Tiredsheep commited on
Commit
3570e68
·
verified ·
1 Parent(s): ea1db2c

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_1000000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_1050000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_1100000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_650000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_700000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_750000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_800000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_850000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_900000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_950000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/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/fql/20260318_204357/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/fql/20260318_204357/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,-0.03912639361797538,0.011553727371692758,-0.03871442280484732,0.0004132635925487032,29.96876976795947,15.896999999998895,0.7,8425.48,-0.38,-469.36,315.94,0.9684482288360595,650000
3
+ 0.0,0.0,-0.04131756587232806,-0.004551512687973089,-0.04127236562684157,-0.0026797551460446493,32.164054093880424,10.712999999999374,0.88,22231.96,-0.16,-294.0,212.26,0.6950085926055908,700000
4
+ 0.0,0.0,-0.022466076104137398,0.0003564863430097549,-0.022172352800020768,0.0015796260048953768,34.940117489885694,7.7609999999995924,0.98,31519.36,-0.02,-215.46,153.22,0.5283847332000733,750000
5
+ 0.0,0.0,-0.05291590747647818,-0.0005847085934070834,-0.05267311739460553,-0.013080478650118486,35.28516013560496,7.387999999999679,1.0,39127.88,0.0,-204.34,145.76,0.47821041584014895,800000
6
+ 0.0,0.0,-0.032766144479428154,-0.003503018465989266,-0.03265409209872803,-0.004353483702456866,35.32794614242517,7.04799999999966,1.0,46480.04,0.0,-185.62,138.96,0.4550000619888306,850000
7
+ 0.0,0.0,-0.03150104137376384,0.005247176351503459,-0.030819870348066776,0.0009528893562258188,35.7202120754883,5.950999999999584,1.0,53193.84,0.0,-157.32,117.02,0.3868748140335083,900000
8
+ 0.0,0.0,-0.04086388995399894,0.01726136735645385,-0.039390048012974695,0.030192186268770696,35.66543523851511,5.74899999999962,1.0,59232.04,0.0,-154.78,112.98,0.37144299983978274,950000
9
+ 0.0,0.0,-0.030574237121643075,0.03080728766650091,-0.02867768529744393,0.022566504695770713,35.73339167900402,5.20399999999965,1.0,64803.74,0.0,-139.42,102.08,0.3415336847305298,1000000
10
+ 0.0,0.0,-0.03488706274647257,0.027593243428239173,-0.033071437248028045,0.02887389258809565,35.764269722875326,5.535999999999644,1.0,70284.76,0.0,-147.62,108.72,0.35794476509094236,1050000
11
+ 0.0,0.0,-0.057190523329548354,0.05433934272193527,-0.053880034758908166,0.04316825562637351,35.81311631827794,4.958999999999704,1.0,75667.9,0.0,-135.02,97.18,0.31993173599243163,1100000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/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,-0.03912639361797538,0.011553727371692758,-0.03871442280484732,0.0004132635925487032,29.96876976795947,15.896999999998895,0.7,8425.48,-0.38,-469.36,315.94,0.9684482288360595,650000
3
+ 0.0,0.0,-0.04131756587232806,-0.004551512687973089,-0.04127236562684157,-0.0026797551460446493,32.164054093880424,10.712999999999374,0.88,22231.96,-0.16,-294.0,212.26,0.6950085926055908,700000
4
+ 0.0,0.0,-0.022466076104137398,0.0003564863430097549,-0.022172352800020768,0.0015796260048953768,34.940117489885694,7.7609999999995924,0.98,31519.36,-0.02,-215.46,153.22,0.5283847332000733,750000
5
+ 0.0,0.0,-0.05291590747647818,-0.0005847085934070834,-0.05267311739460553,-0.013080478650118486,35.28516013560496,7.387999999999679,1.0,39127.88,0.0,-204.34,145.76,0.47821041584014895,800000
