Tiredsheep commited on
Commit
2a701d9
·
verified ·
1 Parent(s): 2cb15af

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_350000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_400000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_450000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_500000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_550000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_600000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_650000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_700000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_750000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_800000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/token.tk +1 -0
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/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,-0.1529013358395068,0.007387254705422741,-0.1529957310725126,0.0052695215290464795,14.135388613167425,45.8410000000137,0.1,23244.14,-1.04,-1021.48,914.82,2.684366087913513,350000
3
+ 0.0,0.0,-0.05559512331346316,-0.03090650828216861,-0.058822381202045276,-0.03959899829459671,11.568698581668409,49.121000000014966,0.02,72111.58,-1.0,-999.64,980.42,2.8308051681518553,400000
4
+ 0.0,0.0,-0.05673273083445942,-0.04269176017109702,-0.05671682596130039,-0.021570025475844704,22.023570724227664,49.32600000001497,0.02,124014.6,-1.0,-1001.4,984.52,2.891884140968323,450000
5
+ 0.0,0.0,-0.05802163687628217,-0.08621652327752224,-0.05733044022540152,0.017279775482631758,20.642217490393847,50.10000000001527,0.0,174609.0,-1.02,-1016.5,1000.0,2.93879008769989,500000
6
+ 0.0,0.0,-0.030774772905158898,0.04051110331752179,-0.031029943084793534,-0.02171824448015815,24.845332782231708,50.10000000001527,0.0,226609.0,-1.0,-1000.0,1000.0,2.9716926622390747,550000
7
+ 0.0,0.0,-0.03404655270869859,0.08580529722208227,-0.033919902278258814,-0.008946934657174211,24.93318889769866,50.10000000001527,0.0,278609.0,-1.02,-1016.68,1000.0,2.9741486930847167,600000
8
+ 0.0,0.0,0.014844828824648553,0.10170227545664318,0.016227769228942875,0.001363745352311514,27.480999796621973,50.10000000001527,0.0,330609.0,-1.0,-1000.0,1000.0,2.929214458465576,650000
9
+ 0.0,0.0,-0.033097229561323646,-0.03900679732878073,-0.032607762042908245,0.011919296441182139,26.282173969778658,50.10000000001527,0.0,382609.0,-1.0,-1000.0,1000.0,2.9111577081680298,700000
10
+ 0.0,0.0,-0.016779065745769355,-0.02946913587786942,-0.01474306040634517,0.040127189979372396,27.229938939486413,50.10000000001527,0.0,434609.0,-1.04,-1037.26,1000.0,2.950404767990112,750000
11
+ 0.0,0.0,-0.037869760674059755,-0.013409799076921365,-0.03464787061085175,0.046933303845022166,31.387938664193378,50.10000000001527,0.0,486609.0,-1.06,-1026.1,1000.0,2.9661246013641356,800000
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/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,-0.1529013358395068,0.007387254705422741,-0.1529957310725126,0.0052695215290464795,14.135388613167425,45.8410000000137,0.1,23244.14,-1.04,-1021.48,914.82,2.684366087913513,350000
3
+ 0.0,0.0,-0.05559512331346316,-0.03090650828216861,-0.058822381202045276,-0.03959899829459671,11.568698581668409,49.121000000014966,0.02,72111.58,-1.0,-999.64,980.42,2.8308051681518553,400000
4
+ 0.0,0.0,-0.05673273083445942,-0.04269176017109702,-0.05671682596130039,-0.021570025475844704,22.023570724227664,49.32600000001497,0.02,124014.6,-1.0,-1001.4,984.52,2.891884140968323,450000
