Tiredsheep commited on
Commit
8520d42
·
verified ·
1 Parent(s): 7902212

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_1000000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_550000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_600000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_650000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_700000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_750000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_800000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_850000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_900000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_950000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/eval.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ avg_gripper_contact_length,num_gripper_contacts,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,-0.045208679826058105,-0.009443602510246361,-0.04571010759770992,-0.007946844763457486,19.476030277234205,25.099999999996967,0.0,12750.0,-1.96,-990.88,500.0,1.4522244644165039,550000
3
+ 0.0,0.0,-0.04359171373519688,-0.024133958213104517,-0.044084560323540294,-0.010180918311127241,20.001843563998072,25.099999999996967,0.0,38750.0,-1.98,-994.66,500.0,1.479248185157776,600000
4
+ 0.0,0.0,-0.06188543606032704,0.008386718576667312,-0.06154777521463779,0.00656728664809419,21.691921257179477,25.099999999996967,0.0,64750.0,-2.0,-998.92,500.0,1.4703149509429931,650000
5
+ 0.0,0.0,-0.05358948324687931,0.0022794882409145163,-0.05355215135144728,-0.0008162327002621311,23.93438265671257,25.099999999996967,0.0,90750.0,-1.96,-991.86,500.0,1.4909824895858765,700000
6
+ 0.0,0.0,-0.036209279021396736,0.0015397555991056738,-0.03648108018789544,-0.002488632786365513,23.0154898662025,25.099999999996967,0.0,116750.0,-2.0,-1000.0,500.0,1.4625277709960938,750000
7
+ 0.0,0.0,-0.05169099664934772,0.0018176864546242228,-0.051698235927194636,0.0013535459839891214,26.335932305081485,25.099999999996967,0.0,142750.0,-2.0,-997.28,500.0,1.4849930715560913,800000
8
+ 0.0,0.0,-0.15175102946105284,-0.013082765300770008,-0.1520390957015453,-0.006953533705881036,18.532099718656436,25.099999999996967,0.0,168750.0,-1.96,-996.1,500.0,1.4656338119506835,850000
9
+ 0.0,0.0,-0.07030068243479547,0.00258280072560366,-0.0702034941504432,0.0003916517172431362,20.69255487077614,25.099999999996967,0.0,194750.0,-1.98,-994.92,500.0,1.4958977556228639,900000
10
+ 0.0,0.0,-0.03494883412923967,0.0013694972465224042,-0.03475923993893174,0.0012520989768730335,25.333153371352903,25.099999999996967,0.0,220750.0,-1.98,-991.54,500.0,1.5121938848495484,950000
11
+ 0.0,0.0,-0.05057051754420574,0.003313339902051983,-0.050386390726983574,-0.0017527144742210004,23.0516499148903,25.099999999996967,0.0,246750.0,-1.96,-995.32,500.0,1.5047405529022218,1000000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/eval_sv.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ avg_gripper_contact_length,num_gripper_contacts,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,-0.045208679826058105,-0.009443602510246361,-0.04571010759770992,-0.007946844763457486,19.476030277234205,25.099999999996967,0.0,12750.0,-1.96,-990.88,500.0,1.4522244644165039,550000
3
+ 0.0,0.0,-0.04359171373519688,-0.024133958213104517,-0.044084560323540294,-0.010180918311127241,20.001843563998072,25.099999999996967,0.0,38750.0,-1.98,-994.66,500.0,1.479248185157776,600000
4