6
+ 0.0,0.0,-0.032766144479428154,-0.003503018465989266,-0.03265409209872803,-0.004353483702456866,35.32794614242517,7.04799999999966,1.0,46480.04,0.0,-185.62,138.96,0.4550000619888306,850000
7
+ 0.0,0.0,-0.03150104137376384,0.005247176351503459,-0.030819870348066776,0.0009528893562258188,35.7202120754883,5.950999999999584,1.0,53193.84,0.0,-157.32,117.02,0.3868748140335083,900000
8
+ 0.0,0.0,-0.04086388995399894,0.01726136735645385,-0.039390048012974695,0.030192186268770696,35.66543523851511,5.74899999999962,1.0,59232.04,0.0,-154.78,112.98,0.37144299983978274,950000
9
+ 0.0,0.0,-0.030574237121643075,0.03080728766650091,-0.02867768529744393,0.022566504695770713,35.73339167900402,5.20399999999965,1.0,64803.74,0.0,-139.42,102.08,0.3415336847305298,1000000
10
+ 0.0,0.0,-0.03488706274647257,0.027593243428239173,-0.033071437248028045,0.02887389258809565,35.764269722875326,5.535999999999644,1.0,70284.76,0.0,-147.62,108.72,0.35794476509094236,1050000
11
+ 0.0,0.0,-0.057190523329548354,0.05433934272193527,-0.053880034758908166,0.04316825562637351,35.81311631827794,4.958999999999704,1.0,75667.9,0.0,-135.02,97.18,0.31993173599243163,1100000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 166.06499,0.18392003,0.0073187067,3.8530107,-49.74785,-166.19409,-203.86937,1.2257384,-1.1291348,64.64655,605000
3
+ 163.4832,0.188674,0.0056459373,6.608623,-54.920998,-163.69753,-203.93028,0.7061405,-0.7997772,54.46456,610000
4
+ 163.008,0.16517335,0.006892648,6.305266,-46.19134,-162.87964,-204.2602,1.3847011,-1.326308,55.98147,615000
5
+ 160.96254,0.17174289,0.007502403,8.1712,-48.609444,-161.38838,-204.69278,0.9587071,-1.2617546,68.04566,620000
6
+ 160.5675,0.17214093,0.007842035,5.5462317,-63.419815,-160.01299,-205.25906,1.1501782,-1.2272242,55.90058,625000
7
+ 161.2798,0.1481994,0.006410057,4.150022,-67.05159,-161.45323,-204.41072,0.8887694,-2.568139,54.22952,630000
8
+ 160.87596,0.17129819,0.00788438,6.541496,-55.990334,-161.01123,-204.22287,0.8897376,-1.1541513,54.47006,635000
9
+ 159.39224,0.17307258,0.007876503,6.6994066,-62.195137,-160.31523,-204.45802,1.3560688,-1.2591391,75.47792,640000
10
+ 160.58253,0.17523213,0.006422887,3.980457,-70.65616,-160.76115,-204.6634,1.0561328,-0.99527085,51.28894,645000
11
+ 159.14476,0.21605548,0.008620408,4.503652,-5.528885,-159.06142,-204.03331,1.3951472,-2.0222147,54.307407,650000
12
+ 154.18674,0.21944734,0.008084733,8.874441,-32.905792,-154.69403,-205.05196,1.6630969,-1.5937506,73.96778,655000
13
+ 151.29675,0.21059063,0.010063103,7.2526956,-30.158476,-151.02248,-205.17006,2.785377,-2.5243456,80.94262,660000
14
+ 151.51698,0.18820634,0.007570233,7.6560135,-34.643505,-151.63295,-204.63821,0.6579086,-0.74998546,68.9203,665000
15
+ 145.1546,0.18303771,0.008442642,7.9371095,-34.121937,-145.48492,-204.83542,0.78543013,-1.7082787,70.20558,670000
16
+ 148.61118,0.19758458,0.0094098365,5.498774,-30.875635,-148.80756,-204.79893,1.2413697,-1.217776,67.877525,675000
17
+ 144.85527,0.16880818,0.008039132,8.378299,-12.463703,-145.80072,-204.67958,1.2972692,-1.2847058,68.44676,680000
18
+ 145.31158,0.17633492,0.00730278,7.5312166,-12.738392,-145.15398,-204.74269,1.8503852,-1.4552251,65.06949,685000
19
+ 142.1703,0.17737314,0.009510728,9.581735,-19.948818,-143.01405,-205.9161,1.3545291,-1.3534076,100.83729,690000
20
+ 141.83751,0.19516939,0.009254462,9.6098,-6.831773,-141.99237,-205.31235,2.117879,-2.3033822,100.75346,695000
21
+ 136.70169,0.20735107,0.0074608414,5.3051624,-8.801661,-136.93526,-206.2875,3.562016,-4.3214855,73.693726,700000
22
+ 139.36197,0.19583015,0.008304932,6.473289,-3.6741135,-140.27823,-205.30725,1.0022086,-0.77213275,65.497574,705000
23
+ 138.24805,0.17990184,0.009083494,5.9896655,-20.30197,-138.13277,-205.23367,1.4769721,-0.898281,61.075073,710000