5
+ 0.0,0.0,-0.05802163687628217,-0.08621652327752224,-0.05733044022540152,0.017279775482631758,20.642217490393847,50.10000000001527,0.0,174609.0,-1.02,-1016.5,1000.0,2.93879008769989,500000
6
+ 0.0,0.0,-0.030774772905158898,0.04051110331752179,-0.031029943084793534,-0.02171824448015815,24.845332782231708,50.10000000001527,0.0,226609.0,-1.0,-1000.0,1000.0,2.9716926622390747,550000
7
+ 0.0,0.0,-0.03404655270869859,0.08580529722208227,-0.033919902278258814,-0.008946934657174211,24.93318889769866,50.10000000001527,0.0,278609.0,-1.02,-1016.68,1000.0,2.9741486930847167,600000
8
+ 0.0,0.0,0.014844828824648553,0.10170227545664318,0.016227769228942875,0.001363745352311514,27.480999796621973,50.10000000001527,0.0,330609.0,-1.0,-1000.0,1000.0,2.929214458465576,650000
9
+ 0.0,0.0,-0.033097229561323646,-0.03900679732878073,-0.032607762042908245,0.011919296441182139,26.282173969778658,50.10000000001527,0.0,382609.0,-1.0,-1000.0,1000.0,2.9111577081680298,700000
10
+ 0.0,0.0,-0.016779065745769355,-0.02946913587786942,-0.01474306040634517,0.040127189979372396,27.229938939486413,50.10000000001527,0.0,434609.0,-1.04,-1037.26,1000.0,2.950404767990112,750000
11
+ 0.0,0.0,-0.037869760674059755,-0.013409799076921365,-0.03464787061085175,0.046933303845022166,31.387938664193378,50.10000000001527,0.0,486609.0,-1.06,-1026.1,1000.0,2.9661246013641356,800000
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/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
+ 5871.761,1.8940518,4.9160805,-71.973625,-183.17738,-247.7591,27.25654,-33.51241,685.3143,305000
3
+ 5767.6646,2.4004653,3.0423431,-96.39906,-179.74226,-251.41548,15.600574,-21.566353,609.393,310000
4
+ 5787.9375,1.9022315,3.8694978,-74.47595,-179.79214,-243.87955,26.68996,-26.129463,638.5002,315000
5
+ 5970.872,2.5217338,4.0310645,-117.3646,-185.47081,-259.1901,16.124487,-9.217263,270.90063,320000
6
+ 5918.931,1.8362584,3.9201531,-70.76561,-184.43526,-259.50424,63.18038,-65.2398,1401.5398,325000
7
+ 6031.963,1.5414059,3.5426233,2.8211284,-187.4723,-270.93835,49.34029,-51.738285,916.8313,330000
8
+ 5993.9014,1.9057289,3.3171303,-91.53526,-186.47679,-261.4422,10.074384,-10.678245,319.93088,335000
9
+ 5953.762,1.3163637,3.0086262,-57.883633,-184.97795,-261.83664,14.447363,-14.306351,289.26672,340000
10
+ 5992.206,2.0833223,3.440588,-83.22244,-186.27632,-261.18634,8.691721,-8.342062,357.2897,345000
11
+ 5959.2256,2.1419008,3.4358215,-85.182144,-184.85014,-259.92587,10.31107,-12.101198,557.7657,350000
12
+ 5882.2715,1.7070062,3.250454,-85.31149,-182.80054,-259.5661,10.131124,-9.325752,425.98157,355000
13
+ 5847.9956,1.5057335,3.4198728,-84.39395,-181.97069,-251.39496,8.991304,-10.474677,466.5335,360000
14
+ 5860.804,2.0430913,3.7112477,-91.53927,-182.1335,-248.5907,13.337586,-22.221615,297.0511,365000
15
+ 5800.087,1.6587083,3.1444876,-62.708496,-180.18211,-250.13515,6.160703,-6.5921106,364.04724,370000
16
+ 5759.017,2.2424946,3.6985207,-24.74614,-179.39458,-251.60928,20.335772,-20.669256,537.0994,375000
17
+ 5755.975,1.6269033,2.5202339,-77.458626,-179.16582,-250.87643,17.559488,-15.781049,469.44482,380000
18
+ 5875.037,1.7859343,4.082632,-26.371931,-182.91643,-259.38153,10.410599,-8.446141,241.41809,385000
19
+ 5929.46,1.719175,2.7735863,-90.837975,-184.32141,-261.22202,7.9525747,-8.881372,326.30072,390000
