Tiredsheep commited on
Commit
2695e24
·
verified ·
1 Parent(s): fb991df

Upload folder using huggingface_hub

Browse files
Files changed (41) hide show
  1. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/env.csv +0 -0
  2. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/env_sv.csv +0 -0
  3. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/eval.csv +31 -0
  4. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/eval_sv.csv +31 -0
  5. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/flags.json +1 -0
  6. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/offline_agent.csv +201 -0
  7. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/offline_agent_sv.csv +201 -0
  8. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/online_agent.csv +101 -0
  9. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/online_agent_sv.csv +101 -0
  10. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_100000.pkl +3 -0
  11. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1000000.pkl +3 -0
  12. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1050000.pkl +3 -0
  13. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1100000.pkl +3 -0
  14. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1150000.pkl +3 -0
  15. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1200000.pkl +3 -0
  16. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1250000.pkl +3 -0
  17. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1300000.pkl +3 -0
  18. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1350000.pkl +3 -0
  19. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1400000.pkl +3 -0
  20. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1450000.pkl +3 -0
  21. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_150000.pkl +3 -0
  22. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1500000.pkl +3 -0
  23. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_200000.pkl +3 -0
  24. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_250000.pkl +3 -0
  25. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_300000.pkl +3 -0
  26. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_350000.pkl +3 -0
  27. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_400000.pkl +3 -0
  28. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_450000.pkl +3 -0
  29. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_50000.pkl +3 -0
  30. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_500000.pkl +3 -0
  31. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_550000.pkl +3 -0
  32. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_600000.pkl +3 -0
  33. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_650000.pkl +3 -0
  34. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_700000.pkl +3 -0
  35. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_750000.pkl +3 -0
  36. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_800000.pkl +3 -0
  37. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_850000.pkl +3 -0
  38. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_900000.pkl +3 -0
  39. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_950000.pkl +3 -0
  40. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/progress.tk +1 -0
  41. pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/token.tk +1 -0
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/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
+ 0.0,0.0,0.43777777777777777,0.43777777777777777,-0.21752387278195334,-0.01681435861690093,-0.20912189880644813,0.21150639354303732,26.52673970158423,25.24999999999688,0.0,12750.0,-5.06,-2563.58,500.0,2.2365325021743776,50000
3
+ 0.0,0.0,0.4577777777777778,0.4577777777777778,-0.3585157853615093,-0.02110211828932586,-0.36165502137284855,-0.05397215168535938,33.55324777946742,25.24999999999688,0.0,38750.0,-4.88,-2481.92,500.0,2.531950454711914,100000
4
+ 0.0,0.0,0.45111111111111113,0.44666666666666666,-0.27631677583611974,-0.014421913622071994,-0.2796101221134508,-0.052209601450214776,9.877903087914778,25.24999999999688,0.0,64750.0,-4.98,-2547.14,500.0,2.19774968624115,150000
5
+ 0.0,0.0,0.46,0.46,-0.19669057149921126,-0.047499884829304194,-0.1975467145006867,-0.026352653806977804,-0.6462479692643176,25.24999999999688,0.0,90750.0,-4.86,-2413.64,500.0,2.1078502368927,200000
6
+ 0.0,0.0,0.4666666666666667,0.4666666666666667,-0.02070559426579503,-0.019626354502082666,-0.02356751555038773,-0.07277561369631666,-0.15020346748244615,25.24999999999688,0.0,116750.0,-4.8,-2468.48,500.0,2.178437900543213,250000
7
+ 0.0,0.0,0.4911111111111111,0.4911111111111111,-0.48146631993201244,0.08878240132004923,-0.48482954445831816,-0.05438525587286345,-1.652327750491406,25.24999999999688,0.0,142750.0,-4.58,-2324.36,500.0,1.728905940055847,300000
8
+ 0.0,0.0,0.45111111111111113,0.4533333333333333,0.05146794007313268,-0.011530876872353123,0.05172254545803034,0.021625651519707113,0.16538275064057067,25.24999999999688,0.0,168750.0,-4.92,-2493.44,500.0,2.139244122505188,350000
9
+ 0.0,0.0,0.4777777777777778,0.47333333333333333,-0.3482517165638528,-0.036977680064874056,-0.3463763078484867,0.05987304131762402,-1.1563562211477896,25.24999999999688,0.0,194750.0,-4.74,-2484.0,500.0,2.096515779495239,400000
10
+ 0.0,0.0,0.42,0.42,-0.3843565278811681,0.023796907091228586,-0.3822803202326906,0.050847478751532615,34.98759275029113,25.24999999999688,0.0,220750.0,-5.22,-2601.02,500.0,2.2818398237228394,450000
11
+ 0.0,0.0,0.4666666666666667,0.4666666666666667,-0.31236989805055215,0.12533052914527734,-0.3056111301993635,0.01008991615671558,30.028966419237378,25.24999999999688,0.0,246750.0,-4.8,-2467.72,500.0,2.3218729162216185,500000
12
+ 0.0,0.0,0.45555555555555555,0.45555555555555555,-0.40172349936092855,0.011118223199901764,-0.4032923294528132,-0.02576445415132523,34.826552997631985,25.24999999999688,0.0,272750.0,-4.9,-2448.28,500.0,2.4831560325622557,550000
13
+ 0.0,0.0,0.46444444444444444,0.46444444444444444,-0.024998549392963084,0.09332482353730552,-0.02228907374025662,0.03788716888492136,36.14579070361761,25.24999999999688,0.0,298750.0,-4.82,-2478.38,500.0,2.489877381324768,600000
14
+ 0.0,0.0,0.4888888888888889,0.4888888888888889,-0.36265728126568497,-0.016117306406359905,-0.3606410375380769,0.025412124852845608,35.02919317956636,25.24999999999688,0.0,324750.0,-4.6,-2356.0,500.0,2.4213984298706053,650000
15
+ 0.0,0.0,0.47555555555555556,0.47555555555555556,-0.3591167343641003,0.03746733376911205,-0.35615142857077403,0.04244057421195315,35.028646787010004,25.24999999999688,0.0,350750.0,-4.72,-2359.14,500.0,2.404485487937927,700000
16
+ 0.0,0.0,0.45555555555555555,0.45555555555555555,-0.4046119632433793,-0.01863620606463089,-0.4026140360736781,0.03677502730021931,34.12412740221993,25.24999999999688,0.0,376750.0,-4.9,-2478.3,500.0,2.1282899951934815,750000
17
+ 0.0,0.0,0.44,0.44,-0.4147372467310027,0.1150247517666796,-0.41059648295295786,0.04452337507235731,34.81379889280921,25.24999999999688,0.0,402750.0,-5.04,-2511.12,500.0,2.2449451446533204,800000
18
+ 0.0,0.0,0.4533333333333333,0.4533333333333333,-0.32834354432201845,0.055204760481709934,-0.32125500273534857,0.11218545710194586,35.168808850574045,25.24999999999688,0.0,428750.0,-4.92,-2498.08,500.0,2.2800823926925657,850000
19
+ 0.0,0.0,0.42444444444444446,0.42444444444444446,-0.4152738274414234,0.04863887760119367,-0.41512037556384507,-0.05906458495037671,34.78850940132069,25.24999999999688,0.0,454750.0,-5.18,-2624.82,500.0,2.2115293312072755,900000
20
+ 0.0,0.0,0.44,0.44,-0.39396780012540517,0.0063853852590698475,-0.3910257556070628,0.04534863348504169,34.91146183376524,25.24999999999688,0.0,480750.0,-5.04,-2530.98,500.0,2.3358656406402587,950000
21
+ 0.0,0.0,0.46,0.46,-0.4036164303506446,0.11872009816392916,-0.3970961514493531,0.11754735188899407,34.875243439002745,25.24999999999688,0.0,506750.0,-4.86,-2446.12,500.0,2.344341344833374,1000000
22
+ 0.0,0.0,0.5222222222222223,0.5222222222222223,-0.19557147455074023,-0.1646443859809676,-0.19096523063308063,0.09973709827140041,23.083936223974206,25.24999999999688,0.0,532750.0,-4.3,-2350.56,500.0,1.7657792139053345,1050000
23
+ 0.0,0.0,0.6177777777777778,0.8111111111111111,-0.2028107272234559,0.008513395208910141,-0.20416053309779378,-0.027675321829484758,26.00787352640352,19.93699999999852,0.54,555841.78,-1.7,-1468.9,393.74,1.4115126943588256,1100000
24
+ 0.0,0.0,0.6644444444444444,0.9866666666666667,-0.18489955850188466,-0.037505177913794846,-0.20327374406560747,-0.3173126991061149,20.65812022576005,7.0649999999994915,0.96,569403.9,-0.12,-619.68,136.3,0.5093571901321411,1150000
25
+ 0.0,0.0,0.6666666666666666,1.0,-0.18450935690441184,-0.014104180329809009,-0.1957416915959816,-0.2061909122127266,29.779490287059485,4.584999999999719,1.0,575370.1,0.0,-424.76,86.7,0.33157341003417967,1200000
26
+ 0.0,0.0,0.6666666666666666,1.0,-0.1892264026313927,-0.1130704162446663,-0.1985675763031858,-0.22234498948827217,29.385895824239192,3.7329999999998105,1.0,579419.7,0.0,-346.88,69.66,0.2709890079498291,1250000
27
+ 0.0,0.0,0.6666666666666666,1.0,-0.19316437884125578,0.03013229369426042,-0.2005301995726068,-0.11876996407633382,30.957503875802214,3.368999999999851,1.0,582866.8,0.0,-298.18,62.38,0.24765194416046143,1300000
28
+ 0.0,0.0,0.6666666666666666,1.0,-0.17929282540755484,0.13041170136968483,-0.1786683392399478,0.2240948278303233,30.972123308236363,3.2929999999998585,1.0,586113.86,0.0,-296.14,60.86,0.2407935619354248,1350000
29
+ 0.0,0.0,0.6666666666666666,1.0,-0.16398114256779658,-0.23975803875637824,-0.17715944625749078,-0.1721856091301362,34.649852491635095,3.1819999999998707,1.0,589193.96,0.0,-287.44,58.64,0.23573916435241699,1400000
30
+ 0.0,0.0,0.6666666666666666,1.0,-0.17047083184529147,-0.1974348787207512,-0.18734459489097735,-0.3071254621764078,33.00862745971615,2.996999999999892,1.0,592165.36,0.0,-260.22,54.94,0.2173864459991455,1450000
31
+ 0.0,0.0,0.6666666666666666,1.0,-0.16921516616423513,-0.38001116208037317,-0.19429954758915774,-0.4764552282580286,28.48762191088764,3.0549999999998847,1.0,595043.6,0.0,-270.96,56.1,0.22617006778717041,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/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
+ 0.0,0.0,0.43777777777777777,0.43777777777777777,-0.21752387278195334,-0.01681435861690093,-0.20912189880644813,0.21150639354303732,26.52673970158423,25.24999999999688,0.0,12750.0,-5.06,-2563.58,500.0,2.2365325021743776,50000
3
+ 0.0,0.0,0.4577777777777778,0.4577777777777778,-0.3585157853615093,-0.02110211828932586,-0.36165502137284855,-0.05397215168535938,33.55324777946742,25.24999999999688,0.0,38750.0,-4.88,-2481.92,500.0,2.531950454711914,100000
4
