689756,1.9635518,0.27597043,-73.01959,-102.48114,0.66417575,-0.84510994,29.559021,275000
57
+ 75.19111,0.17124107,0.004868494,1.7819299,-0.62978095,-75.285645,-99.14807,1.7506199,-2.0601566,39.48151,280000
58
+ 75.84048,0.17282382,0.004762089,1.5640644,-23.696651,-75.63659,-98.72948,1.5653584,-1.641871,39.182503,285000
59
+ 77.1267,0.1614841,0.004564368,1.4720147,-13.019262,-76.88633,-102.22384,0.74960685,-0.61746114,32.94783,290000
60
+ 75.76544,0.17141815,0.0055178343,1.7398165,-16.988184,-75.65664,-101.69015,1.2736738,-1.4554514,41.83953,295000
61
+ 76.635864,0.14744607,0.005023851,1.5743563,-0.584782,-76.39994,-101.90229,1.5239582,-1.8938174,41.32884,300000
62
+ 77.46129,0.17412998,0.004638228,1.342059,-17.788645,-77.03768,-101.77634,0.71829426,-0.6693668,28.695896,305000
63
+ 76.72466,0.1545318,0.0052122613,1.4519883,-21.120298,-76.466225,-98.03576,3.03425,-2.0781636,43.598404,310000
64
+ 75.57037,0.15360549,0.004760652,2.0210125,-19.025454,-75.6536,-96.292786,1.1050506,-1.2073326,41.807243,315000
65
+ 76.31088,0.1821932,0.0042684413,1.3110604,-17.572075,-76.52542,-102.03983,0.9774876,-1.460553,31.604212,320000
66
+ 76.17009,0.14577934,0.005094931,2.4602258,-2.1448374,-76.423,-97.53712,0.64021033,-0.9244,41.700413,325000
67
+ 76.66805,0.18013442,0.0058151293,3.123761,-26.975504,-76.38656,-96.855644,1.8342547,-1.649639,52.216095,330000
68
+ 74.90637,0.19552393,0.0059114364,2.4776518,-20.453072,-74.876785,-96.81951,1.292372,-1.9047073,48.198963,335000
69
+ 75.246086,0.19444835,0.0047489903,1.7694546,-14.899084,-75.08736,-98.05685,1.0610402,-1.3883247,36.45848,340000
70
+ 75.33349,0.185812,0.004568144,1.7257446,-6.5969887,-75.15841,-97.740746,1.34811,-1.2092075,33.351326,345000
71
+ 74.234184,0.18144253,0.005558216,1.7388906,-2.0370588,-74.393486,-97.86261,1.1890099,-1.7553425,60.510056,350000
72
+ 76.92294,0.1716701,0.006939624,1.4936583,0.076892614,-76.374504,-101.781044,2.419923,-1.9424751,49.45552,355000
73
+ 75.48788,0.17435421,0.004126694,1.5934633,0.23749383,-75.32942,-101.3781,1.3588176,-0.8966497,32.65947,360000
74
+ 76.950066,0.18016252,0.0046826857,1.5454744,-19.47968,-76.51261,-97.68133,1.2713382,-1.8522775,39.081287,365000
75
+ 75.42786,0.17308336,0.0051156497,1.4410604,-22.344875,-75.394325,-101.47568,1.5186299,-0.9948284,37.567787,370000
76
+ 75.962975,0.18844849,0.004737594,1.0808581,0.32529652,-75.692276,-97.868515,1.0187595,-0.92260826,30.759777,375000
77
+ 75.29101,0.15229289,0.0049530375,1.473623,0.33619958,-75.070366,-101.72031,1.8707107,-1.2107817,35.63174,380000
78
+ 74.72637,0.17323826,0.005709443,1.3168677,0.22778554,-75.16097,-97.219734,0.6782044,-0.9725463,34.25811,385000
79
+ 75.37696,0.16917092,0.004589432,1.5415841,0.14245959,-75.5144,-98.02363,0.59247607,-0.85387176,29.144514,390000
80
+ 76.250725,0.14337382,0.0042458833,1.2326432,-19.325338,-75.85329,-95.877365,2.7647905,-2.059146,38.37526,395000
81
+ 74.7082,0.17752124,0.0048935134,2.54518,-19.987322,-74.50051,-96.687935,0.9433161,-1.2911152,45.41589,400000
82
+ 76.39416,0.19338073,0.0049577868,1.094451,0.64653534,-76.24535,-101.71774,2.4373226,-2.7447891,35.72,405000
83
+ 75.07018,0.16953117,0.0041138125,2.5702212,-20.740398,-75.1319,-98.580826,0.75422263,-0.94406277,40.691124,410000
84
+ 75.61592,0.1759266,0.005491163,3.4071655,-21.634539,-75.59425,-97.16908,0.92388153,-1.2802472,41.223553,415000
85
+ 75.75282,0.17467783,0.0049461345,1.0449281,0.2638137,-75.52799,-97.75592,0.86754423,-0.7389014,26.490812,420000
86
+ 73.68726,0.17190686,0.0052392734,2.433223,-20.926434,-73.85778,-96.37313,0.7914797,-0.83607787,43.65374,425000
87
+ 74.03972,0.1924868,0.0046745013,1.2936076,0.36832836,-73.70046,-96.76571,1.1836165,-1.3070586,32.442142,430000
88
+ 74.82335,0.17456877,0.004966453,2.2684267,-21.290958,-74.94164,-97.29043,1.4627148,-1.004403,43.938034,435000
89
+ 75.093346,0.1597744,0.0054786047,1.378706,-6.6391125,-74.80169,-98.00499,1.1929238,-1.820936,37.713352,440000
90
+ 77.98258,0.17010978,0.0041302727,1.3982849,-19.406956,-78.032524,-97.75484,0.65974754,-0.6045755,28.2713,445000
91
+ 75.67687,0.19741555,0.0037483405,1.2665154,0.31787091,-75.50506,-97.29696,1.1651934,-2.1025684,32.40206,450000
92
+ 74.56232,0.16952422,0.0046710786,1.6054896,-2.1074126,-74.60201,-101.67597,0.96987534,-1.4829328,42.343292,455000
93
+ 75.37016,0.182322,0.003414574,1.1523014,0.26419675,-75.39504,-96.87724,1.6380284,-1.347887,34.537567,460000
94
+ 76.665215,0.17066343,0.005689806,1.5634272,0.37115115,-76.1993,-101.59394,1.4158288,-0.9835697,38.527283,465000
95
+ 76.2903,0.17334127,0.004649342,1.6899681,-26.172422,-76.24584,-97.886734,3.0308273,-2.0281084,42.643265,470000
96
+ 75.151764,0.18791184,0.0041087638,1.4039841,-20.343409,-74.94998,-97.903305,0.48188308,-0.63385934,25.261377,475000
97
+ 75.02468,0.17096841,0.006478723,1.6735966,0.24995549,-74.80974,-97.55365,2.0562503,-1.3984257,46.07125,480000
98
+ 75.13382,0.17736739,0.005332587,1.2870245,-20.61262,-75.11178,-101.43302,1.7296222,-1.3538662,32.863335,485000
99
+ 75.02145,0.17423227,0.004837034,1.1749878,-7.1569514,-74.79845,-98.19856,0.95705783,-0.65792775,29.315418,490000
100
+ 75.66866,0.20524089,0.005581051,1.4041283,0.19554365,-75.65673,-96.55677,1.9852715,-2.9618545,44.763477,495000
101
+ 77.577614,0.20422369,0.0044557364,1.1933196,-1.5598726,-77.31036,-96.625,2.7646153,-2.3027408,46.922905,500000
102
+ 75.8367,0.17823684,0.0049195355,1.064473,0.32334077,-75.53043,-97.68338,1.3742455,-1.6622494,34.36856,505000
103
+ 77.622826,0.1687201,0.004556067,1.2587925,-23.592281,-77.73319,-102.01577,1.0660472,-1.0647624,30.731285,510000
104
