Tiredsheep commited on
Commit
32eaac9
·
verified ·
1 Parent(s): eb4101f

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1000000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1050000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1100000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1150000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1200000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_750000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_800000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_850000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_900000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_950000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/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-v0/20260311_174116/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-v0/20260311_174116/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,-0.11792073677881715,0.08055357403540245,-0.11923063974968204,-0.037728613954756525,20.600336317443887,24.782999999997017,0.02,12718.3,-1.76,-918.96,493.66,1.4255975675582886,750000
3
+ 0.0,0.0,-0.09650945425521164,0.01736182465013485,-0.09724252089083182,-0.06090970505512287,23.073614741265466,14.663999999998499,0.54,33580.7,-0.66,-437.18,291.28,0.8578839159011841,800000
4
+ 0.0,0.0,-0.05295915512745028,0.0037883463022150656,-0.05315408396063227,-0.0025218808356051716,24.613893526395426,11.50699999999892,0.68,47502.44,-0.4,-306.42,228.14,0.6774530363082886,850000
5
+ 0.0,0.0,-0.04166320834487087,0.03209781789903296,-0.04074499855418524,0.026565513243366614,30.998292098438068,7.8439999999992995,0.82,57677.44,-0.24,-212.32,154.88,0.47439491748809814,900000
6
+ 0.0,0.0,-0.07126811543779511,0.019785438348326318,-0.06813943666919609,0.07010965540036801,26.849876858782828,10.372999999998937,0.68,66138.3,-0.52,-330.6,205.46,0.6116926670074463,950000
7
+ 0.0,0.0,-0.05299761770856916,0.023605865132669063,-0.04876255590093985,0.025816714304391898,33.16811506852172,5.571999999999549,0.88,74281.46,-0.22,-182.38,109.44,0.33792332172393796,1000000
8
+ 0.0,0.0,-0.049045990888683395,0.01962940219352222,-0.04645524917698954,0.035956062498429996,33.348659400529144,4.6869999999997045,0.94,79691.6,-0.08,-128.2,91.74,0.28681011199951173,1050000
9
+ 0.0,0.0,-0.040668070262722913,0.02758184786784967,-0.037939997127480876,0.030520018134867603,33.99438447066257,4.441999999999694,0.92,84324.74,-0.14,-135.34,86.84,0.27652966022491454,1100000
10
+ 0.0,0.0,-0.04816791001655309,0.052417091597445495,-0.04375545076437628,0.059056076320626996,35.85318747941077,3.472999999999825,0.96,87807.14,-0.08,-108.92,67.46,0.22413902759552,1150000
11
+ 0.0,0.0,-0.04770622128496588,0.054507184056699784,-0.042695381496562976,0.03680212041564481,35.85807168452514,2.906000000000008,1.0,91756.3,0.0,-87.96,56.12,0.18627287387847902,1200000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/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,-0.11792073677881715,0.08055357403540245,-0.11923063974968204,-0.037728613954756525,20.600336317443887,24.782999999997017,0.02,12718.3,-1.76,-918.96,493.66,1.4255975675582886,750000
3
+ 0.0,0.0,-0.09650945425521164,0.01736182465013485,-0.09724252089083182,-0.06090970505512287,23.073614741265466,14.663999999998499,0.54,33580.7,-0.66,-437.18,291.28,0.8578839159011841,800000
4
