Tiredsheep commited on
Commit
832d919
·
verified ·
1 Parent(s): ebad278

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +1 -0
  2. O2O-w-diff-ckpts/fawac/20260312_143756/env.csv +0 -0
  3. O2O-w-diff-ckpts/fawac/20260312_143756/env_sv.csv +0 -0
  4. O2O-w-diff-ckpts/fawac/20260312_143756/eval.csv +11 -0
  5. O2O-w-diff-ckpts/fawac/20260312_143756/eval_sv.csv +11 -0
  6. O2O-w-diff-ckpts/fawac/20260312_143756/online_agent.csv +101 -0
  7. O2O-w-diff-ckpts/fawac/20260312_143756/online_agent_sv.csv +101 -0
  8. O2O-w-diff-ckpts/fawac/20260312_143756/params_150000.pkl +3 -0
  9. O2O-w-diff-ckpts/fawac/20260312_143756/params_200000.pkl +3 -0
  10. O2O-w-diff-ckpts/fawac/20260312_143756/params_250000.pkl +3 -0
  11. O2O-w-diff-ckpts/fawac/20260312_143756/params_300000.pkl +3 -0
  12. O2O-w-diff-ckpts/fawac/20260312_143756/params_350000.pkl +3 -0
  13. O2O-w-diff-ckpts/fawac/20260312_143756/params_400000.pkl +3 -0
  14. O2O-w-diff-ckpts/fawac/20260312_143756/params_450000.pkl +3 -0
  15. O2O-w-diff-ckpts/fawac/20260312_143756/params_500000.pkl +3 -0
  16. O2O-w-diff-ckpts/fawac/20260312_143756/params_550000.pkl +3 -0
  17. O2O-w-diff-ckpts/fawac/20260312_143756/params_600000.pkl +3 -0
  18. O2O-w-diff-ckpts/fawac/20260312_143756/progress.tk +1 -0
  19. O2O-w-diff-ckpts/fawac/20260312_143756/token.tk +1 -0
  20. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_150000.png +3 -0
  21. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_200000.png +0 -0
  22. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_250000.png +0 -0
  23. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_300000.png +0 -0
  24. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_350000.png +0 -0
  25. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_400000.png +0 -0
  26. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_450000.png +0 -0
  27. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_500000.png +0 -0
  28. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_550000.png +0 -0
  29. O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_600000.png +0 -0
.gitattributes CHANGED
@@ -428,3 +428,4 @@ dynamics_probing_results/cube-double-play-singletask-v0/ifql/optimal_Q/progress_
428
  dynamics_probing_results/cube-double-play-singletask-v0/ifql/optimal_Q/progress_20260310_154136/mse_progress_critic.png filter=lfs diff=lfs merge=lfs -text
429
  dynamics_probing_results/cube-double-play-singletask-v0/ifql/optimal_V/progress_20260310_165812/mse_progress_critic.png filter=lfs diff=lfs merge=lfs -text
430
  dynamics_probing_results/cube-double-play-singletask-v0/qam/optimal_V/progress_20260310_171821/mse_progress_critic.png filter=lfs diff=lfs merge=lfs -text
 
 
428
  dynamics_probing_results/cube-double-play-singletask-v0/ifql/optimal_Q/progress_20260310_154136/mse_progress_critic.png filter=lfs diff=lfs merge=lfs -text
429
  dynamics_probing_results/cube-double-play-singletask-v0/ifql/optimal_V/progress_20260310_165812/mse_progress_critic.png filter=lfs diff=lfs merge=lfs -text
430
  dynamics_probing_results/cube-double-play-singletask-v0/qam/optimal_V/progress_20260310_171821/mse_progress_critic.png filter=lfs diff=lfs merge=lfs -text
431
+ O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_150000.png filter=lfs diff=lfs merge=lfs -text
O2O-w-diff-ckpts/fawac/20260312_143756/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/fawac/20260312_143756/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/fawac/20260312_143756/eval.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ avg_gripper_contact_length,num_gripper_contacts,xy,prev_qpos,prev_qvel,qpos,qvel,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
2
+ 0.0,0.0,5.105030794078198,0.7406878410088948,0.03492803691074558,0.7409280714290057,0.025350200718513523,0.0,25500.0,-1.0,-1000.0,1000.0,1.3563616704940795,150000