+ 72.729065,0.18495716,0.004488415,2.3433583,0.17506869,-72.71803,-96.62697,1.1740006,-0.77658606,34.7482,515000
105
+ 75.86679,0.15806198,0.0044836663,1.2693106,-2.1657894,-75.51011,-98.057076,1.0225015,-1.5072714,31.5662,520000
106
+ 74.28365,0.17893408,0.005342712,1.2161417,-20.207506,-74.05796,-101.59788,1.8941941,-1.0960438,40.20432,525000
107
+ 76.51851,0.19438621,0.0045921695,1.872508,-3.1509225,-76.02405,-101.80412,1.3759342,-1.1742843,32.558693,530000
108
+ 76.03665,0.16887376,0.004579156,1.4817342,-22.10802,-75.67431,-96.442314,1.3262295,-1.9314198,37.90918,535000
109
+ 76.55369,0.1976506,0.0041317856,1.7356589,0.16111319,-76.46612,-98.3129,0.79691833,-0.96724296,38.00096,540000
110
+ 75.86556,0.19179785,0.005499938,1.0984099,-21.449697,-75.82567,-96.3963,1.2493943,-1.3886977,32.354187,545000
111
+ 76.75013,0.18198681,0.0043019555,0.9724776,0.2862062,-76.41713,-101.76533,1.1463327,-0.77158034,35.20337,550000
112
+ 73.79603,0.16335925,0.0067097316,1.3114116,0.28863078,-73.55068,-95.82879,2.2645822,-2.559294,45.127335,555000
113
+ 75.63264,0.183028,0.004818101,1.5328597,0.5273471,-75.79341,-97.32752,1.1523343,-1.0505443,34.684322,560000
114
+ 75.97444,0.18357235,0.004941107,1.155509,-20.282076,-75.94936,-96.78773,1.8100413,-2.0778418,33.659477,565000
115
+ 74.09864,0.17769143,0.005955529,1.4292096,-18.774115,-74.11126,-96.04309,0.89332813,-0.6728712,34.323746,570000
116
+ 76.17451,0.15643927,0.004241138,0.75153655,0.2645715,-76.21808,-97.074844,1.3721644,-0.86275345,29.849247,575000
117
+ 75.18709,0.15798394,0.005364648,1.9840983,0.1568968,-74.77712,-96.68171,1.1730024,-1.6282007,46.715164,580000
118
+ 75.62283,0.14912751,0.003965403,1.5025504,-20.506687,-75.59527,-101.24512,1.3451264,-0.9970324,31.28887,585000
119
+ 77.22659,0.14390975,0.0061498415,0.9274155,0.26735866,-76.92323,-101.595924,1.6437824,-1.8301972,38.51088,590000
120
+ 75.911995,0.16202618,0.0059885154,0.99498314,-20.095053,-75.67121,-101.4624,1.3185859,-1.2237123,32.00398,595000
121
+ 76.109406,0.17481062,0.0042910003,1.632726,-19.521341,-75.84548,-98.673584,1.6929867,-1.1494046,34.76237,600000
122
+ 76.57238,0.17299065,0.004826917,0.9549036,-18.624517,-76.194176,-101.32232,2.1013381,-1.9072344,42.925934,605000
123
+ 73.33107,0.15891996,0.0050505055,1.742223,0.37571555,-73.047646,-97.04718,1.7087833,-2.82282,43.39171,610000
124
+ 74.6475,0.1480969,0.004080294,2.3980186,0.2424563,-74.50436,-96.93484,1.2021698,-0.84332776,34.482296,615000
125
+ 74.25369,0.15972726,0.0054270755,1.5177301,-20.347647,-73.922905,-96.427124,1.9225743,-1.322736,45.74662,620000
126
+ 75.164894,0.20482457,0.004940849,1.1357363,-13.573316,-75.02468,-97.057724,1.1228409,-0.94821817,29.056866,625000
127
+ 75.18466,0.19275524,0.0050667166,1.9164097,-25.841799,-75.25306,-95.71918,1.6673809,-1.7416581,45.370384,630000
128
+ 74.64077,0.15625282,0.0038956064,0.86831915,-0.8222786,-74.778114,-96.316765,0.92967653,-1.0539528,28.057964,635000
129
+ 74.17575,0.17668682,0.0035360295,2.7713406,0.16459262,-74.0321,-96.60988,1.0919652,-0.7160236,39.362083,640000
130
+ 75.46635,0.19402799,0.0046281293,1.2963392,-24.213758,-75.2751,-101.3454,1.6544627,-1.9869485,36.359634,645000
131
+ 76.76012,0.15460062,0.0046516038,1.1020612,-21.117216,-76.53741,-101.083305,1.3878562,-1.702896,34.280247,650000
132
+ 74.73183,0.17413944,0.0047424803,1.3791819,0.4147437,-74.28755,-98.8556,0.9577234,-1.3379883,33.475044,655000
133
+ 75.295265,0.16010445,0.004362417,1.0407797,-21.316692,-75.31548,-98.02495,1.4378425,-1.1940886,30.841196,660000
134
+ 75.63472,0.214109,0.0057792612,0.9966404,0.118358016,-75.27886,-96.68982,4.7801323,-3.3096912,45.717667,665000
135
+ 77.14607,0.17637122,0.0038743552,0.88797295,-19.48035,-76.92078,-101.59282,0.93629986,-1.1499717,27.440792,670000
136
+ 76.758804,0.17612012,0.0052758777,0.9747308,-28.602879,-76.239174,-101.36825,2.036011,-2.1750312,38.260296,675000
137
+ 76.34906,0.15126765,0.0041373926,1.432854,-23.409822,-76.23927,-97.13292,0.9203272,-1.3813795,29.283045,680000
138
+ 75.31418,0.17608604,0.006000129,1.3054342,-23.531946,-75.10659,-101.2092,1.5457667,-1.081536,36.563744,685000
139
+ 75.402504,0.1718119,0.005498322,1.3741586,-23.498104,-75.53974,-96.72335,1.2025307,-1.2197068,37.069454,690000
140
+ 78.04995,0.1820319,0.0050498536,1.075796,-23.847477,-77.67838,-97.80198,2.3304496,-1.8070223,38.57952,695000
141
+ 76.022606,0.18020788,0.0052392804,1.5017928,0.33611274,-75.939476,-101.3166,0.7149729,-0.96128106,36.594833,700000
142
+ 76.5636,0.18621278,0.0050809914,1.1728699,0.3777874,-76.03124,-97.907585,1.1915258,-1.4652637,34.08281,705000
143
+ 76.342964,0.15121986,0.005594195,2.3566895,0.39034152,-76.19023,-101.368385,2.7018971,-1.7829386,39.646255,710000
144
+ 75.84576,0.17290777,0.004775529,1.8570198,0.13152882,-75.74737,-101.22012,0.82715696,-1.2483065,33.994175,715000
145
+ 74.55044,0.19714662,0.0049432414,1.7479203,-25.150705,-74.9435,-96.28591,1.169524,-0.9507088,35.087635,720000
146
+ 76.07154,0.1585091,0.0054789516,1.2461065,-14.58271,-75.862595,-96.59674,1.8196176,-2.08573,37.94564,725000
147
+ 75.75108,0.2012005,0.005098285,1.2111591,-11.421995,-75.28674,-101.42281,2.5849056,-1.8092581,36.609104,730000
148
+ 74.45454,0.19097184,0.0052967207,1.5703819,0.28306985,-74.04869,-96.55998,1.1513989,-0.9023597,35.937027,735000
149
+ 75.395134,0.16419303,0.0035823935,1.3814119,0.2632022,-75.174515,-101.5835,1.2536503,-0.82750875,28.285887,740000
150
+ 75.86152,0.1861294,0.004833187,1.0017896,0.35835934,-75.88998,-101.04848,1.1092004,-1.3661014,31.578373,745000
151