20
+ 5941.4116,1.9825529,2.152355,-96.71609,-184.51,-254.61523,32.14979,-28.460276,352.21957,395000
21
+ 5898.4424,1.7445388,2.5800514,-76.804695,-182.92206,-254.76103,12.19736,-7.1175885,287.2394,400000
22
+ 6045.312,1.3643417,2.8479002,-75.30816,-187.79968,-269.97708,22.937202,-21.565231,480.8301,405000
23
+ 6018.711,1.7174886,4.3093896,-90.68037,-186.93436,-260.18637,13.3165865,-13.778155,507.78806,410000
24
+ 5910.6113,1.7932918,3.022249,-77.90943,-183.38907,-250.31328,28.484774,-14.00899,597.224,415000
25
+ 5898.3633,1.7706356,2.579974,-89.713585,-182.89513,-259.94028,32.71228,-56.737854,476.192,420000
26
+ 5975.024,2.4498954,3.5148857,-52.366383,-185.48396,-253.99306,59.162846,-68.25073,1023.0222,425000
27
+ 5928.88,1.6927743,2.4773583,-92.527954,-184.1361,-261.7881,11.4037895,-23.146353,333.95212,430000
28
+ 5944.0117,2.0342813,2.4488251,-94.59694,-184.48595,-246.95193,8.664401,-6.2781234,287.4193,435000
29
+ 5926.051,2.0116785,2.3165624,-94.390366,-183.74069,-255.95535,22.054932,-20.227497,409.61172,440000
30
+ 5898.253,1.6544138,2.6246574,-94.341225,-182.69475,-257.6528,39.87038,-49.697197,1672.844,445000
31
+ 5903.6797,1.7188969,2.7460034,-88.200096,-183.45625,-253.81418,26.916037,-41.512817,372.47403,450000
32
+ 5990.394,1.905662,2.4379544,-68.71985,-185.57994,-251.6649,58.926952,-156.05214,861.6428,455000
33
+ 5874.351,1.6283517,2.2525918,-59.164803,-182.02855,-257.94394,15.890784,-9.504339,309.6079,460000
34
+ 5989.9844,1.98539,3.692476,-79.615265,-185.53732,-254.55038,20.398167,-23.559937,684.57837,465000
35
+ 5876.2866,2.0502434,3.1392672,-95.44137,-182.36873,-261.04666,23.951519,-14.06487,584.0054,470000
36
+ 5971.3696,2.6213546,2.5122895,-82.67604,-184.7849,-250.73167,10.525334,-27.705227,303.85828,475000
37
+ 5856.9863,1.571575,2.0271382,-88.938446,-181.6251,-251.11667,35.46268,-29.585922,481.19006,480000
38
+ 5867.75,2.1570697,2.6787584,-87.33108,-181.95786,-252.36604,32.63075,-10.4113035,462.72998,485000
39
+ 5846.1416,2.014437,2.2257402,-96.13499,-181.42357,-261.0154,50.217506,-63.366837,722.66986,490000
40
+ 5931.6084,2.2508614,2.1499608,-96.46583,-184.09534,-251.39644,30.913555,-59.563652,599.4583,495000
41
+ 5861.83,2.0514169,2.1049678,-86.900665,-181.50931,-259.8536,8.420232,-8.2506275,401.22958,500000
42
+ 5876.2017,2.89613,2.5082753,-95.38497,-181.91472,-260.45804,6.735146,-9.543273,336.76605,505000
43
+ 5869.486,2.6086543,2.5674431,-72.146545,-182.02739,-251.89467,9.436847,-7.7110767,275.4989,510000
44
+ 5850.4805,1.5705206,1.9398426,-83.25954,-181.57109,-253.86156,71.28126,-59.415558,1357.3552,515000
45
+ 5825.5913,2.0412621,5.522357,-97.2926,-180.85915,-249.84354,27.756975,-22.687277,781.5454,520000
46
+ 5953.1265,2.2045348,2.4004002,-93.83519,-184.81783,-265.58755,19.634031,-24.209661,667.28864,525000
47
+ 5913.1304,2.0133016,2.521835,-89.607086,-183.37158,-250.35965,59.481365,-65.12344,1103.1454,530000
48
+ 5851.655,2.1286647,2.14639,-12.304062,-181.42969,-253.01567,34.394444,-7.8190594,307.05096,535000
49
+ 5904.866,2.4851723,2.6517675,-99.15173,-182.85716,-251.68933,58.32393,-80.10318,1220.663,540000
50
+ 5814.0654,1.8459404,2.999852,-97.46455,-180.45425,-255.82928,171.2289,-158.98488,6498.887,545000
51
+ 6065.9087,2.5724669,5.335911,-96.40325,-188.05467,-261.43042,56.099754,-58.139378,866.1064,550000
52