24
+ 134.49956,0.17572102,0.009861273,7.050506,0.9544666,-135.24918,-206.38939,0.82946426,-1.2912691,61.190216,715000
25
+ 134.792,0.1727162,0.007591157,5.3293085,0.9350946,-135.14676,-205.04877,1.1084915,-1.2227685,59.223175,720000
26
+ 138.02547,0.15385124,0.009459828,5.120279,-4.3956866,-137.86911,-205.42078,1.1336002,-1.1861212,62.126175,725000
27
+ 134.78238,0.1802071,0.0072565875,6.092469,-23.18277,-135.63205,-206.34114,1.0784248,-1.1421288,58.275932,730000
28
+ 134.92496,0.18499295,0.009287172,5.878539,1.6460104,-136.21405,-205.75291,0.7507756,-0.80237544,57.121605,735000
29
+ 131.3006,0.14087862,0.007332329,8.137138,-23.399137,-132.77654,-204.9767,1.060633,-1.0760254,70.49406,740000
30
+ 133.33417,0.14684187,0.006958673,7.1498237,2.1917746,-135.03014,-206.04889,1.3422222,-1.4479679,62.518593,745000
31
+ 134.33466,0.1470345,0.008124989,5.4722586,-24.076138,-134.778,-205.22353,2.1490679,-1.0711775,61.266457,750000
32
+ 133.0176,0.17566863,0.008899769,6.757254,-2.4877834,-133.79312,-205.42628,1.097014,-1.1732321,72.68582,755000
33
+ 135.12213,0.20439832,0.007642889,8.446967,-0.71190995,-135.65654,-205.30997,1.6737324,-1.5072596,87.67256,760000
34
+ 129.55078,0.18112579,0.008011497,6.2206016,-0.9824583,-130.60344,-206.82866,1.0763506,-0.8933415,54.63727,765000
35
+ 130.72289,0.17807901,0.0077719963,7.5635524,-8.495506,-131.37947,-205.62088,1.2655748,-1.3036174,83.52581,770000
36
+ 133.60071,0.18103437,0.008130168,5.0311975,-5.285836,-133.66814,-208.04678,0.9156441,-0.9095121,58.957764,775000
37
+ 133.97142,0.17851436,0.008970856,6.1729693,1.2569984,-134.00096,-205.19069,1.685972,-1.3054438,77.42645,780000
38
+ 129.82057,0.19789174,0.008799881,6.554498,-1.3195657,-130.19307,-205.44861,0.88551044,-0.8182341,63.70075,785000
39
+ 126.15414,0.1773861,0.008908973,6.889333,12.295847,-127.07729,-205.54996,0.8373528,-1.574405,61.225014,790000
40
+ 128.90784,0.16932961,0.0074163084,5.0215654,-2.304932,-129.07434,-205.01418,0.7193181,-0.8549147,56.69947,795000
41
+ 128.04976,0.17727152,0.009041754,6.8462296,-4.879854,-129.02914,-205.64705,1.289019,-1.5269545,72.47089,800000
42
+ 130.87828,0.18692347,0.008429831,7.256336,-6.3612704,-130.8486,-204.34935,1.3617572,-1.5012062,66.769135,805000
43
+ 127.09188,0.17049426,0.009013321,5.996105,-4.5349913,-127.43845,-204.8757,2.3427446,-3.797897,69.1035,810000
44
+ 130.25587,0.19210024,0.008940079,6.3756695,-7.446972,-130.76746,-205.35568,0.82040745,-0.8347776,72.121315,815000
45
+ 128.4026,0.1786831,0.0080689015,5.4265428,-7.6649265,-128.51245,-204.75883,2.03298,-1.7508552,76.73269,820000
46
+ 125.75116,0.1788582,0.0083336625,5.2586703,-7.9578304,-125.69232,-205.23715,1.1084577,-1.2519847,57.117424,825000
47
+ 129.55247,0.18298557,0.0081755575,5.0046334,-4.478055,-129.91177,-205.55122,0.72170323,-0.62007654,53.597466,830000
48
+ 126.14079,0.17892489,0.0061909566,8.574721,-7.908635,-126.15867,-205.08273,1.6693822,-1.9193003,94.66992,835000
49
+ 125.099075,0.1873132,0.007137706,4.08489,2.0764322,-125.81182,-205.5508,1.642991,-1.209022,50.131462,840000
50
+ 128.37709,0.1660405,0.0065760133,8.804901,-11.114733,-129.40381,-205.03726,0.8765111,-0.9863026,79.410805,845000
51
+ 119.265854,0.15387508,0.0074474737,6.9998055,-6.6110177,-120.043144,-206.00633,1.2161494,-1.2013518,77.7096,850000
52
+ 127.72482,0.17275128,0.0075857434,4.558629,-5.6445417,-128.90286,-205.71637,0.5151682,-0.46823117,45.861435,855000
53
+ 122.64298,0.17497326,0.008562335,4.574209,2.4452627,-123.19976,-204.93591,0.9960772,-0.9761434,62.2931,860000
54
+ 125.76472,0.16894567,0.008695243,5.965881,-1.0118144,-125.85225,-205.23683,2.1083248,-1.9503368,66.369774,865000
55