+ 0.0,0.0,0.45111111111111113,0.44666666666666666,-0.27631677583611974,-0.014421913622071994,-0.2796101221134508,-0.052209601450214776,9.877903087914778,25.24999999999688,0.0,64750.0,-4.98,-2547.14,500.0,2.19774968624115,150000
5
+ 0.0,0.0,0.46,0.46,-0.19669057149921126,-0.047499884829304194,-0.1975467145006867,-0.026352653806977804,-0.6462479692643176,25.24999999999688,0.0,90750.0,-4.86,-2413.64,500.0,2.1078502368927,200000
6
+ 0.0,0.0,0.4666666666666667,0.4666666666666667,-0.02070559426579503,-0.019626354502082666,-0.02356751555038773,-0.07277561369631666,-0.15020346748244615,25.24999999999688,0.0,116750.0,-4.8,-2468.48,500.0,2.178437900543213,250000
7
+ 0.0,0.0,0.4911111111111111,0.4911111111111111,-0.48146631993201244,0.08878240132004923,-0.48482954445831816,-0.05438525587286345,-1.652327750491406,25.24999999999688,0.0,142750.0,-4.58,-2324.36,500.0,1.728905940055847,300000
8
+ 0.0,0.0,0.45111111111111113,0.4533333333333333,0.05146794007313268,-0.011530876872353123,0.05172254545803034,0.021625651519707113,0.16538275064057067,25.24999999999688,0.0,168750.0,-4.92,-2493.44,500.0,2.139244122505188,350000
9
+ 0.0,0.0,0.4777777777777778,0.47333333333333333,-0.3482517165638528,-0.036977680064874056,-0.3463763078484867,0.05987304131762402,-1.1563562211477896,25.24999999999688,0.0,194750.0,-4.74,-2484.0,500.0,2.096515779495239,400000
10
+ 0.0,0.0,0.42,0.42,-0.3843565278811681,0.023796907091228586,-0.3822803202326906,0.050847478751532615,34.98759275029113,25.24999999999688,0.0,220750.0,-5.22,-2601.02,500.0,2.2818398237228394,450000
11
+ 0.0,0.0,0.4666666666666667,0.4666666666666667,-0.31236989805055215,0.12533052914527734,-0.3056111301993635,0.01008991615671558,30.028966419237378,25.24999999999688,0.0,246750.0,-4.8,-2467.72,500.0,2.3218729162216185,500000
12
+ 0.0,0.0,0.45555555555555555,0.45555555555555555,-0.40172349936092855,0.011118223199901764,-0.4032923294528132,-0.02576445415132523,34.826552997631985,25.24999999999688,0.0,272750.0,-4.9,-2448.28,500.0,2.4831560325622557,550000
13
+ 0.0,0.0,0.46444444444444444,0.46444444444444444,-0.024998549392963084,0.09332482353730552,-0.02228907374025662,0.03788716888492136,36.14579070361761,25.24999999999688,0.0,298750.0,-4.82,-2478.38,500.0,2.489877381324768,600000
14
+ 0.0,0.0,0.4888888888888889,0.4888888888888889,-0.36265728126568497,-0.016117306406359905,-0.3606410375380769,0.025412124852845608,35.02919317956636,25.24999999999688,0.0,324750.0,-4.6,-2356.0,500.0,2.4213984298706053,650000
15
+ 0.0,0.0,0.47555555555555556,0.47555555555555556,-0.3591167343641003,0.03746733376911205,-0.35615142857077403,0.04244057421195315,35.028646787010004,25.24999999999688,0.0,350750.0,-4.72,-2359.14,500.0,2.404485487937927,700000
16
+ 0.0,0.0,0.45555555555555555,0.45555555555555555,-0.4046119632433793,-0.01863620606463089,-0.4026140360736781,0.03677502730021931,34.12412740221993,25.24999999999688,0.0,376750.0,-4.9,-2478.3,500.0,2.1282899951934815,750000
17
+ 0.0,0.0,0.44,0.44,-0.4147372467310027,0.1150247517666796,-0.41059648295295786,0.04452337507235731,34.81379889280921,25.24999999999688,0.0,402750.0,-5.04,-2511.12,500.0,2.2449451446533204,800000
18
+ 0.0,0.0,0.4533333333333333,0.4533333333333333,-0.32834354432201845,0.055204760481709934,-0.32125500273534857,0.11218545710194586,35.168808850574045,25.24999999999688,0.0,428750.0,-4.92,-2498.08,500.0,2.2800823926925657,850000
19
+ 0.0,0.0,0.42444444444444446,0.42444444444444446,-0.4152738274414234,0.04863887760119367,-0.41512037556384507,-0.05906458495037671,34.78850940132069,25.24999999999688,0.0,454750.0,-5.18,-2624.82,500.0,2.2115293312072755,900000
20
+ 0.0,0.0,0.44,0.44,-0.39396780012540517,0.0063853852590698475,-0.3910257556070628,0.04534863348504169,34.91146183376524,25.24999999999688,0.0,480750.0,-5.04,-2530.98,500.0,2.3358656406402587,950000
21
+ 0.0,0.0,0.46,0.46,-0.4036164303506446,0.11872009816392916,-0.3970961514493531,0.11754735188899407,34.875243439002745,25.24999999999688,0.0,506750.0,-4.86,-2446.12,500.0,2.344341344833374,1000000
22
+ 0.0,0.0,0.5222222222222223,0.5222222222222223,-0.19557147455074023,-0.1646443859809676,-0.19096523063308063,0.09973709827140041,23.083936223974206,25.24999999999688,0.0,532750.0,-4.3,-2350.56,500.0,1.7657792139053345,1050000
23
+ 0.0,0.0,0.6177777777777778,0.8111111111111111,-0.2028107272234559,0.008513395208910141,-0.20416053309779378,-0.027675321829484758,26.00787352640352,19.93699999999852,0.54,555841.78,-1.7,-1468.9,393.74,1.4115126943588256,1100000
24
+ 0.0,0.0,0.6644444444444444,0.9866666666666667,-0.18489955850188466,-0.037505177913794846,-0.20327374406560747,-0.3173126991061149,20.65812022576005,7.0649999999994915,0.96,569403.9,-0.12,-619.68,136.3,0.5093571901321411,1150000
25
+ 0.0,0.0,0.6666666666666666,1.0,-0.18450935690441184,-0.014104180329809009,-0.1957416915959816,-0.2061909122127266,29.779490287059485,4.584999999999719,1.0,575370.1,0.0,-424.76,86.7,0.33157341003417967,1200000
26
+ 0.0,0.0,0.6666666666666666,1.0,-0.1892264026313927,-0.1130704162446663,-0.1985675763031858,-0.22234498948827217,29.385895824239192,3.7329999999998105,1.0,579419.7,0.0,-346.88,69.66,0.2709890079498291,1250000
27
+ 0.0,0.0,0.6666666666666666,1.0,-0.19316437884125578,0.03013229369426042,-0.2005301995726068,-0.11876996407633382,30.957503875802214,3.368999999999851,1.0,582866.8,0.0,-298.18,62.38,0.24765194416046143,1300000
28
+ 0.0,0.0,0.6666666666666666,1.0,-0.17929282540755484,0.13041170136968483,-0.1786683392399478,0.2240948278303233,30.972123308236363,3.2929999999998585,1.0,586113.86,0.0,-296.14,60.86,0.2407935619354248,1350000
29
+ 0.0,0.0,0.6666666666666666,1.0,-0.16398114256779658,-0.23975803875637824,-0.17715944625749078,-0.1721856091301362,34.649852491635095,3.1819999999998707,1.0,589193.96,0.0,-287.44,58.64,0.23573916435241699,1400000
30
+ 0.0,0.0,0.6666666666666666,1.0,-0.17047083184529147,-0.1974348787207512,-0.18734459489097735,-0.3071254621764078,33.00862745971615,2.996999999999892,1.0,592165.36,0.0,-260.22,54.94,0.2173864459991455,1450000
31
+ 0.0,0.0,0.6666666666666666,1.0,-0.16921516616423513,-0.38001116208037317,-0.19429954758915774,-0.4764552282580286,28.48762191088764,3.0549999999998847,1.0,595043.6,0.0,-270.96,56.1,0.22617006778717041,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/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": "FBRAC", "seed": 10001, "env_name": "puzzle-3x3-play-singletask-task4-v0", "save_dir": "exp/qam-reproduce/main-experiments/puzzle-3x3-play-singletask-task4-v0/20260307_202607", "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": "fbrac", "alpha": 0.03, "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-v0/20260307_202607/offline_agent.csv ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 765.83563,1.6021837,0.6286904,-6.488982,-26.101841,-30.88882,5.4084654,-5.002804,192.62569,5000
3
+ 659.40765,2.00016,0.7092412,-5.9828734,-25.188421,-38.4058,15.174906,-16.86289,382.10062,10000
4
+ 731.4967,2.372879,1.0875167,-9.237475,-26.350965,-32.09999,14.550513,-13.31624,609.51807,15000
5
+ 568.9694,1.6555022,0.4459188,-0.40347928,-21.988993,-27.138332,4.2340026,-2.876065,148.17337,20000
6
+ 601.0348,2.2778206,0.9701943,-0.13725607,-22.807938,-28.446156,2.7388086,-2.3665202,124.46465,25000
7
+ 680.37024,1.8806182,0.4810651,-7.757432,-25.000269,-29.76252,17.082535,-11.897653,613.05096,30000
8
+ 697.4583,3.0116417,0.42786914,-0.7166881,-24.779305,-31.05051,2.6384428,-2.4525685,129.55344,35000
9
+ 526.74066,1.5099964,0.58086807,-6.712298,-21.178896,-26.402308,4.427079,-3.649548,196.70892,40000
10
+ 405.04056,1.6648176,0.48612508,-8.399202,-17.94205,-23.320635,3.5302186,-4.0768538,163.38675,45000
11
+ 238.25438,1.3039632,0.057499558,-0.5034196,-12.095925,-17.019108,2.0829258,-2.0764127,67.3458,50000
12
+ 334.48886,1.9210547,0.23698702,-8.042341,-14.493903,-19.820763,4.1229467,-3.808453,141.36124,55000
13
+ 206.61618,1.5518618,0.052568745,0.17377523,-11.383414,-15.326327,2.1014278,-2.0933437,98.76628,60000
14
+ 233.71173,1.3665959,0.07823632,-4.4993796,-12.981282,-17.327887,2.1655586,-1.7855874,75.16822,65000
15
+ 205.6359,1.0645798,0.025788242,0.062594965,-10.980051,-14.700016,1.4044187,-1.2462677,47.0961,70000
16
+ 184.53488,0.92381096,0.019838616,-5.25856,-10.279561,-13.181872,2.5190582,-2.065224,75.842896,75000
17
+ 165.3933,0.9116851,0.015425332,-4.9271545,-10.06491,-12.450777,0.50272125,-0.46112862,17.537031,80000
18
+ 190.85728,0.8343873,0.011855826,-6.2827854,-10.730659,-13.54065,0.7834301,-0.8772628,27.195747,85000
19
+ 148.16933,0.8760755,0.017743466,-5.1719646,-10.195157,-12.94835,0.713616,-0.8224314,19.808445,90000
20
+ 162.22769,0.60775185,0.011626308,-5.0369287,-9.967345,-12.508363,0.41267958,-0.38169926,15.194725,95000
21
+ 170.5741,0.66204953,0.0077182683,0.1379218,-10.014457,-12.639261,0.3673203,-0.3952324,13.644137,100000
22
+ 167.93109,0.6705857,0.007760443,-5.32316,-9.996104,-12.745358,0.5678703,-0.491456,12.984419,105000
23
+ 167.43095,0.70407563,0.017919473,-5.237779,-10.262448,-13.309525,0.57341725,-0.6602841,23.106346,110000
24
+ 178.95538,0.6246711,0.00900495,-2.564715,-10.122368,-12.108505,1.3386574,-1.7644181,41.344276,115000
25
+ 177.24934,0.64749086,0.0074104974,-0.018119225,-10.213691,-12.659254,0.5981672,-0.82033044,18.22539,120000
26
+ 176.86517,0.65384436,0.0074026957,0.13090593,-10.263158,-12.751968,0.9945152,-1.284841,22.224403,125000
27
+ 181.19426,0.8963084,0.0069414475,-0.2449914,-10.365539,-12.481385,0.9771282,-1.17646,30.182274,130000
28
+ 169.24731,0.54755974,0.0067017167,0.007712133,-9.95346,-12.151448,0.36580163,-0.58395106,15.985694,135000
29
+ 169.77039,0.8133967,0.0070718634,0.043038435,-10.309494,-12.752587,0.47843993,-0.5997886,18.421558,140000
30
+ 185.46378,0.6458473,0.0106830215,0.071392715,-10.567217,-13.231339,0.38249585,-0.4260921,15.0937605,145000
31
+ 168.05153,0.59951603,0.009076204,-2.5156565,-10.10922,-12.114294,0.6113776,-0.7622726,25.534746,150000
32
+ 169.19527,0.6125897,0.013554061,-1.8703699,-10.280016,-13.027193,2.0254316,-2.8177483,52.31817,155000
33
+ 177.61385,0.84377885,0.0064156414,-6.207344,-10.240805,-12.872394,0.5440792,-0.46699473,17.857046,160000
34
+ 179.77597,0.6244446,0.008295828,-6.2084246,-10.40977,-12.563573,0.89771396,-0.942465,25.429382,165000
35
+ 166.47845,0.6078136,0.0070400313,-5.9840918,-9.86718,-12.518258,1.5325005,-1.3825929,29.757889,170000
36
+ 147.23642,0.73520535,0.0048980797,-5.1672006,-9.424698,-11.873857,0.6181532,-0.43923065,14.870267,175000
37
+ 184.99069,0.8377043,0.0068714186,-6.284908,-10.619687,-12.697,0.86049676,-1.1124601,29.691668,180000
38
+ 186.18927,0.8917222,0.0073007243,-6.1163216,-10.245134,-12.548261,0.63243675,-0.6858512,22.231926,185000
39