+ 75.65282,0.1445001,0.005149479,1.062216,-10.552686,-75.43957,-96.87069,0.88214636,-1.3177147,27.105944,750000
152
+ 75.95728,0.17227386,0.005279597,1.1940678,0.33327836,-75.77239,-101.72672,4.346109,-2.8753054,38.89309,755000
153
+ 76.34322,0.20352022,0.0052872133,1.4840506,0.08406684,-75.92916,-97.93582,1.7543421,-1.5530118,38.284397,760000
154
+ 74.776245,0.16879088,0.006055579,1.9930108,-18.118435,-74.50281,-96.315384,2.1695287,-1.5933053,39.25368,765000
155
+ 74.96042,0.16813184,0.004113454,1.7584981,-19.613008,-75.00067,-101.71237,2.2839077,-2.9016442,40.302307,770000
156
+ 74.76333,0.16388899,0.004661346,2.7022786,0.47091004,-75.046646,-97.41351,0.66217196,-1.013584,40.34371,775000
157
+ 74.229294,0.19343126,0.006416703,2.4692082,0.33039516,-73.99806,-97.643585,1.0967736,-1.3321517,43.79091,780000
158
+ 75.416565,0.17425908,0.003668086,1.2698287,0.27987155,-75.6334,-97.289635,1.2957095,-1.4262235,33.954594,785000
159
+ 75.60081,0.16530967,0.0048706895,1.0255699,-6.378746,-75.42797,-101.255325,0.81995666,-1.204587,28.656792,790000
160
+ 74.27994,0.15375671,0.0044320463,1.3771288,0.18815202,-74.48191,-101.191536,2.2490957,-3.2724397,36.4419,795000
161
+ 76.53047,0.20952666,0.0053747473,1.6565043,-20.14599,-76.14369,-96.69442,1.4412935,-2.137904,43.262424,800000
162
+ 74.74387,0.17462245,0.0042906655,1.024825,-21.382315,-74.42066,-97.94988,1.4545403,-1.2457149,35.34482,805000
163
+ 75.19392,0.19354492,0.00433874,0.7274132,-1.4038337,-75.14135,-101.175,1.1306188,-1.5599542,28.208237,810000
164
+ 76.85801,0.16164333,0.004835102,0.66700864,-0.43471622,-76.441124,-101.4944,1.3087367,-1.7230564,31.091316,815000
165
+ 76.13767,0.1495384,0.005115637,0.77401924,-13.2893715,-75.80816,-101.39482,1.0689455,-1.345804,32.70932,820000
166
+ 75.305336,0.17231992,0.0046419594,1.8398697,0.07112831,-75.10143,-101.83293,1.7046297,-1.9716846,43.568092,825000
167
+ 76.567,0.16811752,0.0042868285,1.8700479,-20.745094,-76.645775,-101.57513,0.8532408,-1.2450385,32.630898,830000
168
+ 74.98773,0.18563534,0.004596862,1.0514606,-24.817944,-74.87571,-97.505516,1.1090465,-1.5541327,39.011997,835000
169
+ 76.65766,0.15365115,0.0044383756,1.0770682,0.16945618,-76.42318,-101.57287,1.8027943,-1.3828552,34.077106,840000
170
+ 76.753296,0.18956298,0.0046936367,1.2757796,-19.810596,-76.54563,-96.14814,1.3825455,-0.95745087,35.4794,845000
171
+ 75.32889,0.16963507,0.00487956,2.2739956,-26.32384,-74.960075,-97.077156,0.7361405,-0.72397846,31.089184,850000
172
+ 76.06996,0.18771152,0.004026072,1.8504876,-3.4618168,-75.98891,-96.105934,3.0536225,-1.6104592,36.549843,855000
173
+ 75.126816,0.17626423,0.0043246187,1.489765,-19.507706,-75.14366,-95.99117,0.93258244,-1.2939022,39.209633,860000
174
+ 75.848076,0.17239864,0.0041343165,0.9271634,0.38492677,-75.79543,-101.46111,1.334087,-1.777232,25.82861,865000
175
+ 73.58442,0.1435147,0.004269824,1.431054,-12.949872,-73.72012,-101.3762,0.6934712,-0.48794258,26.571844,870000
176
+ 76.609886,0.1789439,0.0046311216,2.0374365,-21.425507,-76.66947,-97.79672,2.6083088,-1.7171334,39.92,875000
177
+ 76.43827,0.16038644,0.0036243938,1.3946714,-28.67662,-76.52769,-101.47805,1.2798417,-0.972273,29.449665,880000
178
+ 77.32072,0.1834678,0.0052103004,0.8481247,-20.370623,-76.93149,-101.181244,2.1862345,-1.4643611,34.43634,885000
179
+ 74.64918,0.16398865,0.0057309736,0.86438894,-14.237996,-74.432884,-96.28079,3.3748736,-4.9247165,35.93019,890000
180
+ 75.241356,0.15792677,0.006021562,0.7474045,-17.398434,-74.691185,-101.29628,3.362061,-2.6674244,42.045433,895000
181
+ 75.1891,0.17378382,0.0039311624,2.1367555,-20.925356,-75.55729,-96.7508,0.5497845,-0.9676573,30.355785,900000
182
+ 74.939384,0.1611451,0.004972481,0.85965014,0.0906544,-74.86405,-97.27378,1.1559445,-1.5694656,34.369614,905000
183
+ 74.73301,0.17388165,0.004927955,0.88456005,-5.940154,-74.78566,-100.94554,1.0977875,-0.779979,29.93733,910000
184
+ 75.896675,0.17708212,0.004735496,1.4323133,0.40118182,-76.049576,-101.07997,1.3092159,-1.7512333,32.813366,915000
185
+ 75.66502,0.17910153,0.0043902365,1.2272388,-21.443998,-75.83447,-96.67472,1.9156238,-1.1107328,33.460148,920000
186
+ 76.59495,0.1715689,0.0046270606,0.7929449,-34.936596,-76.41819,-96.07402,0.64440584,-0.95501745,28.655613,925000
187
+ 77.83263,0.17525661,0.0044367095,0.9189544,-21.172878,-77.720474,-96.5556,1.0489366,-1.3395783,31.711956,930000
188
+ 74.87873,0.16394076,0.005333377,1.3866163,-22.47118,-75.07471,-96.90521,1.4301957,-1.37533,34.181454,935000
189
+ 74.10323,0.17577523,0.00389915,1.1433057,0.117569625,-74.13269,-96.91331,1.2640636,-0.8261167,32.052288,940000
190
+ 76.72264,0.17515744,0.0041117696,1.2000575,0.6090778,-76.68017,-101.52979,0.62847143,-0.97695756,28.394001,945000
191
+ 76.410164,0.1602318,0.0042320415,1.1298815,-2.8916104,-76.53768,-101.40273,0.8277605,-0.93684524,32.620735,950000
192
+ 74.6888,0.15865418,0.0040520574,0.6838961,0.24761921,-74.93841,-96.74585,0.89912945,-1.0255773,25.55064,955000
193
+ 74.54725,0.19397737,0.0048750266,1.5283365,-10.155268,-74.145874,-97.01991,1.5597275,-1.1662862,35.46494,960000
194
+ 77.305145,0.17689988,0.0039670593,1.3137199,-18.339096,-77.36779,-101.25177,1.7575223,-2.0613444,37.217613,965000
195
+ 75.57466,0.16691267,0.0054320977,1.1250635,-3.30761,-75.30769,-101.4545,4.113034,-2.8020792,41.144695,970000
196
+ 74.72609,0.16404471,0.005326437,0.7725903,0.20911905,-74.417534,-97.30491,2.14773,-1.5918101,37.701744,975000
197
+ 74.19884,0.18076734,0.003427993,1.6985329,-22.363611,-74.45788,-96.998924,0.86337954,-0.8368983,27.986837,980000
198
+ 76.48462,0.18099578,0.0033192176,1.4642502,-19.611706,-76.37711,-96.18432,2.4622948,-1.6884967,43.56331,985000
