Tiredsheep commited on
Commit
f52f76e
·
verified ·
1 Parent(s): b1e689f

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_450000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_500000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_550000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_600000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_650000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_700000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_750000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_800000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_850000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_900000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/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/20260319_065452/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/20260319_065452/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,-0.041389795265924484,0.003133205656727402,-0.04106058676581292,0.002871627911187726,28.610637657985915,19.00099999999842,0.48,9507.36,-0.56,-525.5,378.02,1.108949022293091,450000
3
+ 0.0,0.0,-0.024834286206527934,-0.00940236631900433,-0.024942598970115647,-0.0057291936961925095,33.78176778279931,10.422999999999798,0.94,24839.24,-0.08,-296.02,206.46,0.652148871421814,500000
4
+ 0.0,0.0,-0.028018438899451152,-0.00971685547167347,-0.028430766152545344,0.004738414739182306,33.184751655963275,9.2569999999995,0.94,35574.96,-0.08,-270.62,183.14,0.5784587287902831,550000
5
+ 0.0,0.0,-0.025186477757024556,0.004272738342569619,-0.02484916207537505,-0.00407560414609894,34.90141271403678,7.767999999999515,0.96,43971.46,-0.06,-216.24,153.36,0.4903076648712158,600000
6
+ 0.0,0.0,-0.0329055896924412,-0.0029463682740379724,-0.03283196683193097,-0.0029280122854650117,35.64131318814135,6.689999999999591,1.0,51277.28,0.0,-183.56,131.8,0.4313522434234619,650000
7
+ 0.0,0.0,-0.03960597177489438,-0.003994794117919339,-0.03970962200225866,-0.0051717008289556545,35.54549395439881,6.744999999999583,1.0,58104.92,0.0,-189.0,132.9,0.43181901931762695,700000
8
+ 0.0,0.0,-0.05010768838898703,-0.0024893139619943283,-0.04996731453439365,-0.0044951626645555924,35.10487881359432,6.20999999999953,0.98,64699.3,-0.02,-166.06,122.2,0.3966691207885742,750000
9
+ 0.0,0.0,-0.014864644291215902,0.015451274965324313,-0.014531554866234357,0.008432356542156494,35.84178722440705,5.860999999999625,1.0,70952.32,0.0,-161.7,115.22,0.3773453044891357,800000
10
+ 0.0,0.0,-0.034354459308149295,0.010649474778136603,-0.03352603922640945,0.005660603577936307,35.66690822311571,5.609999999999635,1.0,76701.94,0.0,-151.04,110.2,0.3542423582077026,850000
11
+ 0.0,0.0,-0.050533652228343606,0.023966584133055392,-0.048994219570379555,0.015517652826814237,35.79304637795738,4.8949999999996825,1.0,82129.3,0.0,-133.08,95.9,0.31360247135162356,900000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/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,-0.041389795265924484,0.003133205656727402,-0.04106058676581292,0.002871627911187726,28.610637657985915,19.00099999999842,0.48,9507.36,-0.56,-525.5,378.02,1.108949022293091,450000
3
+ 0.0,0.0,-0.024834286206527934,-0.00940236631900433,-0.024942598970115647,-0.0057291936961925095,33.78176778279931,10.422999999999798,0.94,24839.24,-0.08,-296.02,206.46,0.652148871421814,500000
4
+ 0.0,0.0,-0.028018438899451152,-0.00971685547167347,-0.028430766152545344,0.004738414739182306,33.184751655963275,9.2569999999995,0.94,35574.96,-0.08,-270.62,183.14,0.5784587287902831,550000
5
+ 0.0,0.0,-0.025186477757024556,0.004272738342569619,-0.02484916207537505,-0.00407560414609894,34.90141271403678,7.767999999999515,0.96,43971.46,-0.06,-216.24,153.36,0.4903076648712158,600000
6