3
+ 0.0,0.0,2.055398229317954,0.35276503069175,0.06545532193176526,0.35636294586536754,0.0008643112245796328,0.0,77500.0,-1.0,-1000.0,1000.0,1.3699073886871338,200000
4
+ 0.0,0.0,0.08308641227255664,0.08031808346942965,-0.048037286277882445,0.07623161872538123,-0.0007045208530827653,0.0,129500.0,-1.0,-1000.0,1000.0,1.373996500968933,250000
5
+ 0.0,0.0,-0.026324265215224053,0.06325886733620643,0.01829343723244239,0.06524279510062243,0.04402377772036311,0.0,181500.0,-1.0,-1000.0,1000.0,1.3698944091796874,300000
6
+ 0.0,0.0,0.22641682049257678,0.11443185301247744,0.02819846354375607,0.11702525782448385,0.00684587514231514,0.0,233500.0,-1.0,-1000.0,1000.0,1.3696186113357545,350000
7
+ 0.0,0.0,0.25377130280893234,0.1321521333800439,0.037190633051496134,0.13004407461786158,-0.05379155701031621,0.0,285500.0,-1.0,-1000.0,1000.0,1.3687735176086426,400000
8
+ 0.0,0.0,0.4058281934265829,0.16078360069027206,-0.009239731677186985,0.15874560841509563,-0.026049386722704387,0.0,337500.0,-1.0,-1000.0,1000.0,1.368759217262268,450000
9
+ 0.0,0.0,0.35107334765688647,0.14456071268842197,0.057870586946608835,0.148218843464419,0.017262870280872363,0.0,389500.0,-1.0,-1000.0,1000.0,1.3824154043197632,500000
10
+ 0.0,0.0,0.2902993077244929,0.1361183181966652,-0.02880231533576419,0.13462831185791124,0.014402169270579733,0.0,441500.0,-1.0,-1000.0,1000.0,1.3808778572082518,550000
11
+ 0.0,0.0,0.1680070573303179,0.1106798514951492,-0.04663799962614748,0.10917370048742937,-0.027658090668458805,0.0,493500.0,-1.0,-1000.0,1000.0,1.3654441165924072,600000
O2O-w-diff-ckpts/fawac/20260312_143756/eval_sv.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ avg_gripper_contact_length,num_gripper_contacts,xy,prev_qpos,prev_qvel,qpos,qvel,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
2
+ 0.0,0.0,5.105030794078198,0.7406878410088948,0.03492803691074558,0.7409280714290057,0.025350200718513523,0.0,25500.0,-1.0,-1000.0,1000.0,1.3563616704940795,150000
3
+ 0.0,0.0,2.055398229317954,0.35276503069175,0.06545532193176526,0.35636294586536754,0.0008643112245796328,0.0,77500.0,-1.0,-1000.0,1000.0,1.3699073886871338,200000
4
+ 0.0,0.0,0.08308641227255664,0.08031808346942965,-0.048037286277882445,0.07623161872538123,-0.0007045208530827653,0.0,129500.0,-1.0,-1000.0,1000.0,1.373996500968933,250000
5
+ 0.0,0.0,-0.026324265215224053,0.06325886733620643,0.01829343723244239,0.06524279510062243,0.04402377772036311,0.0,181500.0,-1.0,-1000.0,1000.0,1.3698944091796874,300000
6
+ 0.0,0.0,0.22641682049257678,0.11443185301247744,0.02819846354375607,0.11702525782448385,0.00684587514231514,0.0,233500.0,-1.0,-1000.0,1000.0,1.3696186113357545,350000
7
+ 0.0,0.0,0.25377130280893234,0.1321521333800439,0.037190633051496134,0.13004407461786158,-0.05379155701031621,0.0,285500.0,-1.0,-1000.0,1000.0,1.3687735176086426,400000
8
+ 0.0,0.0,0.4058281934265829,0.16078360069027206,-0.009239731677186985,0.15874560841509563,-0.026049386722704387,0.0,337500.0,-1.0,-1000.0,1000.0,1.368759217262268,450000
9
+ 0.0,0.0,0.35107334765688647,0.14456071268842197,0.057870586946608835,0.148218843464419,0.017262870280872363,0.0,389500.0,-1.0,-1000.0,1000.0,1.3824154043197632,500000
10
+ 0.0,0.0,0.2902993077244929,0.1361183181966652,-0.02880231533576419,0.13462831185791124,0.014402169270579733,0.0,441500.0,-1.0,-1000.0,1000.0,1.3808778572082518,550000
11
+ 0.0,0.0,0.1680070573303179,0.1106798514951492,-0.04663799962614748,0.10917370048742937,-0.027658090668458805,0.0,493500.0,-1.0,-1000.0,1000.0,1.3654441165924072,600000
O2O-w-diff-ckpts/fawac/20260312_143756/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,critic/value_loss,grad/max,grad/min,grad/norm,step
2
+ 0.5438887,1.8132099,-20.293953,-198.35913,-770.7254,1.6854247,33.820065,-47.291294,389.19202,105000
3