199
+ 74.24717,0.16511388,0.004551563,1.0075752,-6.672037,-74.17889,-96.87541,1.5024356,-1.793747,32.19753,990000
200
+ 75.664925,0.18640126,0.0045123636,1.4152069,-25.62262,-75.72377,-101.19276,1.1727759,-1.1715971,27.572561,995000
201
+ 75.05076,0.13989237,0.004350882,1.3810663,0.16375077,-74.93033,-101.369774,2.6451163,-1.7721817,47.582085,1000000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 76.3736,0.16126212,0.004034992,2.7567506,-22.488997,-76.419395,-101.331375,0.91925627,-0.70713276,30.859241,1005000
3
+ 75.19024,0.16226521,0.005006585,1.2319807,-1.252449,-75.26993,-95.6087,0.7810171,-1.0634991,26.332186,1010000
4
+ 77.587326,0.160406,0.004667896,0.937205,0.24865332,-77.41314,-101.60446,0.98823047,-1.1827886,34.58527,1015000
5
+ 75.673096,0.18059139,0.004568995,1.2374898,-3.3825433,-75.140915,-97.146454,1.4598546,-1.5736839,33.53268,1020000
6
+ 76.36009,0.18209244,0.0040468485,1.3673836,-16.283003,-76.422066,-96.03871,1.1156832,-1.3008393,31.620022,1025000
7
+ 75.3624,0.16380483,0.0044515487,1.2927049,-18.501835,-75.1225,-97.359505,1.1659902,-0.801412,29.1259,1030000
8
+ 74.47274,0.18010047,0.004555803,1.4943049,-3.6572404,-74.6054,-101.05033,1.172675,-1.7070957,34.075928,1035000
9
+ 74.684105,0.1187259,0.0036133723,1.4713095,-25.19972,-74.48254,-96.820465,1.489654,-2.0617828,38.005733,1040000
10
+ 75.958275,0.17385966,0.0053226873,1.6747067,0.17443478,-75.84246,-96.668335,3.5792398,-4.8852077,44.03916,1045000
11
+ 74.662094,0.17912589,0.004801737,1.5832918,-7.733428,-74.628334,-101.10064,1.1034018,-1.6413802,36.2871,1050000
12
+ 74.543106,0.16033842,0.0049154703,1.4127251,-4.2315373,-74.062645,-96.41255,0.86956763,-1.0728933,35.147575,1055000
13
+ 74.26521,0.16624026,0.0044251084,1.0447801,0.28031874,-74.22307,-101.36659,1.989546,-1.5136863,32.56465,1060000
14
+ 74.03963,0.16662674,0.0042092106,1.3643519,-10.169152,-73.86351,-101.35631,1.1327494,-1.023887,32.636463,1065000
15
+ 76.32288,0.18294007,0.0037474255,0.958945,-20.115906,-76.65826,-101.37581,0.950357,-0.7886529,23.213577,1070000
16
+ 74.04152,0.1927944,0.004498108,1.4925785,-4.048274,-73.63568,-101.3149,1.6708006,-2.4867134,36.637524,1075000
17
+ 74.25742,0.19111654,0.004273563,1.0709618,-1.5231353,-74.28865,-96.89539,2.0836067,-1.6087121,32.332108,1080000
18
+ 76.52304,0.16905013,0.0038473837,1.6787748,-11.068343,-76.48994,-97.19828,0.7508941,-0.7617247,29.677088,1085000
19
+ 74.21072,0.15865415,0.004197746,0.93572205,-7.9881077,-74.19121,-96.876785,1.3128772,-1.2739197,32.969433,1090000
20
+ 74.117455,0.16600348,0.004374967,1.3322246,-14.437763,-73.74232,-101.2443,0.9280373,-1.166584,32.795097,1095000
21
+ 75.124344,0.16781288,0.004437657,0.98643035,-19.347164,-75.09923,-101.131805,1.4079758,-2.1555252,36.02117,1100000
22
+ 74.78257,0.16720629,0.0039101243,1.0813135,-1.2987559,-74.73491,-96.48818,1.2657005,-1.0044712,37.885574,1105000
23
+ 74.9088,0.14547797,0.0051478837,1.3961383,0.0045756698,-74.465645,-97.38277,1.4490176,-1.7741506,46.7044,1110000
24
+ 73.969315,0.1486617,0.004403141,1.9180094,-15.779437,-73.836075,-96.39335,0.6434722,-0.8718773,28.973963,1115000
25
+ 73.91855,0.1681405,0.0040293164,1.084977,-2.2753682,-74.00711,-101.459694,0.9292737,-0.6220568,25.193336,1120000
26
+ 73.13977,0.19290286,0.004427968,1.5738649,-20.699856,-73.236626,-95.30318,2.3370128,-2.3491569,36.179752,1125000
27
+ 72.034546,0.15209714,0.0039647594,1.2082318,0.15405333,-71.88833,-97.07875,1.6326467,-1.0892915,44.02671,1130000
28
+ 73.754845,0.17102008,0.0036626933,1.5281928,-5.969196,-74.103836,-101.25818,1.0838039,-1.6416357,32.684956,1135000
29
+ 73.96887,0.17437294,0.0030486619,1.483386,-12.456057,-74.17672,-95.83799,1.2496817,-0.9223445,31.915508,1140000
30
+ 72.710884,0.17754813,0.004367279,1.2110065,0.32082328,-72.37957,-95.958145,1.360481,-2.0499213,43.66557,1145000
31
+ 72.90904,0.14608635,0.004128206,1.297979,-3.0331185,-72.79075,-96.330795,1.0413879,-1.1185813,27.82436,1150000
32
+ 73.26079,0.17330165,0.0043709045,1.3704242,0.1723373,-73.009415,-101.01951,0.9136621,-0.96623594,33.590656,1155000
33
+ 74.65189,0.19887543,0.004816601,0.6290967,0.18738362,-74.47182,-101.38344,1.131645,-1.0516155,27.179596,1160000
34
+ 73.52013,0.19541155,0.0036179966,1.4292551,-5.370984,-73.682045,-101.44418,1.0114987,-0.8614003,31.136753,1165000
35
+ 72.81233,0.13453406,0.004284729,0.91953164,-3.014647,-72.969154,-96.40879,0.9424655,-1.1512135,30.352777,1170000
36
+ 71.43316,0.14894965,0.004391227,1.5450664,-9.793786,-71.37936,-97.38359,0.87384385,-1.351225,30.793196,1175000
37
+ 73.120316,0.19337824,0.003106622,0.8666193,-4.272411,-73.018524,-95.8993,1.8932388,-1.4675448,27.390862,1180000
38
+ 72.01802,0.17571342,0.0039361776,0.81978285,0.31432754,-72.293205,-101.09442,0.9691827,-0.91648585,28.17264,1185000
39
+ 75.02432,0.16795054,0.0034364404,1.253643,-8.39315,-74.84048,-95.806206,1.4631256,-0.96740973,26.65761,1190000
40
+ 72.91482,0.15360563,0.004094938,1.2879957,0.3026479,-72.82649,-96.96354,0.79891384,-0.78654605,25.374361,1195000
41
+ 71.9035,0.16356593,0.0033026617,1.4835644,-3.9518642,-72.19718,-101.48056,1.0586807,-1.3715819,34.57077,1200000
42
+ 71.83583,0.13816404,0.00360408,1.0059488,-7.241968,-71.94358,-101.06565,0.57641345,-0.7337242,22.774002,1205000
43
+ 72.91701,0.17836893,0.0043349285,0.70950335,-6.397471,-72.45362,-101.462296,2.2299016,-1.4993432,30.253658,1210000
44
+ 71.47802,0.1777618,0.0034910105,1.3326832,0.21930787,-71.49849,-101.25327,1.3245412,-2.0172765,34.30016,1215000
45