+ 0.0,0.0,-0.0329055896924412,-0.0029463682740379724,-0.03283196683193097,-0.0029280122854650117,35.64131318814135,6.689999999999591,1.0,51277.28,0.0,-183.56,131.8,0.4313522434234619,650000
7
+ 0.0,0.0,-0.03960597177489438,-0.003994794117919339,-0.03970962200225866,-0.0051717008289556545,35.54549395439881,6.744999999999583,1.0,58104.92,0.0,-189.0,132.9,0.43181901931762695,700000
8
+ 0.0,0.0,-0.05010768838898703,-0.0024893139619943283,-0.04996731453439365,-0.0044951626645555924,35.10487881359432,6.20999999999953,0.98,64699.3,-0.02,-166.06,122.2,0.3966691207885742,750000
9
+ 0.0,0.0,-0.014864644291215902,0.015451274965324313,-0.014531554866234357,0.008432356542156494,35.84178722440705,5.860999999999625,1.0,70952.32,0.0,-161.7,115.22,0.3773453044891357,800000
10
+ 0.0,0.0,-0.034354459308149295,0.010649474778136603,-0.03352603922640945,0.005660603577936307,35.66690822311571,5.609999999999635,1.0,76701.94,0.0,-151.04,110.2,0.3542423582077026,850000
11
+ 0.0,0.0,-0.050533652228343606,0.023966584133055392,-0.048994219570379555,0.015517652826814237,35.79304637795738,4.8949999999996825,1.0,82129.3,0.0,-133.08,95.9,0.31360247135162356,900000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/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
+ 167.48549,0.19567522,0.0064570326,3.667916,-77.11559,-167.72112,-205.06798,0.86617225,-0.8868776,44.30571,405000
3
+ 165.54988,0.19446468,0.005881684,5.2426734,-52.67727,-165.62883,-204.34837,0.79633695,-0.8226523,58.885643,410000
4
+ 165.49031,0.20786697,0.0056179846,4.247937,-46.498135,-165.4525,-204.16125,1.5774599,-1.62765,62.642258,415000
5
+ 162.51608,0.17554826,0.007280484,7.759341,-56.845554,-163.10594,-204.31117,0.9193446,-0.6359373,66.16112,420000
6
+ 162.72548,0.19730876,0.00672039,7.20231,-68.08469,-162.51688,-204.66571,1.9016539,-1.9770483,82.07197,425000
7
+ 162.33322,0.19775042,0.0068280445,7.970901,-62.726257,-162.51146,-204.41484,0.8619138,-0.80312914,54.987232,430000
8
+ 162.52757,0.16985548,0.0074067055,6.30325,-52.378536,-162.4255,-203.95612,2.359866,-2.410082,69.256294,435000
9
+ 161.41498,0.20926017,0.0063167075,8.114966,-60.421883,-162.30423,-204.95259,1.0606283,-0.8437691,65.21888,440000
10
+ 160.27211,0.18035519,0.0074985605,4.092114,-75.063705,-160.54434,-204.46071,1.5868115,-0.8959348,56.600006,445000
11
+ 159.98431,0.17590968,0.0066603455,6.7597795,-39.078194,-160.04192,-204.27652,3.2670803,-3.3891234,81.26032,450000
12
+ 155.8368,0.19953394,0.008755211,7.251906,-33.54761,-155.75171,-205.23166,1.6133163,-1.5849503,74.47474,455000
13
+ 155.82188,0.20832345,0.0073266574,5.7205915,-46.975597,-156.03914,-204.57796,1.845359,-1.8789291,70.916565,460000
14
+ 154.75291,0.17090237,0.0071982765,7.6474123,-13.648988,-154.75537,-204.52612,1.2202303,-1.3081964,73.77313,465000
15
+ 148.01265,0.19998561,0.0076620704,9.007244,-32.39515,-148.07744,-205.85199,1.3853973,-1.3983035,91.13993,470000
16
+ 152.5944,0.1859136,0.009349541,9.720627,-43.304993,-152.64525,-205.7781,2.048651,-2.138143,100.03192,475000
17
+ 153.02568,0.20048171,0.0076465956,7.0495667,-40.983387,-153.60759,-204.8608,1.7731274,-1.7724212,77.78151,480000
18
+ 153.32301,0.15206969,0.0066713905,7.282142,-59.513344,-153.40422,-205.44919,2.0461547,-1.8977196,70.97177,485000
19
+ 148.57726,0.1721237,0.00828432,7.0324707,-21.340103,-149.25731,-205.7347,1.0152131,-0.93552303,81.93927,490000
20
+ 147.40173,0.17040211,0.007212114,7.0288773,-13.989721,-147.90291,-205.37665,0.6059987,-0.88580257,64.91175,495000
21
+ 143.32008,0.17066935,0.0064284825,5.645529,-10.173336,-143.59741,-205.89185,0.7526806,-1.2344342,56.818542,500000
22
+ 149.95541,0.19929107,0.009414135,9.027445,-33.269585,-150.47427,-207.01521,1.5683222,-1.6971664,90.451416,505000
23