+ 154.56012,0.6357683,0.0051734694,-5.7099385,-10.014136,-11.901202,0.23764512,-0.45176584,13.292719,190000
40
+ 180.73785,0.68016243,0.012493915,-0.9951538,-10.362998,-12.298567,0.9150623,-0.90026075,18.608864,195000
41
+ 156.42769,0.5406083,0.010871454,-5.8657765,-9.732379,-11.414106,0.397828,-0.39343232,12.373599,200000
42
+ 152.36058,0.49819213,0.005135508,0.057051223,-9.683318,-11.928336,0.3891266,-0.5880272,12.382881,205000
43
+ 176.5956,1.233313,0.0886744,0.030248398,-10.276095,-12.24151,1.4537107,-0.9282865,27.778149,210000
44
+ 171.83875,0.6165701,0.0047560353,-6.6465607,-10.211658,-11.7662115,29.696215,-35.018837,756.26196,215000
45
+ 172.62009,0.5326878,0.0056853434,-6.3995667,-9.920001,-11.237148,1.4372627,-1.9915679,36.506958,220000
46
+ 180.23538,0.7710255,0.008310602,-3.476914,-10.357593,-12.103698,6.9449167,-7.6728425,159.01233,225000
47
+ 202.35654,0.623536,0.009664548,-6.979976,-10.461497,-12.90311,11.982425,-8.520266,156.19504,230000
48
+ 175.02467,0.6973921,0.0036484413,0.0076236203,-10.044597,-11.81559,0.7345868,-0.69639295,19.903526,235000
49
+ 159.80554,0.45775026,0.0028468906,-5.9971485,-9.490813,-11.290129,0.5715412,-0.9018302,16.476353,240000
50
+ 184.23578,0.5587944,0.009563318,0.13283505,-10.344081,-11.88073,6.039843,-2.1321886,62.000935,245000
51
+ 168.88107,0.55373216,0.004218418,0.0033928268,-9.85,-11.579831,0.58938223,-0.7112811,18.301609,250000
52
+ 174.77882,0.65609026,0.009677075,-1.1929206,-10.334462,-11.97413,0.5018153,-0.74498504,19.259005,255000
53
+ 173.60304,0.49550164,0.057665315,0.10255623,-10.086104,-11.614705,0.3608111,-0.4714548,13.10187,260000
54
+ 136.54364,0.5671709,0.008569359,-5.9952245,-9.09184,-12.173267,1.4218653,-0.97921336,27.070915,265000
55
+ 139.4128,0.5666815,0.012221262,-5.5877914,-9.168882,-10.698305,1.565213,-0.6527165,20.274372,270000
56
+ 73.506836,1.5203199,0.022285668,-0.041955203,-7.3469806,-10.391327,1.5978192,-2.9922307,57.787,275000
57
+ 27.610998,1.164614,0.0813962,-0.73090935,-5.7764406,-10.222955,19.017183,-25.999504,431.45224,280000
58
+ 27.119595,1.7720478,0.05192901,-1.8413001,-6.025726,-8.573721,2.4190083,-2.13683,93.0442,285000
59
+ -24.250008,0.9256677,0.026316432,0.07454488,-4.581825,-6.554636,6.6779447,-4.2472944,100.121895,290000
60
+ -20.390938,1.0758183,0.08658199,-0.30989328,-4.6150365,-8.377782,3.0551453,-2.4962025,90.346565,295000
61
+ -16.498161,1.0658042,0.08656137,-0.689571,-4.4234138,-5.9728603,11.717666,-3.7967443,135.73987,300000
62
+ -0.047030687,1.2047861,0.044864323,-0.39579377,-5.062504,-6.5723853,2.733867,-2.6383915,78.87053,305000
63
+ 24.66842,1.4339141,0.06812545,-0.9453143,-5.464335,-7.460776,2.0010555,-3.970329,80.23044,310000
64
+ 57.08395,1.3478177,0.0354898,-2.31592,-6.566472,-9.228335,9.791229,-17.89048,299.3511,315000
65
+ 58.49007,1.1661675,0.01992266,-2.5944738,-6.707392,-8.113166,2.1919036,-2.5281394,63.051888,320000
66
+ 69.478546,1.2611003,0.17228793,-2.3905365,-7.001909,-8.56084,1.982811,-2.5924883,45.643345,325000
67
+ 75.473854,1.0591515,0.08216702,-3.4974403,-7.3666534,-11.31629,3.68392,-2.6599655,87.13903,330000
68
+ 110.46114,1.4645935,0.12601873,-3.56268,-8.153046,-11.584335,21.62598,-14.213672,384.37286,335000
69
+ 91.60313,1.8728783,0.09997296,-3.9194705,-8.132472,-12.728758,6.5907674,-9.217577,179.51366,340000
70
+ 211.90898,1.414748,0.043297052,-7.373649,-11.981903,-13.901321,1.0951144,-2.6829927,57.395164,345000
71
+ 208.48094,1.1299424,0.018726656,-4.0145817,-11.060076,-12.524351,12.127836,-8.864377,279.26437,350000
72
+ 221.60168,1.1644491,0.014549148,-0.0050899535,-11.537845,-13.006124,2.1182814,-1.2011932,50.34645,355000
73
+ 215.62025,1.1093724,0.004584368,0.05094079,-11.169886,-12.417098,0.6071902,-0.8657836,20.528473,360000
74
+ 206.59,0.9738325,0.005425067,-7.554754,-11.105297,-12.592365,7.8277483,-7.3123894,175.32286,365000
75
+ 213.94098,1.2283733,0.010730761,-7.2370524,-11.006741,-12.552486,5.476246,-5.042404,149.02681,370000
76
+ 210.41824,0.95193356,0.0035069976,0.055936135,-11.169073,-12.831029,1.7588912,-1.2388307,38.12802,375000
77
+ 213.70322,0.8525344,0.0031381361,0.105486095,-11.266881,-12.773999,0.7533164,-0.91353565,22.277761,380000
78
+ 215.11736,1.0553427,0.007866616,0.011463873,-11.532251,-12.928121,5.2694488,-2.1667113,81.99637,385000
79
+ 237.22566,0.8842304,0.006482017,-0.103045255,-11.917172,-13.335782,2.0951173,-1.401049,44.060745,390000
80
+ 233.98857,0.71717215,0.017359486,-8.196595,-11.995303,-13.359088,1.2928038,-1.1294444,38.26495,395000
81
+ 238.44266,0.7928901,0.007885563,-8.128179,-11.85877,-13.3147135,1.501866,-0.9583614,37.949493,400000
82
+ 211.88934,0.80187213,0.004741084,0.01992917,-11.228943,-13.056675,1.1704112,-1.3005038,21.36833,405000
83
+ 211.7375,0.89388704,0.007929701,-7.670909,-11.083677,-12.572074,4.565221,-6.765282,79.005066,410000
84
+ 192.21846,0.63190866,0.005588516,-5.315523,-10.850759,-12.966919,2.864249,-3.0567997,43.89519,415000
85
+ 195.34225,0.8523417,0.0098504415,0.0032592192,-10.949989,-13.431428,2.0617378,-2.7542126,74.80307,420000
86
+ 199.7156,0.6708907,0.004021997,-7.653793,-11.066687,-13.093355,0.87798667,-0.9251644,25.516647,425000
87
+ 215.35156,0.71747744,0.0102904355,0.021511368,-11.340289,-13.115202,2.8484344,-4.7299557,105.980606,430000
88
+ 192.69046,0.63387483,0.005113227,-5.08247,-10.783861,-12.5175295,2.9629915,-1.9673165,67.071175,435000
89
+ 208.60841,0.90665257,0.017423494,-7.2842484,-11.183729,-12.988056,5.0020337,-6.51118,150.71396,440000
90
+ 218.52675,0.8288194,0.007495126,-6.655109,-11.334962,-13.001268,2.518001,-1.8602883,60.701496,445000
91
+ 225.07568,0.69063586,0.006955631,0.05613912,-11.636001,-13.33348,13.133558,-10.574776,257.45673,450000
92
+ 217.40187,0.6404463,0.011749755,-2.127318,-11.453603,-13.901229,1.4360842,-1.7082162,55.20945,455000
93
+ 202.99985,0.65999436,0.0031550515,0.02704294,-11.221381,-12.8883705,0.6328006,-0.7153525,16.789566,460000
94
+ 214.28242,0.8867419,0.0139531,0.035153106,-11.070575,-13.339414,18.443316,-8.996445,257.6384,465000
95
+ 197.9649,0.76693296,0.005533337,-6.346168,-10.925061,-12.320607,0.59411484,-0.61756104,19.539333,470000
96
+ 199.45576,0.6775925,0.009561367,-7.513925,-10.935489,-12.862441,0.9523526,-1.0466505,26.872606,475000
97
+ 199.05783,0.7469679,0.008026304,0.022514641,-10.766509,-13.716872,3.540686,-3.6398883,56.827557,480000
98
+ 200.30525,0.66554445,0.0063802856,-5.893139,-11.086493,-12.873415,0.47971138,-0.6317102,17.260618,485000
99
+ 197.07825,1.4026778,0.04568133,-5.924671,-11.036446,-12.936545,1.7228224,-2.2833483,47.612183,490000
100
+ 205.64381,0.8085821,0.013491252,0.024972692,-11.316556,-13.949462,1.8906177,-3.0216806,63.66906,495000
101
+ 201.03307,0.7573624,0.0078037814,-1.7929673,-11.253169,-13.242756,2.0700467,-1.5821402,31.275772,500000
102
+ 205.29408,0.69858223,0.00864162,0.011836991,-10.962378,-13.552504,4.2857895,-2.9071712,47.65284,505000
103
+ 189.26315,0.65446043,0.005856201,-4.953302,-10.748583,-12.580163,1.1588482,-0.46027625,18.971464,510000
104
+ 199.99274,0.8755962,0.008739637,0.024793148,-11.060859,-13.021262,3.6464746,-2.1391551,38.364,515000
105
+ 199.15683,0.8458472,0.013137877,-3.432985,-10.886833,-12.627244,18.443462,-27.306824,522.83264,520000
106
+ 198.07205,0.66033626,0.010442236,-5.821268,-10.699913,-12.617825,1.3565396,-1.2408725,26.831606,525000
107
+ 193.80913,0.8654448,0.010114345,-3.5329723,-10.776813,-14.23219,2.3342757,-1.8234711,39.768982,530000
108
+ 212.67322,0.750793,0.007190569,-7.537203,-11.322237,-13.011983,5.362142,-3.772499,120.79729,535000
109
+ 201.73788,0.97427344,0.0067597083,-0.004365988,-11.128127,-13.233689,5.0091457,-4.6086235,118.67913,540000
110
+ 208.4705,0.89630526,0.0052684015,-7.7038007,-11.345445,-13.276874,1.351526,-2.5186977,31.951614,545000
111
+ 192.42352,1.3909832,0.0071910876,0.04466384,-10.502213,-12.396893,5.1357064,-12.9438505,90.20901,550000
112
+ 199.24362,0.7396743,0.041225906,-0.008153304,-10.992693,-12.947602,3.2429924,-2.8453827,50.65879,555000
113
+ 190.999,1.0895543,0.00899827,0.017479941,-10.715345,-12.77164,3.228522,-2.5635235,58.714333,560000
114
+ 205.28993,1.1392655,0.016544115,-5.948024,-11.013614,-13.270636,4.092912,-3.3292437,104.85714,565000
115
+ 184.51982,0.5839455,0.0068534003,-6.7679415,-10.820575,-13.114037,2.5571058,-2.320312,38.4329,570000
116
+ 194.69737,0.6002811,0.0074726716,-0.0005687773,-10.678622,-12.779314,1.5245283,-1.0189446,44.432365,575000
117
+ 180.62967,0.62724495,0.0060045007,-0.018892206,-10.5710745,-12.905037,3.412776,-4.96128,51.68074,580000
118
+ 186.6097,0.9761743,0.012354504,-7.092346,-10.689708,-12.655322,2.509359,-1.8400003,34.674034,585000
119
+ 216.51566,0.90657306,0.022195611,0.05933933,-11.271781,-13.353215,1.0502617,-1.4664959,43.597816,590000
120
+ 187.5083,0.7601985,0.006861482,-7.111467,-10.7301235,-12.808155,2.5008154,-2.2187479,59.74694,595000
121
+ 198.58205,1.1081961,0.009154725,-7.441075,-11.071409,-13.5168295,1.9160861,-2.5242753,42.073593,600000
122
+ 182.52695,1.1814872,0.0194632,-5.7325964,-10.616381,-12.283111,24.408352,-16.832317,338.05112,605000
123
+ 188.85478,1.4203398,0.018550072,0.020809203,-10.617108,-12.673668,5.6193466,-10.209971,73.19488,610000
124
+ 194.14534,1.4979796,0.015984317,0.00907556,-10.788032,-13.375117,8.384966,-3.2532437,101.55147,615000
125
+ 198.1388,2.0399199,0.011202614,-7.221266,-10.770899,-12.796106,18.75011,-12.728847,283.78595,620000
126
+ 170.3313,1.3425679,0.013039765,-6.247782,-10.54351,-12.792758,8.937038,-11.176909,144.65947,625000
127
+ 197.189,1.7160742,0.036828686,-7.038501,-10.748151,-14.002533,6.7187986,-5.773487,156.8884,630000
128
+ 189.88075,2.0345006,0.019515334,-1.0554963,-10.742221,-13.163227,2.5600157,-4.291641,55.68494,635000
129
+ 188.34203,1.4360673,0.039337553,0.0013011694,-10.575513,-13.885921,16.966856,-14.503444,343.33994,640000
130
+ 189.40709,1.470617,0.037900817,-6.8219676,-10.684285,-13.080578,16.432156,-15.431147,182.5173,645000
131
+ 193.7361,1.3208907,0.021411037,-6.666478,-11.089271,-13.101841,9.781766,-8.872849,265.74576,650000
132
+ 200.03204,1.124224,0.011840192,-0.011641458,-11.083973,-13.581591,3.9326005,-4.914676,94.37413,655000
133
+ 198.36665,1.4689442,0.015040408,-7.02979,-11.023513,-13.589393,4.4939885,-6.1339555,122.75721,660000
134
+ 189.2383,1.3301929,0.012106139,0.023183845,-10.684618,-12.868712,3.764313,-6.537224,79.82384,665000
135
+ 188.52112,1.3359643,0.021334773,-6.597535,-10.853563,-12.287484,43.53568,-36.12303,518.574,670000
136
+ 197.32498,1.5682092,0.012269169,-7.2822394,-10.9973135,-13.337255,3.2160335,-5.2021604,80.79311,675000
137
+ 242.0768,1.6442896,1.4597682,-7.972533,-11.938829,-14.743447,479.07193,-143.57515,2448.211,680000
138
