Tiredsheep commited on
Commit
cc87a9c
·
verified ·
1 Parent(s): 9bc1aa0

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1000000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1050000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1100000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1150000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1200000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1250000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1300000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1350000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1400000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_950000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/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/dsrl/20260319_171246/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/dsrl/20260319_171246/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,-0.05283392896348774,-0.001516944376360035,-0.05250773701716148,-0.0073556390279218824,32.67428328691158,10.39699999999955,0.88,5056.64,-0.16,-310.16,205.94,0.6713686466217041,950000
3
+ 0.0,0.0,-0.04535787752626948,-0.008051200545757729,-0.044771912751681686,0.008956494098503806,34.04691393564854,7.999999999999548,0.92,14805.58,-0.1,-232.76,158.0,0.5190586042404175,1000000
4
+ 0.0,0.0,-0.036214921738431466,0.005711861730532369,-0.035024180790342155,0.002551039010561322,33.18037336418593,7.346999999999648,0.94,23121.32,-0.08,-217.36,144.94,0.4881485033035278,1050000
5
+ 0.0,0.0,-0.04500862339473583,0.0043849711763408366,-0.04378931231791761,0.05134179765696138,32.63731966093074,7.124999999999806,0.98,30559.9,-0.02,-213.82,140.5,0.45664857387542723,1100000
6
+ 0.0,0.0,-0.04109674651656195,0.004209976693943635,-0.039862113193537496,-0.011195139970643425,32.80632296123034,5.6799999999996444,0.98,37184.0,-0.02,-163.02,111.6,0.36850010871887207,1150000
7
+ 0.0,0.0,-0.04622692975129839,0.010557111969761251,-0.04499528033940156,0.0037879943303485634,33.74269166718951,5.508999999999719,0.96,42632.54,-0.08,-163.84,108.18,0.3630454301834106,1200000
8
+ 0.0,0.0,-0.05364677873790791,0.020961692129287807,-0.051607808724926575,0.011310202990081522,33.43058058028419,5.445999999999708,0.96,48533.36,-0.08,-162.4,106.92,0.34997585773468015,1250000
9
+ 0.0,0.0,-0.06132050217545063,0.006995145350504227,-0.059231767590696864,9.679784339145676e-05,31.611226145373184,4.606999999999722,0.98,53530.9,-0.02,-123.5,90.14,0.2985940408706665,1300000
10
+ 0.0,0.0,-0.05074432635976649,0.024356953727913064,-0.04875887187775146,0.01495585605325465,32.85226655878987,5.820999999999677,0.96,59311.1,-0.06,-170.16,114.42,0.37701609611511233,1350000
11
+ 0.0,0.0,-0.05689170525689963,0.03773351502003285,-0.05499873210545782,0.011701215136727205,31.516038438926095,5.18799999999965,0.96,64650.72,-0.06,-145.96,101.76,0.3313642168045044,1400000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/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,-0.05283392896348774,-0.001516944376360035,-0.05250773701716148,-0.0073556390279218824,32.67428328691158,10.39699999999955,0.88,5056.64,-0.16,-310.16,205.94,0.6713686466217041,950000
3
+ 0.0,0.0,-0.04535787752626948,-0.008051200545757729,-0.044771912751681686,0.008956494098503806,34.04691393564854,7.999999999999548,0.92,14805.58,-0.1,-232.76,158.0,0.5190586042404175,1000000
4
+ 0.0,0.0,-0.036214921738431466,0.005711861730532369,-0.035024180790342155,0.002551039010561322,33.18037336418593,7.346999999999648,0.94,23121.32,-0.08,-217.36,144.94,0.4881485033035278,1050000
5
+ 0.0,0.0,-0.04500862339473583,0.0043849711763408366,-0.04378931231791761,0.05134179765696138,32.63731966093074,7.124999999999806,0.98,30559.9,-0.02,-213.82,140.5,0.45664857387542723,1100000
6
+ 0.0,0.0,-0.04109674651656195,0.004209976693943635,-0.039862113193537496,-0.011195139970643425,32.80632296123034,5.6799999999996444,0.98,37184.0,-0.02,-163.02,111.6,0.36850010871887207,1150000
7
+ 0.0,0.0,-0.04622692975129839,0.010557111969761251,-0.04499528033940156,0.0037879943303485634,33.74269166718951,5.508999999999719,0.96,42632.54,-0.08,-163.84,108.18,0.3630454301834106,1200000
8
+ 0.0,0.0,-0.05364677873790791,0.020961692129287807,-0.051607808724926575,0.011310202990081522,33.43058058028419,5.445999999999708,0.96,48533.36,-0.08,-162.4,106.92,0.34997585773468015,1250000
9
+ 0.0,0.0,-0.06132050217545063,0.006995145350504227,-0.059231767590696864,9.679784339145676e-05,31.611226145373184,4.606999999999722,0.98,53530.9,-0.02,-123.5,90.14,0.2985940408706665,1300000
10
+ 0.0,0.0,-0.05074432635976649,0.024356953727913064,-0.04875887187775146,0.01495585605325465,32.85226655878987,5.820999999999677,0.96,59311.1,-0.06,-170.16,114.42,0.37701609611511233,1350000
11
+ 0.0,0.0,-0.05689170525689963,0.03773351502003285,-0.05499873210545782,0.011701215136727205,31.516038438926095,5.18799999999965,0.96,64650.72,-0.06,-145.96,101.76,0.3313642168045044,1400000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/action_std,actor/actor_loss,actor/alpha,actor/alpha_loss,actor/entropy,actor/flow_loss,actor/q,actor/total_loss,critic/critic_loss,critic/distill_loss,critic/q_max,critic/q_mean,critic/q_min,critic/total_loss,grad/max,grad/min,grad/norm,step
2
+ 0.64957917,150.7018,0.0073846807,0.0039111534,-11.970369,0.19286889,-150.6134,150.89857,2.8988838,2.7293117,-24.36157,-153.32928,-194.19379,5.628196,1.047349,-0.9244407,47.309067,905000
3
+ 0.6456761,146.72023,0.007527638,-0.006013591,-13.298868,0.1860447,-146.62012,146.90027,2.0560849,6.4984484,-38.057545,-149.32396,-193.15959,8.554533,1.6038167,-1.5486326,87.740295,910000
4