+ 143.83386,0.21635967,0.008811096,6.158542,-10.253602,-143.92467,-205.18858,1.0830672,-1.2487413,69.21452,510000
24
+ 143.58049,0.16969633,0.008112154,9.762387,0.76416063,-144.50818,-205.55054,0.8924615,-0.9724198,68.65037,515000
25
+ 145.5987,0.17394623,0.006910554,7.2889895,-24.428179,-145.95396,-205.19487,1.0092322,-1.0239633,70.52908,520000
26
+ 146.69211,0.19146621,0.0075450866,6.1868777,-9.25702,-146.57784,-205.09705,1.0554292,-0.87373376,68.77819,525000
27
+ 142.89973,0.18280154,0.007175519,6.0396934,-25.220524,-142.93578,-205.71674,0.9276281,-0.8633447,68.81935,530000
28
+ 141.36533,0.21959041,0.008764679,8.478887,0.5859193,-142.1197,-206.19395,1.5009693,-1.393989,90.56154,535000
29
+ 137.36237,0.1562705,0.008572423,5.9322505,-12.233816,-138.46931,-205.04771,0.82366645,-0.7982413,64.281105,540000
30
+ 142.92825,0.18749253,0.008403229,5.5446715,-19.774248,-143.77115,-205.94035,0.96413815,-0.8476068,71.66766,545000
31
+ 140.93149,0.155054,0.007770218,5.584047,-12.804035,-141.36546,-205.40714,1.4760258,-1.3684826,64.18901,550000
32
+ 141.0002,0.19530866,0.007974592,5.4338493,-36.200287,-141.72774,-206.37257,1.3372481,-1.331801,63.2121,555000
33
+ 141.24763,0.17550132,0.007700878,6.2669873,-2.2707384,-141.6378,-207.10075,1.3368493,-1.3469595,75.03061,560000
34
+ 140.57219,0.18924224,0.007786507,6.4725375,0.4089005,-141.19086,-205.18172,2.4439876,-2.1866329,85.15936,565000
35
+ 138.63402,0.17276807,0.0062528574,6.7979445,-3.1251013,-139.42326,-205.88261,0.7921265,-1.1931211,63.880333,570000
36
+ 142.19792,0.19785896,0.008239184,7.457559,0.10029577,-141.81766,-207.0133,1.8148694,-1.7750885,69.06056,575000
37
+ 139.2745,0.17264107,0.0063999766,6.514232,3.3040586,-139.59532,-205.84743,1.1805369,-1.2126182,67.541664,580000
38
+ 140.02692,0.17796697,0.008632334,5.571322,-7.5147047,-140.23302,-206.46309,1.925531,-1.9691113,63.6473,585000
39
+ 136.25035,0.17271993,0.008099345,7.097467,-2.532997,-136.92773,-205.11371,1.0835787,-0.88618445,73.99472,590000
40
+ 137.46733,0.16921556,0.007193736,7.7015023,-7.030851,-137.56499,-205.96002,1.4068134,-1.2613665,75.3579,595000
41
+ 137.66792,0.17154941,0.008015942,5.185563,-0.569216,-138.89607,-206.0739,2.9796793,-3.4268465,74.2959,600000
42
+ 135.10373,0.16693908,0.006646908,5.80412,2.184588,-135.25902,-204.50961,1.3151475,-1.2130169,75.69939,605000
43
+ 135.35231,0.16820848,0.008425137,5.9416947,-3.1622436,-135.46703,-205.53764,1.817158,-2.5428004,66.93079,610000
44
+ 135.76471,0.16859272,0.0077105477,9.332017,-8.627592,-136.2594,-206.20195,2.3281155,-2.3572195,105.26648,615000
45
+ 133.21127,0.17196903,0.0074661076,7.5867114,-0.24391824,-133.46976,-205.2631,1.5047878,-0.7636516,78.57017,620000
46
+ 129.6157,0.16841707,0.006932726,6.649401,-1.3310146,-129.82869,-206.16164,0.8507668,-0.96281767,74.214485,625000
47
+ 134.35321,0.17210281,0.006987026,4.210756,-2.4110599,-134.27058,-206.92863,0.5960542,-0.5422087,62.31976,630000
48
+ 129.60387,0.1641756,0.0062770853,5.260328,-7.9162254,-129.9022,-206.8165,1.3718913,-1.4371175,79.92915,635000
49
+ 133.5736,0.16880247,0.0063447296,13.204208,1.8115871,-134.01746,-206.66882,4.5894723,-4.501019,218.57669,640000
50
+ 133.40427,0.16304481,0.008025258,11.640389,-8.525708,-133.80951,-205.0647,2.763385,-2.8137224,107.72444,645000
51
+ 125.26873,0.18719992,0.008227516,9.046464,-3.2654839,-125.55214,-205.75052,2.3545206,-2.7136264,94.32333,650000
52
+ 131.1833,0.20691553,0.007943521,7.8112636,-6.796029,-132.23747,-204.83905,0.72375923,-0.71998125,76.81444,655000
53
+ 130.77086,0.20265563,0.0076797316,7.3374505,2.2788925,-131.5885,-206.03737,1.1062745,-1.4081041,77.24916,660000
54
+ 130.51617,0.18267885,0.0086040385,5.771641,2.846492,-130.52478,-205.75645,4.8598995,-5.5520334,152.62906,665000
55
+ 130.34549,0.16835167,0.008239865,7.162015,-4.45434,-130.8058,-204.6025,0.82280326,-1.1717967,67.849396,670000