+ 1.2781159,12.588073,-1.9819508,-199.64795,-864.5277,11.792864,786.6299,-648.49646,4993.462,110000
4
+ 0.891296,7.0006523,-32.830345,-215.3623,-988.854,2.1296918,67.96983,-55.3071,984.38306,115000
5
+ 0.711721,1.0863695,-54.755226,-208.18091,-1071.7822,0.7236358,16.099026,-20.179407,188.62462,120000
6
+ 0.65745157,12.131494,0.3678806,-213.38707,-1176.8921,9.557624,169.82622,-91.90059,2079.5764,125000
7
+ 0.839365,3.086192,-0.8470317,-218.59,-1272.3861,1.8130696,25.781166,-33.654846,353.72742,130000
8
+ 0.70424634,1.7883033,-3.9367278,-207.49068,-337.44513,1.0995249,6.9230266,-9.241151,170.5844,135000
9
+ 1.190222,8.500921,-2.1488543,-220.92119,-1464.1763,1.9627937,168.83179,-143.70276,1195.9128,140000
10
+ 1.5960228,35.974125,-2.9645271,-222.91447,-1542.3455,5.718747,301.86963,-280.36868,3254.907,145000
11
+ 1.4973068,62.240795,2.9074981,-241.68579,-1657.477,25.78544,1037.6803,-534.78424,8736.758,150000
12
+ 1.2443526,58.10321,1.280652,-219.80724,-1716.8263,24.955067,931.4653,-726.6786,5786.8354,155000
13
+ 1.1728579,4.9613147,-99.89271,-230.70543,-1775.4723,12.591453,97.19402,-146.0411,1251.3823,160000
14
+ 0.71675766,5.866159,-95.85062,-220.32634,-416.24927,1.9315861,78.11411,-63.604256,824.3263,165000
15
+ 0.93442845,3.7357616,-28.13069,-228.3568,-1937.6044,3.2476158,9.48291,-12.628977,403.37463,170000
16
+ 1.8440938,24.202406,1.3964834,-234.22855,-2034.3729,5.2632136,400.1874,-406.95798,2307.0635,175000
17
+ 1.3580359,3.6898465,-31.860027,-246.68135,-2120.8403,5.510738,76.07801,-16.620556,553.5663,180000
18
+ 0.9320254,6.302255,-10.106431,-232.89742,-1548.1133,8.694934,77.72845,-111.57091,1439.9633,185000
19
+ 0.7971864,3.3813882,-71.62002,-260.89316,-2290.9268,2.6636531,23.999928,-24.07765,365.19827,190000
20
+ 1.3272791,52.335964,1.122611,-246.81856,-2375.7827,73.486534,561.4526,-316.72134,4926.285,195000
21
+ 1.3273454,5.4180846,-0.42255533,-265.10968,-2424.9028,14.513389,214.47108,-159.98203,2430.2178,200000
22
+ 2.6628096,132.71458,-117.65378,-258.03235,-2474.2397,32.72407,1269.819,-767.4634,14223.068,205000
23
+ 1.2409983,22.634455,-80.25579,-287.98593,-2538.1938,25.180906,949.0618,-625.33826,8044.6934,210000
24
+ 1.112765,18.25007,-10.266013,-260.29294,-2636.6455,33.083454,668.478,-464.6158,5370.5337,215000
25
+ 0.80592513,5.091726,-79.801796,-253.89146,-2727.6633,4.011013,21.579794,-25.313225,442.92822,220000
26
+ 2.3279583,8.346915,-121.37965,-260.2109,-2784.0615,5.226271,20.680542,-17.977869,543.1156,225000
27
+ 0.94521046,4.0682297,-67.827,-268.89508,-2848.1133,3.2452412,59.676,-45.748184,545.52625,230000
28
+ 1.9183781,2.6652887,-166.74037,-273.9585,-2930.8528,3.145419,31.509605,-33.834377,434.59555,235000
29
+ 1.3246528,11.616397,-160.49763,-254.10884,-2986.674,73.94565,2385.9788,-2974.232,14590.93,240000
30
+ 1.0468926,10.692754,-4.0939856,-313.23056,-3059.4983,9.779787,82.26688,-198.31653,1869.5204,245000
31
+ 1.3094637,5.0624213,-94.42933,-265.26407,-3142.0046,3.8674133,30.495056,-12.947486,400.29285,250000
32
+ 1.1347185,28.26716,-108.83682,-267.791,-3212.2341,28.946959,182.75757,-277.64597,3801.7195,255000
33
+ 0.9911141,10.916002,4.286499,-283.89905,-3291.741,14.56842,91.255714,-67.011086,1212.8612,260000
34
+ 1.6715953,19.138155,-134.49713,-285.1061,-3339.3801,14.072327,102.092354,-63.871,1387.574,265000
35
+ 2.5368927,26.356497,1.9813662,-343.71405,-3412.0417,15.076236,297.75412,-156.3499,2830.7563,270000
36
+ 2.6308267,13.699302,-94.40994,-270.077,-3476.0547,17.924883,504.4102,-95.77669,2632.1206,275000
37
+ 1.9482868,7.572933,3.3036659,-274.78342,-3569.5051,11.440316,99.003456,-82.04386,1111.7892,280000
38
+ 1.2840877,11.78049,-0.013258457,-281.07748,-3650.8242,17.843939,118.7369,-240.01831,1850.1168,285000
39
+ 2.1982257,1024.166,-159.82289,-280.63608,-3668.1343,79.93809,1501.3633,-1235.7625,25903.352,290000
40