+ 125.94786,0.1383057,0.008479461,4.7308836,-2.6712341,-126.43677,-204.61719,0.92825365,-0.9658195,60.55772,870000
56
+ 121.66058,0.16267744,0.008358295,6.7826815,0.45956373,-121.7261,-205.45113,1.588254,-1.6754194,71.08594,875000
57
+ 126.3198,0.17335515,0.0076590423,6.5476723,-4.278531,-127.550026,-204.97757,0.85254,-0.95810235,60.830166,880000
58
+ 121.31031,0.12799889,0.0077690147,6.661017,-0.7593195,-121.91808,-203.87338,1.0800246,-1.0673281,62.265892,885000
59
+ 118.265175,0.16439563,0.007025783,9.750159,-4.6881757,-118.79181,-204.3316,0.7642861,-0.7652552,78.00795,890000
60
+ 121.29356,0.15283364,0.00933923,5.049493,2.1012478,-121.23899,-206.63853,1.1793369,-1.0876862,63.65472,895000
61
+ 123.86597,0.18859771,0.006479093,7.5510573,-2.7629201,-124.34247,-204.47723,1.6769525,-1.6799304,81.50221,900000
62
+ 123.144424,0.18178245,0.008937269,5.39239,-5.3957753,-123.978516,-205.16626,1.080127,-1.2902775,66.657234,905000
63
+ 119.567024,0.14595458,0.008484243,5.0229526,-1.6208171,-120.167595,-206.51088,2.794945,-2.8484647,63.342903,910000
64
+ 121.312294,0.19757505,0.0064555034,4.6313562,-2.2028885,-122.39661,-204.56937,0.5778958,-0.47494116,46.29484,915000
65
+ 120.90786,0.16858023,0.007986971,6.264059,-3.227532,-121.625305,-203.9521,0.83155936,-0.65137655,52.080383,920000
66
+ 118.58542,0.16018157,0.00692675,5.60378,-0.1731399,-119.21281,-205.73508,1.1584429,-1.0261184,52.844997,925000
67
+ 115.901054,0.16209687,0.008500233,6.7509246,-1.8309544,-116.8194,-204.3944,1.0212437,-1.1138524,64.64233,930000
68
+ 120.2312,0.17002434,0.008662603,6.1865363,-2.480421,-120.76321,-204.80827,1.4926924,-1.6277838,57.774414,935000
69
+ 121.89121,0.20445296,0.0064974674,6.7060075,-6.2401896,-122.01003,-204.35088,3.294867,-3.8058467,87.78856,940000
70
+ 123.24384,0.16889527,0.0085060885,5.8862596,3.7353697,-124.238525,-205.94595,1.0965049,-0.98953444,61.369213,945000
71
+ 113.954506,0.17830878,0.006728024,5.325522,0.37094387,-114.655174,-206.4011,0.83823407,-0.7807804,55.193123,950000
72
+ 120.30626,0.16915438,0.008961197,6.456205,0.15618852,-120.0121,-204.02203,3.122511,-2.127122,74.995255,955000
73
+ 115.86622,0.15803835,0.00744113,7.123651,-6.7548466,-116.30037,-204.77217,0.7793588,-0.7422339,62.694695,960000
74
+ 120.323235,0.17112324,0.0081722345,8.259368,-10.634113,-120.9295,-206.65465,1.0537194,-1.1855048,67.91823,965000
75
+ 117.53653,0.17185289,0.007443344,4.437994,1.2352298,-118.36358,-203.97156,0.61294854,-0.774995,42.985115,970000
76
+ 115.56567,0.15040475,0.007007843,4.8725734,3.8499665,-117.53937,-208.1213,0.99416,-1.1473113,60.728218,975000
77
+ 116.02283,0.1696934,0.00839741,6.32487,-0.14620957,-116.76444,-204.88855,1.2870429,-1.3454444,64.81055,980000
78
+ 117.67419,0.16840312,0.0072119692,7.4084053,-3.6252892,-118.43728,-203.51674,0.8623505,-0.66422987,71.434586,985000
79
+ 121.12256,0.15654936,0.0068886527,8.685486,-4.2358937,-121.93892,-205.5584,2.1035125,-1.8341234,97.454834,990000
80
+ 116.295,0.16839069,0.007927275,5.5712457,-2.3447587,-117.48417,-203.0156,0.6675778,-0.6183194,60.26319,995000
81
+ 114.8953,0.14208397,0.0072562154,7.0153327,-8.282008,-115.79203,-204.16786,0.5989526,-0.6333319,60.604286,1000000
82
+ 116.5179,0.16138956,0.0073237168,7.122069,-4.784895,-116.84832,-205.22319,0.9614183,-0.9328696,62.088818,1005000
83
+ 120.16047,0.15336904,0.007398617,4.492902,-1.8285015,-120.38596,-204.80447,1.2645375,-1.4332869,56.81818,1010000
84
+ 113.59772,0.16213821,0.009013691,6.207945,-0.09713425,-114.205315,-202.61151,0.96972805,-1.0450631,79.28229,1015000
85
+ 115.616585,0.17628442,0.0075296178,4.9818835,-11.53518,-116.64447,-203.78455,3.2876847,-3.9347348,85.96588,1020000
86
+ 114.117386,0.17975293,0.008942946,5.126064,2.4763105,-115.13273,-204.31221,1.351232,-1.3602425,76.0527,1025000