+ 5898.76,1.7048187,2.3660047,-86.622696,-182.27017,-246.5999,24.31015,-28.83389,487.90588,555000
53
+ 5950.996,2.1459084,2.446482,-97.51486,-184.08269,-265.41873,28.665068,-27.15967,540.08093,560000
54
+ 5840.886,1.591218,2.2557027,-92.67232,-181.04797,-246.14133,26.806112,-35.855026,1009.96625,565000
55
+ 5831.6387,2.1885521,2.7583253,-94.36091,-181.12187,-250.27957,36.22532,-55.962116,575.6697,570000
56
+ 5851.9272,2.033605,3.2618377,-25.705158,-181.42833,-264.14655,64.98533,-48.97135,530.77637,575000
57
+ 5886.203,2.2704682,2.7947192,-84.9144,-181.86746,-257.90253,9.659061,-21.037296,277.6505,580000
58
+ 5910.828,2.3214355,2.8165882,-79.45599,-183.33229,-269.40497,11.612408,-16.156168,356.93988,585000
59
+ 5801.456,2.5063732,2.6754105,-87.880035,-179.82063,-259.07852,20.5378,-26.357876,547.83606,590000
60
+ 6076.964,2.4104042,2.438658,-87.99979,-187.84149,-254.7618,42.279274,-28.806414,557.20776,595000
61
+ 5933.0376,2.082223,1.93503,-70.19748,-183.9329,-258.29132,40.339508,-49.86485,519.39484,600000
62
+ 5846.2334,2.5691662,2.9378412,-89.88512,-181.0238,-258.6775,71.9469,-90.48192,1745.983,605000
63
+ 5771.938,2.4130108,2.392461,-85.09834,-178.94292,-265.1415,21.773771,-15.823792,309.41873,610000
64
+ 5762.5903,1.6616962,2.2130911,-82.899376,-178.73904,-252.42418,13.364055,-11.523616,275.9009,615000
65
+ 5763.46,3.4030762,2.0441422,-94.937195,-178.02054,-265.6575,15.221143,-23.573965,652.56573,620000
66
+ 5929.8267,1.8092803,3.102846,-87.66499,-183.9802,-258.12277,22.174412,-29.507719,619.2873,625000
67
+ 5855.0625,3.0521472,1.979895,-82.03159,-181.03323,-266.5971,112.10038,-50.573006,795.4246,630000
68
+ 5783.7446,1.6896547,2.2932374,-85.21176,-179.21103,-253.1659,30.261974,-31.343908,380.05634,635000
69
+ 5980.2007,3.1555839,1.8454056,-84.5769,-184.9687,-263.45605,19.733498,-18.490345,576.69116,640000
70
+ 5956.0376,1.7195438,2.3911266,-89.05576,-184.38788,-259.31546,279.33768,-166.92435,1994.7156,645000
71
+ 5882.275,2.5826416,2.6107466,-85.780624,-181.7222,-262.43417,26.2144,-18.31871,509.39108,650000
72
+ 5921.021,2.4481626,2.2081666,-87.323166,-183.39525,-261.34586,20.500835,-19.499617,419.9819,655000
73
+ 5832.102,3.7746098,2.2799945,-88.38411,-180.78246,-259.41357,38.25659,-40.83358,722.8473,660000
74
+ 6041.753,2.0196142,3.372923,-89.54133,-186.42009,-264.6956,19.99741,-32.413948,383.71216,665000
75
+ 5839.83,1.836777,1.8842337,-79.406425,-180.28917,-260.38934,51.555695,-115.19076,1081.521,670000
76
+ 5847.6934,2.08855,2.7843838,-89.62659,-181.46194,-256.5856,9.711933,-33.98868,293.5238,675000
77
+ 5915.055,1.8792295,2.186703,-88.01494,-182.9647,-259.76834,27.63028,-21.597162,392.8881,680000
78
+ 5890.183,1.7650334,2.2646089,-26.843998,-182.15482,-255.00014,65.145134,-22.292986,664.73486,685000
79
+ 5886.647,2.2237687,2.334983,-63.381298,-181.72275,-262.33368,46.164,-46.874897,1141.8491,690000
80
+ 5990.0713,1.882427,2.1411972,-66.852806,-184.8446,-260.26474,39.195442,-37.11002,724.3497,695000
81
+ 5814.591,2.7180684,1.9870274,-74.0555,-179.6571,-260.38614,188.9553,-66.324615,1223.7727,700000
82
+ 5945.476,2.3649032,2.8059661,-75.38698,-183.76347,-262.3891,25.782383,-26.681963,397.32556,705000
83
+ 5975.4185,3.1789196,2.3868985,-82.88861,-184.81224,-266.60297,71.845985,-36.424408,672.01,710000
84
+ 5853.425,1.9351764,2.2545602,-60.607464,-180.50427,-263.1289,36.95911,-20.635399,366.7785,715000
85