+ 3.4422145,72.9059,5.110891,-280.75278,-3744.5154,26.292997,504.7603,-728.74866,4660.707,295000
41
+ 2.0288856,113.84336,-44.89023,-298.20923,-3832.0403,11.6393175,238.70139,-191.65225,3514.4053,300000
42
+ 1.708,12.765623,-77.13356,-253.72147,-573.4145,9.47599,43.86109,-70.79715,954.55896,305000
43
+ 2.471643,14.713653,-215.40257,-300.81995,-4008.76,10.872985,60.043137,-40.397438,1075.169,310000
44
+ 1.3279588,28.724775,9.622975,-307.32535,-4062.3357,40.901806,225.51515,-319.03085,2515.2827,315000
45
+ 3.4366956,102.22916,7.592757,-274.38525,-4110.794,69.72842,325.80463,-266.57553,4536.6553,320000
46
+ 2.3626347,31.490799,6.50033,-303.96213,-4180.7334,53.601025,580.0742,-1067.2993,7741.3413,325000
47
+ 2.639145,21.010807,-128.58804,-363.98907,-4212.6265,26.954548,274.41412,-237.17558,3378.606,330000
48
+ 3.7061503,340.44382,0.16660488,-265.96564,-584.7097,69.32098,1498.8301,-1633.974,12718.092,335000
49
+ 1.3816334,386.04733,-45.194504,-289.81497,-4285.5137,89.43854,5188.815,-1671.1956,25681.512,340000
50
+ 1.0350189,24.507185,-39.971245,-284.49545,-4328.005,13.231873,138.02492,-144.17009,1616.0602,345000
51
+ 2.2605903,17.728674,0.56759614,-302.03085,-4352.651,26.531675,211.81241,-396.55164,3278.2925,350000
52
+ 1.9017807,38.441578,-5.37213,-294.79187,-4424.252,16.214056,314.1612,-348.9062,3744.8591,355000
53
+ 1.2786822,19.098055,-2.2169821,-262.56033,-468.99957,11.983975,92.34402,-148.88382,1165.2107,360000
54
+ 1.8650252,16.751652,-216.20743,-323.8543,-4495.9287,18.816494,142.39287,-222.2319,2287.3164,365000
55
+ 0.6753712,32.86084,-109.4809,-311.53238,-4545.5615,12.54392,52.480343,-52.10961,1477.2249,370000
56
+ 2.2657256,27.606556,-153.91223,-308.45505,-4632.8403,106.79425,1442.3115,-765.53455,8524.506,375000
57
+ 2.8273263,27.679785,2.9156952,-339.752,-4688.776,38.32035,280.00763,-239.17967,2614.1292,380000
58
+ 2.8196602,13.519078,2.6544576,-320.85095,-4706.046,20.82991,219.20572,-153.16182,1727.7908,385000
59
+ 1.6756471,24.991924,-31.714155,-342.7174,-4809.5923,30.715673,874.5107,-353.7695,5375.1514,390000
60
+ 3.8512805,51.70699,-13.0252695,-290.1451,-4844.167,29.79132,205.25906,-183.3617,3065.6003,395000
61
+ 2.053247,47.20301,-165.59477,-310.665,-4893.152,399.7819,3232.1902,-4075.7427,36257.285,400000
62
+ 2.156736,19.309752,-163.28506,-306.92743,-4929.846,13.015861,111.22672,-83.80073,1633.9443,405000
63
+ 2.1308699,48.076813,-191.22623,-316.34402,-4998.328,30.846064,98.807014,-104.84859,2088.2473,410000
64
+ 4.5188284,32.340828,7.2072725,-331.30725,-4976.684,38.951283,302.6454,-361.3616,3443.495,415000
65
+ 2.2848845,36.271786,-6.9453506,-322.94165,-5074.506,17.094526,289.98044,-152.29099,3605.4617,420000
66
+ 1.291919,21.798605,9.024152,-271.10107,-591.51447,16.462393,59.200527,-87.00308,998.5123,425000
67
+ 0.8733722,28.240955,-95.03603,-311.2609,-5084.8784,26.710896,245.18524,-160.9907,2587.692,430000
68
+ 2.4887578,303.1664,-101.90847,-329.8884,-5064.558,131.41875,5389.7275,-2804.6804,38070.695,435000
69
+ 2.567887,73.14788,-55.70542,-347.76416,-5157.6353,59.414333,2428.037,-1013.25006,14786.1455,440000
70
+ 1.6631836,26.505102,-80.43593,-308.25644,-5165.7495,24.504486,204.17981,-224.22598,2662.458,445000
71
+ 1.8405964,30.732807,12.898885,-319.39713,-5182.1816,17.119825,114.64608,-85.62942,1954.3293,450000
72
+ 3.5053034,24.767231,8.4465065,-277.25778,-626.6585,33.688362,966.03094,-1121.2153,8289.051,455000
73
+ 1.7430785,62.387978,-81.666435,-375.49823,-5250.8066,51.876728,200.49944,-219.29002,3544.2344,460000
74
+ 3.8096757,47.084534,-2.140256,-284.58798,-3874.2026,46.99366,839.4516,-705.2334,8143.547,465000
75
+ 2.5073512,25.24211,-2.4206934,-302.66818,-5199.246,42.20299,953.2156,-798.9909,6194.949,470000
76
+ 3.215623,14.669705,-7.1319284,-295.0759,-5209.2173,37.11218,318.36478,-693.15515,3251.037,475000
77