87
+ 110.44816,0.14715753,0.0067802547,4.295811,-2.586993,-110.62022,-203.33034,0.70424765,-0.7403217,48.25412,1030000
88
+ 117.278244,0.17829627,0.007805718,23.855564,-3.9626327,-117.24767,-205.33922,2.4298584,-2.5071292,99.925735,1035000
89
+ 109.69245,0.13902918,0.008227926,7.9457526,-6.1348925,-110.80653,-206.0623,1.6366298,-0.8187147,68.35566,1040000
90
+ 116.7493,0.15925063,0.0071774586,4.150496,-0.65462786,-117.793335,-205.6343,0.6666559,-0.7511641,56.890816,1045000
91
+ 111.79544,0.15973426,0.0068122256,7.2828097,-3.6298134,-112.59429,-205.25014,1.6633856,-0.9467573,59.205368,1050000
92
+ 114.60746,0.155947,0.007434671,3.5767076,0.49389577,-115.1189,-207.06587,1.266519,-1.2442901,54.48533,1055000
93
+ 109.1527,0.1466921,0.0070658205,6.020842,-1.6544348,-110.17562,-205.67648,2.9167924,-2.708261,72.65394,1060000
94
+ 109.917465,0.15502699,0.008063718,9.440261,-1.2841355,-110.33163,-201.05067,1.5118653,-1.6482081,90.01755,1065000
95
+ 109.13133,0.16635934,0.0072117792,5.955005,-0.9682492,-109.854515,-205.91417,5.379449,-6.4522386,113.40996,1070000
96
+ 109.034645,0.16033232,0.006181128,4.3973365,-2.270981,-109.33235,-202.5253,0.65905446,-1.0918232,45.84381,1075000
97
+ 108.99739,0.17079943,0.007241169,4.484252,1.0411063,-109.59717,-204.96284,1.5066899,-1.4291681,62.29576,1080000
98
+ 108.68369,0.16419922,0.0062172827,4.55635,-3.0907686,-110.02791,-204.77274,0.5754895,-0.57195,55.65006,1085000
99
+ 111.33707,0.13543914,0.006296018,6.595482,-5.2406754,-112.11529,-205.57396,0.5856975,-0.7354709,58.524788,1090000
100
+ 104.080956,0.14149985,0.0061240876,6.9431505,-4.1115227,-104.53355,-204.43489,0.77252597,-0.8377638,53.278587,1095000
101
+ 103.245415,0.15488975,0.0063337088,4.6604013,6.572258,-104.1961,-207.40462,0.58791816,-0.9585558,46.60469,1100000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 166.06499,0.18392003,0.0073187067,3.8530107,-49.74785,-166.19409,-203.86937,1.2257384,-1.1291348,64.64655,605000
3
+ 163.4832,0.188674,0.0056459373,6.608623,-54.920998,-163.69753,-203.93028,0.7061405,-0.7997772,54.46456,610000
4
+ 163.008,0.16517335,0.006892648,6.305266,-46.19134,-162.87964,-204.2602,1.3847011,-1.326308,55.98147,615000
5
+ 160.96254,0.17174289,0.007502403,8.1712,-48.609444,-161.38838,-204.69278,0.9587071,-1.2617546,68.04566,620000
6
+ 160.5675,0.17214093,0.007842035,5.5462317,-63.419815,-160.01299,-205.25906,1.1501782,-1.2272242,55.90058,625000
7
+ 161.2798,0.1481994,0.006410057,4.150022,-67.05159,-161.45323,-204.41072,0.8887694,-2.568139,54.22952,630000
8
+ 160.87596,0.17129819,0.00788438,6.541496,-55.990334,-161.01123,-204.22287,0.8897376,-1.1541513,54.47006,635000
9
+ 159.39224,0.17307258,0.007876503,6.6994066,-62.195137,-160.31523,-204.45802,1.3560688,-1.2591391,75.47792,640000
10
+ 160.58253,0.17523213,0.006422887,3.980457,-70.65616,-160.76115,-204.6634,1.0561328,-0.99527085,51.28894,645000
11
+ 159.14476,0.21605548,0.008620408,4.503652,-5.528885,-159.06142,-204.03331,1.3951472,-2.0222147,54.307407,650000
12
+ 154.18674,0.21944734,0.008084733,8.874441,-32.905792,-154.69403,-205.05196,1.6630969,-1.5937506,73.96778,655000
13
+ 151.29675,0.21059063,0.010063103,7.2526956,-30.158476,-151.02248,-205.17006,2.785377,-2.5243456,80.94262,660000
14
+ 151.51698,0.18820634,0.007570233,7.6560135,-34.643505,-151.63295,-204.63821,0.6579086,-0.74998546,68.9203,665000
15
+ 145.1546,0.18303771,0.008442642,7.9371095,-34.121937,-145.48492,-204.83542,0.78543013,-1.7082787,70.20558,670000
16
+ 148.61118,0.19758458,0.0094098365,5.498774,-30.875635,-148.80756,-204.79893,1.2413697,-1.217776,67.877525,675000
17
+ 144.85527,0.16880818,0.008039132,8.378299,-12.463703,-145.80072,-204.67958,1.2972692,-1.2847058,68.44676,680000
18