+ 5930.578,1.7091465,2.9165044,-86.2244,-183.62614,-255.59511,39.99667,-25.086946,745.27795,720000
86
+ 5973.6274,2.129209,2.203167,-87.09532,-184.22945,-271.65265,39.450176,-15.029682,339.02924,725000
87
+ 5874.4263,2.204812,2.6295154,-89.427536,-181.64688,-259.07254,36.713593,-25.009945,499.7856,730000
88
+ 5844.165,2.5914044,3.0874832,-72.34619,-180.90941,-257.90765,12.987067,-15.862831,289.103,735000
89
+ 5856.0786,2.080553,2.8568757,-81.042786,-181.15779,-264.91467,18.567627,-26.551252,524.6272,740000
90
+ 5795.31,2.6789055,2.2051413,-88.792404,-178.7486,-259.8927,29.473742,-35.397842,470.44495,745000
91
+ 5948.899,2.3716674,2.720589,-81.41863,-183.42369,-272.17392,104.721016,-44.14767,809.61017,750000
92
+ 5984.039,3.1282895,2.1014168,-70.31526,-184.63475,-270.7957,148.36945,-153.74132,1145.3737,755000
93
+ 5712.984,1.8049266,3.0019228,-79.894264,-176.51553,-265.97952,57.147003,-192.43077,1249.8435,760000
94
+ 5873.886,2.8307214,1.7980355,-79.48781,-180.9145,-258.41583,19.782299,-22.708702,394.83688,765000
95
+ 5903.2676,2.1837742,2.6753433,-81.96055,-182.60889,-263.75366,321.89078,-131.31073,1645.751,770000
96
+ 5843.295,2.4150283,2.16063,-74.18756,-180.5177,-259.20255,42.817543,-25.001143,575.3361,775000
97
+ 6048.0615,2.1657565,3.0755284,-85.435104,-186.7522,-268.38834,114.372635,-132.09586,2876.9993,780000
98
+ 5970.012,2.1291757,3.0120718,-77.06775,-184.27039,-262.6095,236.58716,-65.95772,1105.8915,785000
99
+ 5814.2656,2.4863524,2.4164252,-82.393524,-179.15268,-272.48264,95.57925,-152.09525,1411.3105,790000
100
+ 5724.615,2.1854732,2.1101353,-90.4183,-177.06133,-261.0391,11.025581,-16.828829,299.2559,795000
101
+ 5896.186,2.6806898,2.7020478,-82.219505,-182.28226,-257.5562,70.14204,-29.515423,480.6881,800000
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/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
+ 5871.761,1.8940518,4.9160805,-71.973625,-183.17738,-247.7591,27.25654,-33.51241,685.3143,305000
3
+ 5767.6646,2.4004653,3.0423431,-96.39906,-179.74226,-251.41548,15.600574,-21.566353,609.393,310000
4
+ 5787.9375,1.9022315,3.8694978,-74.47595,-179.79214,-243.87955,26.68996,-26.129463,638.5002,315000
5
+ 5970.872,2.5217338,4.0310645,-117.3646,-185.47081,-259.1901,16.124487,-9.217263,270.90063,320000
6
+ 5918.931,1.8362584,3.9201531,-70.76561,-184.43526,-259.50424,63.18038,-65.2398,1401.5398,325000
7
+ 6031.963,1.5414059,3.5426233,2.8211284,-187.4723,-270.93835,49.34029,-51.738285,916.8313,330000
8
+ 5993.9014,1.9057289,3.3171303,-91.53526,-186.47679,-261.4422,10.074384,-10.678245,319.93088,335000
9
+ 5953.762,1.3163637,3.0086262,-57.883633,-184.97795,-261.83664,14.447363,-14.306351,289.26672,340000
10
+ 5992.206,2.0833223,3.440588,-83.22244,-186.27632,-261.18634,8.691721,-8.342062,357.2897,345000
11
+ 5959.2256,2.1419008,3.4358215,-85.182144,-184.85014,-259.92587,10.31107,-12.101198,557.7657,350000
12
+ 5882.2715,1.7070062,3.250454,-85.31149,-182.80054,-259.5661,10.131124,-9.325752,425.98157,355000
13
+ 5847.9956,1.5057335,3.4198728,-84.39395,-181.97069,-251.39496,8.991304,-10.474677,466.5335,360000
14
+ 5860.804,2.0430913,3.7112477,-91.53927,-182.1335,-248.5907,13.337586,-22.221615,297.0511,365000
15
+ 5800.087,1.6587083,3.1444876,-62.708496,-180.18211,-250.13515,6.160703,-6.5921106,364.04724,370000
16
+ 5759.017,2.2424946,3.6985207,-24.74614,-179.39458,-251.60928,20.335772,-20.669256,537.0994,375000