+ 2.3546038,42.67882,-13.567331,-305.14658,-5119.066,26.473505,293.0109,-240.67027,3943.7148,480000
78
+ 1.4754112,13.321332,-115.30522,-289.1745,-5135.207,17.869389,149.49963,-92.23053,2097.972,485000
79
+ 2.7087083,25.61267,2.4744823,-345.85553,-5181.9023,28.035156,136.52193,-55.59877,1872.7551,490000
80
+ 2.4680452,34.329205,-187.63258,-324.3215,-5153.8594,50.94754,429.00186,-635.61206,7284.2256,495000
81
+ 4.214122,22.833227,29.28771,-295.87814,-5190.1777,23.323032,58.754227,-59.892643,1318.0376,500000
82
+ 1.7673603,21.320158,-7.920763,-308.36563,-5216.719,23.352127,318.3637,-433.9463,4346.461,505000
83
+ 1.6309724,35.978546,-0.11799884,-301.2727,-5275.767,29.694702,128.94225,-221.89899,2155.5132,510000
84
+ 2.8266618,23.906385,-0.1620071,-301.7813,-5172.814,60.120586,966.62213,-3045.2634,9957.987,515000
85
+ 1.6660539,22.331068,-203.73094,-336.86435,-5141.756,23.067068,190.39088,-254.66342,3171.4475,520000
86
+ 1.5183825,456.61148,30.505558,-325.49698,-5178.607,2853.4434,18032.512,-15152.033,175034.25,525000
87
+ 2.8704772,16.820597,-107.208,-298.2567,-5121.9,15.615478,46.01639,-76.24957,1209.9326,530000
88
+ 2.3123832,19.268522,22.607737,-270.4861,-661.0887,18.470984,51.385185,-103.166374,1257.1526,535000
89
+ 2.9883275,4627.16,17.990286,-306.6676,-4448.433,39782.965,66998.0,-39789.477,418222.12,540000
90
+ 1.9476393,25.822346,31.413881,-292.54947,-5084.394,27.280869,140.25482,-257.18887,2095.4167,545000
91
+ 2.8710017,41.817867,1.0241339,-324.27066,-4944.987,30.386026,309.05734,-481.5062,3970.4517,550000
92
+ 1.6604095,25.693562,6.997608,-323.9039,-4899.8325,83.979095,735.0289,-508.12842,6290.3926,555000
93
+ 2.9606295,985.2471,29.413866,-306.9936,-4931.5405,2139.4558,254779.92,-53670.78,772729.7,560000
94
+ 2.588047,96.09582,-116.758415,-296.4847,-4313.9126,96.18322,838.2818,-872.17,11027.073,565000
95
+ 3.2393682,129.38322,45.538307,-275.8795,-921.3194,20.351837,1646.1963,-1272.1537,9809.326,570000
96
+ 1.6896008,2457.9395,-112.414894,-325.1751,-4758.419,1203.1433,34558.605,-40817.344,230226.25,575000
97
+ 3.9171207,54.933224,18.560318,-389.2971,-4746.712,75.49017,1274.7745,-329.17447,10545.225,580000
98
+ 2.8465478,26.915625,-109.279236,-328.10474,-4515.3105,21.497965,57.819965,-153.68292,1695.9602,585000
99
+ 2.465208,48.960514,-66.52698,-286.52045,-4338.9277,11.629,88.01715,-91.2782,1886.7839,590000
100
+ 2.6192799,25.232119,30.684864,-306.3242,-4195.771,33.620625,436.40015,-441.44595,4829.855,595000
101
+ 1.4020565,28.594263,-172.51436,-322.04324,-3918.7715,19.731226,121.1621,-132.39122,2213.8171,600000
O2O-w-diff-ckpts/fawac/20260312_143756/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,critic/value_loss,grad/max,grad/min,grad/norm,step
2
+ 0.5438887,1.8132099,-20.293953,-198.35913,-770.7254,1.6854247,33.820065,-47.291294,389.19202,105000
3
+ 1.2781159,12.588073,-1.9819508,-199.64795,-864.5277,11.792864,786.6299,-648.49646,4993.462,110000
4
+ 0.891296,7.0006523,-32.830345,-215.3623,-988.854,2.1296918,67.96983,-55.3071,984.38306,115000
5
+ 0.711721,1.0863695,-54.755226,-208.18091,-1071.7822,0.7236358,16.099026,-20.179407,188.62462,120000
6
+ 0.65745157,12.131494,0.3678806,-213.38707,-1176.8921,9.557624,169.82622,-91.90059,2079.5764,125000
7
+ 0.839365,3.086192,-0.8470317,-218.59,-1272.3861,1.8130696,25.781166,-33.654846,353.72742,130000
8
+ 0.70424634,1.7883033,-3.9367278,-207.49068,-337.44513,1.0995249,6.9230266,-9.241151,170.5844,135000
9
+ 1.190222,8.500921,-2.1488543,-220.92119,-1464.1763,1.9627937,168.83179,-143.70276,1195.9128,140000
10
+ 1.5960228,35.974125,-2.9645271,-222.91447,-1542.3455,5.718747,301.86963,-280.36868,3254.907,145000
11
+ 1.4973068,62.240795,2.9074981,-241.68579,-1657.477,25.78544,1037.6803,-534.78424,8736.758,150000
12
+ 1.2443526,58.10321,1.280652,-219.80724,-1716.8263,24.955067,931.4653,-726.6786,5786.8354,155000
13