56
+ 128.67735,0.19800368,0.008453807,6.7750473,-1.9288292,-128.57616,-205.5444,1.0318235,-1.1826091,76.67191,675000
57
+ 132.15298,0.17331459,0.008921946,5.7133713,-10.63826,-132.8144,-205.44196,1.300306,-1.4332404,67.709206,680000
58
+ 129.01723,0.1589908,0.007917249,14.891312,-3.26869,-129.69893,-206.63457,4.226044,-4.3646164,212.28627,685000
59
+ 120.28317,0.1683217,0.0075062076,5.829864,-4.912087,-120.80253,-206.08543,0.7674447,-0.8911425,66.658005,690000
60
+ 123.81161,0.1980153,0.009096386,6.4107203,1.2878258,-123.977135,-205.80698,1.2776825,-1.2876694,63.468285,695000
61
+ 127.28594,0.1868704,0.007314084,6.947835,-0.5837963,-127.51147,-204.37605,1.3576275,-1.3117836,58.333168,700000
62
+ 127.88971,0.17334867,0.0072750305,6.102604,-2.4000125,-129.09398,-204.79921,3.3091195,-3.2990892,99.671585,705000
63
+ 124.73989,0.15617944,0.0070948754,6.678425,-0.62553096,-125.288574,-205.67616,2.2406278,-2.279397,97.20337,710000
64
+ 123.89798,0.16168928,0.005984094,3.6356544,-5.4068117,-124.243675,-204.3884,0.7781689,-0.8186628,50.784805,715000
65
+ 124.015945,0.18128647,0.0076978025,5.0764117,-5.684007,-125.027405,-205.69247,1.1297544,-1.0846263,63.527718,720000
66
+ 124.671524,0.14665805,0.0066528553,4.9612737,-4.3483224,-125.13323,-205.58098,0.9111172,-1.0079161,65.68008,725000
67
+ 121.21573,0.16941221,0.007979925,5.523722,-6.3025026,-121.48665,-204.43625,2.195449,-2.0997148,66.964935,730000
68
+ 126.15007,0.17391387,0.0081887795,5.325219,-3.8478744,-126.54293,-205.81104,0.90965265,-0.9093727,61.94135,735000
69
+ 126.47583,0.14763208,0.0071814987,5.051305,-4.6529236,-126.27848,-205.5986,1.2778586,-1.4648507,60.1239,740000
70
+ 128.77768,0.14442918,0.007370624,6.922586,-2.0400465,-129.39436,-204.8978,0.7087724,-0.6734479,68.043434,745000
71
+ 117.931046,0.1324338,0.0076937163,7.8741007,-3.2040744,-117.846794,-205.22688,1.5826957,-1.8547872,98.046005,750000
72
+ 124.367516,0.16642484,0.007405086,6.5933123,-2.3535511,-124.41161,-204.14108,1.0936487,-1.2664713,63.01073,755000
73
+ 121.64808,0.1915566,0.0066976487,4.7848167,1.1328056,-122.66384,-204.71558,0.65306175,-0.6674563,54.81587,760000
74
+ 122.17651,0.17218731,0.008973059,7.5416384,-2.7428489,-122.079445,-205.17902,2.4748929,-2.4992418,113.75863,765000
75
+ 124.02355,0.16666676,0.0070442315,5.4756618,-2.792446,-124.270836,-207.07367,1.1713327,-0.9873855,64.566376,770000
76
+ 116.51552,0.1547986,0.007809484,4.633769,0.44591683,-117.79449,-206.053,0.90732354,-0.7895734,53.127457,775000
77
+ 118.28134,0.17043075,0.0067173885,4.1085763,1.4733262,-118.791275,-205.70857,0.8066257,-0.7708198,63.41597,780000
78
+ 121.61071,0.17019905,0.007643126,4.9541535,-1.993565,-122.31376,-207.64995,1.578781,-1.6184164,59.53936,785000
79
+ 123.74374,0.16746755,0.007987942,10.184382,-1.8332868,-123.88562,-206.04703,2.3295226,-2.3537467,108.74632,790000
80
+ 121.279,0.1711866,0.0082068015,7.071506,-4.9716763,-121.943115,-203.51994,1.1399281,-1.0190309,69.07945,795000
81
+ 119.55472,0.15472825,0.0066366843,6.8990264,-4.8184543,-119.89329,-205.54982,1.0677751,-1.0913696,85.64435,800000
82
+ 119.26788,0.1783436,0.0059155202,7.0572925,1.1404836,-119.79913,-205.70712,1.4340004,-1.5244551,72.713394,805000
83
+ 125.20227,0.17784838,0.008771097,5.240001,-3.5652044,-124.80041,-205.36972,1.3549374,-1.6037079,60.35427,810000
84
+ 119.13305,0.17605576,0.0073857363,5.9666553,-8.716225,-119.50822,-205.58281,0.867326,-0.97653586,55.728546,815000
85
+ 120.24824,0.16106099,0.0093928585,5.4890428,-3.8191023,-120.57568,-206.16995,1.6256813,-2.1772814,69.76528,820000
86
+ 114.9065,0.15479815,0.006699128,8.404312,-1.6271741,-115.79492,-206.71768,1.3601265,-1.0317984,93.77012,825000
87