+ 0.6520092,148.07686,0.00794684,-0.0021262867,-12.767564,0.19685897,-147.97539,148.27159,1.7797962,5.2752795,-41.251713,-150.65785,-194.92314,7.0550756,2.080364,-2.3520403,69.529236,915000
5
+ 0.64387167,145.6529,0.008529211,-0.021643056,-15.037521,0.168358,-145.52463,145.79962,2.5103633,7.0822725,-27.991705,-149.55165,-200.07497,9.592636,0.8959335,-0.83271277,83.56131,920000
6
+ 0.6443628,142.5101,0.008717102,-0.006263846,-13.21857,0.17206314,-142.39487,142.67589,2.4537997,8.610302,-50.697258,-145.04218,-200.04243,11.064102,1.585081,-1.5184572,70.81239,925000
7
+ 0.6459397,140.927,0.008480389,-0.01089365,-13.78457,0.1721743,-140.8101,141.08829,5.0872154,8.597699,-28.781542,-143.55763,-199.01134,13.684915,5.329166,-6.2579737,127.08199,930000
8
+ 0.64319944,141.84119,0.008722902,0.0071477694,-11.680574,0.17882949,-141.7393,142.02716,2.4305074,8.576043,-5.825998,-144.38527,-199.16399,11.006551,3.5280507,-3.7928703,103.83689,935000
9
+ 0.64425504,139.97156,0.008998167,-0.011118646,-13.735657,0.20588909,-139.84796,140.16632,3.944184,9.006977,-4.4794173,-143.4563,-201.29684,12.951161,2.8550928,-3.3423312,103.27793,940000
10
+ 0.651386,139.66237,0.009260213,0.004031261,-12.064669,0.1831057,-139.55066,139.8495,4.9109316,14.727971,-21.125553,-142.76247,-201.14795,19.638903,3.603419,-4.289301,190.96838,945000
11
+ 0.640137,139.44994,0.0091775125,-0.007351368,-13.30102,0.19811411,-139.32787,139.6407,2.4270418,9.129531,-21.783718,-142.23987,-197.76979,11.556573,1.7061672,-1.7516997,121.1713,950000
12
+ 0.6426791,135.42749,0.0090790335,-0.012112856,-13.834157,0.18319193,-135.30188,135.59857,3.0403132,8.618979,-7.5362883,-138.68211,-197.6941,11.659292,4.5675173,-4.5499854,115.47159,955000
13
+ 0.63337094,134.20891,0.0088137565,-0.0061689806,-13.199926,0.18186195,-134.09256,134.38461,3.0431783,10.119224,-20.777418,-137.43066,-202.13985,13.162402,1.9085562,-1.8758999,104.70743,960000
14
+ 0.63879627,135.9805,0.009199868,-0.0144455535,-14.070191,0.18823752,-135.85106,136.15428,3.2220788,12.023146,-11.702482,-139.13391,-201.98006,15.245224,6.89031,-6.0955486,173.157,965000
15
+ 0.64542145,131.52853,0.009403878,-0.0044697067,-12.975305,0.20042129,-131.40651,131.72449,3.9030423,9.858134,-23.658514,-134.7054,-199.74449,13.761177,2.946904,-4.643763,129.85062,970000
16
+ 0.64312863,136.11504,0.008753916,0.00024116815,-12.47245,0.17424478,-136.00586,136.28952,2.505853,15.037982,-18.71401,-138.54468,-202.6374,17.543835,5.7495065,-6.6976337,153.8957,975000
17
+ 0.64272076,137.61932,0.00913095,-0.017201167,-14.383831,0.16994685,-137.488,137.77208,6.3238835,7.14319,-19.34667,-140.59367,-201.13179,13.467073,2.7945497,-1.1010592,112.784004,980000
18
+ 0.64258385,135.89029,0.008974441,0.0014139477,-12.342447,0.17905784,-135.77953,136.07077,7.3492646,6.4168534,-19.472555,-138.94437,-201.29773,13.766118,0.8381354,-0.7669327,94.55718,985000
19
+ 0.6377319,133.7491,0.009123879,-0.016173825,-14.272692,0.17797317,-133.61888,133.9109,3.5941148,10.849093,-8.736182,-135.86003,-197.73398,14.443209,2.0998507,-2.3508563,154.47447,990000
20
+ 0.6439477,132.07384,0.009088719,0.009156483,-11.492544,0.18328777,-131.96939,132.26628,2.7893102,7.057447,-11.367028,-134.75536,-199.50076,9.846757,2.9173787,-2.767536,94.71338,995000
21
+ 0.6387096,126.592316,0.009165639,-0.0035197348,-12.884014,0.14976293,-126.47423,126.73856,3.3048794,7.3797607,0.4622795,-129.97008,-201.34544,10.68464,1.9452043,-1.963064,104.111786,1000000
22
+ 0.6436769,134.2829,0.0091967005,-0.011675034,-13.769481,0.16450031,-134.15625,134.43573,2.8075352,10.069704,-8.649959,-138.0284,-199.03107,12.877239,4.1350527,-4.219297,141.41933,1005000
23
+ 0.6393708,130.03455,0.0091768,-0.002677611,-12.79178,0.16946208,-129.91718,130.20134,2.700304,11.619089,-2.6312935,-132.81506,-196.76668,14.319393,3.947906,-2.8153443,111.05148,1010000
24
+ 0.6377929,130.84421,0.009059305,-0.009709714,-13.5717945,0.17291826,-130.72125,131.00742,5.53376,9.205457,0.81906307,-134.29813,-201.0476,14.739217,3.2433343,-3.461611,128.77237,1015000
25
+ 0.6420637,131.90007,0.008873651,0.008800941,-11.508194,0.18463254,-131.79794,132.0935,2.4390116,10.720815,-0.33855677,-134.59346,-199.44987,13.159826,6.713533,-6.1438246,161.31549,1020000
26
+ 0.64346147,133.72647,0.008947633,-0.010410945,-13.663542,0.1933156,-133.60422,133.90938,3.2366753,7.399705,-2.226372,-136.50731,-199.54782,10.63638,0.61006606,-0.62494546,85.51912,1025000
27
+ 0.6424765,133.03915,0.008892577,0.021179235,-10.118324,0.17378034,-132.94917,133.23412,9.13829,11.8575325,-19.403057,-136.16695,-201.06375,20.995823,1.3234621,-1.1780149,132.55493,1030000
28
+ 0.63616884,131.40976,0.0091326,-0.011191515,-13.725447,0.17570892,-131.28442,131.57428,3.0892167,9.821692,2.2162871,-135.04184,-200.60109,12.91091,8.4072,-9.009076,157.28026,1035000
29
+ 0.6456834,128.5752,0.00893235,0.0030047577,-12.1636095,0.13545552,-128.46654,128.71365,4.866656,8.809172,-9.292302,-132.0081,-199.42606,13.675827,2.4195356,-2.5340447,143.21094,1040000
30
+ 0.649946,131.38197,0.00898779,0.013289325,-11.021402,0.16331893,-131.28293,131.55858,3.522606,10.586989,-0.13379161,-134.07799,-195.6524,14.109595,10.981932,-10.058239,192.63577,1045000
31
+ 0.6497138,130.95598,0.009077237,-0.0025921273,-12.785563,0.16707881,-130.83992,131.12047,2.298644,6.743676,-2.2776089,-133.31009,-201.40294,9.04232,4.3536277,-4.420209,95.833664,1050000
32
+ 0.6500931,127.65683,0.00892281,0.012164069,-11.1367445,0.15112674,-127.55745,127.820114,4.190343,6.204857,0.5221518,-130.76485,-199.17609,10.3952,3.4765105,-3.0589705,116.80771,1055000
33
+ 0.65160066,130.99985,0.008917842,0.012881525,-11.055533,0.15922871,-130.90125,131.17195,12.939476,12.26237,-13.140795,-133.69339,-200.79,25.201847,2.8314824,-3.8499968,244.66103,1060000
34