17
+ 5755.975,1.6269033,2.5202339,-77.458626,-179.16582,-250.87643,17.559488,-15.781049,469.44482,380000
18
+ 5875.037,1.7859343,4.082632,-26.371931,-182.91643,-259.38153,10.410599,-8.446141,241.41809,385000
19
+ 5929.46,1.719175,2.7735863,-90.837975,-184.32141,-261.22202,7.9525747,-8.881372,326.30072,390000
20
+ 5941.4116,1.9825529,2.152355,-96.71609,-184.51,-254.61523,32.14979,-28.460276,352.21957,395000
21
+ 5898.4424,1.7445388,2.5800514,-76.804695,-182.92206,-254.76103,12.19736,-7.1175885,287.2394,400000
22
+ 6045.312,1.3643417,2.8479002,-75.30816,-187.79968,-269.97708,22.937202,-21.565231,480.8301,405000
23
+ 6018.711,1.7174886,4.3093896,-90.68037,-186.93436,-260.18637,13.3165865,-13.778155,507.78806,410000
24
+ 5910.6113,1.7932918,3.022249,-77.90943,-183.38907,-250.31328,28.484774,-14.00899,597.224,415000
25
+ 5898.3633,1.7706356,2.579974,-89.713585,-182.89513,-259.94028,32.71228,-56.737854,476.192,420000
26
+ 5975.024,2.4498954,3.5148857,-52.366383,-185.48396,-253.99306,59.162846,-68.25073,1023.0222,425000
27
+ 5928.88,1.6927743,2.4773583,-92.527954,-184.1361,-261.7881,11.4037895,-23.146353,333.95212,430000
28
+ 5944.0117,2.0342813,2.4488251,-94.59694,-184.48595,-246.95193,8.664401,-6.2781234,287.4193,435000
29
+ 5926.051,2.0116785,2.3165624,-94.390366,-183.74069,-255.95535,22.054932,-20.227497,409.61172,440000
30
+ 5898.253,1.6544138,2.6246574,-94.341225,-182.69475,-257.6528,39.87038,-49.697197,1672.844,445000
31
+ 5903.6797,1.7188969,2.7460034,-88.200096,-183.45625,-253.81418,26.916037,-41.512817,372.47403,450000
32
+ 5990.394,1.905662,2.4379544,-68.71985,-185.57994,-251.6649,58.926952,-156.05214,861.6428,455000
33
+ 5874.351,1.6283517,2.2525918,-59.164803,-182.02855,-257.94394,15.890784,-9.504339,309.6079,460000
34
+ 5989.9844,1.98539,3.692476,-79.615265,-185.53732,-254.55038,20.398167,-23.559937,684.57837,465000
35
+ 5876.2866,2.0502434,3.1392672,-95.44137,-182.36873,-261.04666,23.951519,-14.06487,584.0054,470000
36
+ 5971.3696,2.6213546,2.5122895,-82.67604,-184.7849,-250.73167,10.525334,-27.705227,303.85828,475000
37
+ 5856.9863,1.571575,2.0271382,-88.938446,-181.6251,-251.11667,35.46268,-29.585922,481.19006,480000
38
+ 5867.75,2.1570697,2.6787584,-87.33108,-181.95786,-252.36604,32.63075,-10.4113035,462.72998,485000
39
+ 5846.1416,2.014437,2.2257402,-96.13499,-181.42357,-261.0154,50.217506,-63.366837,722.66986,490000
40
+ 5931.6084,2.2508614,2.1499608,-96.46583,-184.09534,-251.39644,30.913555,-59.563652,599.4583,495000
41
+ 5861.83,2.0514169,2.1049678,-86.900665,-181.50931,-259.8536,8.420232,-8.2506275,401.22958,500000
42
+ 5876.2017,2.89613,2.5082753,-95.38497,-181.91472,-260.45804,6.735146,-9.543273,336.76605,505000
43
+ 5869.486,2.6086543,2.5674431,-72.146545,-182.02739,-251.89467,9.436847,-7.7110767,275.4989,510000
44
+ 5850.4805,1.5705206,1.9398426,-83.25954,-181.57109,-253.86156,71.28126,-59.415558,1357.3552,515000
45
+ 5825.5913,2.0412621,5.522357,-97.2926,-180.85915,-249.84354,27.756975,-22.687277,781.5454,520000
46
+ 5953.1265,2.2045348,2.4004002,-93.83519,-184.81783,-265.58755,19.634031,-24.209661,667.28864,525000
47
+ 5913.1304,2.0133016,2.521835,-89.607086,-183.37158,-250.35965,59.481365,-65.12344,1103.1454,530000
48
+ 5851.655,2.1286647,2.14639,-12.304062,-181.42969,-253.01567,34.394444,-7.8190594,307.05096,535000
49