+ 120.097,0.16746005,0.006814493,4.1595817,-1.5734329,-120.50281,-206.08452,1.1572801,-0.85549325,51.410034,830000
88
+ 117.67734,0.17008564,0.007671733,5.350601,-4.5069532,-117.909355,-206.1611,0.7588518,-0.80344814,53.37732,835000
89
+ 114.65417,0.16920045,0.0073666237,5.48045,-2.833115,-115.54699,-205.97003,1.4267102,-1.4331342,65.50144,840000
90
+ 122.29909,0.15401757,0.00733578,6.1873956,0.41030794,-122.725174,-205.11433,1.6294751,-1.756059,73.50576,845000
91
+ 117.46014,0.16256243,0.0070264367,5.57436,-5.3518634,-118.310974,-204.40797,1.7628577,-1.7481332,73.60051,850000
92
+ 116.12921,0.1701051,0.008142356,4.385185,-2.4319484,-116.4,-205.11307,1.1721158,-0.7617781,53.388767,855000
93
+ 111.94912,0.16629,0.006911484,5.278996,-2.8910408,-112.248375,-204.62372,1.1007055,-2.0297413,56.08844,860000
94
+ 114.12411,0.1559912,0.006650115,4.6135006,0.70084685,-114.53143,-204.02982,1.5123669,-1.0755385,47.407745,865000
95
+ 112.90793,0.14077014,0.0076906797,4.2369733,4.86478,-113.14956,-205.21002,3.4269474,-3.466916,89.83667,870000
96
+ 114.45408,0.1342566,0.0067909732,4.871181,-1.7884042,-115.16229,-204.87788,4.005946,-3.4736922,109.256065,875000
97
+ 114.27825,0.15763375,0.0065204194,4.944038,0.11857743,-115.37237,-206.45389,9.011894,-8.813781,169.84354,880000
98
+ 113.094604,0.13902383,0.006238819,6.3214774,1.6403121,-114.04657,-204.1492,1.0107937,-0.83736336,58.854546,885000
99
+ 113.127686,0.16272166,0.007581317,7.1773987,-4.26268,-113.782616,-206.41917,1.1984901,-0.7919039,70.31241,890000
100
+ 106.584465,0.1291574,0.0059827277,8.343071,-3.594289,-107.54836,-205.76367,1.2096541,-0.9850996,93.31408,895000
101
+ 106.22024,0.1662443,0.006927959,4.371022,2.1495066,-106.728905,-206.62164,0.89579743,-0.76540685,55.537865,900000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/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
+ 167.48549,0.19567522,0.0064570326,3.667916,-77.11559,-167.72112,-205.06798,0.86617225,-0.8868776,44.30571,405000
3
+ 165.54988,0.19446468,0.005881684,5.2426734,-52.67727,-165.62883,-204.34837,0.79633695,-0.8226523,58.885643,410000
4
+ 165.49031,0.20786697,0.0056179846,4.247937,-46.498135,-165.4525,-204.16125,1.5774599,-1.62765,62.642258,415000
5
+ 162.51608,0.17554826,0.007280484,7.759341,-56.845554,-163.10594,-204.31117,0.9193446,-0.6359373,66.16112,420000
6
+ 162.72548,0.19730876,0.00672039,7.20231,-68.08469,-162.51688,-204.66571,1.9016539,-1.9770483,82.07197,425000
7
+ 162.33322,0.19775042,0.0068280445,7.970901,-62.726257,-162.51146,-204.41484,0.8619138,-0.80312914,54.987232,430000
8
+ 162.52757,0.16985548,0.0074067055,6.30325,-52.378536,-162.4255,-203.95612,2.359866,-2.410082,69.256294,435000
9
+ 161.41498,0.20926017,0.0063167075,8.114966,-60.421883,-162.30423,-204.95259,1.0606283,-0.8437691,65.21888,440000
10
+ 160.27211,0.18035519,0.0074985605,4.092114,-75.063705,-160.54434,-204.46071,1.5868115,-0.8959348,56.600006,445000
11
+ 159.98431,0.17590968,0.0066603455,6.7597795,-39.078194,-160.04192,-204.27652,3.2670803,-3.3891234,81.26032,450000
12
+ 155.8368,0.19953394,0.008755211,7.251906,-33.54761,-155.75171,-205.23166,1.6133163,-1.5849503,74.47474,455000
13
+ 155.82188,0.20832345,0.0073266574,5.7205915,-46.975597,-156.03914,-204.57796,1.845359,-1.8789291,70.916565,460000
14
+ 154.75291,0.17090237,0.0071982765,7.6474123,-13.648988,-154.75537,-204.52612,1.2202303,-1.3081964,73.77313,465000
15
+ 148.01265,0.19998561,0.0076620704,9.007244,-32.39515,-148.07744,-205.85199,1.3853973,-1.3983035,91.13993,470000
16
+ 152.5944,0.1859136,0.009349541,9.720627,-43.304993,-152.64525,-205.7781,2.048651,-2.138143,100.03192,475000
17
+ 153.02568,0.20048171,0.0076465956,7.0495667,-40.983387,-153.60759,-204.8608,1.7731274,-1.7724212,77.78151,480000
18