+ 0.6359484,128.98956,0.009028738,-0.0145676,-14.11347,0.16453524,-128.86215,129.13953,4.87865,14.795638,2.5521874,-132.40852,-203.4183,19.674288,5.8538103,-5.565062,256.3157,1065000
35
+ 0.6515784,130.36551,0.008731155,0.02313939,-9.849791,0.17769064,-130.27951,130.56633,3.3478875,9.471329,-9.028017,-132.6255,-198.89438,12.819216,3.5064223,-3.4204888,141.74692,1070000
36
+ 0.64691556,130.03397,0.008780982,0.0016377418,-12.31349,0.18758744,-129.92584,130.22319,5.288713,9.4604025,-11.717187,-133.13121,-203.91858,14.749115,4.100061,-4.317022,195.82889,1075000
37
+ 0.6457896,130.3736,0.008852359,0.011014593,-11.255745,0.17845565,-130.27396,130.56306,2.77008,7.000812,2.0842426,-133.13795,-198.87317,9.770892,0.8889781,-0.74215394,98.143036,1080000
38
+ 0.6339341,128.22278,0.008650115,-0.01828524,-14.613873,0.17000079,-128.09637,128.3745,3.5603375,11.023192,-5.8603177,-131.21172,-202.11484,14.58353,1.30775,-2.7172318,125.77668,1085000
39
+ 0.647675,125.85515,0.008878649,0.011465507,-11.208643,0.14293507,-125.75563,126.00955,3.3309925,11.135959,-2.8454509,-128.616,-198.17473,14.466951,7.339171,-6.916791,189.49203,1090000
40
+ 0.6493406,129.42351,0.009009339,0.0013038666,-12.355276,0.1555685,-129.3122,129.58037,3.755037,10.88584,-19.854837,-131.30974,-197.77388,14.640878,1.9921821,-2.052544,152.27625,1095000
41
+ 0.63755375,128.66808,0.008506677,-0.0007993831,-12.593971,0.17472565,-128.56094,128.84201,3.4266717,12.130094,-0.44392058,-132.04085,-200.69014,15.556766,2.3721266,-1.8825034,128.59317,1100000
42
+ 0.63899446,127.76016,0.008756092,-0.0091879275,-13.549318,0.16961738,-127.641525,127.92059,4.3020515,17.525602,-5.6626096,-131.63622,-193.64856,21.827654,3.11929,-2.8960898,191.44836,1105000
43
+ 0.64544064,128.37085,0.008932823,0.004999105,-11.940367,0.15289347,-128.26419,128.52875,3.8954942,12.806514,-9.769363,-130.42703,-198.04675,16.702007,2.22449,-2.9884005,162.07695,1110000
44
+ 0.6449891,127.93926,0.008896402,0.0023930224,-12.231012,0.1484756,-127.830444,128.09013,2.9962633,18.028687,-20.225975,-130.46208,-201.43259,21.02495,5.1160927,-4.915655,141.19496,1115000
45
+ 0.64609635,126.86199,0.008631525,0.004096158,-12.025442,0.16308823,-126.758194,127.029175,9.132823,10.285053,7.045063,-129.9447,-197.57266,19.417877,2.9880848,-3.1068506,185.71336,1120000
46
+ 0.6343651,121.12844,0.009125771,0.009436834,-11.465914,0.19506696,-121.0238,121.33295,5.845591,14.448578,-7.80011,-124.19207,-194.0828,20.294168,5.411035,-6.017036,242.2438,1125000
47
+ 0.654203,127.2576,0.008833254,-0.0032425842,-12.867088,0.16916002,-127.143936,127.423515,4.277429,9.396747,-7.659291,-130.56648,-204.38275,13.674175,2.6498673,-2.085854,142.41449,1130000
48
+ 0.64578855,122.86132,0.0088823335,-0.0010673444,-12.620165,0.17389992,-122.74922,123.03415,4.2373934,9.545319,-1.4189657,-125.454445,-198.89404,13.782712,1.7773987,-1.1592953,132.07327,1135000
49
+ 0.6475571,125.07985,0.008669866,0.007158252,-11.674353,0.18457934,-124.97864,125.27158,4.2216783,12.946988,1.3269162,-128.13786,-201.08665,17.168667,4.8754377,-3.1758275,195.37497,1140000
50
+ 0.63792074,127.56608,0.009016679,-0.015297731,-14.196604,0.18146299,-127.43807,127.73225,4.1343994,12.408103,-21.158867,-130.97786,-198.54149,16.542503,2.0860784,-2.6888406,161.99232,1145000
51
+ 0.6446864,114.52579,0.008923946,0.012541265,-11.09465,0.14923482,-114.42679,114.68757,4.769302,12.170048,3.2399166,-118.11123,-198.36256,16.93935,2.9589655,-1.846559,185.09534,1150000
52
+ 0.64931226,128.00821,0.009017294,-0.0035438794,-12.893009,0.17765823,-127.89195,128.18233,3.5392807,13.077095,-1.6627975,-131.69408,-200.6327,16.616375,2.9401307,-3.2189884,180.17137,1155000
53
+ 0.6424177,121.901825,0.008877244,-0.0043060696,-12.985068,0.17485727,-121.78655,122.07238,3.418186,10.220291,5.2921014,-125.25063,-201.38846,13.638477,3.8715618,-4.410189,174.45148,1160000
54
+ 0.6467699,123.73031,0.008895677,0.007936269,-11.607851,0.20339999,-123.627045,123.94164,4.082362,12.494229,-4.634413,-126.64101,-202.39903,16.576591,3.221018,-3.6587377,148.94016,1165000
55
+ 0.64175075,120.776566,0.008827237,0.0020765108,-12.264761,0.1310863,-120.668304,120.90973,2.7456422,10.14818,-3.7022433,-123.20943,-200.92612,12.893822,3.489044,-3.6771224,129.35892,1170000
56
+ 0.6507392,121.002075,0.008806826,0.0030400117,-12.154812,0.15441287,-120.89503,121.15952,4.5945735,12.917308,-3.594806,-123.99558,-202.01927,17.51188,2.7325652,-2.8522336,178.54633,1175000
57
+ 0.64157426,123.74624,0.0090952525,0.0031649705,-12.1520195,0.18088892,-123.63572,123.93029,3.5845287,15.911284,-1.0972234,-127.21233,-196.79858,19.495813,2.4038227,-2.4450376,130.83844,1180000
58
+ 0.6433243,117.85934,0.009225725,-0.006214336,-13.173588,0.15454985,-117.7378,118.00767,3.72204,14.02251,4.278977,-120.58494,-200.39676,17.744549,4.3758287,-4.0406146,189.33716,1185000
59
+ 0.64433557,117.17344,0.009059474,-0.010244896,-13.630849,0.15144281,-117.04996,117.31464,7.997051,10.428072,2.875818,-120.55444,-195.33492,18.425123,2.7469976,-2.7671497,179.7463,1190000
60
+ 0.64503264,114.90239,0.009110566,0.017624492,-10.565489,0.15590344,-114.80612,115.07592,4.054363,10.327818,1.8193916,-117.51184,-197.8135,14.382181,2.0243473,-1.5850133,137.0502,1195000
61
+ 0.64813995,122.64922,0.008994774,0.008774815,-11.524454,0.13906372,-122.54556,122.79706,4.616203,9.014315,-4.9589043,-125.33494,-200.17583,13.630518,1.4396579,-2.0060263,125.15717,1200000
62
+ 0.6482269,122.82191,0.008811879,-0.0018795296,-12.713295,0.14165066,-122.709885,122.96168,4.57251,9.807303,-0.32428655,-126.22882,-198.13484,14.379813,6.5346,-7.0436378,165.18135,1205000
63