+ 192.20479,4.2627954,0.01684489,-6.9537897,-10.9061575,-13.534724,3.583988,-6.1020117,60.988323,685000
139
+ 196.50528,2.338691,0.037958905,-6.714103,-10.665697,-13.97715,7.3457546,-6.4295087,104.923164,690000
140
+ 194.09094,1.2467796,0.022775048,-7.0211787,-10.990569,-13.121513,3.6002693,-2.909643,82.87614,695000
141
+ 202.46373,1.5707906,0.017545218,0.031058699,-11.120327,-13.367716,31.172045,-20.007544,515.8703,700000
142
+ 191.42506,1.5027047,0.013783053,-0.00077488273,-11.084956,-13.483303,24.210182,-21.366861,357.74634,705000
143
+ 203.61081,1.7529469,0.021410687,0.018154293,-11.009882,-14.3310585,23.794973,-37.111908,306.36246,710000
144
+ 206.81778,1.4256402,0.030081138,0.031228855,-11.369922,-13.803764,5.162131,-4.334801,94.90725,715000
145
+ 200.0148,1.7125189,0.026379868,-6.422077,-11.40961,-13.96098,15.964751,-23.447302,239.48221,720000
146
+ 222.3844,1.4225386,0.021408772,-6.988091,-11.569625,-14.0765085,10.745068,-12.954043,162.99841,725000
147
+ 191.74806,1.7673517,0.042892266,-7.037634,-10.913546,-13.8408575,10.549533,-7.4445767,188.81169,730000
148
+ 197.4984,1.4084713,0.035166238,0.030241095,-11.023781,-13.665001,6.5388722,-5.5252156,129.47589,735000
149
+ 190.19856,1.2713728,0.015991947,0.0409019,-11.099059,-13.444808,96.00442,-46.672703,1045.2566,740000
150
+ 200.88239,1.4821968,0.022020241,0.07781039,-10.927348,-13.950287,7.0081577,-6.4124856,82.1679,745000
151
+ 222.26498,1.2309402,0.018131454,-6.316382,-11.734271,-14.964303,27.449635,-30.084845,525.82275,750000
152
+ 203.80072,1.3881333,0.018328685,0.03756243,-11.334749,-13.825222,15.13458,-15.341155,221.90392,755000
153
+ 219.65132,1.4201286,0.022070503,0.033253096,-11.793981,-14.783182,25.81133,-8.309686,205.87926,760000
154
+ 214.70154,1.5836687,0.022096535,-6.724631,-11.505874,-13.853908,5.542424,-3.4759905,70.84784,765000
155
+ 172.85913,1.2062778,0.029745394,-4.67491,-10.220461,-14.000096,8.677071,-6.160147,140.10701,770000
156
+ 201.87961,2.1989145,0.055458665,0.058291145,-11.257005,-13.947921,6.1387253,-12.769777,142.79472,775000
157
+ 192.26234,1.4259051,0.085765995,0.07751897,-11.080465,-14.486042,11.505795,-5.548475,106.17093,780000
158
+ 212.00244,2.0602279,0.04200792,0.037065692,-11.661597,-15.079687,24.743269,-50.488342,346.32254,785000
159
+ 243.4657,4.490334,0.051029366,-7.236849,-12.360759,-15.700742,17.54191,-21.103096,317.5962,790000
160
+ 220.95827,2.407246,0.07104465,0.056262143,-11.984148,-14.943441,31.913532,-49.533962,325.21198,795000
161
+ 275.09357,1.8869115,0.0448244,-8.386266,-13.438075,-17.959435,41.08885,-51.35861,499.89056,800000
162
+ 263.66953,1.5353518,0.093992606,-6.2147527,-12.998224,-15.570791,7.0810947,-10.821331,151.98586,805000
163
+ 308.09375,1.9242167,0.08933017,-1.365655,-14.380266,-17.87531,97.613,-100.33113,1148.0574,810000
164
+ 269.2795,1.7303134,0.05282515,-0.5588143,-13.242022,-16.183687,8.579805,-11.124335,213.8691,815000
165
+ 265.06476,1.6052005,0.08327566,-7.579838,-13.343506,-16.330303,9.360092,-6.7537756,140.80104,820000
166
+ 245.95258,1.500428,0.052007973,0.027723767,-12.543301,-15.41915,9.939583,-5.5971117,109.94406,825000
167
+ 246.31494,1.322434,0.069725476,-6.4229865,-12.405265,-15.907201,20.11101,-13.712716,359.60925,830000
168
+ 276.75623,1.4626575,0.042977553,-7.458625,-13.450587,-16.46357,22.16989,-20.805382,453.90485,835000
169
+ 288.70984,1.7469188,0.064233325,0.009323992,-13.317113,-15.5145645,12.806019,-9.176534,192.66711,840000
170
+ 271.47223,1.545115,0.04228407,-8.944012,-13.140963,-16.132929,7.428825,-9.793985,148.91655,845000
171
+ 282.80096,2.183484,0.041012865,-7.4237275,-13.871803,-16.153658,106.01917,-71.691635,609.907,850000
172
+ 289.32956,1.4032918,0.046862382,-3.6966228,-13.639084,-17.59472,11.417584,-16.988056,213.29395,855000
173
+ 299.52448,1.3223305,0.03694533,-8.008354,-13.743215,-16.627932,19.286436,-13.764557,189.76921,860000
174
+ 247.2939,1.783133,0.029351035,0.026756957,-12.576957,-14.97369,5.7099786,-6.119499,97.46098,865000
175
+ 277.36703,1.5912209,0.0695404,-6.614139,-13.019725,-15.305579,6.599827,-6.271028,112.81113,870000
176
+ 277.11496,1.6618536,0.03585663,-6.641693,-13.0950165,-16.107935,23.351604,-45.563564,711.2619,875000
177
+ 257.63733,1.5431423,0.021205448,-6.3843503,-12.569222,-15.032173,7.0079203,-22.216766,137.71234,880000
178
+ 279.86694,1.2823074,0.02003256,-7.081502,-13.545204,-16.064669,2.8603032,-3.1760616,65.754906,885000
179
+ 250.44417,1.3455927,0.018892666,-7.053501,-12.718535,-14.812448,16.549242,-26.789013,373.0989,890000
180
+ 246.92097,1.3430495,0.0277967,-7.2992864,-12.630766,-16.023773,8.900286,-10.251784,169.62172,895000
181
+ 267.66086,1.5184999,0.038148075,-8.146446,-12.616608,-14.128539,10.434516,-8.716731,163.85172,900000
182
+ 257.7609,1.2643542,0.029745674,0.035446733,-12.615993,-16.840384,5.4592714,-9.862244,143.22153,905000
183
+ 215.96512,1.3704925,0.030778388,-5.1163855,-11.650451,-14.847259,6.328729,-4.6861353,100.42914,910000
184
+ 285.5748,1.7026066,0.049104545,0.039148755,-13.531334,-17.043278,12.366107,-10.714995,176.56493,915000
185
+ 271.59805,1.3660213,0.0462795,-6.045883,-13.168204,-16.115929,12.506211,-12.228162,186.9886,920000
186
+ 305.44843,1.3056338,0.0419331,-7.583145,-14.150275,-16.595417,4.113972,-4.954016,107.29399,925000
187
+ 250.91188,1.390064,0.055753674,-7.0336504,-12.760958,-15.307984,32.692642,-23.429476,658.1247,930000
188
+ 270.3161,1.6092503,0.07440764,-7.786128,-13.3153105,-15.526725,14.559508,-26.553371,295.21173,935000
189
+ 261.01526,1.4734774,0.030369094,0.0060186684,-12.906596,-15.6644,8.5740795,-4.8147,112.7963,940000
190
+ 289.14688,1.4108858,0.080184914,0.06460111,-13.593305,-17.208773,15.085419,-11.3698225,232.76971,945000
191
+ 258.2949,1.6135311,0.054134514,-2.7913342,-12.883468,-15.575268,4.272125,-5.820419,80.85396,950000
192
+ 244.87793,1.6436162,0.025013184,0.018937454,-12.426517,-15.08207,13.445557,-13.693498,279.09723,955000
193
+ 246.98149,1.654991,0.06906513,-6.781169,-12.584383,-15.099474,7.827051,-5.7928023,99.09427,960000
194
+ 279.04532,1.6197821,0.039446075,-7.5325694,-13.382105,-15.902283,7.273182,-6.2351856,113.15384,965000
195
+ 273.44766,1.9966375,0.038399324,-3.775235,-13.383623,-16.461988,9.054448,-15.359602,125.392494,970000
196
+ 296.40762,1.7318474,0.07263531,0.0441747,-13.94104,-16.226702,12.145797,-13.230019,166.11374,975000
197
+ 267.5152,1.504002,0.03072446,-7.4600177,-13.116385,-15.22835,11.200559,-12.346513,146.93323,980000
198
+ 278.94644,1.4178462,0.020468755,-7.0365868,-13.115705,-15.335801,4.6417994,-5.4535804,104.737465,985000
199
+ 277.83508,1.3095802,0.03285223,-7.3419785,-13.357108,-15.296889,10.744811,-14.494225,223.08542,990000
200
+ 263.14355,2.0278478,0.049776845,-6.4662156,-12.709213,-14.746011,12.505573,-7.650782,158.32571,995000
201
+ 276.64157,1.5671933,0.041638564,0.04320173,-13.081848,-16.972008,21.746265,-11.967512,274.17526,1000000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/offline_agent_sv.csv ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 765.83563,1.6021837,0.6286904,-6.488982,-26.101841,-30.88882,5.4084654,-5.002804,192.62569,5000
3
+ 659.40765,2.00016,0.7092412,-5.9828734,-25.188421,-38.4058,15.174906,-16.86289,382.10062,10000
4
+ 731.4967,2.372879,1.0875167,-9.237475,-26.350965,-32.09999,14.550513,-13.31624,609.51807,15000
5
+ 568.9694,1.6555022,0.4459188,-0.40347928,-21.988993,-27.138332,4.2340026,-2.876065,148.17337,20000
6
+ 601.0348,2.2778206,0.9701943,-0.13725607,-22.807938,-28.446156,2.7388086,-2.3665202,124.46465,25000
7
+ 680.37024,1.8806182,0.4810651,-7.757432,-25.000269,-29.76252,17.082535,-11.897653,613.05096,30000
8
+ 697.4583,3.0116417,0.42786914,-0.7166881,-24.779305,-31.05051,2.6384428,-2.4525685,129.55344,35000
9
+ 526.74066,1.5099964,0.58086807,-6.712298,-21.178896,-26.402308,4.427079,-3.649548,196.70892,40000
10
+ 405.04056,1.6648176,0.48612508,-8.399202,-17.94205,-23.320635,3.5302186,-4.0768538,163.38675,45000
11
+ 238.25438,1.3039632,0.057499558,-0.5034196,-12.095925,-17.019108,2.0829258,-2.0764127,67.3458,50000
12
+ 334.48886,1.9210547,0.23698702,-8.042341,-14.493903,-19.820763,4.1229467,-3.808453,141.36124,55000
13
+ 206.61618,1.5518618,0.052568745,0.17377523,-11.383414,-15.326327,2.1014278,-2.0933437,98.76628,60000
14
+ 233.71173,1.3665959,0.07823632,-4.4993796,-12.981282,-17.327887,2.1655586,-1.7855874,75.16822,65000
15
+ 205.6359,1.0645798,0.025788242,0.062594965,-10.980051,-14.700016,1.4044187,-1.2462677,47.0961,70000
16
+ 184.53488,0.92381096,0.019838616,-5.25856,-10.279561,-13.181872,2.5190582,-2.065224,75.842896,75000
17
+ 165.3933,0.9116851,0.015425332,-4.9271545,-10.06491,-12.450777,0.50272125,-0.46112862,17.537031,80000
18
+ 190.85728,0.8343873,0.011855826,-6.2827854,-10.730659,-13.54065,0.7834301,-0.8772628,27.195747,85000
19
+ 148.16933,0.8760755,0.017743466,-5.1719646,-10.195157,-12.94835,0.713616,-0.8224314,19.808445,90000
20
+ 162.22769,0.60775185,0.011626308,-5.0369287,-9.967345,-12.508363,0.41267958,-0.38169926,15.194725,95000
21
+ 170.5741,0.66204953,0.0077182683,0.1379218,-10.014457,-12.639261,0.3673203,-0.3952324,13.644137,100000
22
+ 167.93109,0.6705857,0.007760443,-5.32316,-9.996104,-12.745358,0.5678703,-0.491456,12.984419,105000
23
+ 167.43095,0.70407563,0.017919473,-5.237779,-10.262448,-13.309525,0.57341725,-0.6602841,23.106346,110000
24
+ 178.95538,0.6246711,0.00900495,-2.564715,-10.122368,-12.108505,1.3386574,-1.7644181,41.344276,115000
25
+ 177.24934,0.64749086,0.0074104974,-0.018119225,-10.213691,-12.659254,0.5981672,-0.82033044,18.22539,120000
26
+ 176.86517,0.65384436,0.0074026957,0.13090593,-10.263158,-12.751968,0.9945152,-1.284841,22.224403,125000
27
+ 181.19426,0.8963084,0.0069414475,-0.2449914,-10.365539,-12.481385,0.9771282,-1.17646,30.182274,130000
28
+ 169.24731,0.54755974,0.0067017167,0.007712133,-9.95346,-12.151448,0.36580163,-0.58395106,15.985694,135000
29
+ 169.77039,0.8133967,0.0070718634,0.043038435,-10.309494,-12.752587,0.47843993,-0.5997886,18.421558,140000
30
+ 185.46378,0.6458473,0.0106830215,0.071392715,-10.567217,-13.231339,0.38249585,-0.4260921,15.0937605,145000
31
+ 168.05153,0.59951603,0.009076204,-2.5156565,-10.10922,-12.114294,0.6113776,-0.7622726,25.534746,150000
32
+ 169.19527,0.6125897,0.013554061,-1.8703699,-10.280016,-13.027193,2.0254316,-2.8177483,52.31817,155000
33
+ 177.61385,0.84377885,0.0064156414,-6.207344,-10.240805,-12.872394,0.5440792,-0.46699473,17.857046,160000
34
+ 179.77597,0.6244446,0.008295828,-6.2084246,-10.40977,-12.563573,0.89771396,-0.942465,25.429382,165000
35
+ 166.47845,0.6078136,0.0070400313,-5.9840918,-9.86718,-12.518258,1.5325005,-1.3825929,29.757889,170000
36
+ 147.23642,0.73520535,0.0048980797,-5.1672006,-9.424698,-11.873857,0.6181532,-0.43923065,14.870267,175000