+ 0.0,0.0,-0.06188543606032704,0.008386718576667312,-0.06154777521463779,0.00656728664809419,21.691921257179477,25.099999999996967,0.0,64750.0,-2.0,-998.92,500.0,1.4703149509429931,650000
5
+ 0.0,0.0,-0.05358948324687931,0.0022794882409145163,-0.05355215135144728,-0.0008162327002621311,23.93438265671257,25.099999999996967,0.0,90750.0,-1.96,-991.86,500.0,1.4909824895858765,700000
6
+ 0.0,0.0,-0.036209279021396736,0.0015397555991056738,-0.03648108018789544,-0.002488632786365513,23.0154898662025,25.099999999996967,0.0,116750.0,-2.0,-1000.0,500.0,1.4625277709960938,750000
7
+ 0.0,0.0,-0.05169099664934772,0.0018176864546242228,-0.051698235927194636,0.0013535459839891214,26.335932305081485,25.099999999996967,0.0,142750.0,-2.0,-997.28,500.0,1.4849930715560913,800000
8
+ 0.0,0.0,-0.15175102946105284,-0.013082765300770008,-0.1520390957015453,-0.006953533705881036,18.532099718656436,25.099999999996967,0.0,168750.0,-1.96,-996.1,500.0,1.4656338119506835,850000
9
+ 0.0,0.0,-0.07030068243479547,0.00258280072560366,-0.0702034941504432,0.0003916517172431362,20.69255487077614,25.099999999996967,0.0,194750.0,-1.98,-994.92,500.0,1.4958977556228639,900000
10
+ 0.0,0.0,-0.03494883412923967,0.0013694972465224042,-0.03475923993893174,0.0012520989768730335,25.333153371352903,25.099999999996967,0.0,220750.0,-1.98,-991.54,500.0,1.5121938848495484,950000
11
+ 0.0,0.0,-0.05057051754420574,0.003313339902051983,-0.050386390726983574,-0.0017527144742210004,23.0516499148903,25.099999999996967,0.0,246750.0,-1.96,-995.32,500.0,1.5047405529022218,1000000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/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
+ 0.28151488,1.3679458,-117.57557,-196.26733,-201.60513,0.5473567,1.6540325,-1.7458922,42.865982,505000
3
+ 0.27320343,0.8818515,-114.02416,-197.31013,-202.31465,0.31733093,0.31924358,-0.2611033,21.353575,510000
4
+ 0.27288023,0.6635541,-105.08616,-196.66191,-201.62112,0.31961736,0.58451897,-0.51145786,24.18597,515000
5
+ 0.21717826,1.8525089,-113.21461,-196.82993,-201.53462,1.3462973,0.27760527,-0.50415957,29.789907,520000
6
+ 0.27447873,3.5085404,-114.78676,-196.89038,-201.73462,0.751215,0.68293566,-1.143901,48.674404,525000
7
+ 0.18240884,2.7691534,-118.447685,-198.4314,-201.98524,0.78718084,0.87146145,-0.7928112,40.355507,530000
8
+ 0.27058977,1.6293715,-116.15254,-197.22307,-201.68236,0.4680131,0.48810583,-0.48786283,33.592873,535000
9
+ 0.19864887,0.89552253,-107.78058,-197.46251,-201.7817,2.620424,3.011138,-3.2007966,87.951935,540000
10
+ 0.23265545,4.9054008,-119.63841,-197.96553,-201.92238,0.4588452,0.35057047,-0.37386054,32.864044,545000
11
+ 0.20704427,1.7377484,-116.404,-197.73976,-202.12962,0.27090666,0.6564834,-0.40423638,25.919077,550000
12
+ 0.54726166,3.6790376,-87.680374,-196.72754,-202.17487,1.2794352,0.6808947,-1.287793,58.59329,555000
13
+ 0.20342907,0.8894622,-111.42883,-197.50682,-201.7978,0.410326,0.43686277,-0.50907445,26.587254,560000
14
+ 0.20791128,1.1105734,-114.37624,-197.63121,-201.79001,1.4491473,2.5245621,-1.2903048,66.53999,565000
15
+ 0.2939803,3.0964353,-99.36632,-195.03299,-201.84224,0.83528566,2.8726315,-3.293177,83.79313,570000
16
+ 0.32355437,5.039891,-115.42413,-196.54956,-202.28564,0.77278656,1.381225,-1.5029335,47.95576,575000
17
+ 0.18365243,0.88625336,-123.4931,-198.4967,-202.39961,0.2975734,1.3179002,-0.7063966,35.20346,580000
18
+ 0.25667286,0.74812543,-126.39267,-198.5968,-201.30237,1.3177568,23.464783,-20.68448,238.22758,585000
19
+ 0.26917368,1.0241398,-108.897575,-196.15378,-202.41202,0.5315728,0.7512089,-0.58387065,32.541847,590000
20