+ 153.32301,0.15206969,0.0066713905,7.282142,-59.513344,-153.40422,-205.44919,2.0461547,-1.8977196,70.97177,485000
19
+ 148.57726,0.1721237,0.00828432,7.0324707,-21.340103,-149.25731,-205.7347,1.0152131,-0.93552303,81.93927,490000
20
+ 147.40173,0.17040211,0.007212114,7.0288773,-13.989721,-147.90291,-205.37665,0.6059987,-0.88580257,64.91175,495000
21
+ 143.32008,0.17066935,0.0064284825,5.645529,-10.173336,-143.59741,-205.89185,0.7526806,-1.2344342,56.818542,500000
22
+ 149.95541,0.19929107,0.009414135,9.027445,-33.269585,-150.47427,-207.01521,1.5683222,-1.6971664,90.451416,505000
23
+ 143.83386,0.21635967,0.008811096,6.158542,-10.253602,-143.92467,-205.18858,1.0830672,-1.2487413,69.21452,510000
24
+ 143.58049,0.16969633,0.008112154,9.762387,0.76416063,-144.50818,-205.55054,0.8924615,-0.9724198,68.65037,515000
25
+ 145.5987,0.17394623,0.006910554,7.2889895,-24.428179,-145.95396,-205.19487,1.0092322,-1.0239633,70.52908,520000
26
+ 146.69211,0.19146621,0.0075450866,6.1868777,-9.25702,-146.57784,-205.09705,1.0554292,-0.87373376,68.77819,525000
27
+ 142.89973,0.18280154,0.007175519,6.0396934,-25.220524,-142.93578,-205.71674,0.9276281,-0.8633447,68.81935,530000
28
+ 141.36533,0.21959041,0.008764679,8.478887,0.5859193,-142.1197,-206.19395,1.5009693,-1.393989,90.56154,535000
29
+ 137.36237,0.1562705,0.008572423,5.9322505,-12.233816,-138.46931,-205.04771,0.82366645,-0.7982413,64.281105,540000
30
+ 142.92825,0.18749253,0.008403229,5.5446715,-19.774248,-143.77115,-205.94035,0.96413815,-0.8476068,71.66766,545000
31
+ 140.93149,0.155054,0.007770218,5.584047,-12.804035,-141.36546,-205.40714,1.4760258,-1.3684826,64.18901,550000
32
+ 141.0002,0.19530866,0.007974592,5.4338493,-36.200287,-141.72774,-206.37257,1.3372481,-1.331801,63.2121,555000
33
+ 141.24763,0.17550132,0.007700878,6.2669873,-2.2707384,-141.6378,-207.10075,1.3368493,-1.3469595,75.03061,560000
34
+ 140.57219,0.18924224,0.007786507,6.4725375,0.4089005,-141.19086,-205.18172,2.4439876,-2.1866329,85.15936,565000
35
+ 138.63402,0.17276807,0.0062528574,6.7979445,-3.1251013,-139.42326,-205.88261,0.7921265,-1.1931211,63.880333,570000
36
+ 142.19792,0.19785896,0.008239184,7.457559,0.10029577,-141.81766,-207.0133,1.8148694,-1.7750885,69.06056,575000
37
+ 139.2745,0.17264107,0.0063999766,6.514232,3.3040586,-139.59532,-205.84743,1.1805369,-1.2126182,67.541664,580000
38
+ 140.02692,0.17796697,0.008632334,5.571322,-7.5147047,-140.23302,-206.46309,1.925531,-1.9691113,63.6473,585000
39
+ 136.25035,0.17271993,0.008099345,7.097467,-2.532997,-136.92773,-205.11371,1.0835787,-0.88618445,73.99472,590000
40
+ 137.46733,0.16921556,0.007193736,7.7015023,-7.030851,-137.56499,-205.96002,1.4068134,-1.2613665,75.3579,595000
41
+ 137.66792,0.17154941,0.008015942,5.185563,-0.569216,-138.89607,-206.0739,2.9796793,-3.4268465,74.2959,600000
42
+ 135.10373,0.16693908,0.006646908,5.80412,2.184588,-135.25902,-204.50961,1.3151475,-1.2130169,75.69939,605000
43
+ 135.35231,0.16820848,0.008425137,5.9416947,-3.1622436,-135.46703,-205.53764,1.817158,-2.5428004,66.93079,610000
44
+ 135.76471,0.16859272,0.0077105477,9.332017,-8.627592,-136.2594,-206.20195,2.3281155,-2.3572195,105.26648,615000
45
+ 133.21127,0.17196903,0.0074661076,7.5867114,-0.24391824,-133.46976,-205.2631,1.5047878,-0.7636516,78.57017,620000
46
+ 129.6157,0.16841707,0.006932726,6.649401,-1.3310146,-129.82869,-206.16164,0.8507668,-0.96281767,74.214485,625000
47
+ 134.35321,0.17210281,0.006987026,4.210756,-2.4110599,-134.27058,-206.92863,0.5960542,-0.5422087,62.31976,630000
48
+ 129.60387,0.1641756,0.0062770853,5.260328,-7.9162254,-129.9022,-206.8165,1.3718913,-1.4371175,79.92915,635000
49
+ 133.5736,0.16880247,0.0063447296,13.204208,1.8115871,-134.01746,-206.66882,4.5894723,-4.501019,218.57669,640000
50