+ 70.541435,0.19724692,0.003652035,0.7652063,-4.1820507,-70.70284,-96.37173,1.6545161,-2.1329937,31.04283,1220000
46
+ 74.55499,0.17596623,0.004031517,1.1557817,0.09904024,-74.46221,-96.20546,1.6184902,-1.1219198,30.325119,1225000
47
+ 71.76327,0.17399082,0.0038376313,1.2229992,-5.712422,-71.74358,-96.78729,1.046965,-1.4414052,25.971926,1230000
48
+ 73.76575,0.1880761,0.0039387164,0.94726,-12.486578,-73.93151,-101.29208,1.3889935,-1.3468126,29.550253,1235000
49
+ 73.44036,0.16989419,0.002874831,0.9730005,0.1862239,-73.34222,-100.976616,1.1281018,-1.1313455,32.210754,1240000
50
+ 71.0824,0.15372543,0.0037915288,0.8880045,-4.557827,-71.38328,-95.89701,0.9873497,-0.7084835,23.479889,1245000
51
+ 72.12303,0.16203251,0.004432588,1.4166687,-0.36879793,-72.19301,-96.12771,0.87325,-0.8786865,31.856876,1250000
52
+ 70.71483,0.16711704,0.003267773,1.2168912,-1.7609712,-70.763664,-95.42293,1.4326043,-0.9610408,25.352371,1255000
53
+ 73.35865,0.1701645,0.0045065316,1.2605709,-8.001924,-72.938,-101.19355,1.1101851,-0.7619438,29.544804,1260000
54
+ 71.47918,0.16846848,0.0030703358,1.6761624,-1.7734034,-71.464516,-96.054276,0.75295955,-0.89371663,33.133823,1265000
55
+ 72.62645,0.1396319,0.0046533705,1.4718493,-11.397171,-72.31248,-101.105415,1.314541,-0.9717361,32.088654,1270000
56
+ 72.362434,0.21679927,0.004142361,1.3562047,-3.3384907,-72.54049,-101.269135,0.93103313,-1.3786839,31.383598,1275000
57
+ 72.3257,0.1813513,0.004435095,1.224371,-5.6181407,-72.41426,-101.19414,1.0196927,-1.3987182,39.935196,1280000
58
+ 70.43165,0.16398369,0.0040978235,0.7157497,-3.3432398,-70.20101,-97.01792,0.9778404,-1.2448231,24.637756,1285000
59
+ 72.417015,0.1657362,0.0037298508,1.4336922,-8.802335,-72.44781,-101.33109,1.4309983,-1.4196442,37.776386,1290000
60
+ 71.352196,0.17829673,0.0037149822,1.3962086,-6.284891,-70.95512,-96.099495,0.8587481,-0.59003645,26.878494,1295000
61
+ 73.75285,0.17469701,0.0033377528,1.0388254,0.20863661,-74.02999,-95.08054,0.7276101,-0.5410866,25.037237,1300000
62
+ 69.84317,0.1745565,0.0039990502,1.6943512,0.60238504,-69.93587,-95.861145,1.0566344,-1.1092072,33.990765,1305000
63
+ 71.31266,0.176333,0.0040649576,0.8668149,0.22128457,-70.75657,-95.752525,3.3544424,-2.2752805,36.20549,1310000
64
+ 71.28539,0.15826192,0.004477262,1.1358747,0.13033321,-71.12756,-95.839386,1.1252196,-1.6748937,28.499107,1315000
65
+ 69.71512,0.16984993,0.0035646288,0.8312403,-6.851823,-69.774734,-95.189735,0.753836,-0.96795416,24.99398,1320000
66
+ 68.180145,0.16804743,0.003833527,1.4724591,0.16382352,-68.57019,-96.15063,1.5996144,-1.7549843,32.075485,1325000
67
+ 71.807236,0.18484701,0.0030738376,1.0674227,-17.491495,-72.0914,-96.12698,0.7150487,-0.619815,25.74543,1330000
68
+ 70.79505,0.20448703,0.003467015,0.75372905,-2.9302332,-70.66709,-94.96783,0.698382,-1.0272086,23.82904,1335000
69
+ 69.36334,0.17619228,0.0035435425,0.8719894,-3.5559518,-69.414024,-95.781395,0.83227205,-1.2477953,26.751457,1340000
70
+ 70.29772,0.16240212,0.0032369103,1.0122864,-9.195236,-70.509674,-96.499886,0.7647252,-0.970433,27.97999,1345000
71
+ 70.9414,0.16623425,0.0034629367,0.9373564,-3.783517,-71.04604,-95.28674,0.70621026,-0.45904887,21.556768,1350000
72
+ 69.2381,0.17843236,0.0036561887,0.59573424,-0.67955744,-69.121574,-95.068275,2.070631,-1.3922846,22.151022,1355000
73
+ 70.04399,0.17731507,0.003743596,0.9829914,-7.1278086,-70.01884,-95.37591,0.766159,-1.0119274,24.100758,1360000
74
+ 68.95021,0.16894549,0.0040254244,1.1135714,-8.809863,-68.71968,-101.09153,0.7472088,-1.0249399,29.147232,1365000
75
+ 71.6269,0.18463433,0.0032548248,0.76845735,-2.3085592,-71.38976,-96.26893,1.1152825,-0.98190516,26.351933,1370000
76
+ 71.96596,0.1745919,0.0029995828,1.2559837,-2.2084122,-72.09374,-95.03906,0.5410599,-0.79959655,22.030416,1375000
77
+ 71.73646,0.13170159,0.0035758724,0.82944643,-5.966658,-71.61819,-95.29014,2.7713974,-1.8887846,34.31599,1380000
78
+ 69.66202,0.15479013,0.0032418284,1.0281842,0.23350447,-69.66575,-95.20587,1.0900494,-0.7404007,25.254559,1385000
79
+ 69.0119,0.13992378,0.004529108,0.78430307,-3.556167,-68.76698,-94.11712,1.383415,-2.0840619,27.29232,1390000
80
+ 70.07528,0.16131167,0.003924593,0.9211446,-2.7645788,-70.17521,-101.11183,1.0491749,-1.586039,25.045261,1395000
81
+ 70.546684,0.14646691,0.0033818388,1.0421568,-2.4502428,-70.73177,-94.84245,1.0392264,-1.3447294,25.138416,1400000
82
+ 68.44015,0.14561915,0.0034842156,0.89445925,0.20968649,-68.93722,-101.21905,0.8875234,-1.1312239,25.55478,1405000
83
+ 69.7362,0.17260098,0.0046980293,1.0644884,-3.8935628,-69.58669,-95.392,1.417354,-1.8824861,31.425953,1410000
84
+ 70.39106,0.16419382,0.0037081372,0.8128624,-4.4051757,-70.11311,-95.52031,1.422281,-2.147822,30.368656,1415000
85
+ 68.912186,0.13980536,0.0038141166,1.1930919,-2.9495528,-68.75697,-94.57687,1.0105412,-1.0243251,29.475147,1420000
86
+ 71.78066,0.16737282,0.0036250567,0.9494378,-17.430876,-71.616646,-95.27406,0.7597466,-0.81583464,22.43295,1425000
87
+ 67.10184,0.14636797,0.0051905,1.2714226,-3.7945487,-66.57366,-95.43164,1.0625892,-1.1052965,26.244701,1430000
88
+ 70.94045,0.15795437,0.003806308,0.90862507,0.2999703,-70.81637,-101.205925,0.8846934,-0.6272787,28.060215,1435000
89
+ 67.35466,0.15247108,0.0034970355,1.056297,-0.19172591,-67.30981,-95.37934,0.82261264,-0.9006869,25.05006,1440000
90
+ 70.13174,0.17309926,0.003167439,0.9783397,-4.496887,-70.106995,-101.16413,2.2397223,-1.7203447,33.27373,1445000
91
+ 66.732895,0.1560943,0.0031407264,0.92051405,-7.2462745,-66.911766,-94.73261,0.61070323,-0.44655803,18.343079,1450000
92
+ 68.12715,0.13257456,0.0041884533,1.1757519,0.2322202,-68.345436,-95.59335,2.0319486,-0.77507,42.26417,1455000