37
+ 184.99069,0.8377043,0.0068714186,-6.284908,-10.619687,-12.697,0.86049676,-1.1124601,29.691668,180000
38
+ 186.18927,0.8917222,0.0073007243,-6.1163216,-10.245134,-12.548261,0.63243675,-0.6858512,22.231926,185000
39
+ 154.56012,0.6357683,0.0051734694,-5.7099385,-10.014136,-11.901202,0.23764512,-0.45176584,13.292719,190000
40
+ 180.73785,0.68016243,0.012493915,-0.9951538,-10.362998,-12.298567,0.9150623,-0.90026075,18.608864,195000
41
+ 156.42769,0.5406083,0.010871454,-5.8657765,-9.732379,-11.414106,0.397828,-0.39343232,12.373599,200000
42
+ 152.36058,0.49819213,0.005135508,0.057051223,-9.683318,-11.928336,0.3891266,-0.5880272,12.382881,205000
43
+ 176.5956,1.233313,0.0886744,0.030248398,-10.276095,-12.24151,1.4537107,-0.9282865,27.778149,210000
44
+ 171.83875,0.6165701,0.0047560353,-6.6465607,-10.211658,-11.7662115,29.696215,-35.018837,756.26196,215000
45
+ 172.62009,0.5326878,0.0056853434,-6.3995667,-9.920001,-11.237148,1.4372627,-1.9915679,36.506958,220000
46
+ 180.23538,0.7710255,0.008310602,-3.476914,-10.357593,-12.103698,6.9449167,-7.6728425,159.01233,225000
47
+ 202.35654,0.623536,0.009664548,-6.979976,-10.461497,-12.90311,11.982425,-8.520266,156.19504,230000
48
+ 175.02467,0.6973921,0.0036484413,0.0076236203,-10.044597,-11.81559,0.7345868,-0.69639295,19.903526,235000
49
+ 159.80554,0.45775026,0.0028468906,-5.9971485,-9.490813,-11.290129,0.5715412,-0.9018302,16.476353,240000
50
+ 184.23578,0.5587944,0.009563318,0.13283505,-10.344081,-11.88073,6.039843,-2.1321886,62.000935,245000
51
+ 168.88107,0.55373216,0.004218418,0.0033928268,-9.85,-11.579831,0.58938223,-0.7112811,18.301609,250000
52
+ 174.77882,0.65609026,0.009677075,-1.1929206,-10.334462,-11.97413,0.5018153,-0.74498504,19.259005,255000
53
+ 173.60304,0.49550164,0.057665315,0.10255623,-10.086104,-11.614705,0.3608111,-0.4714548,13.10187,260000
54
+ 136.54364,0.5671709,0.008569359,-5.9952245,-9.09184,-12.173267,1.4218653,-0.97921336,27.070915,265000
55
+ 139.4128,0.5666815,0.012221262,-5.5877914,-9.168882,-10.698305,1.565213,-0.6527165,20.274372,270000
56
+ 73.506836,1.5203199,0.022285668,-0.041955203,-7.3469806,-10.391327,1.5978192,-2.9922307,57.787,275000
57
+ 27.610998,1.164614,0.0813962,-0.73090935,-5.7764406,-10.222955,19.017183,-25.999504,431.45224,280000
58
+ 27.119595,1.7720478,0.05192901,-1.8413001,-6.025726,-8.573721,2.4190083,-2.13683,93.0442,285000
59
+ -24.250008,0.9256677,0.026316432,0.07454488,-4.581825,-6.554636,6.6779447,-4.2472944,100.121895,290000
60
+ -20.390938,1.0758183,0.08658199,-0.30989328,-4.6150365,-8.377782,3.0551453,-2.4962025,90.346565,295000
61
+ -16.498161,1.0658042,0.08656137,-0.689571,-4.4234138,-5.9728603,11.717666,-3.7967443,135.73987,300000
62
+ -0.047030687,1.2047861,0.044864323,-0.39579377,-5.062504,-6.5723853,2.733867,-2.6383915,78.87053,305000
63
+ 24.66842,1.4339141,0.06812545,-0.9453143,-5.464335,-7.460776,2.0010555,-3.970329,80.23044,310000
64
+ 57.08395,1.3478177,0.0354898,-2.31592,-6.566472,-9.228335,9.791229,-17.89048,299.3511,315000
65
+ 58.49007,1.1661675,0.01992266,-2.5944738,-6.707392,-8.113166,2.1919036,-2.5281394,63.051888,320000
66
+ 69.478546,1.2611003,0.17228793,-2.3905365,-7.001909,-8.56084,1.982811,-2.5924883,45.643345,325000
67
+ 75.473854,1.0591515,0.08216702,-3.4974403,-7.3666534,-11.31629,3.68392,-2.6599655,87.13903,330000
68
+ 110.46114,1.4645935,0.12601873,-3.56268,-8.153046,-11.584335,21.62598,-14.213672,384.37286,335000
69
+ 91.60313,1.8728783,0.09997296,-3.9194705,-8.132472,-12.728758,6.5907674,-9.217577,179.51366,340000
70
+ 211.90898,1.414748,0.043297052,-7.373649,-11.981903,-13.901321,1.0951144,-2.6829927,57.395164,345000
71
+ 208.48094,1.1299424,0.018726656,-4.0145817,-11.060076,-12.524351,12.127836,-8.864377,279.26437,350000
72
+ 221.60168,1.1644491,0.014549148,-0.0050899535,-11.537845,-13.006124,2.1182814,-1.2011932,50.34645,355000
73
+ 215.62025,1.1093724,0.004584368,0.05094079,-11.169886,-12.417098,0.6071902,-0.8657836,20.528473,360000
74
+ 206.59,0.9738325,0.005425067,-7.554754,-11.105297,-12.592365,7.8277483,-7.3123894,175.32286,365000
75
+ 213.94098,1.2283733,0.010730761,-7.2370524,-11.006741,-12.552486,5.476246,-5.042404,149.02681,370000
76
+ 210.41824,0.95193356,0.0035069976,0.055936135,-11.169073,-12.831029,1.7588912,-1.2388307,38.12802,375000
77
+ 213.70322,0.8525344,0.0031381361,0.105486095,-11.266881,-12.773999,0.7533164,-0.91353565,22.277761,380000
78
+ 215.11736,1.0553427,0.007866616,0.011463873,-11.532251,-12.928121,5.2694488,-2.1667113,81.99637,385000
79
+ 237.22566,0.8842304,0.006482017,-0.103045255,-11.917172,-13.335782,2.0951173,-1.401049,44.060745,390000
80
+ 233.98857,0.71717215,0.017359486,-8.196595,-11.995303,-13.359088,1.2928038,-1.1294444,38.26495,395000
81
+ 238.44266,0.7928901,0.007885563,-8.128179,-11.85877,-13.3147135,1.501866,-0.9583614,37.949493,400000
82
+ 211.88934,0.80187213,0.004741084,0.01992917,-11.228943,-13.056675,1.1704112,-1.3005038,21.36833,405000
83
+ 211.7375,0.89388704,0.007929701,-7.670909,-11.083677,-12.572074,4.565221,-6.765282,79.005066,410000
84
+ 192.21846,0.63190866,0.005588516,-5.315523,-10.850759,-12.966919,2.864249,-3.0567997,43.89519,415000
85
+ 195.34225,0.8523417,0.0098504415,0.0032592192,-10.949989,-13.431428,2.0617378,-2.7542126,74.80307,420000
86
+ 199.7156,0.6708907,0.004021997,-7.653793,-11.066687,-13.093355,0.87798667,-0.9251644,25.516647,425000
87
+ 215.35156,0.71747744,0.0102904355,0.021511368,-11.340289,-13.115202,2.8484344,-4.7299557,105.980606,430000
88
+ 192.69046,0.63387483,0.005113227,-5.08247,-10.783861,-12.5175295,2.9629915,-1.9673165,67.071175,435000
89
+ 208.60841,0.90665257,0.017423494,-7.2842484,-11.183729,-12.988056,5.0020337,-6.51118,150.71396,440000
90
+ 218.52675,0.8288194,0.007495126,-6.655109,-11.334962,-13.001268,2.518001,-1.8602883,60.701496,445000
91
+ 225.07568,0.69063586,0.006955631,0.05613912,-11.636001,-13.33348,13.133558,-10.574776,257.45673,450000
92
+ 217.40187,0.6404463,0.011749755,-2.127318,-11.453603,-13.901229,1.4360842,-1.7082162,55.20945,455000
93
+ 202.99985,0.65999436,0.0031550515,0.02704294,-11.221381,-12.8883705,0.6328006,-0.7153525,16.789566,460000
94
+ 214.28242,0.8867419,0.0139531,0.035153106,-11.070575,-13.339414,18.443316,-8.996445,257.6384,465000
95
+ 197.9649,0.76693296,0.005533337,-6.346168,-10.925061,-12.320607,0.59411484,-0.61756104,19.539333,470000
96
+ 199.45576,0.6775925,0.009561367,-7.513925,-10.935489,-12.862441,0.9523526,-1.0466505,26.872606,475000
97
+ 199.05783,0.7469679,0.008026304,0.022514641,-10.766509,-13.716872,3.540686,-3.6398883,56.827557,480000
98
+ 200.30525,0.66554445,0.0063802856,-5.893139,-11.086493,-12.873415,0.47971138,-0.6317102,17.260618,485000
99
+ 197.07825,1.4026778,0.04568133,-5.924671,-11.036446,-12.936545,1.7228224,-2.2833483,47.612183,490000
100
+ 205.64381,0.8085821,0.013491252,0.024972692,-11.316556,-13.949462,1.8906177,-3.0216806,63.66906,495000
101
+ 201.03307,0.7573624,0.0078037814,-1.7929673,-11.253169,-13.242756,2.0700467,-1.5821402,31.275772,500000
102
+ 205.29408,0.69858223,0.00864162,0.011836991,-10.962378,-13.552504,4.2857895,-2.9071712,47.65284,505000
103
+ 189.26315,0.65446043,0.005856201,-4.953302,-10.748583,-12.580163,1.1588482,-0.46027625,18.971464,510000
104
+ 199.99274,0.8755962,0.008739637,0.024793148,-11.060859,-13.021262,3.6464746,-2.1391551,38.364,515000
105
+ 199.15683,0.8458472,0.013137877,-3.432985,-10.886833,-12.627244,18.443462,-27.306824,522.83264,520000
106
+ 198.07205,0.66033626,0.010442236,-5.821268,-10.699913,-12.617825,1.3565396,-1.2408725,26.831606,525000
107
+ 193.80913,0.8654448,0.010114345,-3.5329723,-10.776813,-14.23219,2.3342757,-1.8234711,39.768982,530000
108
+ 212.67322,0.750793,0.007190569,-7.537203,-11.322237,-13.011983,5.362142,-3.772499,120.79729,535000
109
+ 201.73788,0.97427344,0.0067597083,-0.004365988,-11.128127,-13.233689,5.0091457,-4.6086235,118.67913,540000
110
+ 208.4705,0.89630526,0.0052684015,-7.7038007,-11.345445,-13.276874,1.351526,-2.5186977,31.951614,545000
111
+ 192.42352,1.3909832,0.0071910876,0.04466384,-10.502213,-12.396893,5.1357064,-12.9438505,90.20901,550000
112
+ 199.24362,0.7396743,0.041225906,-0.008153304,-10.992693,-12.947602,3.2429924,-2.8453827,50.65879,555000
113
+ 190.999,1.0895543,0.00899827,0.017479941,-10.715345,-12.77164,3.228522,-2.5635235,58.714333,560000
114
+ 205.28993,1.1392655,0.016544115,-5.948024,-11.013614,-13.270636,4.092912,-3.3292437,104.85714,565000
115
+ 184.51982,0.5839455,0.0068534003,-6.7679415,-10.820575,-13.114037,2.5571058,-2.320312,38.4329,570000
116
+ 194.69737,0.6002811,0.0074726716,-0.0005687773,-10.678622,-12.779314,1.5245283,-1.0189446,44.432365,575000
117
+ 180.62967,0.62724495,0.0060045007,-0.018892206,-10.5710745,-12.905037,3.412776,-4.96128,51.68074,580000
118
+ 186.6097,0.9761743,0.012354504,-7.092346,-10.689708,-12.655322,2.509359,-1.8400003,34.674034,585000
119
+ 216.51566,0.90657306,0.022195611,0.05933933,-11.271781,-13.353215,1.0502617,-1.4664959,43.597816,590000
120
+ 187.5083,0.7601985,0.006861482,-7.111467,-10.7301235,-12.808155,2.5008154,-2.2187479,59.74694,595000
121
+ 198.58205,1.1081961,0.009154725,-7.441075,-11.071409,-13.5168295,1.9160861,-2.5242753,42.073593,600000
122
+ 182.52695,1.1814872,0.0194632,-5.7325964,-10.616381,-12.283111,24.408352,-16.832317,338.05112,605000
123
+ 188.85478,1.4203398,0.018550072,0.020809203,-10.617108,-12.673668,5.6193466,-10.209971,73.19488,610000
124
+ 194.14534,1.4979796,0.015984317,0.00907556,-10.788032,-13.375117,8.384966,-3.2532437,101.55147,615000
125
+ 198.1388,2.0399199,0.011202614,-7.221266,-10.770899,-12.796106,18.75011,-12.728847,283.78595,620000
126
+ 170.3313,1.3425679,0.013039765,-6.247782,-10.54351,-12.792758,8.937038,-11.176909,144.65947,625000
127
+ 197.189,1.7160742,0.036828686,-7.038501,-10.748151,-14.002533,6.7187986,-5.773487,156.8884,630000
128
+ 189.88075,2.0345006,0.019515334,-1.0554963,-10.742221,-13.163227,2.5600157,-4.291641,55.68494,635000
129
+ 188.34203,1.4360673,0.039337553,0.0013011694,-10.575513,-13.885921,16.966856,-14.503444,343.33994,640000
130
+ 189.40709,1.470617,0.037900817,-6.8219676,-10.684285,-13.080578,16.432156,-15.431147,182.5173,645000
131
+ 193.7361,1.3208907,0.021411037,-6.666478,-11.089271,-13.101841,9.781766,-8.872849,265.74576,650000
132
+ 200.03204,1.124224,0.011840192,-0.011641458,-11.083973,-13.581591,3.9326005,-4.914676,94.37413,655000
133
+ 198.36665,1.4689442,0.015040408,-7.02979,-11.023513,-13.589393,4.4939885,-6.1339555,122.75721,660000
134
+ 189.2383,1.3301929,0.012106139,0.023183845,-10.684618,-12.868712,3.764313,-6.537224,79.82384,665000
135
+ 188.52112,1.3359643,0.021334773,-6.597535,-10.853563,-12.287484,43.53568,-36.12303,518.574,670000