+ 133.40427,0.16304481,0.008025258,11.640389,-8.525708,-133.80951,-205.0647,2.763385,-2.8137224,107.72444,645000
51
+ 125.26873,0.18719992,0.008227516,9.046464,-3.2654839,-125.55214,-205.75052,2.3545206,-2.7136264,94.32333,650000
52
+ 131.1833,0.20691553,0.007943521,7.8112636,-6.796029,-132.23747,-204.83905,0.72375923,-0.71998125,76.81444,655000
53
+ 130.77086,0.20265563,0.0076797316,7.3374505,2.2788925,-131.5885,-206.03737,1.1062745,-1.4081041,77.24916,660000
54
+ 130.51617,0.18267885,0.0086040385,5.771641,2.846492,-130.52478,-205.75645,4.8598995,-5.5520334,152.62906,665000
55
+ 130.34549,0.16835167,0.008239865,7.162015,-4.45434,-130.8058,-204.6025,0.82280326,-1.1717967,67.849396,670000
56
+ 128.67735,0.19800368,0.008453807,6.7750473,-1.9288292,-128.57616,-205.5444,1.0318235,-1.1826091,76.67191,675000
57
+ 132.15298,0.17331459,0.008921946,5.7133713,-10.63826,-132.8144,-205.44196,1.300306,-1.4332404,67.709206,680000
58
+ 129.01723,0.1589908,0.007917249,14.891312,-3.26869,-129.69893,-206.63457,4.226044,-4.3646164,212.28627,685000
59
+ 120.28317,0.1683217,0.0075062076,5.829864,-4.912087,-120.80253,-206.08543,0.7674447,-0.8911425,66.658005,690000
60
+ 123.81161,0.1980153,0.009096386,6.4107203,1.2878258,-123.977135,-205.80698,1.2776825,-1.2876694,63.468285,695000
61
+ 127.28594,0.1868704,0.007314084,6.947835,-0.5837963,-127.51147,-204.37605,1.3576275,-1.3117836,58.333168,700000
62
+ 127.88971,0.17334867,0.0072750305,6.102604,-2.4000125,-129.09398,-204.79921,3.3091195,-3.2990892,99.671585,705000
63
+ 124.73989,0.15617944,0.0070948754,6.678425,-0.62553096,-125.288574,-205.67616,2.2406278,-2.279397,97.20337,710000
64
+ 123.89798,0.16168928,0.005984094,3.6356544,-5.4068117,-124.243675,-204.3884,0.7781689,-0.8186628,50.784805,715000
65
+ 124.015945,0.18128647,0.0076978025,5.0764117,-5.684007,-125.027405,-205.69247,1.1297544,-1.0846263,63.527718,720000
66
+ 124.671524,0.14665805,0.0066528553,4.9612737,-4.3483224,-125.13323,-205.58098,0.9111172,-1.0079161,65.68008,725000
67
+ 121.21573,0.16941221,0.007979925,5.523722,-6.3025026,-121.48665,-204.43625,2.195449,-2.0997148,66.964935,730000
68
+ 126.15007,0.17391387,0.0081887795,5.325219,-3.8478744,-126.54293,-205.81104,0.90965265,-0.9093727,61.94135,735000
69
+ 126.47583,0.14763208,0.0071814987,5.051305,-4.6529236,-126.27848,-205.5986,1.2778586,-1.4648507,60.1239,740000
70
+ 128.77768,0.14442918,0.007370624,6.922586,-2.0400465,-129.39436,-204.8978,0.7087724,-0.6734479,68.043434,745000
71
+ 117.931046,0.1324338,0.0076937163,7.8741007,-3.2040744,-117.846794,-205.22688,1.5826957,-1.8547872,98.046005,750000
72
+ 124.367516,0.16642484,0.007405086,6.5933123,-2.3535511,-124.41161,-204.14108,1.0936487,-1.2664713,63.01073,755000
73
+ 121.64808,0.1915566,0.0066976487,4.7848167,1.1328056,-122.66384,-204.71558,0.65306175,-0.6674563,54.81587,760000
74
+ 122.17651,0.17218731,0.008973059,7.5416384,-2.7428489,-122.079445,-205.17902,2.4748929,-2.4992418,113.75863,765000
75
+ 124.02355,0.16666676,0.0070442315,5.4756618,-2.792446,-124.270836,-207.07367,1.1713327,-0.9873855,64.566376,770000
76
+ 116.51552,0.1547986,0.007809484,4.633769,0.44591683,-117.79449,-206.053,0.90732354,-0.7895734,53.127457,775000
77
+ 118.28134,0.17043075,0.0067173885,4.1085763,1.4733262,-118.791275,-205.70857,0.8066257,-0.7708198,63.41597,780000
78
+ 121.61071,0.17019905,0.007643126,4.9541535,-1.993565,-122.31376,-207.64995,1.578781,-1.6184164,59.53936,785000
79
+ 123.74374,0.16746755,0.007987942,10.184382,-1.8332868,-123.88562,-206.04703,2.3295226,-2.3537467,108.74632,790000
80
+ 121.279,0.1711866,0.0082068015,7.071506,-4.9716763,-121.943115,-203.51994,1.1399281,-1.0190309,69.07945,795000
81
+ 119.55472,0.15472825,0.0066366843,6.8990264,-4.8184543,-119.89329,-205.54982,1.0677751,-1.0913696,85.64435,800000
82