+ 1.1728579,4.9613147,-99.89271,-230.70543,-1775.4723,12.591453,97.19402,-146.0411,1251.3823,160000
14
+ 0.71675766,5.866159,-95.85062,-220.32634,-416.24927,1.9315861,78.11411,-63.604256,824.3263,165000
15
+ 0.93442845,3.7357616,-28.13069,-228.3568,-1937.6044,3.2476158,9.48291,-12.628977,403.37463,170000
16
+ 1.8440938,24.202406,1.3964834,-234.22855,-2034.3729,5.2632136,400.1874,-406.95798,2307.0635,175000
17
+ 1.3580359,3.6898465,-31.860027,-246.68135,-2120.8403,5.510738,76.07801,-16.620556,553.5663,180000
18
+ 0.9320254,6.302255,-10.106431,-232.89742,-1548.1133,8.694934,77.72845,-111.57091,1439.9633,185000
19
+ 0.7971864,3.3813882,-71.62002,-260.89316,-2290.9268,2.6636531,23.999928,-24.07765,365.19827,190000
20
+ 1.3272791,52.335964,1.122611,-246.81856,-2375.7827,73.486534,561.4526,-316.72134,4926.285,195000
21
+ 1.3273454,5.4180846,-0.42255533,-265.10968,-2424.9028,14.513389,214.47108,-159.98203,2430.2178,200000
22
+ 2.6628096,132.71458,-117.65378,-258.03235,-2474.2397,32.72407,1269.819,-767.4634,14223.068,205000
23
+ 1.2409983,22.634455,-80.25579,-287.98593,-2538.1938,25.180906,949.0618,-625.33826,8044.6934,210000
24
+ 1.112765,18.25007,-10.266013,-260.29294,-2636.6455,33.083454,668.478,-464.6158,5370.5337,215000
25
+ 0.80592513,5.091726,-79.801796,-253.89146,-2727.6633,4.011013,21.579794,-25.313225,442.92822,220000
26
+ 2.3279583,8.346915,-121.37965,-260.2109,-2784.0615,5.226271,20.680542,-17.977869,543.1156,225000
27
+ 0.94521046,4.0682297,-67.827,-268.89508,-2848.1133,3.2452412,59.676,-45.748184,545.52625,230000
28
+ 1.9183781,2.6652887,-166.74037,-273.9585,-2930.8528,3.145419,31.509605,-33.834377,434.59555,235000
29
+ 1.3246528,11.616397,-160.49763,-254.10884,-2986.674,73.94565,2385.9788,-2974.232,14590.93,240000
30
+ 1.0468926,10.692754,-4.0939856,-313.23056,-3059.4983,9.779787,82.26688,-198.31653,1869.5204,245000
31
+ 1.3094637,5.0624213,-94.42933,-265.26407,-3142.0046,3.8674133,30.495056,-12.947486,400.29285,250000
32
+ 1.1347185,28.26716,-108.83682,-267.791,-3212.2341,28.946959,182.75757,-277.64597,3801.7195,255000
33
+ 0.9911141,10.916002,4.286499,-283.89905,-3291.741,14.56842,91.255714,-67.011086,1212.8612,260000
34
+ 1.6715953,19.138155,-134.49713,-285.1061,-3339.3801,14.072327,102.092354,-63.871,1387.574,265000
35
+ 2.5368927,26.356497,1.9813662,-343.71405,-3412.0417,15.076236,297.75412,-156.3499,2830.7563,270000
36
+ 2.6308267,13.699302,-94.40994,-270.077,-3476.0547,17.924883,504.4102,-95.77669,2632.1206,275000
37
+ 1.9482868,7.572933,3.3036659,-274.78342,-3569.5051,11.440316,99.003456,-82.04386,1111.7892,280000
38
+ 1.2840877,11.78049,-0.013258457,-281.07748,-3650.8242,17.843939,118.7369,-240.01831,1850.1168,285000
39
+ 2.1982257,1024.166,-159.82289,-280.63608,-3668.1343,79.93809,1501.3633,-1235.7625,25903.352,290000
40
+ 3.4422145,72.9059,5.110891,-280.75278,-3744.5154,26.292997,504.7603,-728.74866,4660.707,295000
41
+ 2.0288856,113.84336,-44.89023,-298.20923,-3832.0403,11.6393175,238.70139,-191.65225,3514.4053,300000
42
+ 1.708,12.765623,-77.13356,-253.72147,-573.4145,9.47599,43.86109,-70.79715,954.55896,305000
43
+ 2.471643,14.713653,-215.40257,-300.81995,-4008.76,10.872985,60.043137,-40.397438,1075.169,310000
44
+ 1.3279588,28.724775,9.622975,-307.32535,-4062.3357,40.901806,225.51515,-319.03085,2515.2827,315000
45
+ 3.4366956,102.22916,7.592757,-274.38525,-4110.794,69.72842,325.80463,-266.57553,4536.6553,320000
46
+ 2.3626347,31.490799,6.50033,-303.96213,-4180.7334,53.601025,580.0742,-1067.2993,7741.3413,325000
47
+ 2.639145,21.010807,-128.58804,-363.98907,-4212.6265,26.954548,274.41412,-237.17558,3378.606,330000
48
+ 3.7061503,340.44382,0.16660488,-265.96564,-584.7097,69.32098,1498.8301,-1633.974,12718.092,335000
49
+ 1.3816334,386.04733,-45.194504,-289.81497,-4285.5137,89.43854,5188.815,-1671.1956,25681.512,340000
50