136
+ 197.32498,1.5682092,0.012269169,-7.2822394,-10.9973135,-13.337255,3.2160335,-5.2021604,80.79311,675000
137
+ 242.0768,1.6442896,1.4597682,-7.972533,-11.938829,-14.743447,479.07193,-143.57515,2448.211,680000
138
+ 192.20479,4.2627954,0.01684489,-6.9537897,-10.9061575,-13.534724,3.583988,-6.1020117,60.988323,685000
139
+ 196.50528,2.338691,0.037958905,-6.714103,-10.665697,-13.97715,7.3457546,-6.4295087,104.923164,690000
140
+ 194.09094,1.2467796,0.022775048,-7.0211787,-10.990569,-13.121513,3.6002693,-2.909643,82.87614,695000
141
+ 202.46373,1.5707906,0.017545218,0.031058699,-11.120327,-13.367716,31.172045,-20.007544,515.8703,700000
142
+ 191.42506,1.5027047,0.013783053,-0.00077488273,-11.084956,-13.483303,24.210182,-21.366861,357.74634,705000
143
+ 203.61081,1.7529469,0.021410687,0.018154293,-11.009882,-14.3310585,23.794973,-37.111908,306.36246,710000
144
+ 206.81778,1.4256402,0.030081138,0.031228855,-11.369922,-13.803764,5.162131,-4.334801,94.90725,715000
145
+ 200.0148,1.7125189,0.026379868,-6.422077,-11.40961,-13.96098,15.964751,-23.447302,239.48221,720000
146
+ 222.3844,1.4225386,0.021408772,-6.988091,-11.569625,-14.0765085,10.745068,-12.954043,162.99841,725000
147
+ 191.74806,1.7673517,0.042892266,-7.037634,-10.913546,-13.8408575,10.549533,-7.4445767,188.81169,730000
148
+ 197.4984,1.4084713,0.035166238,0.030241095,-11.023781,-13.665001,6.5388722,-5.5252156,129.47589,735000
149
+ 190.19856,1.2713728,0.015991947,0.0409019,-11.099059,-13.444808,96.00442,-46.672703,1045.2566,740000
150
+ 200.88239,1.4821968,0.022020241,0.07781039,-10.927348,-13.950287,7.0081577,-6.4124856,82.1679,745000
151
+ 222.26498,1.2309402,0.018131454,-6.316382,-11.734271,-14.964303,27.449635,-30.084845,525.82275,750000
152
+ 203.80072,1.3881333,0.018328685,0.03756243,-11.334749,-13.825222,15.13458,-15.341155,221.90392,755000
153
+ 219.65132,1.4201286,0.022070503,0.033253096,-11.793981,-14.783182,25.81133,-8.309686,205.87926,760000
154
+ 214.70154,1.5836687,0.022096535,-6.724631,-11.505874,-13.853908,5.542424,-3.4759905,70.84784,765000
155
+ 172.85913,1.2062778,0.029745394,-4.67491,-10.220461,-14.000096,8.677071,-6.160147,140.10701,770000
156
+ 201.87961,2.1989145,0.055458665,0.058291145,-11.257005,-13.947921,6.1387253,-12.769777,142.79472,775000
157
+ 192.26234,1.4259051,0.085765995,0.07751897,-11.080465,-14.486042,11.505795,-5.548475,106.17093,780000
158
+ 212.00244,2.0602279,0.04200792,0.037065692,-11.661597,-15.079687,24.743269,-50.488342,346.32254,785000
159
+ 243.4657,4.490334,0.051029366,-7.236849,-12.360759,-15.700742,17.54191,-21.103096,317.5962,790000
160
+ 220.95827,2.407246,0.07104465,0.056262143,-11.984148,-14.943441,31.913532,-49.533962,325.21198,795000
161
+ 275.09357,1.8869115,0.0448244,-8.386266,-13.438075,-17.959435,41.08885,-51.35861,499.89056,800000
162
+ 263.66953,1.5353518,0.093992606,-6.2147527,-12.998224,-15.570791,7.0810947,-10.821331,151.98586,805000
163
+ 308.09375,1.9242167,0.08933017,-1.365655,-14.380266,-17.87531,97.613,-100.33113,1148.0574,810000
164
+ 269.2795,1.7303134,0.05282515,-0.5588143,-13.242022,-16.183687,8.579805,-11.124335,213.8691,815000
165
+ 265.06476,1.6052005,0.08327566,-7.579838,-13.343506,-16.330303,9.360092,-6.7537756,140.80104,820000
166
+ 245.95258,1.500428,0.052007973,0.027723767,-12.543301,-15.41915,9.939583,-5.5971117,109.94406,825000
167
+ 246.31494,1.322434,0.069725476,-6.4229865,-12.405265,-15.907201,20.11101,-13.712716,359.60925,830000
168
+ 276.75623,1.4626575,0.042977553,-7.458625,-13.450587,-16.46357,22.16989,-20.805382,453.90485,835000
169
+ 288.70984,1.7469188,0.064233325,0.009323992,-13.317113,-15.5145645,12.806019,-9.176534,192.66711,840000
170
+ 271.47223,1.545115,0.04228407,-8.944012,-13.140963,-16.132929,7.428825,-9.793985,148.91655,845000
171
+ 282.80096,2.183484,0.041012865,-7.4237275,-13.871803,-16.153658,106.01917,-71.691635,609.907,850000
172
+ 289.32956,1.4032918,0.046862382,-3.6966228,-13.639084,-17.59472,11.417584,-16.988056,213.29395,855000
173
+ 299.52448,1.3223305,0.03694533,-8.008354,-13.743215,-16.627932,19.286436,-13.764557,189.76921,860000
174
+ 247.2939,1.783133,0.029351035,0.026756957,-12.576957,-14.97369,5.7099786,-6.119499,97.46098,865000
175
+ 277.36703,1.5912209,0.0695404,-6.614139,-13.019725,-15.305579,6.599827,-6.271028,112.81113,870000
176
+ 277.11496,1.6618536,0.03585663,-6.641693,-13.0950165,-16.107935,23.351604,-45.563564,711.2619,875000
177
+ 257.63733,1.5431423,0.021205448,-6.3843503,-12.569222,-15.032173,7.0079203,-22.216766,137.71234,880000
178
+ 279.86694,1.2823074,0.02003256,-7.081502,-13.545204,-16.064669,2.8603032,-3.1760616,65.754906,885000
179
+ 250.44417,1.3455927,0.018892666,-7.053501,-12.718535,-14.812448,16.549242,-26.789013,373.0989,890000
180
+ 246.92097,1.3430495,0.0277967,-7.2992864,-12.630766,-16.023773,8.900286,-10.251784,169.62172,895000
181
+ 267.66086,1.5184999,0.038148075,-8.146446,-12.616608,-14.128539,10.434516,-8.716731,163.85172,900000
182
+ 257.7609,1.2643542,0.029745674,0.035446733,-12.615993,-16.840384,5.4592714,-9.862244,143.22153,905000
183
+ 215.96512,1.3704925,0.030778388,-5.1163855,-11.650451,-14.847259,6.328729,-4.6861353,100.42914,910000
184
+ 285.5748,1.7026066,0.049104545,0.039148755,-13.531334,-17.043278,12.366107,-10.714995,176.56493,915000
185
+ 271.59805,1.3660213,0.0462795,-6.045883,-13.168204,-16.115929,12.506211,-12.228162,186.9886,920000
186
+ 305.44843,1.3056338,0.0419331,-7.583145,-14.150275,-16.595417,4.113972,-4.954016,107.29399,925000
187
+ 250.91188,1.390064,0.055753674,-7.0336504,-12.760958,-15.307984,32.692642,-23.429476,658.1247,930000
188
+ 270.3161,1.6092503,0.07440764,-7.786128,-13.3153105,-15.526725,14.559508,-26.553371,295.21173,935000
189
+ 261.01526,1.4734774,0.030369094,0.0060186684,-12.906596,-15.6644,8.5740795,-4.8147,112.7963,940000
190
+ 289.14688,1.4108858,0.080184914,0.06460111,-13.593305,-17.208773,15.085419,-11.3698225,232.76971,945000
191
+ 258.2949,1.6135311,0.054134514,-2.7913342,-12.883468,-15.575268,4.272125,-5.820419,80.85396,950000
192
+ 244.87793,1.6436162,0.025013184,0.018937454,-12.426517,-15.08207,13.445557,-13.693498,279.09723,955000
193
+ 246.98149,1.654991,0.06906513,-6.781169,-12.584383,-15.099474,7.827051,-5.7928023,99.09427,960000
194
+ 279.04532,1.6197821,0.039446075,-7.5325694,-13.382105,-15.902283,7.273182,-6.2351856,113.15384,965000
195
+ 273.44766,1.9966375,0.038399324,-3.775235,-13.383623,-16.461988,9.054448,-15.359602,125.392494,970000
196
+ 296.40762,1.7318474,0.07263531,0.0441747,-13.94104,-16.226702,12.145797,-13.230019,166.11374,975000
197
+ 267.5152,1.504002,0.03072446,-7.4600177,-13.116385,-15.22835,11.200559,-12.346513,146.93323,980000
198
+ 278.94644,1.4178462,0.020468755,-7.0365868,-13.115705,-15.335801,4.6417994,-5.4535804,104.737465,985000
199
+ 277.83508,1.3095802,0.03285223,-7.3419785,-13.357108,-15.296889,10.744811,-14.494225,223.08542,990000
200
+ 263.14355,2.0278478,0.049776845,-6.4662156,-12.709213,-14.746011,12.505573,-7.650782,158.32571,995000
201
+ 276.64157,1.5671933,0.041638564,0.04320173,-13.081848,-16.972008,21.746265,-11.967512,274.17526,1000000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 267.68866,1.4088535,0.03931066,-6.9038725,-13.392489,-15.533377,7.8855624,-7.5010567,135.29652,1005000
3
+ 1112.3322,1.984475,10.742353,0.41276073,-42.14535,-59.79415,55.71938,-62.330772,958.20703,1010000
4
+ 1715.2013,1.5903562,3.5095162,0.4605354,-53.385353,-68.212074,89.19365,-81.504814,1392.0804,1015000
5
+ 1545.8058,2.2092047,4.8227134,-1.9068984,-48.91058,-78.1931,110.186,-116.26901,1977.3127,1020000
6
+ 1399.7871,1.4221535,2.6521769,-10.066313,-46.225586,-82.51231,68.17937,-49.955185,993.28174,1025000
7
+ 1279.9465,1.8441339,1.0928452,-12.253825,-42.339985,-77.353004,52.30184,-53.00834,871.9143,1030000
8
+ 1351.1782,2.4236808,0.90655243,-3.3353026,-43.613876,-79.39681,78.39344,-55.824833,1037.2725,1035000
9
+ 1351.8593,1.2882159,0.8226742,-14.620143,-43.874012,-76.03303,28.736454,-40.385326,689.8349,1040000
10
+ 1361.9901,1.5720296,0.78135604,0.2649409,-44.461933,-77.68661,39.443275,-36.79028,771.50867,1045000
11
+ 1423.3855,1.6008321,0.75225306,-11.17995,-45.94403,-72.16529,44.890846,-56.67198,856.28284,1050000
12
+ 1443.7227,1.5126578,0.8641836,-8.018409,-46.841194,-77.09378,14.771598,-27.549463,453.5498,1055000
13
+ 1499.1228,1.888588,0.96301156,0.13840298,-47.865833,-77.26242,197.99901,-93.53446,2956.6328,1060000
14
+ 1632.9812,1.5505105,2.5249832,-12.656214,-50.814888,-77.67004,61.2485,-66.74157,1292.2936,1065000
15
+ 1680.4874,1.7280169,1.5229267,-14.514323,-53.347595,-80.39926,41.369457,-37.111515,871.34216,1070000
16
+ 1615.9247,1.4858844,1.3429966,-9.717057,-51.08008,-79.767365,33.873405,-54.52906,950.13715,1075000
17
+ 1626.6082,1.6617403,1.3028336,-1.3534408,-51.722534,-83.007034,69.05535,-57.94984,1139.5002,1080000
18
+ 1628.897,1.6588995,0.8593742,-12.528567,-51.622395,-81.97237,110.84701,-74.73213,1347.9208,1085000
19
+ 1778.1377,1.4682983,0.8992745,-10.865739,-56.307888,-82.98716,751.31104,-874.9646,9702.466,1090000
20
+ 1705.2139,1.6409278,2.3709774,-16.111637,-53.44712,-83.40457,108.51762,-81.402565,1537.5283,1095000
21
+ 1816.0396,1.4261129,1.1480669,-9.399056,-57.34042,-83.30008,37.78412,-72.212364,1093.7533,1100000
22
+ 1616.158,1.3777504,1.2069961,-1.4958088,-51.92104,-83.45945,29.884058,-28.966272,599.5887,1105000
23
+ 1466.327,2.0823355,0.7782973,0.08161016,-47.24676,-78.2598,24.057533,-17.337423,424.30316,1110000
24
+ 1345.7612,1.7703071,1.0122242,-11.447843,-43.505592,-72.43661,41.204647,-23.638586,576.2456,1115000
25
+ 1304.4719,1.5335093,1.5310543,-3.0083501,-42.56012,-73.60587,43.443466,-87.00511,1089.2518,1120000
26
+ 1299.6656,1.762334,0.86777097,-8.549863,-42.373577,-66.632805,46.348507,-55.871597,862.3503,1125000
27
+ 1279.5211,1.7405804,0.7955356,0.18201177,-41.665863,-69.98425,598.6476,-687.40173,9029.373,1130000
28
+ 1289.4403,1.5113071,0.9300028,-12.5879135,-42.18419,-67.40251,60.47645,-110.379456,1703.8925,1135000
29
+ 1293.4578,1.6645868,1.3353149,-8.672985,-42.129436,-70.14176,17.084726,-20.654804,363.91336,1140000
30
+ 1286.974,1.7784851,1.0855192,0.19049403,-41.975468,-66.71396,24.96079,-47.3837,576.4783,1145000
31
+ 1319.4684,1.4983282,1.0615162,-9.636896,-43.060627,-71.9817,122.46675,-130.6209,2244.659,1150000
32
+ 1265.1582,1.3862095,0.8215707,0.12342571,-41.127716,-67.290596,57.936237,-110.21466,1518.064,1155000
33
+ 1251.5525,1.4343393,0.83452934,0.048267335,-40.992306,-66.94525,22.33871,-18.454924,443.2627,1160000
34
+ 1237.1354,1.7087436,0.65222067,-9.088323,-40.457886,-71.33321,21.280493,-18.701065,469.01385,1165000
35