+ 0.0,0.0,-0.05295915512745028,0.0037883463022150656,-0.05315408396063227,-0.0025218808356051716,24.613893526395426,11.50699999999892,0.68,47502.44,-0.4,-306.42,228.14,0.6774530363082886,850000
5
+ 0.0,0.0,-0.04166320834487087,0.03209781789903296,-0.04074499855418524,0.026565513243366614,30.998292098438068,7.8439999999992995,0.82,57677.44,-0.24,-212.32,154.88,0.47439491748809814,900000
6
+ 0.0,0.0,-0.07126811543779511,0.019785438348326318,-0.06813943666919609,0.07010965540036801,26.849876858782828,10.372999999998937,0.68,66138.3,-0.52,-330.6,205.46,0.6116926670074463,950000
7
+ 0.0,0.0,-0.05299761770856916,0.023605865132669063,-0.04876255590093985,0.025816714304391898,33.16811506852172,5.571999999999549,0.88,74281.46,-0.22,-182.38,109.44,0.33792332172393796,1000000
8
+ 0.0,0.0,-0.049045990888683395,0.01962940219352222,-0.04645524917698954,0.035956062498429996,33.348659400529144,4.6869999999997045,0.94,79691.6,-0.08,-128.2,91.74,0.28681011199951173,1050000
9
+ 0.0,0.0,-0.040668070262722913,0.02758184786784967,-0.037939997127480876,0.030520018134867603,33.99438447066257,4.441999999999694,0.92,84324.74,-0.14,-135.34,86.84,0.27652966022491454,1100000
10
+ 0.0,0.0,-0.04816791001655309,0.052417091597445495,-0.04375545076437628,0.059056076320626996,35.85318747941077,3.472999999999825,0.96,87807.14,-0.08,-108.92,67.46,0.22413902759552,1150000
11
+ 0.0,0.0,-0.04770622128496588,0.054507184056699784,-0.042695381496562976,0.03680212041564481,35.85807168452514,2.906000000000008,1.0,91756.3,0.0,-87.96,56.12,0.18627287387847902,1200000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/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
+ 465.6196,0.81841063,1.1236056,-11.36395,-54.15289,-82.0626,1.2080362,-1.0556109,41.984074,705000
3
+ 546.2911,0.96888983,1.0945818,-13.228003,-62.140102,-99.133316,14.638731,-20.538275,371.85364,710000
4
+ 637.21375,1.1063571,0.8040487,-14.426423,-70.33097,-113.34798,2.8355744,-5.136333,85.36949,715000
5
+ 663.91235,0.85081387,2.5131938,-8.141239,-73.167015,-146.77887,41.871704,-31.181345,324.60306,720000
6
+ 680.91205,0.7399711,1.084289,-22.242535,-74.8449,-138.3399,10.703172,-11.01247,157.07745,725000
7
+ 672.14124,0.86586,1.5902919,-14.508825,-74.2562,-152.4537,2.0307786,-2.227756,78.058624,730000
8
+ 697.70026,1.1120151,1.0253289,-19.018822,-76.334435,-163.71333,4.2635384,-3.1500998,70.9296,735000
9
+ 732.7845,0.7506688,1.606485,-24.055885,-79.85696,-161.73535,3.5367434,-4.9189754,89.14953,740000
10
+ 742.1727,0.8457148,1.2820374,-23.142214,-80.684395,-159.63246,1.8967052,-2.482845,60.6397,745000
11
+ 728.9455,0.781517,1.804602,-13.702221,-79.69405,-175.43938,3.4760473,-2.9023764,108.25044,750000
12
+ 731.62274,0.70063925,2.7182157,-20.464916,-80.19263,-159.08464,5.163271,-6.5979495,112.94063,755000
13
+ 743.1306,1.1025522,1.6857113,-13.602175,-81.194725,-167.06898,3.302068,-3.0587456,101.27006,760000
14
+ 742.6371,1.0258996,1.2748029,-18.302967,-80.49554,-166.01239,3.291719,-2.995929,89.038734,765000
15
+ 726.3953,0.70194405,3.2309434,-8.004897,-79.00548,-151.07039,7.064162,-7.367014,152.42877,770000
16
+ 755.8016,0.8265406,1.9664587,-13.788102,-82.45023,-174.07503,2.507893,-2.5432522,85.35356,775000
17
+ 811.45056,0.88795114,2.9086301,-13.893632,-87.72507,-177.4908,5.6733665,-6.404198,161.313,780000
18
+ 801.59143,1.0346997,1.7518463,-30.061255,-86.26504,-163.65536,5.2699966,-6.453117,211.41852,785000
19