+ 0.20999932,7.1297913,-114.124466,-197.34161,-201.29153,0.56290585,1.8172331,-1.8535792,57.777363,595000
21
+ 0.34980488,2.996516,-50.94675,-195.98485,-201.8338,0.3522152,0.30194408,-0.60609347,29.864792,600000
22
+ 0.23287001,1.283832,-112.99899,-196.43492,-201.88556,0.59573424,0.62535006,-0.6648403,30.025799,605000
23
+ 0.20733222,5.4156084,-108.31813,-195.53783,-201.9973,0.43449625,0.44626456,-0.33433348,30.98367,610000
24
+ 0.17679593,0.963052,1.6970215,-195.78557,-201.37227,0.72425824,0.90278065,-0.6197777,44.73395,615000
25
+ 0.21745202,1.700425,-107.33527,-198.11101,-202.61778,0.42532775,0.7204849,-0.83581525,29.771805,620000
26
+ 0.20381191,1.0259497,-119.65048,-198.23157,-201.89142,0.1621667,0.12525539,-0.11229912,11.691943,625000
27
+ 0.23844421,1.7597793,-120.380775,-196.8516,-202.08263,0.98163456,0.89655316,-0.8415526,43.155235,630000
28
+ 0.19640857,0.6432218,-0.19647455,-196.94397,-202.32443,0.23496918,0.21203998,-0.5150403,16.805426,635000
29
+ 0.2228381,0.50240827,-112.65958,-196.02684,-201.8109,0.9673743,10.944034,-14.124673,95.95603,640000
30
+ 0.21035776,0.32957402,-119.08429,-196.56883,-201.82741,0.2597439,0.62142384,-0.24015854,19.484793,645000
31
+ 0.23692667,2.9116364,-100.791504,-195.81944,-202.72948,3.3242607,24.696434,-34.206417,274.49,650000
32
+ 0.22429028,0.790951,-116.54854,-197.5158,-202.2497,0.21305278,0.5469615,-0.22177504,19.689455,655000
33
+ 0.22324073,5.743797,-116.58049,-197.78084,-201.91689,0.4892276,0.65391195,-0.74351454,41.698902,660000
34
+ 0.2807219,1.7126979,-4.443463,-196.1184,-202.6389,0.61890334,0.36668956,-0.51175845,24.600725,665000
35
+ 0.22769052,0.47176132,-117.85102,-196.86992,-201.94023,0.2311412,0.2545864,-0.66788805,20.402552,670000
36
+ 0.24710889,0.7650828,-112.49883,-198.5739,-201.46075,0.40726048,0.94634753,-0.3991265,28.8612,675000
37
+ 0.19586933,0.6413523,2.593665,-197.35368,-202.63179,0.21252811,0.22613311,-0.22345085,12.830652,680000
38
+ 0.2121733,1.800538,-114.68246,-197.79381,-202.6819,0.55777687,0.55496824,-0.46448857,24.08638,685000
39
+ 0.18601698,1.0308292,-104.76732,-197.7094,-202.01569,0.2612077,0.31795603,-0.45961863,20.921528,690000
40
+ 0.25067684,5.597922,-116.53043,-197.3109,-201.53462,0.4950927,0.73856056,-1.0686986,43.28185,695000
41
+ 0.2433196,0.35063756,-114.56178,-197.2335,-201.84528,2.3025396,22.944872,-23.762333,251.18472,700000
42
+ 0.18343644,0.51658046,-118.16664,-197.77913,-201.96896,0.45058432,1.5937461,-0.55113554,37.044807,705000
43
+ 0.5561836,1.3197453,-110.2334,-197.64726,-201.74164,1.3984197,2.2105432,-3.328204,91.72406,710000
44
+ 0.19259882,1.1433498,-114.36381,-197.58861,-201.69302,0.19874229,0.66855574,-0.35846078,21.190615,715000
45
+ 0.5174674,3.6081338,-106.34114,-197.1386,-202.90057,0.45915952,0.4612481,-0.5012204,30.61485,720000
46
+ 0.18387222,3.0593145,-108.32109,-197.26422,-201.98793,0.7400432,1.5449739,-1.1135386,56.20678,725000
47
+ 0.20622474,0.43268892,-113.246605,-198.23642,-202.83722,0.1705702,0.11852865,-0.20306247,12.91727,730000
48
+ 0.26115564,0.7219555,-112.14153,-197.87035,-201.46628,0.26400158,0.16126822,-0.34953716,19.397507,735000
49
+ 0.1838325,1.2934164,1.0252949,-195.79349,-202.30888,0.5783698,0.5941217,-0.47271237,40.044468,740000
50
+ 0.20743918,1.6359543,-118.39907,-196.5624,-201.62025,0.22131145,0.31305873,-0.3589571,19.365173,745000
51
+ 0.342717,1.9268992,-106.142296,-196.74245,-201.49142,0.30690774,0.42956075,-0.4346062,29.057062,750000
52
+ 0.39888537,2.9546206,-115.51216,-197.97148,-201.96727,0.29927617,0.36201042,-0.76751834,36.117203,755000