+ 0.64885443,119.04972,0.008879627,-0.005523769,-13.122072,0.15794732,-118.933205,119.20214,4.077433,10.730473,11.272026,-122.46378,-201.40628,14.807905,1.6039982,-1.5456866,132.4802,1210000
64
+ 0.64679086,118.25969,0.00927239,0.002384684,-12.242819,0.1725135,-118.14617,118.43459,3.5752003,16.373291,-5.152007,-121.83054,-197.13692,19.948492,3.9841888,-4.6052136,181.06442,1215000
65
+ 0.63963574,115.85088,0.009266445,0.0025325387,-12.226698,0.19816566,-115.73758,116.05158,2.623193,15.49966,3.3659444,-118.97924,-191.18114,18.122852,4.3173656,-4.5448523,163.09218,1220000
66
+ 0.6408415,119.53094,0.008920147,-0.0036461405,-12.908753,0.16490355,-119.415794,119.69219,4.4396887,12.567731,0.071359076,-122.40454,-202.06708,17.00742,2.4281492,-1.6997082,161.32214,1225000
67
+ 0.64951825,117.53186,0.008930664,0.0077735516,-11.629566,0.18072787,-117.42801,117.72036,3.8052118,12.603823,-4.5255795,-120.033035,-198.92616,16.409035,4.048297,-4.1396346,153.7415,1230000
68
+ 0.6443987,116.69121,0.009285788,0.0014932253,-12.339192,0.19225386,-116.57663,116.88496,11.37549,10.427495,-4.158517,-119.6074,-200.36372,21.802986,1.6340364,-1.8847488,170.70439,1235000
69
+ 0.647457,120.67511,0.008920028,0.011330311,-11.22979,0.18333381,-120.574936,120.869774,3.8335664,11.93994,0.49240735,-123.73693,-196.69443,15.773507,1.3824825,-2.6235902,131.4314,1240000
70
+ 0.6403355,124.81528,0.009370808,-0.017486205,-14.36603,0.16729832,-124.680664,124.96509,6.0552797,14.319133,-2.448477,-128.26085,-202.24838,20.374413,3.325889,-4.124484,211.43396,1245000
71
+ 0.6520071,110.385956,0.009097379,0.022334697,-10.04493,0.1552166,-110.29457,110.56351,9.601237,9.694278,1.2187202,-112.474,-202.27718,19.295515,1.436751,-1.5673035,129.54807,1250000
72
+ 0.6477352,118.98874,0.009047766,0.015052356,-10.836346,0.17546567,-118.89069,119.17926,4.308233,11.233907,-3.2541728,-121.830765,-202.47957,15.542139,2.562027,-2.3481553,156.86609,1255000
73
+ 0.64065725,112.17088,0.008857012,0.0017468461,-12.3027725,0.15449029,-112.06192,112.32712,5.6124887,12.180911,1.1758058,-114.81287,-199.2972,17.7934,4.4628534,-3.886786,239.3055,1260000
74
+ 0.64927626,117.14756,0.009172237,-0.004553193,-12.99641,0.15574382,-117.02836,117.29875,4.6105037,9.692355,1.6862127,-119.35561,-199.91214,14.302858,1.7083036,-1.1564096,100.72284,1265000
75
+ 0.6429951,114.06596,0.0089529,0.0037521585,-12.0809,0.13629413,-113.9578,114.20601,5.5177517,11.148578,-6.066795,-116.94024,-201.36945,16.666328,7.8392086,-7.598033,177.33257,1270000
76
+ 0.6464833,112.25809,0.009070328,0.012297712,-11.144182,0.2003727,-112.157,112.47076,3.231723,16.43261,3.0978484,-115.973465,-201.32623,19.664333,8.753054,-7.70531,219.8671,1275000
77
+ 0.6506226,114.58414,0.009182967,0.0061694034,-11.828169,0.1750027,-114.475525,114.76531,3.822048,11.152361,-2.1532774,-118.09695,-199.8836,14.974409,5.253914,-3.7122436,181.8985,1280000
78
+ 0.640391,112.95409,0.009046027,-0.012180471,-13.846499,0.1752911,-112.828835,113.117195,3.9170544,10.174132,-5.180314,-116.466385,-200.85608,14.091187,1.4002293,-1.5551641,157.82344,1285000
79
+ 0.6428818,115.33292,0.008761847,-0.016254377,-14.355131,0.1607546,-115.20713,115.47742,3.1520157,9.532843,1.8268281,-118.808655,-196.15352,12.684858,4.303178,-3.7281432,149.70311,1290000
80
+ 0.6545102,114.88161,0.009073204,0.009440424,-11.459527,0.1758267,-114.77763,115.06687,3.217564,10.768365,1.9948866,-117.873245,-205.17899,13.9859295,2.9214945,-3.0960853,128.22278,1295000
81
+ 0.640372,111.52092,0.008958156,-0.004128108,-12.960821,0.15947884,-111.404816,111.67627,2.9603481,15.305817,-4.794442,-115.219315,-196.61714,18.266165,3.2598855,-3.605085,172.10674,1300000
82
+ 0.6537245,114.51038,0.009147227,0.01640186,-10.706903,0.14415249,-114.412445,114.67094,3.7942283,11.266907,-6.461761,-117.326454,-202.75018,15.061135,1.5988618,-1.4535776,141.7763,1305000
83
+ 0.6502832,117.74184,0.009226036,-0.010104087,-13.595171,0.16582777,-117.61641,117.89756,6.373242,9.119621,-3.1261113,-121.17539,-196.2378,15.492863,2.4404974,-2.2938354,198.55696,1310000
84
+ 0.647272,113.45999,0.009016421,-6.068123e-05,-12.50673,0.14499871,-113.34721,113.60493,6.7242227,12.71226,-0.5686109,-116.22347,-196.03593,19.436483,2.3494055,-2.7704031,204.50917,1315000
85
+ 0.6458139,114.17797,0.009027589,0.011275808,-11.250961,0.14049578,-114.07641,114.32974,4.4963546,14.397052,-2.9785705,-117.58416,-198.89218,18.893406,4.8288846,-5.2105284,208.18324,1320000
86
+ 0.64601594,110.90183,0.009054594,-0.0015176161,-12.667607,0.14092796,-110.78713,111.041245,4.6074166,11.118781,2.1445642,-113.69979,-205.34677,15.726198,1.219183,-1.8442292,140.09387,1325000
87
+ 0.6506617,113.2155,0.008986488,0.021422971,-10.116091,0.16338587,-113.12459,113.40031,5.0259624,10.890882,-3.2295315,-115.67024,-199.84262,15.916843,4.2463875,-2.3562052,185.6183,1330000
88
+ 0.649967,116.233475,0.008834956,0.017954338,-10.467807,0.17815104,-116.141,116.42958,4.816658,10.451474,-4.215202,-118.33241,-205.55103,15.268132,2.4100456,-2.7659202,153.1049,1335000
89
+ 0.6466452,107.099396,0.008813689,0.0033907508,-12.115286,0.16813843,-106.992615,107.27092,7.8739176,19.054605,-0.32951507,-110.60833,-200.93468,26.928524,5.333829,-5.635,249.46735,1340000
90
+ 0.65498704,117.57684,0.00895129,0.011861319,-11.174904,0.15469585,-117.47682,117.7434,3.692595,12.595698,-10.456402,-121.457115,-199.54724,16.288294,3.0344439,-3.0227292,180.97241,1345000
91
+ 0.64690304,109.53754,0.009036077,0.007916392,-11.623913,0.16451342,-109.432495,109.70997,3.7063599,9.938777,-1.150664,-112.26192,-194.88191,13.645137,1.0101067,-0.9871163,124.34044,1350000
92
+ 0.6384787,113.004745,0.008856147,0.00039751377,-12.455114,0.18957643,-112.89444,113.19472,6.998569,13.156044,-1.5698242,-116.19375,-190.97313,20.154613,2.070468,-2.6271808,192.5716,1355000