+ 836.6672,0.88803995,1.7781258,-12.564307,-89.74905,-164.25452,3.3984246,-2.3019583,88.32464,790000
20
+ 821.3939,0.75088835,1.9713658,-11.1195345,-88.6531,-169.62543,5.6572666,-3.410582,101.82065,795000
21
+ 814.6178,1.1354451,2.3074334,-8.806876,-87.200485,-173.29482,2.9793403,-4.5194807,106.94792,800000
22
+ 815.6896,0.84854585,1.8201178,-15.95384,-87.56225,-176.79903,4.606282,-3.3462722,64.690765,805000
23
+ 825.4287,0.91687167,2.6571732,-19.61758,-88.82926,-169.85847,13.634879,-17.472647,345.63837,810000
24
+ 812.5793,0.92447376,1.8379374,1.8082858,-87.139404,-179.29163,4.874089,-3.9921858,88.27918,815000
25
+ 857.6756,1.1372097,1.5933145,-14.004423,-91.919586,-177.87892,2.5720367,-3.538718,75.97684,820000
26
+ 873.69507,0.8438103,4.3647175,-17.28784,-93.00951,-179.19385,6.6556892,-8.23767,225.49554,825000
27
+ 856.2044,0.98419803,2.0345762,-14.581861,-91.40692,-178.51208,10.640467,-6.0319614,124.23228,830000
28
+ 850.2963,1.3034866,1.6815786,2.9812052,-91.31109,-170.73338,3.2378714,-3.5065284,98.9593,835000
29
+ 816.5262,1.2276424,7.118873,-15.38664,-88.17141,-177.76566,13.770598,-12.308954,492.27917,840000
30
+ 849.7882,0.8515302,2.6306596,-12.464495,-90.90546,-175.64166,5.089262,-5.0256653,123.65368,845000
31
+ 818.24567,0.83872867,2.1523762,-11.403466,-87.44491,-167.80272,3.6000674,-6.998281,102.6013,850000
32
+ 844.14777,0.7334003,3.6573417,-21.104345,-90.63686,-171.11201,3.234544,-5.14006,135.88593,855000
33
+ 849.10205,0.95774424,3.170405,-9.40099,-90.91134,-172.79446,5.897796,-5.4423003,128.65514,860000
34
+ 831.85297,0.7107818,2.4543092,1.3658731,-89.12344,-183.40419,22.0624,-13.142601,372.89038,865000
35
+ 817.024,1.0893174,3.5954804,-13.09017,-87.84246,-180.07903,23.282425,-13.043039,418.21802,870000
36
+ 828.43243,0.7290988,2.0284088,-21.486635,-89.03163,-168.52557,3.6716325,-3.724155,100.09861,875000
37
+ 861.56775,1.0233431,2.1956291,2.890051,-92.152855,-173.85007,7.5021696,-6.2479978,229.02,880000
38
+ 818.9171,0.873749,1.6139306,-6.461884,-87.90475,-173.01865,3.115896,-2.376929,79.267685,885000
39
+ 827.2077,0.9748045,2.1557236,-16.353313,-88.37176,-174.84595,11.447926,-12.383914,143.66083,890000
40
+ 818.4335,0.94920665,2.7341537,-13.238591,-87.90961,-175.47081,12.184214,-4.5799055,124.62165,895000
41
+ 815.4623,0.8257357,4.8815236,-17.03804,-88.14011,-176.98466,2.1908813,-2.909083,111.24521,900000
42
+ 822.1278,1.0623518,2.6017373,-17.936195,-88.248344,-165.03804,3.3722165,-2.7935047,100.11694,905000
43
+ 818.0708,1.0847962,2.5250068,-14.334162,-87.82354,-169.82787,7.7858114,-3.4837196,136.30885,910000
44
+ 807.32477,0.84587926,6.0430307,-14.835784,-87.08108,-176.65538,6.5264883,-3.8868356,130.27444,915000
45
+ 797.6246,1.1040574,3.5802162,-7.3075585,-85.54949,-168.70578,40.742443,-38.94762,385.46698,920000
46
+ 807.28204,1.3100274,3.2214944,-13.513386,-86.48238,-167.65393,5.2905717,-3.5353851,104.48674,925000
47
+ 816.18915,0.9200321,2.1150706,-6.3140936,-87.80828,-174.31543,4.0962963,-3.7608216,94.33987,930000
48
+ 801.44464,1.008792,8.683487,-12.829634,-85.607574,-176.44075,7.8203206,-7.6275454,173.38614,935000
49
+ 822.7811,1.0069238,2.9012797,1.1720642,-88.116264,-179.63513,5.8929358,-8.020462,170.79768,940000
50
+ 789.784,0.9478226,1.7192688,-4.0691237,-85.16396,-173.9382,4.3704333,-4.9161263,84.32592,945000
51
+ 824.9942,1.1865407,9.153063,-5.5211782,-88.64688,-176.71016,7.2606997,-6.881381,222.74138,950000