53
+ 0.25550774,0.69708544,1.5863101,-196.9575,-201.42139,0.35720944,1.362993,-0.8911854,32.050552,760000
54
+ 0.30542928,0.9014816,-120.474686,-198.0811,-202.55956,0.30944538,0.34409022,-0.25772864,26.4512,765000
55
+ 0.21454956,1.5189804,-103.21516,-196.44168,-201.75328,0.4965789,0.47857141,-0.31988594,23.304667,770000
56
+ 0.2946815,7.125183,-52.90066,-197.10245,-201.92921,0.51495355,0.9057102,-0.9378179,52.493298,775000
57
+ 0.29272252,2.0223546,-115.97852,-197.04034,-201.716,0.26166525,0.32529357,-0.40765575,30.570107,780000
58
+ 0.21112216,0.69459873,-116.840416,-197.09535,-201.71696,0.25466192,0.4839949,-0.41814822,17.658909,785000
59
+ 0.21516418,0.5677008,-115.33554,-197.29573,-201.46992,0.2355237,0.372268,-0.27352995,15.203005,790000
60
+ 0.35048306,6.0323114,1.518379,-196.81018,-201.73032,0.5283071,1.2215377,-1.4728961,57.786854,795000
61
+ 0.19274646,1.6278225,-11.075903,-197.42288,-201.98389,1.0597178,2.827676,-1.6957632,53.74861,800000
62
+ 0.18534285,1.1293973,-103.938705,-197.33792,-201.97673,0.24593619,0.19733503,-0.29460046,19.391724,805000
63
+ 0.1942617,0.82742864,-95.54976,-196.38438,-201.55983,0.3674674,0.72673535,-0.46469298,21.283966,810000
64
+ 0.2513615,0.57039446,-115.05267,-197.93156,-201.37651,0.38246718,0.48759913,-0.39969885,24.384182,815000
65
+ 0.25541663,14.341056,-28.798662,-197.6595,-202.15845,0.4586607,0.47105017,-0.7181096,54.913162,820000
66
+ 0.23280045,0.92496175,-106.32727,-197.34691,-201.80602,0.27314016,0.23081213,-0.61360013,24.851683,825000
67
+ 0.1799389,0.5382301,-116.66339,-198.6927,-202.85634,0.50182265,1.2207873,-0.52330506,32.217194,830000
68
+ 0.18431965,3.106555,-14.728426,-195.71803,-201.97372,0.5069317,2.0661137,-2.009743,50.197533,835000
69
+ 0.3109461,2.0052853,-113.99501,-198.01773,-201.8755,0.55111736,0.45289674,-0.5201333,26.485298,840000
70
+ 0.26204938,2.2099895,-115.29876,-198.38446,-201.51923,0.43229246,0.45427436,-1.3061216,36.417953,845000
71
+ 0.39554882,1.6936333,-96.29887,-195.7379,-201.74887,0.51444554,0.67240566,-0.6275097,33.671074,850000
72
+ 0.35058117,0.797997,-144.38356,-198.98204,-201.67049,0.24330299,0.5086603,-0.5508972,22.609514,855000
73
+ 0.2424115,3.607502,-116.501945,-197.72685,-201.94107,0.30781993,0.2821566,-0.5467718,33.00189,860000
74
+ 0.24931444,2.2267907,-63.42356,-197.50822,-201.73557,0.7519123,0.55299306,-0.64862907,38.55998,865000
75
+ 0.30314243,0.68746173,-6.8432083,-197.22166,-201.68391,1.107604,0.45256907,-1.2043123,40.82213,870000
76
+ 0.17858481,4.9079185,1.4815458,-195.68713,-201.56258,0.361052,0.9543465,-0.41194147,40.93859,875000
77
+ 0.2547429,0.8216201,-109.524475,-198.16957,-201.82434,0.37077633,0.55655074,-0.5496283,29.920786,880000
78
+ 0.13830899,3.5438817,-35.59545,-197.37263,-201.7524,0.38688,0.51881355,-0.7030177,27.959583,885000
79
+ 0.21345022,1.0047772,-113.33901,-198.40157,-201.20174,0.1638509,0.38660938,-0.2901807,18.211798,890000
80
+ 0.20016423,0.6836743,-128.68051,-198.7656,-201.67204,0.27244282,0.3877259,-0.7865525,27.882278,895000
81
+ 0.2176958,5.7559314,-8.439866,-195.71028,-201.7041,0.50807965,0.56410813,-0.40820423,34.89879,900000
82
+ 0.22371714,8.141101,-117.69934,-197.3199,-202.3908,0.5161405,1.1499469,-0.72085965,34.278664,905000
83
+ 0.19294196,0.750726,-107.05853,-198.13867,-202.03969,0.20104943,0.4446591,-0.18358262,14.345686,910000
84
+ 0.44288665,0.8703701,-83.0558,-197.37979,-201.37357,1.6488875,1.5900047,-1.9246057,47.483368,915000
85