93
+ 70.20675,0.14916918,0.0037276875,0.84473306,-0.73442304,-69.94979,-95.03497,1.5051199,-1.2759912,24.696892,1460000
94
+ 67.38401,0.13980876,0.003427883,1.2872165,-1.9582437,-67.564384,-94.32253,0.8946817,-1.2846408,34.436886,1465000
95
+ 68.73985,0.14177802,0.0036858409,1.2849604,-2.6749399,-68.73579,-101.136314,0.6663092,-0.616998,22.529232,1470000
96
+ 66.48951,0.15403253,0.004005681,1.0786892,-5.9617763,-66.680786,-95.10512,1.0196017,-1.406595,24.918098,1475000
97
+ 69.32544,0.14815642,0.0032583242,1.0767046,-6.889009,-69.85786,-94.68003,0.8822439,-0.84480006,23.071806,1480000
98
+ 68.34089,0.13575733,0.0044534155,1.6808642,-2.5871985,-67.97242,-101.21109,1.5335231,-2.052412,35.21878,1485000
99
+ 69.631516,0.14579369,0.004033158,0.9740473,-2.3551226,-69.83093,-94.99319,0.8973195,-1.1116451,26.086996,1490000
100
+ 69.73529,0.15006372,0.003508728,2.5475318,-7.269166,-69.76975,-101.29422,0.96641976,-1.3351471,47.688168,1495000
101
+ 66.7444,0.17514527,0.003237996,1.1470073,-2.9238153,-66.99261,-94.233864,1.0496291,-0.7826105,23.721369,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 76.3736,0.16126212,0.004034992,2.7567506,-22.488997,-76.419395,-101.331375,0.91925627,-0.70713276,30.859241,1005000
3
+ 75.19024,0.16226521,0.005006585,1.2319807,-1.252449,-75.26993,-95.6087,0.7810171,-1.0634991,26.332186,1010000
4
+ 77.587326,0.160406,0.004667896,0.937205,0.24865332,-77.41314,-101.60446,0.98823047,-1.1827886,34.58527,1015000
5
+ 75.673096,0.18059139,0.004568995,1.2374898,-3.3825433,-75.140915,-97.146454,1.4598546,-1.5736839,33.53268,1020000
6
+ 76.36009,0.18209244,0.0040468485,1.3673836,-16.283003,-76.422066,-96.03871,1.1156832,-1.3008393,31.620022,1025000
7
+ 75.3624,0.16380483,0.0044515487,1.2927049,-18.501835,-75.1225,-97.359505,1.1659902,-0.801412,29.1259,1030000
8
+ 74.47274,0.18010047,0.004555803,1.4943049,-3.6572404,-74.6054,-101.05033,1.172675,-1.7070957,34.075928,1035000
9
+ 74.684105,0.1187259,0.0036133723,1.4713095,-25.19972,-74.48254,-96.820465,1.489654,-2.0617828,38.005733,1040000
10
+ 75.958275,0.17385966,0.0053226873,1.6747067,0.17443478,-75.84246,-96.668335,3.5792398,-4.8852077,44.03916,1045000
11
+ 74.662094,0.17912589,0.004801737,1.5832918,-7.733428,-74.628334,-101.10064,1.1034018,-1.6413802,36.2871,1050000
12
+ 74.543106,0.16033842,0.0049154703,1.4127251,-4.2315373,-74.062645,-96.41255,0.86956763,-1.0728933,35.147575,1055000
13
+ 74.26521,0.16624026,0.0044251084,1.0447801,0.28031874,-74.22307,-101.36659,1.989546,-1.5136863,32.56465,1060000
14
+ 74.03963,0.16662674,0.0042092106,1.3643519,-10.169152,-73.86351,-101.35631,1.1327494,-1.023887,32.636463,1065000
15
+ 76.32288,0.18294007,0.0037474255,0.958945,-20.115906,-76.65826,-101.37581,0.950357,-0.7886529,23.213577,1070000
16
+ 74.04152,0.1927944,0.004498108,1.4925785,-4.048274,-73.63568,-101.3149,1.6708006,-2.4867134,36.637524,1075000
17
+ 74.25742,0.19111654,0.004273563,1.0709618,-1.5231353,-74.28865,-96.89539,2.0836067,-1.6087121,32.332108,1080000
18
+ 76.52304,0.16905013,0.0038473837,1.6787748,-11.068343,-76.48994,-97.19828,0.7508941,-0.7617247,29.677088,1085000
19
+ 74.21072,0.15865415,0.004197746,0.93572205,-7.9881077,-74.19121,-96.876785,1.3128772,-1.2739197,32.969433,1090000
20
+ 74.117455,0.16600348,0.004374967,1.3322246,-14.437763,-73.74232,-101.2443,0.9280373,-1.166584,32.795097,1095000
21
+ 75.124344,0.16781288,0.004437657,0.98643035,-19.347164,-75.09923,-101.131805,1.4079758,-2.1555252,36.02117,1100000
22
+ 74.78257,0.16720629,0.0039101243,1.0813135,-1.2987559,-74.73491,-96.48818,1.2657005,-1.0044712,37.885574,1105000
23
+ 74.9088,0.14547797,0.0051478837,1.3961383,0.0045756698,-74.465645,-97.38277,1.4490176,-1.7741506,46.7044,1110000
24
+ 73.969315,0.1486617,0.004403141,1.9180094,-15.779437,-73.836075,-96.39335,0.6434722,-0.8718773,28.973963,1115000
25
+ 73.91855,0.1681405,0.0040293164,1.084977,-2.2753682,-74.00711,-101.459694,0.9292737,-0.6220568,25.193336,1120000
26
+ 73.13977,0.19290286,0.004427968,1.5738649,-20.699856,-73.236626,-95.30318,2.3370128,-2.3491569,36.179752,1125000
27
+ 72.034546,0.15209714,0.0039647594,1.2082318,0.15405333,-71.88833,-97.07875,1.6326467,-1.0892915,44.02671,1130000
28
+ 73.754845,0.17102008,0.0036626933,1.5281928,-5.969196,-74.103836,-101.25818,1.0838039,-1.6416357,32.684956,1135000
29
+ 73.96887,0.17437294,0.0030486619,1.483386,-12.456057,-74.17672,-95.83799,1.2496817,-0.9223445,31.915508,1140000
30
+ 72.710884,0.17754813,0.004367279,1.2110065,0.32082328,-72.37957,-95.958145,1.360481,-2.0499213,43.66557,1145000
31
+ 72.90904,0.14608635,0.004128206,1.297979,-3.0331185,-72.79075,-96.330795,1.0413879,-1.1185813,27.82436,1150000
32
+ 73.26079,0.17330165,0.0043709045,1.3704242,0.1723373,-73.009415,-101.01951,0.9136621,-0.96623594,33.590656,1155000
33
+ 74.65189,0.19887543,0.004816601,0.6290967,0.18738362,-74.47182,-101.38344,1.131645,-1.0516155,27.179596,1160000
34
+ 73.52013,0.19541155,0.0036179966,1.4292551,-5.370984,-73.682045,-101.44418,1.0114987,-0.8614003,31.136753,1165000
35
+ 72.81233,0.13453406,0.004284729,0.91953164,-3.014647,-72.969154,-96.40879,0.9424655,-1.1512135,30.352777,1170000
36
+ 71.43316,0.14894965,0.004391227,1.5450664,-9.793786,-71.37936,-97.38359,0.87384385,-1.351225,30.793196,1175000
37
+ 73.120316,0.19337824,0.003106622,0.8666193,-4.272411,-73.018524,-95.8993,1.8932388,-1.4675448,27.390862,1180000
38
+ 72.01802,0.17571342,0.0039361776,0.81978285,0.31432754,-72.293205,-101.09442,0.9691827,-0.91648585,28.17264,1185000
39
+ 75.02432,0.16795054,0.0034364404,1.253643,-8.39315,-74.84048,-95.806206,1.4631256,-0.96740973,26.65761,1190000