93
+ 0.648685,111.786545,0.008915576,0.0006879418,-12.422838,0.1734461,-111.6758,111.96068,6.390017,17.947966,-0.5389264,-114.93783,-201.47035,24.337982,4.1185493,-4.3518553,206.97682,1360000
94
+ 0.6352581,112.57388,0.008620251,-0.010738254,-13.745701,0.15453134,-112.4554,112.71768,6.8232455,13.671289,3.3701587,-115.37007,-205.83994,20.494535,5.488877,-5.2978363,168.96352,1365000
95
+ 0.64159805,110.45322,0.008756304,0.007611946,-11.63069,0.17662528,-110.35138,110.63746,5.7681456,12.019351,3.3162706,-113.35797,-207.35071,17.787497,3.9804285,-2.6857562,193.08621,1370000
96
+ 0.6408267,113.0753,0.008632488,-0.0017199839,-12.699245,0.147456,-112.96568,113.22104,8.125893,14.11017,0.83949864,-116.79419,-207.1678,22.236063,4.5080733,-4.0304775,258.75665,1375000
97
+ 0.6397829,110.71371,0.008669383,-0.006050022,-13.197861,0.12458696,-110.5993,110.832245,6.530372,15.973853,0.23870188,-113.98866,-197.05211,22.504225,2.548031,-2.7735126,189.4527,1380000
98
+ 0.6432681,114.64104,0.0086661335,0.007909206,-11.587343,0.16378748,-114.54061,114.81274,9.1607275,12.998151,-1.7160121,-117.71901,-204.69936,22.158878,2.8976448,-3.0264082,195.94702,1385000
99
+ 0.6481236,112.09666,0.00864457,0.013332654,-10.9576845,0.14119871,-112.00194,112.25119,4.4792476,11.576927,-3.3647635,-115.136986,-207.22119,16.056175,4.187701,-4.346514,162.3062,1390000
100
+ 0.6461619,102.99063,0.008717327,0.003082734,-12.146367,0.15386128,-102.88475,103.147575,8.580803,11.377608,3.0804865,-106.71206,-203.95619,19.958412,2.9298205,-2.8845365,191.06606,1395000
101
+ 0.6443515,105.557556,0.008843963,0.0077762953,-11.620723,0.14426093,-105.45479,105.709595,7.241668,10.259685,-2.9795413,-108.697914,-204.44325,17.501352,1.4702905,-1.2912726,149.87917,1400000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/action_std,actor/actor_loss,actor/alpha,actor/alpha_loss,actor/entropy,actor/flow_loss,actor/q,actor/total_loss,critic/critic_loss,critic/distill_loss,critic/q_max,critic/q_mean,critic/q_min,critic/total_loss,grad/max,grad/min,grad/norm,step
2
+ 0.64957917,150.7018,0.0073846807,0.0039111534,-11.970369,0.19286889,-150.6134,150.89857,2.8988838,2.7293117,-24.36157,-153.32928,-194.19379,5.628196,1.047349,-0.9244407,47.309067,905000
3
+ 0.6456761,146.72023,0.007527638,-0.006013591,-13.298868,0.1860447,-146.62012,146.90027,2.0560849,6.4984484,-38.057545,-149.32396,-193.15959,8.554533,1.6038167,-1.5486326,87.740295,910000
4
+ 0.6520092,148.07686,0.00794684,-0.0021262867,-12.767564,0.19685897,-147.97539,148.27159,1.7797962,5.2752795,-41.251713,-150.65785,-194.92314,7.0550756,2.080364,-2.3520403,69.529236,915000
5
+ 0.64387167,145.6529,0.008529211,-0.021643056,-15.037521,0.168358,-145.52463,145.79962,2.5103633,7.0822725,-27.991705,-149.55165,-200.07497,9.592636,0.8959335,-0.83271277,83.56131,920000
6
+ 0.6443628,142.5101,0.008717102,-0.006263846,-13.21857,0.17206314,-142.39487,142.67589,2.4537997,8.610302,-50.697258,-145.04218,-200.04243,11.064102,1.585081,-1.5184572,70.81239,925000
7
+ 0.6459397,140.927,0.008480389,-0.01089365,-13.78457,0.1721743,-140.8101,141.08829,5.0872154,8.597699,-28.781542,-143.55763,-199.01134,13.684915,5.329166,-6.2579737,127.08199,930000
8
+ 0.64319944,141.84119,0.008722902,0.0071477694,-11.680574,0.17882949,-141.7393,142.02716,2.4305074,8.576043,-5.825998,-144.38527,-199.16399,11.006551,3.5280507,-3.7928703,103.83689,935000
9
+ 0.64425504,139.97156,0.008998167,-0.011118646,-13.735657,0.20588909,-139.84796,140.16632,3.944184,9.006977,-4.4794173,-143.4563,-201.29684,12.951161,2.8550928,-3.3423312,103.27793,940000
10
+ 0.651386,139.66237,0.009260213,0.004031261,-12.064669,0.1831057,-139.55066,139.8495,4.9109316,14.727971,-21.125553,-142.76247,-201.14795,19.638903,3.603419,-4.289301,190.96838,945000
11
+ 0.640137,139.44994,0.0091775125,-0.007351368,-13.30102,0.19811411,-139.32787,139.6407,2.4270418,9.129531,-21.783718,-142.23987,-197.76979,11.556573,1.7061672,-1.7516997,121.1713,950000
12
+ 0.6426791,135.42749,0.0090790335,-0.012112856,-13.834157,0.18319193,-135.30188,135.59857,3.0403132,8.618979,-7.5362883,-138.68211,-197.6941,11.659292,4.5675173,-4.5499854,115.47159,955000
13
+ 0.63337094,134.20891,0.0088137565,-0.0061689806,-13.199926,0.18186195,-134.09256,134.38461,3.0431783,10.119224,-20.777418,-137.43066,-202.13985,13.162402,1.9085562,-1.8758999,104.70743,960000
14
+ 0.63879627,135.9805,0.009199868,-0.0144455535,-14.070191,0.18823752,-135.85106,136.15428,3.2220788,12.023146,-11.702482,-139.13391,-201.98006,15.245224,6.89031,-6.0955486,173.157,965000
15
+ 0.64542145,131.52853,0.009403878,-0.0044697067,-12.975305,0.20042129,-131.40651,131.72449,3.9030423,9.858134,-23.658514,-134.7054,-199.74449,13.761177,2.946904,-4.643763,129.85062,970000
16
+ 0.64312863,136.11504,0.008753916,0.00024116815,-12.47245,0.17424478,-136.00586,136.28952,2.505853,15.037982,-18.71401,-138.54468,-202.6374,17.543835,5.7495065,-6.6976337,153.8957,975000
17
+ 0.64272076,137.61932,0.00913095,-0.017201167,-14.383831,0.16994685,-137.488,137.77208,6.3238835,7.14319,-19.34667,-140.59367,-201.13179,13.467073,2.7945497,-1.1010592,112.784004,980000
18
+ 0.64258385,135.89029,0.008974441,0.0014139477,-12.342447,0.17905784,-135.77953,136.07077,7.3492646,6.4168534,-19.472555,-138.94437,-201.29773,13.766118,0.8381354,-0.7669327,94.55718,985000
19
+ 0.6377319,133.7491,0.009123879,-0.016173825,-14.272692,0.17797317,-133.61888,133.9109,3.5941148,10.849093,-8.736182,-135.86003,-197.73398,14.443209,2.0998507,-2.3508563,154.47447,990000
20
+ 0.6439477,132.07384,0.009088719,0.009156483,-11.492544,0.18328777,-131.96939,132.26628,2.7893102,7.057447,-11.367028,-134.75536,-199.50076,9.846757,2.9173787,-2.767536,94.71338,995000