+ 0.2502564,0.93681777,-109.61879,-196.37273,-201.49348,0.77336514,0.90091616,-0.99384695,38.94538,920000
86
+ 0.18045104,2.6536875,-116.96084,-197.25926,-202.77849,0.24716902,0.20564084,-0.19198194,19.724516,925000
87
+ 0.18700318,3.4181633,-107.43266,-197.43373,-202.22858,0.25894508,3.6463504,-4.1287622,91.958466,930000
88
+ 0.2197352,0.64853996,-117.80402,-197.00378,-201.56564,0.35504135,0.8208639,-0.9416095,33.029896,935000
89
+ 0.27855515,1.9775794,-111.84432,-196.79407,-201.39027,0.5546989,0.4992905,-0.6635656,29.005682,940000
90
+ 0.21411197,0.1813355,-106.01232,-196.78,-201.42703,0.26119184,0.19236724,-0.46903753,17.143261,945000
91
+ 0.47639832,2.0799088,-104.056694,-196.35103,-201.76283,0.50088924,0.60990757,-1.2370815,52.305363,950000
92
+ 0.24203944,1.4328291,-108.03511,-198.30064,-202.72194,0.22935477,0.3288415,-0.31413868,20.92698,955000
93
+ 0.16525133,0.37330374,-115.08775,-198.45479,-201.3627,0.12580411,0.1513339,-0.22423577,13.818131,960000
94
+ 0.25764734,2.149467,-114.82085,-198.3171,-201.8747,0.67621654,0.8581521,-0.46659857,33.170395,965000
95
+ 0.23798777,0.81865627,-108.886406,-196.85611,-201.69499,0.20447679,0.21806982,-0.179387,12.928571,970000
96
+ 0.19391151,0.7437521,-116.47728,-197.01656,-202.24945,0.30134866,0.3109061,-0.57164663,22.965488,975000
97
+ 0.2193725,2.0909705,1.911398,-196.5345,-201.60338,0.43130064,0.5324235,-0.6716699,26.362938,980000
98
+ 0.19416448,1.4691485,-127.62163,-197.78995,-201.47626,0.32404184,0.35760576,-0.29358342,26.073727,985000
99
+ 0.45503724,1.5672207,-115.73127,-197.866,-201.90178,0.86495936,0.4736203,-0.95301783,40.679337,990000
100
+ 0.191916,0.7574911,-39.409218,-195.85443,-202.08179,0.25690138,0.22509296,-0.22975853,14.134158,995000
101
+ 0.194795,6.4382157,-115.57567,-197.69698,-201.41603,0.49787083,1.2578332,-1.2705175,52.097664,1000000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/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
+ 0.28151488,1.3679458,-117.57557,-196.26733,-201.60513,0.5473567,1.6540325,-1.7458922,42.865982,505000
3
+ 0.27320343,0.8818515,-114.02416,-197.31013,-202.31465,0.31733093,0.31924358,-0.2611033,21.353575,510000
4
+ 0.27288023,0.6635541,-105.08616,-196.66191,-201.62112,0.31961736,0.58451897,-0.51145786,24.18597,515000
5
+ 0.21717826,1.8525089,-113.21461,-196.82993,-201.53462,1.3462973,0.27760527,-0.50415957,29.789907,520000
6
+ 0.27447873,3.5085404,-114.78676,-196.89038,-201.73462,0.751215,0.68293566,-1.143901,48.674404,525000
7
+ 0.18240884,2.7691534,-118.447685,-198.4314,-201.98524,0.78718084,0.87146145,-0.7928112,40.355507,530000
8
+ 0.27058977,1.6293715,-116.15254,-197.22307,-201.68236,0.4680131,0.48810583,-0.48786283,33.592873,535000
9
+ 0.19864887,0.89552253,-107.78058,-197.46251,-201.7817,2.620424,3.011138,-3.2007966,87.951935,540000
10
+ 0.23265545,4.9054008,-119.63841,-197.96553,-201.92238,0.4588452,0.35057047,-0.37386054,32.864044,545000
11
+ 0.20704427,1.7377484,-116.404,-197.73976,-202.12962,0.27090666,0.6564834,-0.40423638,25.919077,550000
12
+ 0.54726166,3.6790376,-87.680374,-196.72754,-202.17487,1.2794352,0.6808947,-1.287793,58.59329,555000
13
+ 0.20342907,0.8894622,-111.42883,-197.50682,-201.7978,0.410326,0.43686277,-0.50907445,26.587254,560000
14
+ 0.20791128,1.1105734,-114.37624,-197.63121,-201.79001,1.4491473,2.5245621,-1.2903048,66.53999,565000
15
+ 0.2939803,3.0964353,-99.36632,-195.03299,-201.84224,0.83528566,2.8726315,-3.293177,83.79313,570000
16
+ 0.32355437,5.039891,-115.42413,-196.54956,-202.28564,0.77278656,1.381225,-1.5029335,47.95576,575000