40
+ 72.91482,0.15360563,0.004094938,1.2879957,0.3026479,-72.82649,-96.96354,0.79891384,-0.78654605,25.374361,1195000
41
+ 71.9035,0.16356593,0.0033026617,1.4835644,-3.9518642,-72.19718,-101.48056,1.0586807,-1.3715819,34.57077,1200000
42
+ 71.83583,0.13816404,0.00360408,1.0059488,-7.241968,-71.94358,-101.06565,0.57641345,-0.7337242,22.774002,1205000
43
+ 72.91701,0.17836893,0.0043349285,0.70950335,-6.397471,-72.45362,-101.462296,2.2299016,-1.4993432,30.253658,1210000
44
+ 71.47802,0.1777618,0.0034910105,1.3326832,0.21930787,-71.49849,-101.25327,1.3245412,-2.0172765,34.30016,1215000
45
+ 70.541435,0.19724692,0.003652035,0.7652063,-4.1820507,-70.70284,-96.37173,1.6545161,-2.1329937,31.04283,1220000
46
+ 74.55499,0.17596623,0.004031517,1.1557817,0.09904024,-74.46221,-96.20546,1.6184902,-1.1219198,30.325119,1225000
47
+ 71.76327,0.17399082,0.0038376313,1.2229992,-5.712422,-71.74358,-96.78729,1.046965,-1.4414052,25.971926,1230000
48
+ 73.76575,0.1880761,0.0039387164,0.94726,-12.486578,-73.93151,-101.29208,1.3889935,-1.3468126,29.550253,1235000
49
+ 73.44036,0.16989419,0.002874831,0.9730005,0.1862239,-73.34222,-100.976616,1.1281018,-1.1313455,32.210754,1240000
50
+ 71.0824,0.15372543,0.0037915288,0.8880045,-4.557827,-71.38328,-95.89701,0.9873497,-0.7084835,23.479889,1245000
51
+ 72.12303,0.16203251,0.004432588,1.4166687,-0.36879793,-72.19301,-96.12771,0.87325,-0.8786865,31.856876,1250000
52
+ 70.71483,0.16711704,0.003267773,1.2168912,-1.7609712,-70.763664,-95.42293,1.4326043,-0.9610408,25.352371,1255000
53
+ 73.35865,0.1701645,0.0045065316,1.2605709,-8.001924,-72.938,-101.19355,1.1101851,-0.7619438,29.544804,1260000
54
+ 71.47918,0.16846848,0.0030703358,1.6761624,-1.7734034,-71.464516,-96.054276,0.75295955,-0.89371663,33.133823,1265000
55
+ 72.62645,0.1396319,0.0046533705,1.4718493,-11.397171,-72.31248,-101.105415,1.314541,-0.9717361,32.088654,1270000
56
+ 72.362434,0.21679927,0.004142361,1.3562047,-3.3384907,-72.54049,-101.269135,0.93103313,-1.3786839,31.383598,1275000
57
+ 72.3257,0.1813513,0.004435095,1.224371,-5.6181407,-72.41426,-101.19414,1.0196927,-1.3987182,39.935196,1280000
58
+ 70.43165,0.16398369,0.0040978235,0.7157497,-3.3432398,-70.20101,-97.01792,0.9778404,-1.2448231,24.637756,1285000
59
+ 72.417015,0.1657362,0.0037298508,1.4336922,-8.802335,-72.44781,-101.33109,1.4309983,-1.4196442,37.776386,1290000
60
+ 71.352196,0.17829673,0.0037149822,1.3962086,-6.284891,-70.95512,-96.099495,0.8587481,-0.59003645,26.878494,1295000
61
+ 73.75285,0.17469701,0.0033377528,1.0388254,0.20863661,-74.02999,-95.08054,0.7276101,-0.5410866,25.037237,1300000
62
+ 69.84317,0.1745565,0.0039990502,1.6943512,0.60238504,-69.93587,-95.861145,1.0566344,-1.1092072,33.990765,1305000
63
+ 71.31266,0.176333,0.0040649576,0.8668149,0.22128457,-70.75657,-95.752525,3.3544424,-2.2752805,36.20549,1310000
64
+ 71.28539,0.15826192,0.004477262,1.1358747,0.13033321,-71.12756,-95.839386,1.1252196,-1.6748937,28.499107,1315000
65
+ 69.71512,0.16984993,0.0035646288,0.8312403,-6.851823,-69.774734,-95.189735,0.753836,-0.96795416,24.99398,1320000
66
+ 68.180145,0.16804743,0.003833527,1.4724591,0.16382352,-68.57019,-96.15063,1.5996144,-1.7549843,32.075485,1325000
67
+ 71.807236,0.18484701,0.0030738376,1.0674227,-17.491495,-72.0914,-96.12698,0.7150487,-0.619815,25.74543,1330000
68
+ 70.79505,0.20448703,0.003467015,0.75372905,-2.9302332,-70.66709,-94.96783,0.698382,-1.0272086,23.82904,1335000
69
+ 69.36334,0.17619228,0.0035435425,0.8719894,-3.5559518,-69.414024,-95.781395,0.83227205,-1.2477953,26.751457,1340000
70
+ 70.29772,0.16240212,0.0032369103,1.0122864,-9.195236,-70.509674,-96.499886,0.7647252,-0.970433,27.97999,1345000
71
+ 70.9414,0.16623425,0.0034629367,0.9373564,-3.783517,-71.04604,-95.28674,0.70621026,-0.45904887,21.556768,1350000
72
+ 69.2381,0.17843236,0.0036561887,0.59573424,-0.67955744,-69.121574,-95.068275,2.070631,-1.3922846,22.151022,1355000
73
+ 70.04399,0.17731507,0.003743596,0.9829914,-7.1278086,-70.01884,-95.37591,0.766159,-1.0119274,24.100758,1360000
74
+ 68.95021,0.16894549,0.0040254244,1.1135714,-8.809863,-68.71968,-101.09153,0.7472088,-1.0249399,29.147232,1365000
75
+ 71.6269,0.18463433,0.0032548248,0.76845735,-2.3085592,-71.38976,-96.26893,1.1152825,-0.98190516,26.351933,1370000
76
+ 71.96596,0.1745919,0.0029995828,1.2559837,-2.2084122,-72.09374,-95.03906,0.5410599,-0.79959655,22.030416,1375000
77
+ 71.73646,0.13170159,0.0035758724,0.82944643,-5.966658,-71.61819,-95.29014,2.7713974,-1.8887846,34.31599,1380000
78
+ 69.66202,0.15479013,0.0032418284,1.0281842,0.23350447,-69.66575,-95.20587,1.0900494,-0.7404007,25.254559,1385000
79
+ 69.0119,0.13992378,0.004529108,0.78430307,-3.556167,-68.76698,-94.11712,1.383415,-2.0840619,27.29232,1390000
80
+ 70.07528,0.16131167,0.003924593,0.9211446,-2.7645788,-70.17521,-101.11183,1.0491749,-1.586039,25.045261,1395000
81
+ 70.546684,0.14646691,0.0033818388,1.0421568,-2.4502428,-70.73177,-94.84245,1.0392264,-1.3447294,25.138416,1400000
82
+ 68.44015,0.14561915,0.0034842156,0.89445925,0.20968649,-68.93722,-101.21905,0.8875234,-1.1312239,25.55478,1405000
83
+ 69.7362,0.17260098,0.0046980293,1.0644884,-3.8935628,-69.58669,-95.392,1.417354,-1.8824861,31.425953,1410000
84
+ 70.39106,0.16419382,0.0037081372,0.8128624,-4.4051757,-70.11311,-95.52031,1.422281,-2.147822,30.368656,1415000
85
+ 68.912186,0.13980536,0.0038141166,1.1930919,-2.9495528,-68.75697,-94.57687,1.0105412,-1.0243251,29.475147,1420000
86
+ 71.78066,0.16737282,0.0036250567,0.9494378,-17.430876,-71.616646,-95.27406,0.7597466,-0.81583464,22.43295,1425000