+ 1216.2067,1.7223518,0.5282306,-8.488932,-40.243904,-65.59868,56.015026,-33.444843,856.48755,1170000
36
+ 1157.7,2.1678822,0.59743017,-7.2374935,-38.265087,-66.4953,62.35377,-98.422745,1914.8926,1175000
37
+ 1262.2103,1.6522536,0.47672454,-8.731358,-40.763393,-67.34456,386.4156,-603.8318,8877.757,1180000
38
+ 1134.7732,1.5606987,0.84955806,0.10125837,-37.65989,-65.56664,79.48327,-41.97281,604.95337,1185000
39
+ 1246.2874,1.9047253,0.76601666,-4.1464605,-40.39286,-60.26588,76.96265,-62.443645,910.8077,1190000
40
+ 1201.1742,1.7441663,0.9834858,0.11679183,-39.414482,-67.01651,25.082905,-29.861097,522.0871,1195000
41
+ 1132.1952,2.1799216,0.59045506,-4.076939,-37.50172,-67.10253,17.275702,-27.554323,372.71222,1200000
42
+ 1133.4022,2.337708,0.53230953,-8.7419195,-37.39731,-65.72711,139.27545,-163.49234,2307.3547,1205000
43
+ 1191.8982,2.1275148,1.1485914,-4.185615,-39.196857,-64.50581,33.160294,-29.220823,485.1326,1210000
44
+ 1099.1879,1.5225437,0.61688894,0.13713586,-36.243286,-66.688255,83.581566,-103.4112,1632.4791,1215000
45
+ 1096.2028,1.3176053,0.49507275,-8.017102,-36.4039,-61.908253,66.809296,-43.879528,882.56836,1220000
46
+ 1134.9069,1.8215057,0.5515834,0.16329394,-37.295734,-63.74407,25.747894,-35.220882,650.5691,1225000
47
+ 1062.2971,2.2437077,0.35260937,-5.366328,-35.58605,-61.949997,10.816052,-21.373169,287.51437,1230000
48
+ 1088.4963,1.6123674,0.6017415,-8.040646,-36.246273,-62.801094,21.359034,-17.860128,433.26913,1235000
49
+ 1105.1843,2.169574,0.7880024,0.15789719,-36.57005,-55.85452,17.738949,-18.830717,351.38147,1240000
50
+ 1014.55756,1.6286772,0.7496149,-8.041414,-34.0442,-61.15982,64.62798,-51.074207,1037.2422,1245000
51
+ 1062.6317,1.7488,0.6586797,-6.868817,-35.59154,-61.463604,14.950943,-15.30704,337.07446,1250000
52
+ 1021.0381,1.9508193,0.524615,-7.623377,-34.035034,-60.42178,29.652773,-41.944572,768.6366,1255000
53
+ 1042.9147,1.8219255,0.589209,-4.170612,-34.76184,-61.59908,65.564575,-97.74245,1055.358,1260000
54
+ 1064.6616,1.7785683,0.6775779,-8.374534,-35.48404,-63.42629,245.08138,-176.48752,3901.6006,1265000
55
+ 1022.0283,1.5939684,0.51441544,-8.011361,-34.069534,-61.259087,17.442753,-15.442152,392.15723,1270000
56
+ 1046.9692,1.8973331,0.44753033,-4.093784,-34.844185,-62.976685,38.25728,-59.16902,983.1293,1275000
57
+ 1005.1585,3.4101725,0.6126125,-6.9530654,-33.563934,-62.26867,30.53552,-56.245,667.795,1280000
58
+ 992.0208,1.8304389,0.5197272,-3.9432771,-33.12934,-54.467266,15.399989,-12.620692,311.48993,1285000
59
+ 1019.02484,1.6473945,0.5097627,-3.4628353,-34.280613,-61.320107,39.080883,-36.313705,637.80035,1290000
60
+ 1000.0847,1.3804036,0.53485787,-3.4230027,-33.47364,-55.75906,14.579895,-22.705143,351.68405,1295000
61
+ 1055.3236,1.570911,0.41076985,0.10180658,-35.225502,-58.050465,32.00715,-31.83492,602.17456,1300000
62
+ 977.0629,1.6474469,0.36713377,0.12735263,-33.071026,-58.77141,11.556188,-11.334629,252.74693,1305000
63
+ 1004.4386,1.4042209,0.40256625,0.10607278,-33.251087,-59.400726,21.952833,-28.388336,483.1765,1310000
64
+ 973.13715,2.2797143,0.5686254,0.24148414,-32.81665,-60.703125,157.13669,-180.11693,2096.3845,1315000
65
+ 1019.5919,2.1334767,0.45943522,-3.9889195,-33.93997,-58.1032,31.277973,-41.853043,694.9395,1320000
66
+ 980.74396,2.019571,0.72115487,0.13752578,-33.168427,-57.595108,23.592466,-27.177952,446.56128,1325000
67
+ 947.28937,1.8670952,0.48287374,-3.490411,-32.070557,-58.876225,11.970242,-16.344648,316.18823,1330000
68
+ 1009.1186,1.5634699,0.53077215,-7.059696,-33.468056,-56.746777,79.836464,-59.256042,1296.6663,1335000
69
+ 976.69324,1.8579994,0.5473419,-3.6507556,-32.66158,-59.171265,61.352154,-85.86398,1064.6143,1340000
70
+ 966.873,1.3797152,0.7942819,-5.2744145,-32.507767,-51.44307,33.89161,-40.156902,695.81274,1345000
71
+ 958.8593,1.7312464,0.5962896,-3.2036493,-32.3607,-59.61998,22.461092,-12.394116,320.2329,1350000
72
+ 966.4926,1.6424762,0.5976972,-0.5312719,-32.21387,-49.287575,25.69508,-18.511955,490.4871,1355000
73
+ 931.96716,1.4873109,0.5703177,-3.6446056,-31.628983,-59.422615,23.199131,-44.77473,671.0537,1360000
74
+ 974.30536,1.7824643,0.34377274,-7.6361866,-32.866825,-51.979122,59.418167,-36.560192,967.0204,1365000
75
+ 1054.0168,2.2685337,1.6032265,-5.6338663,-34.066017,-58.0128,132.95032,-179.68718,1482.0166,1370000
76
+ 991.6777,1.9908036,0.47393733,-3.551461,-33.06245,-56.935383,16.996244,-30.385847,451.42566,1375000
77
+ 1022.147,1.5503615,0.7335879,-5.243371,-33.949062,-56.928726,24.945232,-42.41589,537.3681,1380000
78
+ 946.9285,1.3697314,0.69136953,0.12638913,-31.831501,-58.15019,31.951912,-27.96132,537.6957,1385000
79
+ 978.232,1.5960903,0.45921144,-6.7356358,-32.781715,-57.858547,18.535944,-25.387478,323.4632,1390000
80
+ 974.00635,1.6225451,0.3470671,-2.7387297,-32.7626,-56.328526,86.42191,-98.28944,1712.0845,1395000
81
+ 978.3624,1.782857,0.5965244,-5.219137,-32.66504,-51.42003,42.472176,-33.013077,579.2614,1400000
82
+ 935.0318,1.5618505,0.49775657,0.13188517,-31.424103,-57.331596,34.993958,-33.55738,598.2323,1405000
83
+ 977.98615,2.1054888,0.50587076,-3.8492565,-32.876186,-55.53638,164.47426,-198.71548,2248.0852,1410000
84
+ 956.54083,1.9200814,0.359478,-8.436712,-32.076176,-58.982304,166.04228,-129.48111,2010.1477,1415000
85
+ 961.5347,2.1000857,0.3592233,-4.1974864,-32.18301,-49.838825,64.99234,-52.294247,823.8678,1420000
86
+ 945.0291,1.5010263,0.5404995,-3.470895,-31.702887,-54.704685,55.13077,-49.569153,1172.9525,1425000
87
+ 948.204,1.4171557,0.4547492,-7.7275867,-31.732935,-50.87491,21.920708,-20.082417,470.72665,1430000
88
+ 995.37665,1.8593936,0.37440005,0.207879,-33.185993,-57.23715,90.60968,-79.103264,993.97656,1435000
89
+ 938.72076,1.8518388,0.36457843,-1.8668805,-31.680079,-57.715523,42.216473,-31.085176,544.26227,1440000
90
+ 1009.138,2.020258,0.55652905,-3.9808915,-33.366776,-57.075993,26.28008,-27.88968,459.08313,1445000
91
+ 954.4287,1.8483782,0.3915897,-3.8229523,-31.841858,-57.345627,34.293972,-32.270935,530.3979,1450000
92
+ 964.94904,2.6924238,0.36155894,0.086354524,-32.06257,-57.715504,13.612427,-20.147936,379.7895,1455000
93
+ 952.9128,1.3321792,0.3737553,-5.602263,-31.911255,-57.54415,60.04731,-44.5605,695.1691,1460000
94
+ 963.8164,1.7375429,0.53159124,-7.2942657,-32.091866,-57.05253,39.63265,-33.20988,565.0148,1465000
95
+ 983.3326,1.4512699,0.4449893,-2.7516131,-33.036922,-57.5248,39.23619,-31.308935,574.3199,1470000
96
+ 907.6964,1.6896024,0.5687704,-4.0599065,-30.58747,-57.045944,68.21157,-37.409706,480.54306,1475000
97
+ 972.24915,1.8674045,0.33310643,-3.763487,-32.258663,-57.850742,57.25515,-62.93685,892.1237,1480000
98
+ 982.372,1.4361999,0.3381035,-5.207757,-32.8469,-57.105606,43.496696,-85.11271,1013.11743,1485000
99
+ 960.1848,2.1824136,0.7470978,-4.576998,-31.776493,-55.911407,73.197815,-57.997204,1155.5182,1490000
100
+ 952.635,2.7298892,0.31568906,-3.3374836,-31.635544,-54.043365,28.119844,-21.588932,413.9017,1495000
101
+ 929.4487,1.8813431,0.4038535,-4.091554,-30.717823,-55.512394,16.127228,-11.69282,232.17311,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 267.68866,1.4088535,0.03931066,-6.9038725,-13.392489,-15.533377,7.8855624,-7.5010567,135.29652,1005000
3
+ 1112.3322,1.984475,10.742353,0.41276073,-42.14535,-59.79415,55.71938,-62.330772,958.20703,1010000
4
+ 1715.2013,1.5903562,3.5095162,0.4605354,-53.385353,-68.212074,89.19365,-81.504814,1392.0804,1015000
5
+ 1545.8058,2.2092047,4.8227134,-1.9068984,-48.91058,-78.1931,110.186,-116.26901,1977.3127,1020000
6
+ 1399.7871,1.4221535,2.6521769,-10.066313,-46.225586,-82.51231,68.17937,-49.955185,993.28174,1025000
7
+ 1279.9465,1.8441339,1.0928452,-12.253825,-42.339985,-77.353004,52.30184,-53.00834,871.9143,1030000
8
+ 1351.1782,2.4236808,0.90655243,-3.3353026,-43.613876,-79.39681,78.39344,-55.824833,1037.2725,1035000
9
+ 1351.8593,1.2882159,0.8226742,-14.620143,-43.874012,-76.03303,28.736454,-40.385326,689.8349,1040000
10
+ 1361.9901,1.5720296,0.78135604,0.2649409,-44.461933,-77.68661,39.443275,-36.79028,771.50867,1045000
11
+ 1423.3855,1.6008321,0.75225306,-11.17995,-45.94403,-72.16529,44.890846,-56.67198,856.28284,1050000
12
+ 1443.7227,1.5126578,0.8641836,-8.018409,-46.841194,-77.09378,14.771598,-27.549463,453.5498,1055000
13
+ 1499.1228,1.888588,0.96301156,0.13840298,-47.865833,-77.26242,197.99901,-93.53446,2956.6328,1060000
14
+ 1632.9812,1.5505105,2.5249832,-12.656214,-50.814888,-77.67004,61.2485,-66.74157,1292.2936,1065000
15
+ 1680.4874,1.7280169,1.5229267,-14.514323,-53.347595,-80.39926,41.369457,-37.111515,871.34216,1070000
16
+ 1615.9247,1.4858844,1.3429966,-9.717057,-51.08008,-79.767365,33.873405,-54.52906,950.13715,1075000
17
+ 1626.6082,1.6617403,1.3028336,-1.3534408,-51.722534,-83.007034,69.05535,-57.94984,1139.5002,1080000
18
+ 1628.897,1.6588995,0.8593742,-12.528567,-51.622395,-81.97237,110.84701,-74.73213,1347.9208,1085000
19
+ 1778.1377,1.4682983,0.8992745,-10.865739,-56.307888,-82.98716,751.31104,-874.9646,9702.466,1090000
20
+ 1705.2139,1.6409278,2.3709774,-16.111637,-53.44712,-83.40457,108.51762,-81.402565,1537.5283,1095000
21
+ 1816.0396,1.4261129,1.1480669,-9.399056,-57.34042,-83.30008,37.78412,-72.212364,1093.7533,1100000
22
+ 1616.158,1.3777504,1.2069961,-1.4958088,-51.92104,-83.45945,29.884058,-28.966272,599.5887,1105000
23
+ 1466.327,2.0823355,0.7782973,0.08161016,-47.24676,-78.2598,24.057533,-17.337423,424.30316,1110000
24
+ 1345.7612,1.7703071,1.0122242,-11.447843,-43.505592,-72.43661,41.204647,-23.638586,576.2456,1115000
25
+ 1304.4719,1.5335093,1.5310543,-3.0083501,-42.56012,-73.60587,43.443466,-87.00511,1089.2518,1120000
26
+ 1299.6656,1.762334,0.86777097,-8.549863,-42.373577,-66.632805,46.348507,-55.871597,862.3503,1125000
27
+ 1279.5211,1.7405804,0.7955356,0.18201177,-41.665863,-69.98425,598.6476,-687.40173,9029.373,1130000
28
+ 1289.4403,1.5113071,0.9300028,-12.5879135,-42.18419,-67.40251,60.47645,-110.379456,1703.8925,1135000
29
+ 1293.4578,1.6645868,1.3353149,-8.672985,-42.129436,-70.14176,17.084726,-20.654804,363.91336,1140000
30
+ 1286.974,1.7784851,1.0855192,0.19049403,-41.975468,-66.71396,24.96079,-47.3837,576.4783,1145000
31
+ 1319.4684,1.4983282,1.0615162,-9.636896,-43.060627,-71.9817,122.46675,-130.6209,2244.659,1150000
32
+ 1265.1582,1.3862095,0.8215707,0.12342571,-41.127716,-67.290596,57.936237,-110.21466,1518.064,1155000
33
+ 1251.5525,1.4343393,0.83452934,0.048267335,-40.992306,-66.94525,22.33871,-18.454924,443.2627,1160000
34
+ 1237.1354,1.7087436,0.65222067,-9.088323,-40.457886,-71.33321,21.280493,-18.701065,469.01385,1165000
35
+ 1216.2067,1.7223518,0.5282306,-8.488932,-40.243904,-65.59868,56.015026,-33.444843,856.48755,1170000
36
+ 1157.7,2.1678822,0.59743017,-7.2374935,-38.265087,-66.4953,62.35377,-98.422745,1914.8926,1175000