21
+ 0.6387096,126.592316,0.009165639,-0.0035197348,-12.884014,0.14976293,-126.47423,126.73856,3.3048794,7.3797607,0.4622795,-129.97008,-201.34544,10.68464,1.9452043,-1.963064,104.111786,1000000
22
+ 0.6436769,134.2829,0.0091967005,-0.011675034,-13.769481,0.16450031,-134.15625,134.43573,2.8075352,10.069704,-8.649959,-138.0284,-199.03107,12.877239,4.1350527,-4.219297,141.41933,1005000
23
+ 0.6393708,130.03455,0.0091768,-0.002677611,-12.79178,0.16946208,-129.91718,130.20134,2.700304,11.619089,-2.6312935,-132.81506,-196.76668,14.319393,3.947906,-2.8153443,111.05148,1010000
24
+ 0.6377929,130.84421,0.009059305,-0.009709714,-13.5717945,0.17291826,-130.72125,131.00742,5.53376,9.205457,0.81906307,-134.29813,-201.0476,14.739217,3.2433343,-3.461611,128.77237,1015000
25
+ 0.6420637,131.90007,0.008873651,0.008800941,-11.508194,0.18463254,-131.79794,132.0935,2.4390116,10.720815,-0.33855677,-134.59346,-199.44987,13.159826,6.713533,-6.1438246,161.31549,1020000
26
+ 0.64346147,133.72647,0.008947633,-0.010410945,-13.663542,0.1933156,-133.60422,133.90938,3.2366753,7.399705,-2.226372,-136.50731,-199.54782,10.63638,0.61006606,-0.62494546,85.51912,1025000
27
+ 0.6424765,133.03915,0.008892577,0.021179235,-10.118324,0.17378034,-132.94917,133.23412,9.13829,11.8575325,-19.403057,-136.16695,-201.06375,20.995823,1.3234621,-1.1780149,132.55493,1030000
28
+ 0.63616884,131.40976,0.0091326,-0.011191515,-13.725447,0.17570892,-131.28442,131.57428,3.0892167,9.821692,2.2162871,-135.04184,-200.60109,12.91091,8.4072,-9.009076,157.28026,1035000
29
+ 0.6456834,128.5752,0.00893235,0.0030047577,-12.1636095,0.13545552,-128.46654,128.71365,4.866656,8.809172,-9.292302,-132.0081,-199.42606,13.675827,2.4195356,-2.5340447,143.21094,1040000
30
+ 0.649946,131.38197,0.00898779,0.013289325,-11.021402,0.16331893,-131.28293,131.55858,3.522606,10.586989,-0.13379161,-134.07799,-195.6524,14.109595,10.981932,-10.058239,192.63577,1045000
31
+ 0.6497138,130.95598,0.009077237,-0.0025921273,-12.785563,0.16707881,-130.83992,131.12047,2.298644,6.743676,-2.2776089,-133.31009,-201.40294,9.04232,4.3536277,-4.420209,95.833664,1050000
32
+ 0.6500931,127.65683,0.00892281,0.012164069,-11.1367445,0.15112674,-127.55745,127.820114,4.190343,6.204857,0.5221518,-130.76485,-199.17609,10.3952,3.4765105,-3.0589705,116.80771,1055000
33
+ 0.65160066,130.99985,0.008917842,0.012881525,-11.055533,0.15922871,-130.90125,131.17195,12.939476,12.26237,-13.140795,-133.69339,-200.79,25.201847,2.8314824,-3.8499968,244.66103,1060000
34
+ 0.6359484,128.98956,0.009028738,-0.0145676,-14.11347,0.16453524,-128.86215,129.13953,4.87865,14.795638,2.5521874,-132.40852,-203.4183,19.674288,5.8538103,-5.565062,256.3157,1065000
35
+ 0.6515784,130.36551,0.008731155,0.02313939,-9.849791,0.17769064,-130.27951,130.56633,3.3478875,9.471329,-9.028017,-132.6255,-198.89438,12.819216,3.5064223,-3.4204888,141.74692,1070000
36
+ 0.64691556,130.03397,0.008780982,0.0016377418,-12.31349,0.18758744,-129.92584,130.22319,5.288713,9.4604025,-11.717187,-133.13121,-203.91858,14.749115,4.100061,-4.317022,195.82889,1075000
37
+ 0.6457896,130.3736,0.008852359,0.011014593,-11.255745,0.17845565,-130.27396,130.56306,2.77008,7.000812,2.0842426,-133.13795,-198.87317,9.770892,0.8889781,-0.74215394,98.143036,1080000
38
+ 0.6339341,128.22278,0.008650115,-0.01828524,-14.613873,0.17000079,-128.09637,128.3745,3.5603375,11.023192,-5.8603177,-131.21172,-202.11484,14.58353,1.30775,-2.7172318,125.77668,1085000
39
+ 0.647675,125.85515,0.008878649,0.011465507,-11.208643,0.14293507,-125.75563,126.00955,3.3309925,11.135959,-2.8454509,-128.616,-198.17473,14.466951,7.339171,-6.916791,189.49203,1090000
40
+ 0.6493406,129.42351,0.009009339,0.0013038666,-12.355276,0.1555685,-129.3122,129.58037,3.755037,10.88584,-19.854837,-131.30974,-197.77388,14.640878,1.9921821,-2.052544,152.27625,1095000
41
+ 0.63755375,128.66808,0.008506677,-0.0007993831,-12.593971,0.17472565,-128.56094,128.84201,3.4266717,12.130094,-0.44392058,-132.04085,-200.69014,15.556766,2.3721266,-1.8825034,128.59317,1100000
42
+ 0.63899446,127.76016,0.008756092,-0.0091879275,-13.549318,0.16961738,-127.641525,127.92059,4.3020515,17.525602,-5.6626096,-131.63622,-193.64856,21.827654,3.11929,-2.8960898,191.44836,1105000
43
+ 0.64544064,128.37085,0.008932823,0.004999105,-11.940367,0.15289347,-128.26419,128.52875,3.8954942,12.806514,-9.769363,-130.42703,-198.04675,16.702007,2.22449,-2.9884005,162.07695,1110000
44
+ 0.6449891,127.93926,0.008896402,0.0023930224,-12.231012,0.1484756,-127.830444,128.09013,2.9962633,18.028687,-20.225975,-130.46208,-201.43259,21.02495,5.1160927,-4.915655,141.19496,1115000
45
+ 0.64609635,126.86199,0.008631525,0.004096158,-12.025442,0.16308823,-126.758194,127.029175,9.132823,10.285053,7.045063,-129.9447,-197.57266,19.417877,2.9880848,-3.1068506,185.71336,1120000
46
+ 0.6343651,121.12844,0.009125771,0.009436834,-11.465914,0.19506696,-121.0238,121.33295,5.845591,14.448578,-7.80011,-124.19207,-194.0828,20.294168,5.411035,-6.017036,242.2438,1125000
47
+ 0.654203,127.2576,0.008833254,-0.0032425842,-12.867088,0.16916002,-127.143936,127.423515,4.277429,9.396747,-7.659291,-130.56648,-204.38275,13.674175,2.6498673,-2.085854,142.41449,1130000
48
+ 0.64578855,122.86132,0.0088823335,-0.0010673444,-12.620165,0.17389992,-122.74922,123.03415,4.2373934,9.545319,-1.4189657,-125.454445,-198.89404,13.782712,1.7773987,-1.1592953,132.07327,1135000
49
+ 0.6475571,125.07985,0.008669866,0.007158252,-11.674353,0.18457934,-124.97864,125.27158,4.2216783,12.946988,1.3269162,-128.13786,-201.08665,17.168667,4.8754377,-3.1758275,195.37497,1140000
50