87
+ 67.10184,0.14636797,0.0051905,1.2714226,-3.7945487,-66.57366,-95.43164,1.0625892,-1.1052965,26.244701,1430000
88
+ 70.94045,0.15795437,0.003806308,0.90862507,0.2999703,-70.81637,-101.205925,0.8846934,-0.6272787,28.060215,1435000
89
+ 67.35466,0.15247108,0.0034970355,1.056297,-0.19172591,-67.30981,-95.37934,0.82261264,-0.9006869,25.05006,1440000
90
+ 70.13174,0.17309926,0.003167439,0.9783397,-4.496887,-70.106995,-101.16413,2.2397223,-1.7203447,33.27373,1445000
91
+ 66.732895,0.1560943,0.0031407264,0.92051405,-7.2462745,-66.911766,-94.73261,0.61070323,-0.44655803,18.343079,1450000
92
+ 68.12715,0.13257456,0.0041884533,1.1757519,0.2322202,-68.345436,-95.59335,2.0319486,-0.77507,42.26417,1455000
93
+ 70.20675,0.14916918,0.0037276875,0.84473306,-0.73442304,-69.94979,-95.03497,1.5051199,-1.2759912,24.696892,1460000
94
+ 67.38401,0.13980876,0.003427883,1.2872165,-1.9582437,-67.564384,-94.32253,0.8946817,-1.2846408,34.436886,1465000
95
+ 68.73985,0.14177802,0.0036858409,1.2849604,-2.6749399,-68.73579,-101.136314,0.6663092,-0.616998,22.529232,1470000
96
+ 66.48951,0.15403253,0.004005681,1.0786892,-5.9617763,-66.680786,-95.10512,1.0196017,-1.406595,24.918098,1475000
97
+ 69.32544,0.14815642,0.0032583242,1.0767046,-6.889009,-69.85786,-94.68003,0.8822439,-0.84480006,23.071806,1480000
98
+ 68.34089,0.13575733,0.0044534155,1.6808642,-2.5871985,-67.97242,-101.21109,1.5335231,-2.052412,35.21878,1485000
99
+ 69.631516,0.14579369,0.004033158,0.9740473,-2.3551226,-69.83093,-94.99319,0.8973195,-1.1116451,26.086996,1490000
100
+ 69.73529,0.15006372,0.003508728,2.5475318,-7.269166,-69.76975,-101.29422,0.96641976,-1.3351471,47.688168,1495000
101
+ 66.7444,0.17514527,0.003237996,1.1470073,-2.9238153,-66.99261,-94.233864,1.0496291,-0.7826105,23.721369,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:588e2ec3f31bc2661cbc1691efbf5216b10c4450d95d988419f9de6e19acdb3f
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d454a1a6ba6f6676ec7c9940a1dcacb4f4915a231856afd80feb25214e9c6da3
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c695ce79ccb64315106501a56192ad7f9aeda30f74fe40dd759c0512c4059342
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d9b9c084b5ee8fb24f7cf03d23a4493f81388e45b79b163ec859a38c9dc9cf
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2c9f014b4409531db9504656302d4c42920f8096df56acc735fb8bea8fbd06
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a880719fedb48f24672e7c82cf075fa7ff36fb4300cdb35c77276600caea37b
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6986069d2bf29fe9c700b248f80cb85b17fe029385581b2622fed5b030479a0
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cd18e0e05b0bfb95d97dba64a148870b771768563c2d03e2b3cde033951728a
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4910e4cd4cef1092965dcb8e9f7edec25eaff3336392a38221fe8ed2871600b2
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a6d4d5cef2fad8cbfec083090db3fa6dca00ba11be7e8ced111e69b3e21e7e7
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1685d29c616730aa2767163a9b5677b09c2a4586e0138cfa9198c9aaee0fb174
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf1bc150bed5f410b6e9e4c9d6d28916f0594b06cce1b4a01d22351c4a4c6af
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_1500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:357c3a11e0ab73236516a427712fad3eb7f1127fa65ef8179ca9c4f883f5f9d4
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16cc10c32f8b959fc723db7686ee2ab5e22dfbd9b2bf0c91a963e52b3121d70
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844681e21cbd117f2a4bca86a2a48a8267d0fca2a82ccb6e7fd303ddfff7f6e8
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65af971234174ece05e68a0ea3b79141a46b7e0324e62d35b7b02a125aac12e
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059d7bcbcf342de0358ce45bff290f22a533b8c9d482f086607dfe218c807074
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe26f91102c99a6da8350ece1be38a54ed9e0bfcbea8a251ba2c32cb27cac50
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b296e72cab1633b3e08bf5a4645532e4f14d00e8c589cb06e8a67c1b5a032a41
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_50000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e7eba5a5ddf0f654622f16e7a4bf21fe3214a1b14bbb970c9465e3701d93062
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428594917fedf3687358f26ec4354ffea05b302432a69dd9d6659c202eca46c6
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf980ff33cfc40633676869f047725e17a5495101fae66554d0b8d9bdbaa650
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984c3ecfc53c6e24fa748af4ae252a265849dd40e53ee75148f2fccf49bbf137
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0c9b2ad4c089db68eb3db9ed49919ad34fe6eeaa38d25d3739c604e5572edb
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea2ceb4439a9b2a1ca29eb2af1983a72dbd85a96a67843ece01f4609c103842
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:602758da8b4c9b0dfee142e1fc89f8275c43b0b250ea08dd3df74fb4502c85d2
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0751274e70388fbc09595a81d10ed4947ef294dc62f8f992e70bd4590eba75
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67955204fcede6a5fe7da47640478ccae0c73bb8613e972c2848eaa1e72f7ddb
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab0c8d825bcd11ee1972a05d06028250bc1ee3b289eb3392e24362ac71e5bc9b
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e95e15fabab14b9521b127f5d00deb63a923fe565cdce3a2178c8a12422ded8
3
+ size 220402479
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_113045/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-reproduce/runs/qbw6ot8z