17
+ 0.18365243,0.88625336,-123.4931,-198.4967,-202.39961,0.2975734,1.3179002,-0.7063966,35.20346,580000
18
+ 0.25667286,0.74812543,-126.39267,-198.5968,-201.30237,1.3177568,23.464783,-20.68448,238.22758,585000
19
+ 0.26917368,1.0241398,-108.897575,-196.15378,-202.41202,0.5315728,0.7512089,-0.58387065,32.541847,590000
20
+ 0.20999932,7.1297913,-114.124466,-197.34161,-201.29153,0.56290585,1.8172331,-1.8535792,57.777363,595000
21
+ 0.34980488,2.996516,-50.94675,-195.98485,-201.8338,0.3522152,0.30194408,-0.60609347,29.864792,600000
22
+ 0.23287001,1.283832,-112.99899,-196.43492,-201.88556,0.59573424,0.62535006,-0.6648403,30.025799,605000
23
+ 0.20733222,5.4156084,-108.31813,-195.53783,-201.9973,0.43449625,0.44626456,-0.33433348,30.98367,610000
24
+ 0.17679593,0.963052,1.6970215,-195.78557,-201.37227,0.72425824,0.90278065,-0.6197777,44.73395,615000
25
+ 0.21745202,1.700425,-107.33527,-198.11101,-202.61778,0.42532775,0.7204849,-0.83581525,29.771805,620000
26
+ 0.20381191,1.0259497,-119.65048,-198.23157,-201.89142,0.1621667,0.12525539,-0.11229912,11.691943,625000
27
+ 0.23844421,1.7597793,-120.380775,-196.8516,-202.08263,0.98163456,0.89655316,-0.8415526,43.155235,630000
28
+ 0.19640857,0.6432218,-0.19647455,-196.94397,-202.32443,0.23496918,0.21203998,-0.5150403,16.805426,635000
29
+ 0.2228381,0.50240827,-112.65958,-196.02684,-201.8109,0.9673743,10.944034,-14.124673,95.95603,640000
30
+ 0.21035776,0.32957402,-119.08429,-196.56883,-201.82741,0.2597439,0.62142384,-0.24015854,19.484793,645000
31
+ 0.23692667,2.9116364,-100.791504,-195.81944,-202.72948,3.3242607,24.696434,-34.206417,274.49,650000
32
+ 0.22429028,0.790951,-116.54854,-197.5158,-202.2497,0.21305278,0.5469615,-0.22177504,19.689455,655000
33
+ 0.22324073,5.743797,-116.58049,-197.78084,-201.91689,0.4892276,0.65391195,-0.74351454,41.698902,660000
34
+ 0.2807219,1.7126979,-4.443463,-196.1184,-202.6389,0.61890334,0.36668956,-0.51175845,24.600725,665000
35
+ 0.22769052,0.47176132,-117.85102,-196.86992,-201.94023,0.2311412,0.2545864,-0.66788805,20.402552,670000
36
+ 0.24710889,0.7650828,-112.49883,-198.5739,-201.46075,0.40726048,0.94634753,-0.3991265,28.8612,675000
37
+ 0.19586933,0.6413523,2.593665,-197.35368,-202.63179,0.21252811,0.22613311,-0.22345085,12.830652,680000
38
+ 0.2121733,1.800538,-114.68246,-197.79381,-202.6819,0.55777687,0.55496824,-0.46448857,24.08638,685000
39
+ 0.18601698,1.0308292,-104.76732,-197.7094,-202.01569,0.2612077,0.31795603,-0.45961863,20.921528,690000
40
+ 0.25067684,5.597922,-116.53043,-197.3109,-201.53462,0.4950927,0.73856056,-1.0686986,43.28185,695000
41
+ 0.2433196,0.35063756,-114.56178,-197.2335,-201.84528,2.3025396,22.944872,-23.762333,251.18472,700000
42
+ 0.18343644,0.51658046,-118.16664,-197.77913,-201.96896,0.45058432,1.5937461,-0.55113554,37.044807,705000
43
+ 0.5561836,1.3197453,-110.2334,-197.64726,-201.74164,1.3984197,2.2105432,-3.328204,91.72406,710000
44
+ 0.19259882,1.1433498,-114.36381,-197.58861,-201.69302,0.19874229,0.66855574,-0.35846078,21.190615,715000
45
+ 0.5174674,3.6081338,-106.34114,-197.1386,-202.90057,0.45915952,0.4612481,-0.5012204,30.61485,720000
46
+ 0.18387222,3.0593145,-108.32109,-197.26422,-201.98793,0.7400432,1.5449739,-1.1135386,56.20678,725000
47
+ 0.20622474,0.43268892,-113.246605,-198.23642,-202.83722,0.1705702,0.11852865,-0.20306247,12.91727,730000
48
+ 0.26115564,0.7219555,-112.14153,-197.87035,-201.46628,0.26400158,0.16126822,-0.34953716,19.397507,735000
49