+ 145.31158,0.17633492,0.00730278,7.5312166,-12.738392,-145.15398,-204.74269,1.8503852,-1.4552251,65.06949,685000
19
+ 142.1703,0.17737314,0.009510728,9.581735,-19.948818,-143.01405,-205.9161,1.3545291,-1.3534076,100.83729,690000
20
+ 141.83751,0.19516939,0.009254462,9.6098,-6.831773,-141.99237,-205.31235,2.117879,-2.3033822,100.75346,695000
21
+ 136.70169,0.20735107,0.0074608414,5.3051624,-8.801661,-136.93526,-206.2875,3.562016,-4.3214855,73.693726,700000
22
+ 139.36197,0.19583015,0.008304932,6.473289,-3.6741135,-140.27823,-205.30725,1.0022086,-0.77213275,65.497574,705000
23
+ 138.24805,0.17990184,0.009083494,5.9896655,-20.30197,-138.13277,-205.23367,1.4769721,-0.898281,61.075073,710000
24
+ 134.49956,0.17572102,0.009861273,7.050506,0.9544666,-135.24918,-206.38939,0.82946426,-1.2912691,61.190216,715000
25
+ 134.792,0.1727162,0.007591157,5.3293085,0.9350946,-135.14676,-205.04877,1.1084915,-1.2227685,59.223175,720000
26
+ 138.02547,0.15385124,0.009459828,5.120279,-4.3956866,-137.86911,-205.42078,1.1336002,-1.1861212,62.126175,725000
27
+ 134.78238,0.1802071,0.0072565875,6.092469,-23.18277,-135.63205,-206.34114,1.0784248,-1.1421288,58.275932,730000
28
+ 134.92496,0.18499295,0.009287172,5.878539,1.6460104,-136.21405,-205.75291,0.7507756,-0.80237544,57.121605,735000
29
+ 131.3006,0.14087862,0.007332329,8.137138,-23.399137,-132.77654,-204.9767,1.060633,-1.0760254,70.49406,740000
30
+ 133.33417,0.14684187,0.006958673,7.1498237,2.1917746,-135.03014,-206.04889,1.3422222,-1.4479679,62.518593,745000
31
+ 134.33466,0.1470345,0.008124989,5.4722586,-24.076138,-134.778,-205.22353,2.1490679,-1.0711775,61.266457,750000
32
+ 133.0176,0.17566863,0.008899769,6.757254,-2.4877834,-133.79312,-205.42628,1.097014,-1.1732321,72.68582,755000
33
+ 135.12213,0.20439832,0.007642889,8.446967,-0.71190995,-135.65654,-205.30997,1.6737324,-1.5072596,87.67256,760000
34
+ 129.55078,0.18112579,0.008011497,6.2206016,-0.9824583,-130.60344,-206.82866,1.0763506,-0.8933415,54.63727,765000
35
+ 130.72289,0.17807901,0.0077719963,7.5635524,-8.495506,-131.37947,-205.62088,1.2655748,-1.3036174,83.52581,770000
36
+ 133.60071,0.18103437,0.008130168,5.0311975,-5.285836,-133.66814,-208.04678,0.9156441,-0.9095121,58.957764,775000
37
+ 133.97142,0.17851436,0.008970856,6.1729693,1.2569984,-134.00096,-205.19069,1.685972,-1.3054438,77.42645,780000
38
+ 129.82057,0.19789174,0.008799881,6.554498,-1.3195657,-130.19307,-205.44861,0.88551044,-0.8182341,63.70075,785000
39
+ 126.15414,0.1773861,0.008908973,6.889333,12.295847,-127.07729,-205.54996,0.8373528,-1.574405,61.225014,790000
40
+ 128.90784,0.16932961,0.0074163084,5.0215654,-2.304932,-129.07434,-205.01418,0.7193181,-0.8549147,56.69947,795000
41
+ 128.04976,0.17727152,0.009041754,6.8462296,-4.879854,-129.02914,-205.64705,1.289019,-1.5269545,72.47089,800000
42
+ 130.87828,0.18692347,0.008429831,7.256336,-6.3612704,-130.8486,-204.34935,1.3617572,-1.5012062,66.769135,805000
43
+ 127.09188,0.17049426,0.009013321,5.996105,-4.5349913,-127.43845,-204.8757,2.3427446,-3.797897,69.1035,810000
44
+ 130.25587,0.19210024,0.008940079,6.3756695,-7.446972,-130.76746,-205.35568,0.82040745,-0.8347776,72.121315,815000
45
+ 128.4026,0.1786831,0.0080689015,5.4265428,-7.6649265,-128.51245,-204.75883,2.03298,-1.7508552,76.73269,820000
46
+ 125.75116,0.1788582,0.0083336625,5.2586703,-7.9578304,-125.69232,-205.23715,1.1084577,-1.2519847,57.117424,825000
47
+ 129.55247,0.18298557,0.0081755575,5.0046334,-4.478055,-129.91177,-205.55122,0.72170323,-0.62007654,53.597466,830000
48
+ 126.14079,0.17892489,0.0061909566,8.574721,-7.908635,-126.15867,-205.08273,1.6693822,-1.9193003,94.66992,835000
49
+ 125.099075,0.1873132,0.007137706,4.08489,2.0764322,-125.81182,-205.5508,1.642991,-1.209022,50.131462,840000
50