52
+ 824.4029,0.8665612,1.7638229,-2.909749,-88.6196,-175.43427,3.8148217,-3.349576,119.40874,955000
53
+ 806.5779,0.9581369,2.8446064,-0.10830647,-87.04192,-175.54784,29.862322,-20.50166,248.45856,960000
54
+ 785.4926,1.2244725,2.44311,-9.8916025,-84.419945,-175.17445,10.324041,-12.467247,262.9479,965000
55
+ 801.0488,1.4246898,3.3001099,4.6096745,-86.25793,-170.68814,10.98877,-7.508617,230.33171,970000
56
+ 764.7654,1.320433,3.6353219,3.842195,-82.22524,-173.84268,5.236082,-7.353639,159.05194,975000
57
+ 784.8559,1.4569926,2.4485958,-1.5190287,-84.79397,-171.02652,7.1664934,-4.2041893,113.01891,980000
58
+ 793.38116,1.1430097,2.3987548,-7.880472,-85.027596,-170.22273,2.9698412,-2.8183246,92.272446,985000
59
+ 779.76855,1.0683768,2.6716027,-7.97765,-84.237305,-174.13637,5.895965,-5.472577,140.53635,990000
60
+ 800.7679,1.0358073,2.5296407,0.40002912,-85.64357,-175.96257,4.281317,-4.680817,130.54555,995000
61
+ 803.8106,1.030752,3.0216992,-8.481567,-85.86129,-176.91336,8.742975,-9.962112,132.51953,1000000
62
+ 794.7214,0.92816013,3.0356417,-4.878607,-85.48058,-175.48169,5.716288,-6.0086284,158.93863,1005000
63
+ 763.47314,1.4061759,4.1431727,-6.285754,-82.75642,-177.95168,8.956754,-9.514206,202.82379,1010000
64
+ 776.60065,1.1385876,1.9558533,-5.4142046,-83.54696,-173.70955,12.469626,-38.96815,217.97194,1015000
65
+ 772.2595,1.2470807,3.5920281,-8.76853,-83.50921,-178.37651,49.332054,-19.001867,289.3059,1020000
66
+ 779.70856,0.94340855,2.867046,-1.5288203,-84.01375,-173.64851,4.327296,-4.511773,109.07686,1025000
67
+ 782.7774,1.144792,3.579909,-5.222701,-84.0837,-172.74721,8.446587,-8.258749,220.00987,1030000
68
+ 766.9288,1.422796,3.1829202,-10.659761,-83.33257,-178.47719,96.98977,-139.29384,1881.8447,1035000
69
+ 773.7901,0.9723615,1.8466476,-4.2821617,-83.21708,-176.62354,4.8421736,-11.59739,148.57526,1040000
70
+ 777.8897,1.2788678,3.5332317,0.43829265,-83.99164,-172.87958,11.342791,-11.059691,262.52893,1045000
71
+ 751.4419,1.0283935,3.172348,-3.476324,-80.698524,-175.6037,4.9738507,-3.251622,100.74846,1050000
72
+ 772.93225,0.86249167,4.829609,0.5710677,-83.357475,-179.59732,4.0909886,-3.9958684,162.89328,1055000
73
+ 781.8692,1.2861929,2.9595265,-7.8503,-84.05609,-172.67033,47.021355,-54.538956,477.89777,1060000
74
+ 758.9853,0.924101,7.45284,-11.151691,-82.36117,-178.48665,4.242269,-5.716688,148.18277,1065000
75
+ 739.78735,1.095613,2.9070144,-3.3291981,-79.6008,-181.1872,25.086863,-20.934887,507.5326,1070000
76
+ 726.2571,1.0612983,4.633859,1.539807,-78.33248,-171.9849,4.087657,-3.082177,116.96988,1075000
77
+ 779.5099,1.121779,2.8009026,-0.88189137,-83.79241,-169.58157,14.984497,-13.51723,162.76492,1080000
78
+ 746.0341,0.9614953,3.1808999,-4.6362214,-80.638145,-172.50136,3.7230651,-7.7260327,136.39964,1085000
79
+ 772.87897,0.88279605,2.7648294,-2.6480782,-83.429,-169.74504,4.602887,-6.5078864,145.46599,1090000
80
+ 749.1165,0.91280735,3.57897,-0.8589153,-81.124016,-176.74033,5.9986715,-5.2789354,162.04115,1095000
81
+ 742.49304,1.5110476,4.602141,-1.5603689,-80.63448,-170.14088,24.996365,-77.5461,446.55362,1100000
82
+ 755.995,0.9607856,4.3424206,-4.1272326,-81.26471,-172.49211,2.6034567,-7.6686254,202.96646,1105000
83
+ 786.7699,1.024046,3.8512008,-6.360158,-84.74026,-173.14548,5.021449,-5.5410438,213.84694,1110000
84
+ 747.8398,0.9937867,3.3437545,-3.5045774,-80.843864,-169.77373,3.6408672,-3.282739,122.41185,1115000