+ 0.1838325,1.2934164,1.0252949,-195.79349,-202.30888,0.5783698,0.5941217,-0.47271237,40.044468,740000
50
+ 0.20743918,1.6359543,-118.39907,-196.5624,-201.62025,0.22131145,0.31305873,-0.3589571,19.365173,745000
51
+ 0.342717,1.9268992,-106.142296,-196.74245,-201.49142,0.30690774,0.42956075,-0.4346062,29.057062,750000
52
+ 0.39888537,2.9546206,-115.51216,-197.97148,-201.96727,0.29927617,0.36201042,-0.76751834,36.117203,755000
53
+ 0.25550774,0.69708544,1.5863101,-196.9575,-201.42139,0.35720944,1.362993,-0.8911854,32.050552,760000
54
+ 0.30542928,0.9014816,-120.474686,-198.0811,-202.55956,0.30944538,0.34409022,-0.25772864,26.4512,765000
55
+ 0.21454956,1.5189804,-103.21516,-196.44168,-201.75328,0.4965789,0.47857141,-0.31988594,23.304667,770000
56
+ 0.2946815,7.125183,-52.90066,-197.10245,-201.92921,0.51495355,0.9057102,-0.9378179,52.493298,775000
57
+ 0.29272252,2.0223546,-115.97852,-197.04034,-201.716,0.26166525,0.32529357,-0.40765575,30.570107,780000
58
+ 0.21112216,0.69459873,-116.840416,-197.09535,-201.71696,0.25466192,0.4839949,-0.41814822,17.658909,785000
59
+ 0.21516418,0.5677008,-115.33554,-197.29573,-201.46992,0.2355237,0.372268,-0.27352995,15.203005,790000
60
+ 0.35048306,6.0323114,1.518379,-196.81018,-201.73032,0.5283071,1.2215377,-1.4728961,57.786854,795000
61
+ 0.19274646,1.6278225,-11.075903,-197.42288,-201.98389,1.0597178,2.827676,-1.6957632,53.74861,800000
62
+ 0.18534285,1.1293973,-103.938705,-197.33792,-201.97673,0.24593619,0.19733503,-0.29460046,19.391724,805000
63
+ 0.1942617,0.82742864,-95.54976,-196.38438,-201.55983,0.3674674,0.72673535,-0.46469298,21.283966,810000
64
+ 0.2513615,0.57039446,-115.05267,-197.93156,-201.37651,0.38246718,0.48759913,-0.39969885,24.384182,815000
65
+ 0.25541663,14.341056,-28.798662,-197.6595,-202.15845,0.4586607,0.47105017,-0.7181096,54.913162,820000
66
+ 0.23280045,0.92496175,-106.32727,-197.34691,-201.80602,0.27314016,0.23081213,-0.61360013,24.851683,825000
67
+ 0.1799389,0.5382301,-116.66339,-198.6927,-202.85634,0.50182265,1.2207873,-0.52330506,32.217194,830000
68
+ 0.18431965,3.106555,-14.728426,-195.71803,-201.97372,0.5069317,2.0661137,-2.009743,50.197533,835000
69
+ 0.3109461,2.0052853,-113.99501,-198.01773,-201.8755,0.55111736,0.45289674,-0.5201333,26.485298,840000
70
+ 0.26204938,2.2099895,-115.29876,-198.38446,-201.51923,0.43229246,0.45427436,-1.3061216,36.417953,845000
71
+ 0.39554882,1.6936333,-96.29887,-195.7379,-201.74887,0.51444554,0.67240566,-0.6275097,33.671074,850000
72
+ 0.35058117,0.797997,-144.38356,-198.98204,-201.67049,0.24330299,0.5086603,-0.5508972,22.609514,855000
73
+ 0.2424115,3.607502,-116.501945,-197.72685,-201.94107,0.30781993,0.2821566,-0.5467718,33.00189,860000
74
+ 0.24931444,2.2267907,-63.42356,-197.50822,-201.73557,0.7519123,0.55299306,-0.64862907,38.55998,865000
75
+ 0.30314243,0.68746173,-6.8432083,-197.22166,-201.68391,1.107604,0.45256907,-1.2043123,40.82213,870000
76
+ 0.17858481,4.9079185,1.4815458,-195.68713,-201.56258,0.361052,0.9543465,-0.41194147,40.93859,875000
77
+ 0.2547429,0.8216201,-109.524475,-198.16957,-201.82434,0.37077633,0.55655074,-0.5496283,29.920786,880000
78
+ 0.13830899,3.5438817,-35.59545,-197.37263,-201.7524,0.38688,0.51881355,-0.7030177,27.959583,885000
79
+ 0.21345022,1.0047772,-113.33901,-198.40157,-201.20174,0.1638509,0.38660938,-0.2901807,18.211798,890000
80
+ 0.20016423,0.6836743,-128.68051,-198.7656,-201.67204,0.27244282,0.3877259,-0.7865525,27.882278,895000
81
+ 0.2176958,5.7559314,-8.439866,-195.71028,-201.7041,0.50807965,0.56410813,-0.40820423,34.89879,900000