+ 5904.866,2.4851723,2.6517675,-99.15173,-182.85716,-251.68933,58.32393,-80.10318,1220.663,540000
50
+ 5814.0654,1.8459404,2.999852,-97.46455,-180.45425,-255.82928,171.2289,-158.98488,6498.887,545000
51
+ 6065.9087,2.5724669,5.335911,-96.40325,-188.05467,-261.43042,56.099754,-58.139378,866.1064,550000
52
+ 5898.76,1.7048187,2.3660047,-86.622696,-182.27017,-246.5999,24.31015,-28.83389,487.90588,555000
53
+ 5950.996,2.1459084,2.446482,-97.51486,-184.08269,-265.41873,28.665068,-27.15967,540.08093,560000
54
+ 5840.886,1.591218,2.2557027,-92.67232,-181.04797,-246.14133,26.806112,-35.855026,1009.96625,565000
55
+ 5831.6387,2.1885521,2.7583253,-94.36091,-181.12187,-250.27957,36.22532,-55.962116,575.6697,570000
56
+ 5851.9272,2.033605,3.2618377,-25.705158,-181.42833,-264.14655,64.98533,-48.97135,530.77637,575000
57
+ 5886.203,2.2704682,2.7947192,-84.9144,-181.86746,-257.90253,9.659061,-21.037296,277.6505,580000
58
+ 5910.828,2.3214355,2.8165882,-79.45599,-183.33229,-269.40497,11.612408,-16.156168,356.93988,585000
59
+ 5801.456,2.5063732,2.6754105,-87.880035,-179.82063,-259.07852,20.5378,-26.357876,547.83606,590000
60
+ 6076.964,2.4104042,2.438658,-87.99979,-187.84149,-254.7618,42.279274,-28.806414,557.20776,595000
61
+ 5933.0376,2.082223,1.93503,-70.19748,-183.9329,-258.29132,40.339508,-49.86485,519.39484,600000
62
+ 5846.2334,2.5691662,2.9378412,-89.88512,-181.0238,-258.6775,71.9469,-90.48192,1745.983,605000
63
+ 5771.938,2.4130108,2.392461,-85.09834,-178.94292,-265.1415,21.773771,-15.823792,309.41873,610000
64
+ 5762.5903,1.6616962,2.2130911,-82.899376,-178.73904,-252.42418,13.364055,-11.523616,275.9009,615000
65
+ 5763.46,3.4030762,2.0441422,-94.937195,-178.02054,-265.6575,15.221143,-23.573965,652.56573,620000
66
+ 5929.8267,1.8092803,3.102846,-87.66499,-183.9802,-258.12277,22.174412,-29.507719,619.2873,625000
67
+ 5855.0625,3.0521472,1.979895,-82.03159,-181.03323,-266.5971,112.10038,-50.573006,795.4246,630000
68
+ 5783.7446,1.6896547,2.2932374,-85.21176,-179.21103,-253.1659,30.261974,-31.343908,380.05634,635000
69
+ 5980.2007,3.1555839,1.8454056,-84.5769,-184.9687,-263.45605,19.733498,-18.490345,576.69116,640000
70
+ 5956.0376,1.7195438,2.3911266,-89.05576,-184.38788,-259.31546,279.33768,-166.92435,1994.7156,645000
71
+ 5882.275,2.5826416,2.6107466,-85.780624,-181.7222,-262.43417,26.2144,-18.31871,509.39108,650000
72
+ 5921.021,2.4481626,2.2081666,-87.323166,-183.39525,-261.34586,20.500835,-19.499617,419.9819,655000
73
+ 5832.102,3.7746098,2.2799945,-88.38411,-180.78246,-259.41357,38.25659,-40.83358,722.8473,660000
74
+ 6041.753,2.0196142,3.372923,-89.54133,-186.42009,-264.6956,19.99741,-32.413948,383.71216,665000
75
+ 5839.83,1.836777,1.8842337,-79.406425,-180.28917,-260.38934,51.555695,-115.19076,1081.521,670000
76
+ 5847.6934,2.08855,2.7843838,-89.62659,-181.46194,-256.5856,9.711933,-33.98868,293.5238,675000
77
+ 5915.055,1.8792295,2.186703,-88.01494,-182.9647,-259.76834,27.63028,-21.597162,392.8881,680000
78
+ 5890.183,1.7650334,2.2646089,-26.843998,-182.15482,-255.00014,65.145134,-22.292986,664.73486,685000
79
+ 5886.647,2.2237687,2.334983,-63.381298,-181.72275,-262.33368,46.164,-46.874897,1141.8491,690000
80
+ 5990.0713,1.882427,2.1411972,-66.852806,-184.8446,-260.26474,39.195442,-37.11002,724.3497,695000
81
+ 5814.591,2.7180684,1.9870274,-74.0555,-179.6571,-260.38614,188.9553,-66.324615,1223.7727,700000
82