85
+ 748.08636,1.0441396,2.2978904,-5.0051723,-80.769875,-177.15416,5.7250886,-4.6281466,114.81393,1120000
86
+ 760.3195,1.162122,5.345125,-1.5750333,-82.18004,-173.24872,4.989203,-3.7931163,188.70528,1125000
87
+ 738.3895,0.89868814,8.036774,0.9329643,-79.979065,-163.36629,4.0700746,-6.786559,185.56117,1130000
88
+ 737.3061,1.166426,3.893212,-4.3804793,-79.505516,-168.27571,10.1778345,-10.743447,163.11159,1135000
89
+ 754.48975,1.1586841,3.477158,0.58109266,-81.50789,-176.57925,18.525763,-43.310474,285.7217,1140000
90
+ 768.57385,1.3588877,2.3503096,-8.951154,-83.07848,-171.75304,4.0929456,-3.6449401,115.25751,1145000
91
+ 743.0384,1.3868654,2.9513142,-2.8600378,-80.35519,-168.25781,7.373462,-18.51666,209.3815,1150000
92
+ 725.30554,1.0891142,3.4836445,-2.7572443,-78.07903,-161.69513,2.918522,-3.582534,116.23711,1155000
93
+ 721.3528,1.0683625,4.294023,-3.766752,-78.199394,-169.6512,6.2206526,-5.197524,172.62381,1160000
94
+ 697.695,0.9212343,3.2086072,-3.3202493,-76.09308,-168.157,9.597168,-12.099722,183.00174,1165000
95
+ 689.135,1.4198904,6.2075567,-2.4790874,-74.99386,-161.61044,4.523798,-3.8588696,122.59117,1170000
96
+ 718.4333,0.98258626,2.77606,-3.2432916,-77.67492,-170.34811,10.872143,-17.217663,280.0887,1175000
97
+ 670.39,0.97958964,3.823124,5.079156,-73.39196,-167.05965,7.0553327,-4.885489,176.71344,1180000
98
+ 682.00226,0.97916967,3.056808,-4.3080034,-74.36465,-173.52403,7.257842,-5.7979527,176.77054,1185000
99
+ 713.1941,0.9178184,6.9183044,-1.0316137,-76.8005,-168.61725,7.139532,-3.6453657,162.761,1190000
100
+ 678.20886,0.9235699,6.2784615,-0.27244383,-73.6663,-164.10226,3.0379324,-4.231762,160.38223,1195000
101
+ 685.7073,1.3519387,2.309632,-7.092517,-74.19012,-181.69281,4.5999546,-5.0287685,124.88434,1200000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/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
+ 465.6196,0.81841063,1.1236056,-11.36395,-54.15289,-82.0626,1.2080362,-1.0556109,41.984074,705000
3
+ 546.2911,0.96888983,1.0945818,-13.228003,-62.140102,-99.133316,14.638731,-20.538275,371.85364,710000
4
+ 637.21375,1.1063571,0.8040487,-14.426423,-70.33097,-113.34798,2.8355744,-5.136333,85.36949,715000
5
+ 663.91235,0.85081387,2.5131938,-8.141239,-73.167015,-146.77887,41.871704,-31.181345,324.60306,720000
6
+ 680.91205,0.7399711,1.084289,-22.242535,-74.8449,-138.3399,10.703172,-11.01247,157.07745,725000
7
+ 672.14124,0.86586,1.5902919,-14.508825,-74.2562,-152.4537,2.0307786,-2.227756,78.058624,730000
8
+ 697.70026,1.1120151,1.0253289,-19.018822,-76.334435,-163.71333,4.2635384,-3.1500998,70.9296,735000
9
+ 732.7845,0.7506688,1.606485,-24.055885,-79.85696,-161.73535,3.5367434,-4.9189754,89.14953,740000
10
+ 742.1727,0.8457148,1.2820374,-23.142214,-80.684395,-159.63246,1.8967052,-2.482845,60.6397,745000
11
+ 728.9455,0.781517,1.804602,-13.702221,-79.69405,-175.43938,3.4760473,-2.9023764,108.25044,750000
12
+ 731.62274,0.70063925,2.7182157,-20.464916,-80.19263,-159.08464,5.163271,-6.5979495,112.94063,755000
13
+ 743.1306,1.1025522,1.6857113,-13.602175,-81.194725,-167.06898,3.302068,-3.0587456,101.27006,760000
14
+ 742.6371,1.0258996,1.2748029,-18.302967,-80.49554,-166.01239,3.291719,-2.995929,89.038734,765000
15
+ 726.3953,0.70194405,3.2309434,-8.004897,-79.00548,-151.07039,7.064162,-7.367014,152.42877,770000
16