82
+ 0.22371714,8.141101,-117.69934,-197.3199,-202.3908,0.5161405,1.1499469,-0.72085965,34.278664,905000
83
+ 0.19294196,0.750726,-107.05853,-198.13867,-202.03969,0.20104943,0.4446591,-0.18358262,14.345686,910000
84
+ 0.44288665,0.8703701,-83.0558,-197.37979,-201.37357,1.6488875,1.5900047,-1.9246057,47.483368,915000
85
+ 0.2502564,0.93681777,-109.61879,-196.37273,-201.49348,0.77336514,0.90091616,-0.99384695,38.94538,920000
86
+ 0.18045104,2.6536875,-116.96084,-197.25926,-202.77849,0.24716902,0.20564084,-0.19198194,19.724516,925000
87
+ 0.18700318,3.4181633,-107.43266,-197.43373,-202.22858,0.25894508,3.6463504,-4.1287622,91.958466,930000
88
+ 0.2197352,0.64853996,-117.80402,-197.00378,-201.56564,0.35504135,0.8208639,-0.9416095,33.029896,935000
89
+ 0.27855515,1.9775794,-111.84432,-196.79407,-201.39027,0.5546989,0.4992905,-0.6635656,29.005682,940000
90
+ 0.21411197,0.1813355,-106.01232,-196.78,-201.42703,0.26119184,0.19236724,-0.46903753,17.143261,945000
91
+ 0.47639832,2.0799088,-104.056694,-196.35103,-201.76283,0.50088924,0.60990757,-1.2370815,52.305363,950000
92
+ 0.24203944,1.4328291,-108.03511,-198.30064,-202.72194,0.22935477,0.3288415,-0.31413868,20.92698,955000
93
+ 0.16525133,0.37330374,-115.08775,-198.45479,-201.3627,0.12580411,0.1513339,-0.22423577,13.818131,960000
94
+ 0.25764734,2.149467,-114.82085,-198.3171,-201.8747,0.67621654,0.8581521,-0.46659857,33.170395,965000
95
+ 0.23798777,0.81865627,-108.886406,-196.85611,-201.69499,0.20447679,0.21806982,-0.179387,12.928571,970000
96
+ 0.19391151,0.7437521,-116.47728,-197.01656,-202.24945,0.30134866,0.3109061,-0.57164663,22.965488,975000
97
+ 0.2193725,2.0909705,1.911398,-196.5345,-201.60338,0.43130064,0.5324235,-0.6716699,26.362938,980000
98
+ 0.19416448,1.4691485,-127.62163,-197.78995,-201.47626,0.32404184,0.35760576,-0.29358342,26.073727,985000
99
+ 0.45503724,1.5672207,-115.73127,-197.866,-201.90178,0.86495936,0.4736203,-0.95301783,40.679337,990000
100
+ 0.191916,0.7574911,-39.409218,-195.85443,-202.08179,0.25690138,0.22509296,-0.22975853,14.134158,995000
101
+ 0.194795,6.4382157,-115.57567,-197.69698,-201.41603,0.49787083,1.2578332,-1.2705175,52.097664,1000000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2219465d95888f8d3a376f9993e4e609a591b370fbbc92b9559b5cb30b3ab8b
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c285151f400c50896c60b64b895a418792a9d4768464bfff111c996adde318c4
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d94c0eb67a5094a6a06165faf403a0733095e736b8d8de3fe7f38ee3b016d35
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de36fd6940ef3b12175bf76388cceb2bd6b90096e912c4247e79c7cbbf2639bd
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa74e3dcf6edb0e80663f056f27a0822c1b3642dc6eb281f520208f72d1e2f18
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea19d74ae9e0b6eff57b84e463c0a0eea44e516d4c7d9b0410a45de05abc26f
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00e27fed6c59f961e18594232a1f4fe3e7a61092570ef5f4e654e03b26e70c6
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b408704888ac71a57405b5e22096d2774763660c5aa117c819810682e073c2c
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9ef4429b8ac78d8031b2a26f42a58b61a9dce85a6c68269d9d60cbc2c2b68e
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eca2cafd53d5568aa0b7e33bbd1652decd5c89c89c4a920c58e0235bae27fc6
3
+ size 217718393
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fawac/20260311_034054/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-reproduce/runs/37qoaol1