+ 1.0350189,24.507185,-39.971245,-284.49545,-4328.005,13.231873,138.02492,-144.17009,1616.0602,345000
51
+ 2.2605903,17.728674,0.56759614,-302.03085,-4352.651,26.531675,211.81241,-396.55164,3278.2925,350000
52
+ 1.9017807,38.441578,-5.37213,-294.79187,-4424.252,16.214056,314.1612,-348.9062,3744.8591,355000
53
+ 1.2786822,19.098055,-2.2169821,-262.56033,-468.99957,11.983975,92.34402,-148.88382,1165.2107,360000
54
+ 1.8650252,16.751652,-216.20743,-323.8543,-4495.9287,18.816494,142.39287,-222.2319,2287.3164,365000
55
+ 0.6753712,32.86084,-109.4809,-311.53238,-4545.5615,12.54392,52.480343,-52.10961,1477.2249,370000
56
+ 2.2657256,27.606556,-153.91223,-308.45505,-4632.8403,106.79425,1442.3115,-765.53455,8524.506,375000
57
+ 2.8273263,27.679785,2.9156952,-339.752,-4688.776,38.32035,280.00763,-239.17967,2614.1292,380000
58
+ 2.8196602,13.519078,2.6544576,-320.85095,-4706.046,20.82991,219.20572,-153.16182,1727.7908,385000
59
+ 1.6756471,24.991924,-31.714155,-342.7174,-4809.5923,30.715673,874.5107,-353.7695,5375.1514,390000
60
+ 3.8512805,51.70699,-13.0252695,-290.1451,-4844.167,29.79132,205.25906,-183.3617,3065.6003,395000
61
+ 2.053247,47.20301,-165.59477,-310.665,-4893.152,399.7819,3232.1902,-4075.7427,36257.285,400000
62
+ 2.156736,19.309752,-163.28506,-306.92743,-4929.846,13.015861,111.22672,-83.80073,1633.9443,405000
63
+ 2.1308699,48.076813,-191.22623,-316.34402,-4998.328,30.846064,98.807014,-104.84859,2088.2473,410000
64
+ 4.5188284,32.340828,7.2072725,-331.30725,-4976.684,38.951283,302.6454,-361.3616,3443.495,415000
65
+ 2.2848845,36.271786,-6.9453506,-322.94165,-5074.506,17.094526,289.98044,-152.29099,3605.4617,420000
66
+ 1.291919,21.798605,9.024152,-271.10107,-591.51447,16.462393,59.200527,-87.00308,998.5123,425000
67
+ 0.8733722,28.240955,-95.03603,-311.2609,-5084.8784,26.710896,245.18524,-160.9907,2587.692,430000
68
+ 2.4887578,303.1664,-101.90847,-329.8884,-5064.558,131.41875,5389.7275,-2804.6804,38070.695,435000
69
+ 2.567887,73.14788,-55.70542,-347.76416,-5157.6353,59.414333,2428.037,-1013.25006,14786.1455,440000
70
+ 1.6631836,26.505102,-80.43593,-308.25644,-5165.7495,24.504486,204.17981,-224.22598,2662.458,445000
71
+ 1.8405964,30.732807,12.898885,-319.39713,-5182.1816,17.119825,114.64608,-85.62942,1954.3293,450000
72
+ 3.5053034,24.767231,8.4465065,-277.25778,-626.6585,33.688362,966.03094,-1121.2153,8289.051,455000
73
+ 1.7430785,62.387978,-81.666435,-375.49823,-5250.8066,51.876728,200.49944,-219.29002,3544.2344,460000
74
+ 3.8096757,47.084534,-2.140256,-284.58798,-3874.2026,46.99366,839.4516,-705.2334,8143.547,465000
75
+ 2.5073512,25.24211,-2.4206934,-302.66818,-5199.246,42.20299,953.2156,-798.9909,6194.949,470000
76
+ 3.215623,14.669705,-7.1319284,-295.0759,-5209.2173,37.11218,318.36478,-693.15515,3251.037,475000
77
+ 2.3546038,42.67882,-13.567331,-305.14658,-5119.066,26.473505,293.0109,-240.67027,3943.7148,480000
78
+ 1.4754112,13.321332,-115.30522,-289.1745,-5135.207,17.869389,149.49963,-92.23053,2097.972,485000
79
+ 2.7087083,25.61267,2.4744823,-345.85553,-5181.9023,28.035156,136.52193,-55.59877,1872.7551,490000
80
+ 2.4680452,34.329205,-187.63258,-324.3215,-5153.8594,50.94754,429.00186,-635.61206,7284.2256,495000
81
+ 4.214122,22.833227,29.28771,-295.87814,-5190.1777,23.323032,58.754227,-59.892643,1318.0376,500000
82
+ 1.7673603,21.320158,-7.920763,-308.36563,-5216.719,23.352127,318.3637,-433.9463,4346.461,505000
83
+ 1.6309724,35.978546,-0.11799884,-301.2727,-5275.767,29.694702,128.94225,-221.89899,2155.5132,510000
84
+ 2.8266618,23.906385,-0.1620071,-301.7813,-5172.814,60.120586,966.62213,-3045.2634,9957.987,515000
85
+ 1.6660539,22.331068,-203.73094,-336.86435,-5141.756,23.067068,190.39088,-254.66342,3171.4475,520000
86
+ 1.5183825,456.61148,30.505558,-325.49698,-5178.607,2853.4434,18032.512,-15152.033,175034.25,525000
87