+ 755.8016,0.8265406,1.9664587,-13.788102,-82.45023,-174.07503,2.507893,-2.5432522,85.35356,775000
17
+ 811.45056,0.88795114,2.9086301,-13.893632,-87.72507,-177.4908,5.6733665,-6.404198,161.313,780000
18
+ 801.59143,1.0346997,1.7518463,-30.061255,-86.26504,-163.65536,5.2699966,-6.453117,211.41852,785000
19
+ 836.6672,0.88803995,1.7781258,-12.564307,-89.74905,-164.25452,3.3984246,-2.3019583,88.32464,790000
20
+ 821.3939,0.75088835,1.9713658,-11.1195345,-88.6531,-169.62543,5.6572666,-3.410582,101.82065,795000
21
+ 814.6178,1.1354451,2.3074334,-8.806876,-87.200485,-173.29482,2.9793403,-4.5194807,106.94792,800000
22
+ 815.6896,0.84854585,1.8201178,-15.95384,-87.56225,-176.79903,4.606282,-3.3462722,64.690765,805000
23
+ 825.4287,0.91687167,2.6571732,-19.61758,-88.82926,-169.85847,13.634879,-17.472647,345.63837,810000
24
+ 812.5793,0.92447376,1.8379374,1.8082858,-87.139404,-179.29163,4.874089,-3.9921858,88.27918,815000
25
+ 857.6756,1.1372097,1.5933145,-14.004423,-91.919586,-177.87892,2.5720367,-3.538718,75.97684,820000
26
+ 873.69507,0.8438103,4.3647175,-17.28784,-93.00951,-179.19385,6.6556892,-8.23767,225.49554,825000
27
+ 856.2044,0.98419803,2.0345762,-14.581861,-91.40692,-178.51208,10.640467,-6.0319614,124.23228,830000
28
+ 850.2963,1.3034866,1.6815786,2.9812052,-91.31109,-170.73338,3.2378714,-3.5065284,98.9593,835000
29
+ 816.5262,1.2276424,7.118873,-15.38664,-88.17141,-177.76566,13.770598,-12.308954,492.27917,840000
30
+ 849.7882,0.8515302,2.6306596,-12.464495,-90.90546,-175.64166,5.089262,-5.0256653,123.65368,845000
31
+ 818.24567,0.83872867,2.1523762,-11.403466,-87.44491,-167.80272,3.6000674,-6.998281,102.6013,850000
32
+ 844.14777,0.7334003,3.6573417,-21.104345,-90.63686,-171.11201,3.234544,-5.14006,135.88593,855000
33
+ 849.10205,0.95774424,3.170405,-9.40099,-90.91134,-172.79446,5.897796,-5.4423003,128.65514,860000
34
+ 831.85297,0.7107818,2.4543092,1.3658731,-89.12344,-183.40419,22.0624,-13.142601,372.89038,865000
35
+ 817.024,1.0893174,3.5954804,-13.09017,-87.84246,-180.07903,23.282425,-13.043039,418.21802,870000
36
+ 828.43243,0.7290988,2.0284088,-21.486635,-89.03163,-168.52557,3.6716325,-3.724155,100.09861,875000
37
+ 861.56775,1.0233431,2.1956291,2.890051,-92.152855,-173.85007,7.5021696,-6.2479978,229.02,880000
38
+ 818.9171,0.873749,1.6139306,-6.461884,-87.90475,-173.01865,3.115896,-2.376929,79.267685,885000
39
+ 827.2077,0.9748045,2.1557236,-16.353313,-88.37176,-174.84595,11.447926,-12.383914,143.66083,890000
40
+ 818.4335,0.94920665,2.7341537,-13.238591,-87.90961,-175.47081,12.184214,-4.5799055,124.62165,895000
41
+ 815.4623,0.8257357,4.8815236,-17.03804,-88.14011,-176.98466,2.1908813,-2.909083,111.24521,900000
42
+ 822.1278,1.0623518,2.6017373,-17.936195,-88.248344,-165.03804,3.3722165,-2.7935047,100.11694,905000
43
+ 818.0708,1.0847962,2.5250068,-14.334162,-87.82354,-169.82787,7.7858114,-3.4837196,136.30885,910000
44
+ 807.32477,0.84587926,6.0430307,-14.835784,-87.08108,-176.65538,6.5264883,-3.8868356,130.27444,915000
45
+ 797.6246,1.1040574,3.5802162,-7.3075585,-85.54949,-168.70578,40.742443,-38.94762,385.46698,920000
46
+ 807.28204,1.3100274,3.2214944,-13.513386,-86.48238,-167.65393,5.2905717,-3.5353851,104.48674,925000
47
+ 816.18915,0.9200321,2.1150706,-6.3140936,-87.80828,-174.31543,4.0962963,-3.7608216,94.33987,930000
48
+ 801.44464,1.008792,8.683487,-12.829634,-85.607574,-176.44075,7.8203206,-7.6275454,173.38614,935000
49