+ 119.26788,0.1783436,0.0059155202,7.0572925,1.1404836,-119.79913,-205.70712,1.4340004,-1.5244551,72.713394,805000
83
+ 125.20227,0.17784838,0.008771097,5.240001,-3.5652044,-124.80041,-205.36972,1.3549374,-1.6037079,60.35427,810000
84
+ 119.13305,0.17605576,0.0073857363,5.9666553,-8.716225,-119.50822,-205.58281,0.867326,-0.97653586,55.728546,815000
85
+ 120.24824,0.16106099,0.0093928585,5.4890428,-3.8191023,-120.57568,-206.16995,1.6256813,-2.1772814,69.76528,820000
86
+ 114.9065,0.15479815,0.006699128,8.404312,-1.6271741,-115.79492,-206.71768,1.3601265,-1.0317984,93.77012,825000
87
+ 120.097,0.16746005,0.006814493,4.1595817,-1.5734329,-120.50281,-206.08452,1.1572801,-0.85549325,51.410034,830000
88
+ 117.67734,0.17008564,0.007671733,5.350601,-4.5069532,-117.909355,-206.1611,0.7588518,-0.80344814,53.37732,835000
89
+ 114.65417,0.16920045,0.0073666237,5.48045,-2.833115,-115.54699,-205.97003,1.4267102,-1.4331342,65.50144,840000
90
+ 122.29909,0.15401757,0.00733578,6.1873956,0.41030794,-122.725174,-205.11433,1.6294751,-1.756059,73.50576,845000
91
+ 117.46014,0.16256243,0.0070264367,5.57436,-5.3518634,-118.310974,-204.40797,1.7628577,-1.7481332,73.60051,850000
92
+ 116.12921,0.1701051,0.008142356,4.385185,-2.4319484,-116.4,-205.11307,1.1721158,-0.7617781,53.388767,855000
93
+ 111.94912,0.16629,0.006911484,5.278996,-2.8910408,-112.248375,-204.62372,1.1007055,-2.0297413,56.08844,860000
94
+ 114.12411,0.1559912,0.006650115,4.6135006,0.70084685,-114.53143,-204.02982,1.5123669,-1.0755385,47.407745,865000
95
+ 112.90793,0.14077014,0.0076906797,4.2369733,4.86478,-113.14956,-205.21002,3.4269474,-3.466916,89.83667,870000
96
+ 114.45408,0.1342566,0.0067909732,4.871181,-1.7884042,-115.16229,-204.87788,4.005946,-3.4736922,109.256065,875000
97
+ 114.27825,0.15763375,0.0065204194,4.944038,0.11857743,-115.37237,-206.45389,9.011894,-8.813781,169.84354,880000
98
+ 113.094604,0.13902383,0.006238819,6.3214774,1.6403121,-114.04657,-204.1492,1.0107937,-0.83736336,58.854546,885000
99
+ 113.127686,0.16272166,0.007581317,7.1773987,-4.26268,-113.782616,-206.41917,1.1984901,-0.7919039,70.31241,890000
100
+ 106.584465,0.1291574,0.0059827277,8.343071,-3.594289,-107.54836,-205.76367,1.2096541,-0.9850996,93.31408,895000
101
+ 106.22024,0.1662443,0.006927959,4.371022,2.1495066,-106.728905,-206.62164,0.89579743,-0.76540685,55.537865,900000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_450000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d977cbb7680903825f52c02703504d78763215b30e35df02d6c7c82855b7a77f
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_500000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d88622b83d7cde9851b89ca499080822d2d4db8afe4654ac161f003793f3fc
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d99a26719689eb2d5576f995e2b3db8ca487a7bd23ca5ffd8111e9ad394c78b
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00628944f652a47e009da732772c75947359cf9acdafd761e07684b3b41abaa
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb055b178aca4437d0d66f5857d2583386e95ff8902af4a492dc3b47c1aad95
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0aea38cdf87f476ed5f77d11b6dcc9c5f11626da69f0427fd2d233e1a117df7
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9511de6c45a9ae9c7dfaa5693b7b85ed372250611fbd8c87d8374c286d2eb8ef
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92483f7ccacb3e3eec891095f9aa630f5c766caaf99b160c1679f945b9fe6d5e
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7cd5dc543eeb576e53476f7a1e2b7b5a50f9ef8515b29fc8b7743bfced691d1
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15a2d32a8dce68c254e5b7f49f9d05b99f38fb4ce9e213e4c5770902c755b049
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_065452/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/l4ext3v1