+ 5945.476,2.3649032,2.8059661,-75.38698,-183.76347,-262.3891,25.782383,-26.681963,397.32556,705000
83
+ 5975.4185,3.1789196,2.3868985,-82.88861,-184.81224,-266.60297,71.845985,-36.424408,672.01,710000
84
+ 5853.425,1.9351764,2.2545602,-60.607464,-180.50427,-263.1289,36.95911,-20.635399,366.7785,715000
85
+ 5930.578,1.7091465,2.9165044,-86.2244,-183.62614,-255.59511,39.99667,-25.086946,745.27795,720000
86
+ 5973.6274,2.129209,2.203167,-87.09532,-184.22945,-271.65265,39.450176,-15.029682,339.02924,725000
87
+ 5874.4263,2.204812,2.6295154,-89.427536,-181.64688,-259.07254,36.713593,-25.009945,499.7856,730000
88
+ 5844.165,2.5914044,3.0874832,-72.34619,-180.90941,-257.90765,12.987067,-15.862831,289.103,735000
89
+ 5856.0786,2.080553,2.8568757,-81.042786,-181.15779,-264.91467,18.567627,-26.551252,524.6272,740000
90
+ 5795.31,2.6789055,2.2051413,-88.792404,-178.7486,-259.8927,29.473742,-35.397842,470.44495,745000
91
+ 5948.899,2.3716674,2.720589,-81.41863,-183.42369,-272.17392,104.721016,-44.14767,809.61017,750000
92
+ 5984.039,3.1282895,2.1014168,-70.31526,-184.63475,-270.7957,148.36945,-153.74132,1145.3737,755000
93
+ 5712.984,1.8049266,3.0019228,-79.894264,-176.51553,-265.97952,57.147003,-192.43077,1249.8435,760000
94
+ 5873.886,2.8307214,1.7980355,-79.48781,-180.9145,-258.41583,19.782299,-22.708702,394.83688,765000
95
+ 5903.2676,2.1837742,2.6753433,-81.96055,-182.60889,-263.75366,321.89078,-131.31073,1645.751,770000
96
+ 5843.295,2.4150283,2.16063,-74.18756,-180.5177,-259.20255,42.817543,-25.001143,575.3361,775000
97
+ 6048.0615,2.1657565,3.0755284,-85.435104,-186.7522,-268.38834,114.372635,-132.09586,2876.9993,780000
98
+ 5970.012,2.1291757,3.0120718,-77.06775,-184.27039,-262.6095,236.58716,-65.95772,1105.8915,785000
99
+ 5814.2656,2.4863524,2.4164252,-82.393524,-179.15268,-272.48264,95.57925,-152.09525,1411.3105,790000
100
+ 5724.615,2.1854732,2.1101353,-90.4183,-177.06133,-261.0391,11.025581,-16.828829,299.2559,795000
101
+ 5896.186,2.6806898,2.7020478,-82.219505,-182.28226,-257.5562,70.14204,-29.515423,480.6881,800000
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed973ea8395a6de7e768db706b5e8c090244786b095cc131f50d8597cd8e0acb
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbece7b24f9ebf117e6622b8ff8229faaea8b7cfa5d047e7fc3f7c843f900fac
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2800034353ab7a3b5e245d67842eb67817609d227aef1153e5f961b6285fb65c
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a1f7531caaf1d5ba9282e4db2061ffe64bb7e6a018228aae6fc088b44350eb
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74b0e84020c7850f8460a7fd5ac7228697b624c2aa1bac71da760d8f47c3b5e6
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab0cf6ac8e77c5cd9d019b57e8ca3be80f0bdb8095e0beab81aadf36142fcf6
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d56ee32ecb9bf2e0ff92b2545bd9cfde9f1be90cf89b9992a007fa8b665863
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0640d878a92c111ad672ada2e61d8d9bb47ab008b37ec8af71173eef03a892c
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bfd30c0b70bb56a9401de77321a2dcbb6d6908dda3f9a1f93cc19d0b92cd16d
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a166f3d6e66e7c27df0249d54ace317acbc85855171b6b033dedb2b7eec52a7d
3
+ size 209132226
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/fbrac/20260325_020531/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/z8o7pf5g