+ 822.7811,1.0069238,2.9012797,1.1720642,-88.116264,-179.63513,5.8929358,-8.020462,170.79768,940000
50
+ 789.784,0.9478226,1.7192688,-4.0691237,-85.16396,-173.9382,4.3704333,-4.9161263,84.32592,945000
51
+ 824.9942,1.1865407,9.153063,-5.5211782,-88.64688,-176.71016,7.2606997,-6.881381,222.74138,950000
52
+ 824.4029,0.8665612,1.7638229,-2.909749,-88.6196,-175.43427,3.8148217,-3.349576,119.40874,955000
53
+ 806.5779,0.9581369,2.8446064,-0.10830647,-87.04192,-175.54784,29.862322,-20.50166,248.45856,960000
54
+ 785.4926,1.2244725,2.44311,-9.8916025,-84.419945,-175.17445,10.324041,-12.467247,262.9479,965000
55
+ 801.0488,1.4246898,3.3001099,4.6096745,-86.25793,-170.68814,10.98877,-7.508617,230.33171,970000
56
+ 764.7654,1.320433,3.6353219,3.842195,-82.22524,-173.84268,5.236082,-7.353639,159.05194,975000
57
+ 784.8559,1.4569926,2.4485958,-1.5190287,-84.79397,-171.02652,7.1664934,-4.2041893,113.01891,980000
58
+ 793.38116,1.1430097,2.3987548,-7.880472,-85.027596,-170.22273,2.9698412,-2.8183246,92.272446,985000
59
+ 779.76855,1.0683768,2.6716027,-7.97765,-84.237305,-174.13637,5.895965,-5.472577,140.53635,990000
60
+ 800.7679,1.0358073,2.5296407,0.40002912,-85.64357,-175.96257,4.281317,-4.680817,130.54555,995000
61
+ 803.8106,1.030752,3.0216992,-8.481567,-85.86129,-176.91336,8.742975,-9.962112,132.51953,1000000
62
+ 794.7214,0.92816013,3.0356417,-4.878607,-85.48058,-175.48169,5.716288,-6.0086284,158.93863,1005000
63
+ 763.47314,1.4061759,4.1431727,-6.285754,-82.75642,-177.95168,8.956754,-9.514206,202.82379,1010000
64
+ 776.60065,1.1385876,1.9558533,-5.4142046,-83.54696,-173.70955,12.469626,-38.96815,217.97194,1015000
65
+ 772.2595,1.2470807,3.5920281,-8.76853,-83.50921,-178.37651,49.332054,-19.001867,289.3059,1020000
66
+ 779.70856,0.94340855,2.867046,-1.5288203,-84.01375,-173.64851,4.327296,-4.511773,109.07686,1025000
67
+ 782.7774,1.144792,3.579909,-5.222701,-84.0837,-172.74721,8.446587,-8.258749,220.00987,1030000
68
+ 766.9288,1.422796,3.1829202,-10.659761,-83.33257,-178.47719,96.98977,-139.29384,1881.8447,1035000
69
+ 773.7901,0.9723615,1.8466476,-4.2821617,-83.21708,-176.62354,4.8421736,-11.59739,148.57526,1040000
70
+ 777.8897,1.2788678,3.5332317,0.43829265,-83.99164,-172.87958,11.342791,-11.059691,262.52893,1045000
71
+ 751.4419,1.0283935,3.172348,-3.476324,-80.698524,-175.6037,4.9738507,-3.251622,100.74846,1050000
72
+ 772.93225,0.86249167,4.829609,0.5710677,-83.357475,-179.59732,4.0909886,-3.9958684,162.89328,1055000
73
+ 781.8692,1.2861929,2.9595265,-7.8503,-84.05609,-172.67033,47.021355,-54.538956,477.89777,1060000
74
+ 758.9853,0.924101,7.45284,-11.151691,-82.36117,-178.48665,4.242269,-5.716688,148.18277,1065000
75
+ 739.78735,1.095613,2.9070144,-3.3291981,-79.6008,-181.1872,25.086863,-20.934887,507.5326,1070000
76
+ 726.2571,1.0612983,4.633859,1.539807,-78.33248,-171.9849,4.087657,-3.082177,116.96988,1075000
77
+ 779.5099,1.121779,2.8009026,-0.88189137,-83.79241,-169.58157,14.984497,-13.51723,162.76492,1080000
78
+ 746.0341,0.9614953,3.1808999,-4.6362214,-80.638145,-172.50136,3.7230651,-7.7260327,136.39964,1085000
79
+ 772.87897,0.88279605,2.7648294,-2.6480782,-83.429,-169.74504,4.602887,-6.5078864,145.46599,1090000
80
+ 749.1165,0.91280735,3.57897,-0.8589153,-81.124016,-176.74033,5.9986715,-5.2789354,162.04115,1095000
81
+ 742.49304,1.5110476,4.602141,-1.5603689,-80.63448,-170.14088,24.996365,-77.5461,446.55362,1100000
82