+ 0.63792074,127.56608,0.009016679,-0.015297731,-14.196604,0.18146299,-127.43807,127.73225,4.1343994,12.408103,-21.158867,-130.97786,-198.54149,16.542503,2.0860784,-2.6888406,161.99232,1145000
51
+ 0.6446864,114.52579,0.008923946,0.012541265,-11.09465,0.14923482,-114.42679,114.68757,4.769302,12.170048,3.2399166,-118.11123,-198.36256,16.93935,2.9589655,-1.846559,185.09534,1150000
52
+ 0.64931226,128.00821,0.009017294,-0.0035438794,-12.893009,0.17765823,-127.89195,128.18233,3.5392807,13.077095,-1.6627975,-131.69408,-200.6327,16.616375,2.9401307,-3.2189884,180.17137,1155000
53
+ 0.6424177,121.901825,0.008877244,-0.0043060696,-12.985068,0.17485727,-121.78655,122.07238,3.418186,10.220291,5.2921014,-125.25063,-201.38846,13.638477,3.8715618,-4.410189,174.45148,1160000
54
+ 0.6467699,123.73031,0.008895677,0.007936269,-11.607851,0.20339999,-123.627045,123.94164,4.082362,12.494229,-4.634413,-126.64101,-202.39903,16.576591,3.221018,-3.6587377,148.94016,1165000
55
+ 0.64175075,120.776566,0.008827237,0.0020765108,-12.264761,0.1310863,-120.668304,120.90973,2.7456422,10.14818,-3.7022433,-123.20943,-200.92612,12.893822,3.489044,-3.6771224,129.35892,1170000
56
+ 0.6507392,121.002075,0.008806826,0.0030400117,-12.154812,0.15441287,-120.89503,121.15952,4.5945735,12.917308,-3.594806,-123.99558,-202.01927,17.51188,2.7325652,-2.8522336,178.54633,1175000
57
+ 0.64157426,123.74624,0.0090952525,0.0031649705,-12.1520195,0.18088892,-123.63572,123.93029,3.5845287,15.911284,-1.0972234,-127.21233,-196.79858,19.495813,2.4038227,-2.4450376,130.83844,1180000
58
+ 0.6433243,117.85934,0.009225725,-0.006214336,-13.173588,0.15454985,-117.7378,118.00767,3.72204,14.02251,4.278977,-120.58494,-200.39676,17.744549,4.3758287,-4.0406146,189.33716,1185000
59
+ 0.64433557,117.17344,0.009059474,-0.010244896,-13.630849,0.15144281,-117.04996,117.31464,7.997051,10.428072,2.875818,-120.55444,-195.33492,18.425123,2.7469976,-2.7671497,179.7463,1190000
60
+ 0.64503264,114.90239,0.009110566,0.017624492,-10.565489,0.15590344,-114.80612,115.07592,4.054363,10.327818,1.8193916,-117.51184,-197.8135,14.382181,2.0243473,-1.5850133,137.0502,1195000
61
+ 0.64813995,122.64922,0.008994774,0.008774815,-11.524454,0.13906372,-122.54556,122.79706,4.616203,9.014315,-4.9589043,-125.33494,-200.17583,13.630518,1.4396579,-2.0060263,125.15717,1200000
62
+ 0.6482269,122.82191,0.008811879,-0.0018795296,-12.713295,0.14165066,-122.709885,122.96168,4.57251,9.807303,-0.32428655,-126.22882,-198.13484,14.379813,6.5346,-7.0436378,165.18135,1205000
63
+ 0.64885443,119.04972,0.008879627,-0.005523769,-13.122072,0.15794732,-118.933205,119.20214,4.077433,10.730473,11.272026,-122.46378,-201.40628,14.807905,1.6039982,-1.5456866,132.4802,1210000
64
+ 0.64679086,118.25969,0.00927239,0.002384684,-12.242819,0.1725135,-118.14617,118.43459,3.5752003,16.373291,-5.152007,-121.83054,-197.13692,19.948492,3.9841888,-4.6052136,181.06442,1215000
65
+ 0.63963574,115.85088,0.009266445,0.0025325387,-12.226698,0.19816566,-115.73758,116.05158,2.623193,15.49966,3.3659444,-118.97924,-191.18114,18.122852,4.3173656,-4.5448523,163.09218,1220000
66
+ 0.6408415,119.53094,0.008920147,-0.0036461405,-12.908753,0.16490355,-119.415794,119.69219,4.4396887,12.567731,0.071359076,-122.40454,-202.06708,17.00742,2.4281492,-1.6997082,161.32214,1225000
67
+ 0.64951825,117.53186,0.008930664,0.0077735516,-11.629566,0.18072787,-117.42801,117.72036,3.8052118,12.603823,-4.5255795,-120.033035,-198.92616,16.409035,4.048297,-4.1396346,153.7415,1230000
68
+ 0.6443987,116.69121,0.009285788,0.0014932253,-12.339192,0.19225386,-116.57663,116.88496,11.37549,10.427495,-4.158517,-119.6074,-200.36372,21.802986,1.6340364,-1.8847488,170.70439,1235000
69
+ 0.647457,120.67511,0.008920028,0.011330311,-11.22979,0.18333381,-120.574936,120.869774,3.8335664,11.93994,0.49240735,-123.73693,-196.69443,15.773507,1.3824825,-2.6235902,131.4314,1240000
70
+ 0.6403355,124.81528,0.009370808,-0.017486205,-14.36603,0.16729832,-124.680664,124.96509,6.0552797,14.319133,-2.448477,-128.26085,-202.24838,20.374413,3.325889,-4.124484,211.43396,1245000
71
+ 0.6520071,110.385956,0.009097379,0.022334697,-10.04493,0.1552166,-110.29457,110.56351,9.601237,9.694278,1.2187202,-112.474,-202.27718,19.295515,1.436751,-1.5673035,129.54807,1250000
72
+ 0.6477352,118.98874,0.009047766,0.015052356,-10.836346,0.17546567,-118.89069,119.17926,4.308233,11.233907,-3.2541728,-121.830765,-202.47957,15.542139,2.562027,-2.3481553,156.86609,1255000
73
+ 0.64065725,112.17088,0.008857012,0.0017468461,-12.3027725,0.15449029,-112.06192,112.32712,5.6124887,12.180911,1.1758058,-114.81287,-199.2972,17.7934,4.4628534,-3.886786,239.3055,1260000
74
+ 0.64927626,117.14756,0.009172237,-0.004553193,-12.99641,0.15574382,-117.02836,117.29875,4.6105037,9.692355,1.6862127,-119.35561,-199.91214,14.302858,1.7083036,-1.1564096,100.72284,1265000
75
+ 0.6429951,114.06596,0.0089529,0.0037521585,-12.0809,0.13629413,-113.9578,114.20601,5.5177517,11.148578,-6.066795,-116.94024,-201.36945,16.666328,7.8392086,-7.598033,177.33257,1270000
76
+ 0.6464833,112.25809,0.009070328,0.012297712,-11.144182,0.2003727,-112.157,112.47076,3.231723,16.43261,3.0978484,-115.973465,-201.32623,19.664333,8.753054,-7.70531,219.8671,1275000
77
+ 0.6506226,114.58414,0.009182967,0.0061694034,-11.828169,0.1750027,-114.475525,114.76531,3.822048,11.152361,-2.1532774,-118.09695,-199.8836,14.974409,5.253914,-3.7122436,181.8985,1280000
78
+ 0.640391,112.95409,0.009046027,-0.012180471,-13.846499,0.1752911,-112.828835,113.117195,3.9170544,10.174132,-5.180314,-116.466385,-200.85608,14.091187,1.4002293,-1.5551641,157.82344,1285000
79
+ 0.6428818,115.33292,0.008761847,-0.016254377,-14.355131,0.1607546,-115.20713,115.47742,3.1520157,9.532843,1.8268281,-118.808655,-196.15352,12.684858,4.303178,-3.7281432,149.70311,1290000