+ 2.8704772,16.820597,-107.208,-298.2567,-5121.9,15.615478,46.01639,-76.24957,1209.9326,530000
88
+ 2.3123832,19.268522,22.607737,-270.4861,-661.0887,18.470984,51.385185,-103.166374,1257.1526,535000
89
+ 2.9883275,4627.16,17.990286,-306.6676,-4448.433,39782.965,66998.0,-39789.477,418222.12,540000
90
+ 1.9476393,25.822346,31.413881,-292.54947,-5084.394,27.280869,140.25482,-257.18887,2095.4167,545000
91
+ 2.8710017,41.817867,1.0241339,-324.27066,-4944.987,30.386026,309.05734,-481.5062,3970.4517,550000
92
+ 1.6604095,25.693562,6.997608,-323.9039,-4899.8325,83.979095,735.0289,-508.12842,6290.3926,555000
93
+ 2.9606295,985.2471,29.413866,-306.9936,-4931.5405,2139.4558,254779.92,-53670.78,772729.7,560000
94
+ 2.588047,96.09582,-116.758415,-296.4847,-4313.9126,96.18322,838.2818,-872.17,11027.073,565000
95
+ 3.2393682,129.38322,45.538307,-275.8795,-921.3194,20.351837,1646.1963,-1272.1537,9809.326,570000
96
+ 1.6896008,2457.9395,-112.414894,-325.1751,-4758.419,1203.1433,34558.605,-40817.344,230226.25,575000
97
+ 3.9171207,54.933224,18.560318,-389.2971,-4746.712,75.49017,1274.7745,-329.17447,10545.225,580000
98
+ 2.8465478,26.915625,-109.279236,-328.10474,-4515.3105,21.497965,57.819965,-153.68292,1695.9602,585000
99
+ 2.465208,48.960514,-66.52698,-286.52045,-4338.9277,11.629,88.01715,-91.2782,1886.7839,590000
100
+ 2.6192799,25.232119,30.684864,-306.3242,-4195.771,33.620625,436.40015,-441.44595,4829.855,595000
101
+ 1.4020565,28.594263,-172.51436,-322.04324,-3918.7715,19.731226,121.1621,-132.39122,2213.8171,600000
O2O-w-diff-ckpts/fawac/20260312_143756/params_150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39abe101e87ec7621408dcfe78621b0bfa12c3261ed665b56e77e8d2fa8fc25d
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf71bebfe5c31195bd9b967b7116259fc7116fc3c24b5343c0c469f5b708c16
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab99cc6d9c45be8fe8b476636d74a6e7a9380667f8c30ec9ae0b4e315b40471
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68167280c83c41a371f478e01fd6f594e698e42743fc49a49e036c484ce87034
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c1e86068f04a4832821bc43f1e9c6faf0142e5692838e0476f73706ead1b9f
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca222fc2e840368e8e7ea669ab8585a1b9020c056a98661fcd31b9c261486776
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faba4dd1317709a24ce57cb4a836a1a3bde24f0e88354c28020ec14746204653
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94651680984b5187804c93b69e4ebe1a6dde200cee2c9ab258d91d89b710960
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644db65f7c7fd145c9965b779d04d2c2f9dec0304390678183c7bcf04a1ab030
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018aa869fc6b3a34d99f2b5ae1cc2f69673a6a5337c15379b39458d0fe2999af
3
+ size 214338962
O2O-w-diff-ckpts/fawac/20260312_143756/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/fawac/20260312_143756/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/5na63dtv
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_150000.png ADDED

Git LFS Details

  • SHA256: b7253d9d9d4d00c68068a481532cbe5f495e3772e75188f9d503450318e86f2d
  • Pointer size: 131 Bytes
  • Size of remote file: 217 kB
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_200000.png ADDED
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_250000.png ADDED
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_300000.png ADDED
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_350000.png ADDED
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_400000.png ADDED
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_450000.png ADDED
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_500000.png ADDED
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_550000.png ADDED
O2O-w-diff-ckpts/fawac/20260312_143756/visited_states_600000.png ADDED