+ 755.995,0.9607856,4.3424206,-4.1272326,-81.26471,-172.49211,2.6034567,-7.6686254,202.96646,1105000
83
+ 786.7699,1.024046,3.8512008,-6.360158,-84.74026,-173.14548,5.021449,-5.5410438,213.84694,1110000
84
+ 747.8398,0.9937867,3.3437545,-3.5045774,-80.843864,-169.77373,3.6408672,-3.282739,122.41185,1115000
85
+ 748.08636,1.0441396,2.2978904,-5.0051723,-80.769875,-177.15416,5.7250886,-4.6281466,114.81393,1120000
86
+ 760.3195,1.162122,5.345125,-1.5750333,-82.18004,-173.24872,4.989203,-3.7931163,188.70528,1125000
87
+ 738.3895,0.89868814,8.036774,0.9329643,-79.979065,-163.36629,4.0700746,-6.786559,185.56117,1130000
88
+ 737.3061,1.166426,3.893212,-4.3804793,-79.505516,-168.27571,10.1778345,-10.743447,163.11159,1135000
89
+ 754.48975,1.1586841,3.477158,0.58109266,-81.50789,-176.57925,18.525763,-43.310474,285.7217,1140000
90
+ 768.57385,1.3588877,2.3503096,-8.951154,-83.07848,-171.75304,4.0929456,-3.6449401,115.25751,1145000
91
+ 743.0384,1.3868654,2.9513142,-2.8600378,-80.35519,-168.25781,7.373462,-18.51666,209.3815,1150000
92
+ 725.30554,1.0891142,3.4836445,-2.7572443,-78.07903,-161.69513,2.918522,-3.582534,116.23711,1155000
93
+ 721.3528,1.0683625,4.294023,-3.766752,-78.199394,-169.6512,6.2206526,-5.197524,172.62381,1160000
94
+ 697.695,0.9212343,3.2086072,-3.3202493,-76.09308,-168.157,9.597168,-12.099722,183.00174,1165000
95
+ 689.135,1.4198904,6.2075567,-2.4790874,-74.99386,-161.61044,4.523798,-3.8588696,122.59117,1170000
96
+ 718.4333,0.98258626,2.77606,-3.2432916,-77.67492,-170.34811,10.872143,-17.217663,280.0887,1175000
97
+ 670.39,0.97958964,3.823124,5.079156,-73.39196,-167.05965,7.0553327,-4.885489,176.71344,1180000
98
+ 682.00226,0.97916967,3.056808,-4.3080034,-74.36465,-173.52403,7.257842,-5.7979527,176.77054,1185000
99
+ 713.1941,0.9178184,6.9183044,-1.0316137,-76.8005,-168.61725,7.139532,-3.6453657,162.761,1190000
100
+ 678.20886,0.9235699,6.2784615,-0.27244383,-73.6663,-164.10226,3.0379324,-4.231762,160.38223,1195000
101
+ 685.7073,1.3519387,2.309632,-7.092517,-74.19012,-181.69281,4.5999546,-5.0287685,124.88434,1200000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900f2d545dbe65e1ecda4c76f3182ef0ba1b410f3f90b42ffc6ed1293594e378
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6e1a40223355650cefb99dcc889aff2df52fc37d45de0450a1861a3713b899
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2165e09d3f7a7e0f91c0f7b45f50dc3dceabc349e114018d6da970f94d548c7
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c405e2140422e72200d3863ef51bde396c7d5a7946882c0588bfd6f554c37a4
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72eda53cb9371c7eb39adb7ac32542101de76333d3c5834ee79bbac8e1237883
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd4acb960ea55d58bf9a241d905155d38b76faf83798bb8d3898b41c4a9ac64
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8917ffb4b4dafbc93995cf3fb36454fffeab811944a0528978c3f3de67f65708
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f8d070573df03907b007beba387b82aa3bcf82a54eb7a4422dd2fea93b3dd7
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8adc5dbe4e428d9b6d914bb9737812b68bfa3dd1dd6cd01d4f6db2c0371460b8
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dbbb905ac521f661132caf6bac49eb2c679687ac68d989a3e5d3c53fb2615e2
3
+ size 207971010
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_174116/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/bgmg5trf