80
+ 0.6545102,114.88161,0.009073204,0.009440424,-11.459527,0.1758267,-114.77763,115.06687,3.217564,10.768365,1.9948866,-117.873245,-205.17899,13.9859295,2.9214945,-3.0960853,128.22278,1295000
81
+ 0.640372,111.52092,0.008958156,-0.004128108,-12.960821,0.15947884,-111.404816,111.67627,2.9603481,15.305817,-4.794442,-115.219315,-196.61714,18.266165,3.2598855,-3.605085,172.10674,1300000
82
+ 0.6537245,114.51038,0.009147227,0.01640186,-10.706903,0.14415249,-114.412445,114.67094,3.7942283,11.266907,-6.461761,-117.326454,-202.75018,15.061135,1.5988618,-1.4535776,141.7763,1305000
83
+ 0.6502832,117.74184,0.009226036,-0.010104087,-13.595171,0.16582777,-117.61641,117.89756,6.373242,9.119621,-3.1261113,-121.17539,-196.2378,15.492863,2.4404974,-2.2938354,198.55696,1310000
84
+ 0.647272,113.45999,0.009016421,-6.068123e-05,-12.50673,0.14499871,-113.34721,113.60493,6.7242227,12.71226,-0.5686109,-116.22347,-196.03593,19.436483,2.3494055,-2.7704031,204.50917,1315000
85
+ 0.6458139,114.17797,0.009027589,0.011275808,-11.250961,0.14049578,-114.07641,114.32974,4.4963546,14.397052,-2.9785705,-117.58416,-198.89218,18.893406,4.8288846,-5.2105284,208.18324,1320000
86
+ 0.64601594,110.90183,0.009054594,-0.0015176161,-12.667607,0.14092796,-110.78713,111.041245,4.6074166,11.118781,2.1445642,-113.69979,-205.34677,15.726198,1.219183,-1.8442292,140.09387,1325000
87
+ 0.6506617,113.2155,0.008986488,0.021422971,-10.116091,0.16338587,-113.12459,113.40031,5.0259624,10.890882,-3.2295315,-115.67024,-199.84262,15.916843,4.2463875,-2.3562052,185.6183,1330000
88
+ 0.649967,116.233475,0.008834956,0.017954338,-10.467807,0.17815104,-116.141,116.42958,4.816658,10.451474,-4.215202,-118.33241,-205.55103,15.268132,2.4100456,-2.7659202,153.1049,1335000
89
+ 0.6466452,107.099396,0.008813689,0.0033907508,-12.115286,0.16813843,-106.992615,107.27092,7.8739176,19.054605,-0.32951507,-110.60833,-200.93468,26.928524,5.333829,-5.635,249.46735,1340000
90
+ 0.65498704,117.57684,0.00895129,0.011861319,-11.174904,0.15469585,-117.47682,117.7434,3.692595,12.595698,-10.456402,-121.457115,-199.54724,16.288294,3.0344439,-3.0227292,180.97241,1345000
91
+ 0.64690304,109.53754,0.009036077,0.007916392,-11.623913,0.16451342,-109.432495,109.70997,3.7063599,9.938777,-1.150664,-112.26192,-194.88191,13.645137,1.0101067,-0.9871163,124.34044,1350000
92
+ 0.6384787,113.004745,0.008856147,0.00039751377,-12.455114,0.18957643,-112.89444,113.19472,6.998569,13.156044,-1.5698242,-116.19375,-190.97313,20.154613,2.070468,-2.6271808,192.5716,1355000
93
+ 0.648685,111.786545,0.008915576,0.0006879418,-12.422838,0.1734461,-111.6758,111.96068,6.390017,17.947966,-0.5389264,-114.93783,-201.47035,24.337982,4.1185493,-4.3518553,206.97682,1360000
94
+ 0.6352581,112.57388,0.008620251,-0.010738254,-13.745701,0.15453134,-112.4554,112.71768,6.8232455,13.671289,3.3701587,-115.37007,-205.83994,20.494535,5.488877,-5.2978363,168.96352,1365000
95
+ 0.64159805,110.45322,0.008756304,0.007611946,-11.63069,0.17662528,-110.35138,110.63746,5.7681456,12.019351,3.3162706,-113.35797,-207.35071,17.787497,3.9804285,-2.6857562,193.08621,1370000
96
+ 0.6408267,113.0753,0.008632488,-0.0017199839,-12.699245,0.147456,-112.96568,113.22104,8.125893,14.11017,0.83949864,-116.79419,-207.1678,22.236063,4.5080733,-4.0304775,258.75665,1375000
97
+ 0.6397829,110.71371,0.008669383,-0.006050022,-13.197861,0.12458696,-110.5993,110.832245,6.530372,15.973853,0.23870188,-113.98866,-197.05211,22.504225,2.548031,-2.7735126,189.4527,1380000
98
+ 0.6432681,114.64104,0.0086661335,0.007909206,-11.587343,0.16378748,-114.54061,114.81274,9.1607275,12.998151,-1.7160121,-117.71901,-204.69936,22.158878,2.8976448,-3.0264082,195.94702,1385000
99
+ 0.6481236,112.09666,0.00864457,0.013332654,-10.9576845,0.14119871,-112.00194,112.25119,4.4792476,11.576927,-3.3647635,-115.136986,-207.22119,16.056175,4.187701,-4.346514,162.3062,1390000
100
+ 0.6461619,102.99063,0.008717327,0.003082734,-12.146367,0.15386128,-102.88475,103.147575,8.580803,11.377608,3.0804865,-106.71206,-203.95619,19.958412,2.9298205,-2.8845365,191.06606,1395000
101
+ 0.6443515,105.557556,0.008843963,0.0077762953,-11.620723,0.14426093,-105.45479,105.709595,7.241668,10.259685,-2.9795413,-108.697914,-204.44325,17.501352,1.4702905,-1.2912726,149.87917,1400000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ca092b2764afe384a3dceffb8eee79e8912c32a9c333f28afc4d55eafd16e5
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1051728dcfd8a97817dbb5a5f86c9d1fdb75c3dcd519017219a9eecde5747898
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0d3249f5363ed70143c997bf984e2288e96496247ae54269bc7bf7c82f94a6
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a2e8c0d5f41cb989218362be45faada7f145a843150039bfb8411ff4be465bb
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e752056b1a34cbbc3463864c3cb756cbb6ab8ba9d981ea2c60b0cc76180eba2e
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90041272ac01c7d55307e83f1e7105c0ad1be7b19c89874aa3e68324ec78971
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abff2bd9543e949e77e76b4c039e3f6265855c3163663c3a632f2430f673cf09
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0474652d379bf509edf91d77739c49d21e08fce73079fd894b4329b714bd3296
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_1400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91617fbe62e7be31690ced9a5db6353174b59d0a64825a03b79b149f8f763038
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d71305b55a93734a47343a130e5d8130b89b77ea6ec58b7a75251386acc8738
3
+ size 326957888
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/dsrl/20260319_171246/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/bkgh6i7n