+ 128.37709,0.1660405,0.0065760133,8.804901,-11.114733,-129.40381,-205.03726,0.8765111,-0.9863026,79.410805,845000
51
+ 119.265854,0.15387508,0.0074474737,6.9998055,-6.6110177,-120.043144,-206.00633,1.2161494,-1.2013518,77.7096,850000
52
+ 127.72482,0.17275128,0.0075857434,4.558629,-5.6445417,-128.90286,-205.71637,0.5151682,-0.46823117,45.861435,855000
53
+ 122.64298,0.17497326,0.008562335,4.574209,2.4452627,-123.19976,-204.93591,0.9960772,-0.9761434,62.2931,860000
54
+ 125.76472,0.16894567,0.008695243,5.965881,-1.0118144,-125.85225,-205.23683,2.1083248,-1.9503368,66.369774,865000
55
+ 125.94786,0.1383057,0.008479461,4.7308836,-2.6712341,-126.43677,-204.61719,0.92825365,-0.9658195,60.55772,870000
56
+ 121.66058,0.16267744,0.008358295,6.7826815,0.45956373,-121.7261,-205.45113,1.588254,-1.6754194,71.08594,875000
57
+ 126.3198,0.17335515,0.0076590423,6.5476723,-4.278531,-127.550026,-204.97757,0.85254,-0.95810235,60.830166,880000
58
+ 121.31031,0.12799889,0.0077690147,6.661017,-0.7593195,-121.91808,-203.87338,1.0800246,-1.0673281,62.265892,885000
59
+ 118.265175,0.16439563,0.007025783,9.750159,-4.6881757,-118.79181,-204.3316,0.7642861,-0.7652552,78.00795,890000
60
+ 121.29356,0.15283364,0.00933923,5.049493,2.1012478,-121.23899,-206.63853,1.1793369,-1.0876862,63.65472,895000
61
+ 123.86597,0.18859771,0.006479093,7.5510573,-2.7629201,-124.34247,-204.47723,1.6769525,-1.6799304,81.50221,900000
62
+ 123.144424,0.18178245,0.008937269,5.39239,-5.3957753,-123.978516,-205.16626,1.080127,-1.2902775,66.657234,905000
63
+ 119.567024,0.14595458,0.008484243,5.0229526,-1.6208171,-120.167595,-206.51088,2.794945,-2.8484647,63.342903,910000
64
+ 121.312294,0.19757505,0.0064555034,4.6313562,-2.2028885,-122.39661,-204.56937,0.5778958,-0.47494116,46.29484,915000
65
+ 120.90786,0.16858023,0.007986971,6.264059,-3.227532,-121.625305,-203.9521,0.83155936,-0.65137655,52.080383,920000
66
+ 118.58542,0.16018157,0.00692675,5.60378,-0.1731399,-119.21281,-205.73508,1.1584429,-1.0261184,52.844997,925000
67
+ 115.901054,0.16209687,0.008500233,6.7509246,-1.8309544,-116.8194,-204.3944,1.0212437,-1.1138524,64.64233,930000
68
+ 120.2312,0.17002434,0.008662603,6.1865363,-2.480421,-120.76321,-204.80827,1.4926924,-1.6277838,57.774414,935000
69
+ 121.89121,0.20445296,0.0064974674,6.7060075,-6.2401896,-122.01003,-204.35088,3.294867,-3.8058467,87.78856,940000
70
+ 123.24384,0.16889527,0.0085060885,5.8862596,3.7353697,-124.238525,-205.94595,1.0965049,-0.98953444,61.369213,945000
71
+ 113.954506,0.17830878,0.006728024,5.325522,0.37094387,-114.655174,-206.4011,0.83823407,-0.7807804,55.193123,950000
72
+ 120.30626,0.16915438,0.008961197,6.456205,0.15618852,-120.0121,-204.02203,3.122511,-2.127122,74.995255,955000
73
+ 115.86622,0.15803835,0.00744113,7.123651,-6.7548466,-116.30037,-204.77217,0.7793588,-0.7422339,62.694695,960000
74
+ 120.323235,0.17112324,0.0081722345,8.259368,-10.634113,-120.9295,-206.65465,1.0537194,-1.1855048,67.91823,965000
75
+ 117.53653,0.17185289,0.007443344,4.437994,1.2352298,-118.36358,-203.97156,0.61294854,-0.774995,42.985115,970000
76
+ 115.56567,0.15040475,0.007007843,4.8725734,3.8499665,-117.53937,-208.1213,0.99416,-1.1473113,60.728218,975000
77
+ 116.02283,0.1696934,0.00839741,6.32487,-0.14620957,-116.76444,-204.88855,1.2870429,-1.3454444,64.81055,980000
78
+ 117.67419,0.16840312,0.0072119692,7.4084053,-3.6252892,-118.43728,-203.51674,0.8623505,-0.66422987,71.434586,985000
79
+ 121.12256,0.15654936,0.0068886527,8.685486,-4.2358937,-121.93892,-205.5584,2.1035125,-1.8341234,97.454834,990000
80
+ 116.295,0.16839069,0.007927275,5.5712457,-2.3447587,-117.48417,-203.0156,0.6675778,-0.6183194,60.26319,995000
81
+ 114.8953,0.14208397,0.0072562154,7.0153327,-8.282008,-115.79203,-204.16786,0.5989526,-0.6333319,60.604286,1000000