37
+ 1262.2103,1.6522536,0.47672454,-8.731358,-40.763393,-67.34456,386.4156,-603.8318,8877.757,1180000
38
+ 1134.7732,1.5606987,0.84955806,0.10125837,-37.65989,-65.56664,79.48327,-41.97281,604.95337,1185000
39
+ 1246.2874,1.9047253,0.76601666,-4.1464605,-40.39286,-60.26588,76.96265,-62.443645,910.8077,1190000
40
+ 1201.1742,1.7441663,0.9834858,0.11679183,-39.414482,-67.01651,25.082905,-29.861097,522.0871,1195000
41
+ 1132.1952,2.1799216,0.59045506,-4.076939,-37.50172,-67.10253,17.275702,-27.554323,372.71222,1200000
42
+ 1133.4022,2.337708,0.53230953,-8.7419195,-37.39731,-65.72711,139.27545,-163.49234,2307.3547,1205000
43
+ 1191.8982,2.1275148,1.1485914,-4.185615,-39.196857,-64.50581,33.160294,-29.220823,485.1326,1210000
44
+ 1099.1879,1.5225437,0.61688894,0.13713586,-36.243286,-66.688255,83.581566,-103.4112,1632.4791,1215000
45
+ 1096.2028,1.3176053,0.49507275,-8.017102,-36.4039,-61.908253,66.809296,-43.879528,882.56836,1220000
46
+ 1134.9069,1.8215057,0.5515834,0.16329394,-37.295734,-63.74407,25.747894,-35.220882,650.5691,1225000
47
+ 1062.2971,2.2437077,0.35260937,-5.366328,-35.58605,-61.949997,10.816052,-21.373169,287.51437,1230000
48
+ 1088.4963,1.6123674,0.6017415,-8.040646,-36.246273,-62.801094,21.359034,-17.860128,433.26913,1235000
49
+ 1105.1843,2.169574,0.7880024,0.15789719,-36.57005,-55.85452,17.738949,-18.830717,351.38147,1240000
50
+ 1014.55756,1.6286772,0.7496149,-8.041414,-34.0442,-61.15982,64.62798,-51.074207,1037.2422,1245000
51
+ 1062.6317,1.7488,0.6586797,-6.868817,-35.59154,-61.463604,14.950943,-15.30704,337.07446,1250000
52
+ 1021.0381,1.9508193,0.524615,-7.623377,-34.035034,-60.42178,29.652773,-41.944572,768.6366,1255000
53
+ 1042.9147,1.8219255,0.589209,-4.170612,-34.76184,-61.59908,65.564575,-97.74245,1055.358,1260000
54
+ 1064.6616,1.7785683,0.6775779,-8.374534,-35.48404,-63.42629,245.08138,-176.48752,3901.6006,1265000
55
+ 1022.0283,1.5939684,0.51441544,-8.011361,-34.069534,-61.259087,17.442753,-15.442152,392.15723,1270000
56
+ 1046.9692,1.8973331,0.44753033,-4.093784,-34.844185,-62.976685,38.25728,-59.16902,983.1293,1275000
57
+ 1005.1585,3.4101725,0.6126125,-6.9530654,-33.563934,-62.26867,30.53552,-56.245,667.795,1280000
58
+ 992.0208,1.8304389,0.5197272,-3.9432771,-33.12934,-54.467266,15.399989,-12.620692,311.48993,1285000
59
+ 1019.02484,1.6473945,0.5097627,-3.4628353,-34.280613,-61.320107,39.080883,-36.313705,637.80035,1290000
60
+ 1000.0847,1.3804036,0.53485787,-3.4230027,-33.47364,-55.75906,14.579895,-22.705143,351.68405,1295000
61
+ 1055.3236,1.570911,0.41076985,0.10180658,-35.225502,-58.050465,32.00715,-31.83492,602.17456,1300000
62
+ 977.0629,1.6474469,0.36713377,0.12735263,-33.071026,-58.77141,11.556188,-11.334629,252.74693,1305000
63
+ 1004.4386,1.4042209,0.40256625,0.10607278,-33.251087,-59.400726,21.952833,-28.388336,483.1765,1310000
64
+ 973.13715,2.2797143,0.5686254,0.24148414,-32.81665,-60.703125,157.13669,-180.11693,2096.3845,1315000
65
+ 1019.5919,2.1334767,0.45943522,-3.9889195,-33.93997,-58.1032,31.277973,-41.853043,694.9395,1320000
66
+ 980.74396,2.019571,0.72115487,0.13752578,-33.168427,-57.595108,23.592466,-27.177952,446.56128,1325000
67
+ 947.28937,1.8670952,0.48287374,-3.490411,-32.070557,-58.876225,11.970242,-16.344648,316.18823,1330000
68
+ 1009.1186,1.5634699,0.53077215,-7.059696,-33.468056,-56.746777,79.836464,-59.256042,1296.6663,1335000
69
+ 976.69324,1.8579994,0.5473419,-3.6507556,-32.66158,-59.171265,61.352154,-85.86398,1064.6143,1340000
70
+ 966.873,1.3797152,0.7942819,-5.2744145,-32.507767,-51.44307,33.89161,-40.156902,695.81274,1345000
71
+ 958.8593,1.7312464,0.5962896,-3.2036493,-32.3607,-59.61998,22.461092,-12.394116,320.2329,1350000
72
+ 966.4926,1.6424762,0.5976972,-0.5312719,-32.21387,-49.287575,25.69508,-18.511955,490.4871,1355000
73
+ 931.96716,1.4873109,0.5703177,-3.6446056,-31.628983,-59.422615,23.199131,-44.77473,671.0537,1360000
74
+ 974.30536,1.7824643,0.34377274,-7.6361866,-32.866825,-51.979122,59.418167,-36.560192,967.0204,1365000
75
+ 1054.0168,2.2685337,1.6032265,-5.6338663,-34.066017,-58.0128,132.95032,-179.68718,1482.0166,1370000
76
+ 991.6777,1.9908036,0.47393733,-3.551461,-33.06245,-56.935383,16.996244,-30.385847,451.42566,1375000
77
+ 1022.147,1.5503615,0.7335879,-5.243371,-33.949062,-56.928726,24.945232,-42.41589,537.3681,1380000
78
+ 946.9285,1.3697314,0.69136953,0.12638913,-31.831501,-58.15019,31.951912,-27.96132,537.6957,1385000
79
+ 978.232,1.5960903,0.45921144,-6.7356358,-32.781715,-57.858547,18.535944,-25.387478,323.4632,1390000
80
+ 974.00635,1.6225451,0.3470671,-2.7387297,-32.7626,-56.328526,86.42191,-98.28944,1712.0845,1395000
81
+ 978.3624,1.782857,0.5965244,-5.219137,-32.66504,-51.42003,42.472176,-33.013077,579.2614,1400000
82
+ 935.0318,1.5618505,0.49775657,0.13188517,-31.424103,-57.331596,34.993958,-33.55738,598.2323,1405000
83
+ 977.98615,2.1054888,0.50587076,-3.8492565,-32.876186,-55.53638,164.47426,-198.71548,2248.0852,1410000
84
+ 956.54083,1.9200814,0.359478,-8.436712,-32.076176,-58.982304,166.04228,-129.48111,2010.1477,1415000
85
+ 961.5347,2.1000857,0.3592233,-4.1974864,-32.18301,-49.838825,64.99234,-52.294247,823.8678,1420000
86
+ 945.0291,1.5010263,0.5404995,-3.470895,-31.702887,-54.704685,55.13077,-49.569153,1172.9525,1425000
87
+ 948.204,1.4171557,0.4547492,-7.7275867,-31.732935,-50.87491,21.920708,-20.082417,470.72665,1430000
88
+ 995.37665,1.8593936,0.37440005,0.207879,-33.185993,-57.23715,90.60968,-79.103264,993.97656,1435000
89
+ 938.72076,1.8518388,0.36457843,-1.8668805,-31.680079,-57.715523,42.216473,-31.085176,544.26227,1440000
90
+ 1009.138,2.020258,0.55652905,-3.9808915,-33.366776,-57.075993,26.28008,-27.88968,459.08313,1445000
91
+ 954.4287,1.8483782,0.3915897,-3.8229523,-31.841858,-57.345627,34.293972,-32.270935,530.3979,1450000
92
+ 964.94904,2.6924238,0.36155894,0.086354524,-32.06257,-57.715504,13.612427,-20.147936,379.7895,1455000
93
+ 952.9128,1.3321792,0.3737553,-5.602263,-31.911255,-57.54415,60.04731,-44.5605,695.1691,1460000
94
+ 963.8164,1.7375429,0.53159124,-7.2942657,-32.091866,-57.05253,39.63265,-33.20988,565.0148,1465000
95
+ 983.3326,1.4512699,0.4449893,-2.7516131,-33.036922,-57.5248,39.23619,-31.308935,574.3199,1470000
96
+ 907.6964,1.6896024,0.5687704,-4.0599065,-30.58747,-57.045944,68.21157,-37.409706,480.54306,1475000
97
+ 972.24915,1.8674045,0.33310643,-3.763487,-32.258663,-57.850742,57.25515,-62.93685,892.1237,1480000
98
+ 982.372,1.4361999,0.3381035,-5.207757,-32.8469,-57.105606,43.496696,-85.11271,1013.11743,1485000
99
+ 960.1848,2.1824136,0.7470978,-4.576998,-31.776493,-55.911407,73.197815,-57.997204,1155.5182,1490000
100
+ 952.635,2.7298892,0.31568906,-3.3374836,-31.635544,-54.043365,28.119844,-21.588932,413.9017,1495000
101
+ 929.4487,1.8813431,0.4038535,-4.091554,-30.717823,-55.512394,16.127228,-11.69282,232.17311,1500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf8ef735fad37959641bd695579905b1044992efc09512153c7f4b6290f716e
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51063b54d69cd69bde4b076dcc2183204c7d0a3679bccd8b7cb1f7d3ee3404fd
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2d83f73aa095a4870579e08d39e689dde0e0cc9ff7b2735aef2e0452f17788
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db11605fdf7b348014dfaf37a556a530887a51dc32957bf19cb7a00959c7797
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90ec2b899484b0bcf72dc8e901ffa9c50177bd1de52e6d7230903703f22be396
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5862cb682a2358ecea1867c6baccca0db35edbda71d6dc6f45f33a5d1bd23e3d
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72af3245522c6d559cbc107b52fbc53a1e4a8de9c9b11a3bb01ef385d7467af9
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be888c4c082c719241d69f27dec2ed0047f571265b77c2b92d4d9e0aa15e9162
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a752dd1d8717b35f865b8d263697ae9af7d80ca2c68644587dd96bcddb75b31
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa565b2d761e6da4a4f6337e365c922df90c8424e3c01ac0e484b57a5853af1
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599cdec94495d78e84465ab3121853a5a86deb559a9b9dbe4e7cea64a6888536
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ee527bc2940daaa2727fb6b5b8739994e5d06125e8e8e35b2c1015915b92dd
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_1500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91a6b8be39aaa2debd2e5c43a6437bd52b9fadee00a0aee2b299a963fe8c57c
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547d71aa13afa7f513836715ddbcd473b91e8917610f97a9466614b476d8e311
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fcd1f299eb0d73bfdbccccd3a49d002610cf21e98ca9f382cc2d9db4a015c02
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4882d6acda5c68e23b4df6978a68d2831f9bb095663afa52074153e5135228b8
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df57a09821c5039d1b9caa523c7a7c2a50f560d7cfc643316622c086905a409f
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b13b209c791a2b0f5482b046a78a3a7cb4fd50ef2ce112ef01fe80807b2db1
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:032597dc7d155f04d1c5412baeb49299393864a3cd807461a1d0ad4e230b16fe
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_50000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20bc31282375e274b1de5987e16141721676fdf6903fb7adbd77bfa45ce4dac3
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd9107fb323a27cc4fdf135f9ad4b8ab1a6f5b47b38c5c5bf79f972ef5d7ac7
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3966bb8bf038850374f69f30dc3cb8b761833a7e34c49c3a966b288e1bb59327
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb18f33e698439d1492bb3bcb54f3fc93f49e886e84c78fb56dbe0e56a6ae6f
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197619a6bf4124d76ee473c3205ab8e309a6bc4c3d74aedbb596328858613370
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3896b0e83628f2c4c07e8765f21c3d92864f5efc16f1c2542fbd29b482ba5c3b
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a4b6fdf61774fb3da3b212e4fe800636eb67d2eed65e4c5b4ae15a8e85deb0
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85a7d196f0b64bf98feb31257c1aa3a35f4fcf32fd5fd902f286f873a6aeb2d
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8495781588dc61f7890e4235cdaba5ad457456588f04298fe25451dca2e5554
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a790111ce0b698592030bd11286f8e65cd014c834b027be2f5f5ea62b18b413a
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93e08ac5f21e582a173ae72902920e022727a2ed11f77d4c65bafbdd4a0cbfe
3
+ size 210293443
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260307_202607/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-reproduce/runs/rlalm5lx