82
+ 116.5179,0.16138956,0.0073237168,7.122069,-4.784895,-116.84832,-205.22319,0.9614183,-0.9328696,62.088818,1005000
83
+ 120.16047,0.15336904,0.007398617,4.492902,-1.8285015,-120.38596,-204.80447,1.2645375,-1.4332869,56.81818,1010000
84
+ 113.59772,0.16213821,0.009013691,6.207945,-0.09713425,-114.205315,-202.61151,0.96972805,-1.0450631,79.28229,1015000
85
+ 115.616585,0.17628442,0.0075296178,4.9818835,-11.53518,-116.64447,-203.78455,3.2876847,-3.9347348,85.96588,1020000
86
+ 114.117386,0.17975293,0.008942946,5.126064,2.4763105,-115.13273,-204.31221,1.351232,-1.3602425,76.0527,1025000
87
+ 110.44816,0.14715753,0.0067802547,4.295811,-2.586993,-110.62022,-203.33034,0.70424765,-0.7403217,48.25412,1030000
88
+ 117.278244,0.17829627,0.007805718,23.855564,-3.9626327,-117.24767,-205.33922,2.4298584,-2.5071292,99.925735,1035000
89
+ 109.69245,0.13902918,0.008227926,7.9457526,-6.1348925,-110.80653,-206.0623,1.6366298,-0.8187147,68.35566,1040000
90
+ 116.7493,0.15925063,0.0071774586,4.150496,-0.65462786,-117.793335,-205.6343,0.6666559,-0.7511641,56.890816,1045000
91
+ 111.79544,0.15973426,0.0068122256,7.2828097,-3.6298134,-112.59429,-205.25014,1.6633856,-0.9467573,59.205368,1050000
92
+ 114.60746,0.155947,0.007434671,3.5767076,0.49389577,-115.1189,-207.06587,1.266519,-1.2442901,54.48533,1055000
93
+ 109.1527,0.1466921,0.0070658205,6.020842,-1.6544348,-110.17562,-205.67648,2.9167924,-2.708261,72.65394,1060000
94
+ 109.917465,0.15502699,0.008063718,9.440261,-1.2841355,-110.33163,-201.05067,1.5118653,-1.6482081,90.01755,1065000
95
+ 109.13133,0.16635934,0.0072117792,5.955005,-0.9682492,-109.854515,-205.91417,5.379449,-6.4522386,113.40996,1070000
96
+ 109.034645,0.16033232,0.006181128,4.3973365,-2.270981,-109.33235,-202.5253,0.65905446,-1.0918232,45.84381,1075000
97
+ 108.99739,0.17079943,0.007241169,4.484252,1.0411063,-109.59717,-204.96284,1.5066899,-1.4291681,62.29576,1080000
98
+ 108.68369,0.16419922,0.0062172827,4.55635,-3.0907686,-110.02791,-204.77274,0.5754895,-0.57195,55.65006,1085000
99
+ 111.33707,0.13543914,0.006296018,6.595482,-5.2406754,-112.11529,-205.57396,0.5856975,-0.7354709,58.524788,1090000
100
+ 104.080956,0.14149985,0.0061240876,6.9431505,-4.1115227,-104.53355,-204.43489,0.77252597,-0.8377638,53.278587,1095000
101
+ 103.245415,0.15488975,0.0063337088,4.6604013,6.572258,-104.1961,-207.40462,0.58791816,-0.9585558,46.60469,1100000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900e5343c55a0907bc345c5000c49f7aa421e547f85d74bf1feb59a8209f9388
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e8fe8cfd547b7bc3e475c6f0d01935e4e07f0571dbffcfed9b075274dca734
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eea9c43b0551ea7f977395454341cbde2798ec8011728ecadc69665421731e5
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0baf0adc5b2791f570e0f4879af462a5a41628e9ef4ebd44ebe21382ae661af6
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91bdc9633a5be369d3cda5c81b2a2d4d50bd71625e2da7e5e3e796806dc1df7
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0274752d0846e2261ff188b490ab454bcc6c8c5ac470c98fc4604601e425a41
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c420ec04d0537243867e51adcdf7901b53c1c156add5ca4b1d37e52d093892
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af444341c96d45345a2c03bab8e00bb671dbbf37332f56042e86030c78b8541
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9902e996bd5cbd290bee6fcd8c2a81907cdbe7b2c1eb24c85a59a94ce4bdfb
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca4f018a18ed41ffc49d4b1465065e850076b94e11dd8003d049fcae8af7e50
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260318_204357/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/3fl61b7m