Tiredsheep commited on
Commit
c99760f
·
verified ·
1 Parent(s): 720cca2

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_132025/env.csv +0 -0
  2. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/env_sv.csv +0 -0
  3. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/eval.csv +11 -0
  4. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/eval_sv.csv +11 -0
  5. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/online_agent.csv +101 -0
  6. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/online_agent_sv.csv +101 -0
  7. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_1000000.pkl +3 -0
  8. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_550000.pkl +3 -0
  9. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_600000.pkl +3 -0
  10. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_650000.pkl +3 -0
  11. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_700000.pkl +3 -0
  12. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_750000.pkl +3 -0
  13. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_800000.pkl +3 -0
  14. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_850000.pkl +3 -0
  15. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_900000.pkl +3 -0
  16. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_950000.pkl +3 -0
  17. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/progress.tk +1 -0
  18. O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/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_132025/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_132025/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,-0.09498251168780765,-0.013197870179437169,-0.0945643339628625,-0.00609527653425641,26.588728771522668,19.603999999998358,0.52,9737.62,-0.58,-549.5,390.08,1.1435554504394532,550000
3
+ 0.0,0.0,-0.019826137455678693,-0.002810450544527137,-0.019809051780409915,-0.0017838244377587152,33.2212070139612,10.340999999999372,0.88,25835.22,-0.18,-302.4,204.82,0.6484672927856445,600000
4
+ 0.0,0.0,-0.0259945074617933,-0.00940222806410379,-0.026028116077478722,-0.007664788237821865,34.59759496027192,8.717999999999444,0.94,35439.06,-0.08,-261.12,172.36,0.5558805274963379,650000
5
+ 0.0,0.0,-0.01191526818400421,-0.0023680869235649495,-0.011552095152660173,-0.0024082902096243214,35.08093480859642,7.5739999999995,0.96,43805.68,-0.06,-201.14,149.48,0.48268651008605956,700000
6
+ 0.0,0.0,-0.018465557677737377,-0.00197346516686753,-0.018242402189354943,-0.002410030489796426,35.78190532911201,6.762999999999621,1.0,51093.54,0.0,-187.62,133.26,0.43434730052948,750000
7
+ 0.0,0.0,-0.011080140917169285,0.005232061979744675,-0.010170162933486812,0.0035193533089336853,35.890048170248754,5.984999999999577,1.0,57647.74,0.0,-161.9,117.7,0.38916958808898927,800000
8
+ 0.0,0.0,-0.013959008388810616,0.00017343851055458606,-0.012970906234943526,-0.0024050242369721385,35.82168312380342,6.542999999999548,0.98,63938.78,-0.02,-184.14,128.86,0.4197626256942749,850000
9
+ 0.0,0.0,-0.03455892293373485,0.011379755551324176,-0.033157210607302666,0.0070523042836518465,35.84337818325878,5.445999999999623,1.0,70178.1,0.0,-147.7,106.92,0.35422301292419434,900000
10
+ 0.0,0.0,-0.013115179118446346,0.024918138578309535,-0.01100833343712233,0.04868535042021669,35.90617896323714,5.519999999999633,1.0,75767.46,0.0,-150.98,108.4,0.35133440494537355,950000
11
+ 0.0,0.0,-0.024247860510539097,0.019189046702536634,-0.02186849635628987,0.01721655699064539,35.12364501944059,5.651999999999656,0.98,81536.52,-0.02,-155.34,111.04,0.36151604652404784,1000000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/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,-0.09498251168780765,-0.013197870179437169,-0.0945643339628625,-0.00609527653425641,26.588728771522668,19.603999999998358,0.52,9737.62,-0.58,-549.5,390.08,1.1435554504394532,550000
3
+ 0.0,0.0,-0.019826137455678693,-0.002810450544527137,-0.019809051780409915,-0.0017838244377587152,33.2212070139612,10.340999999999372,0.88,25835.22,-0.18,-302.4,204.82,0.6484672927856445,600000
4
+ 0.0,0.0,-0.0259945074617933,-0.00940222806410379,-0.026028116077478722,-0.007664788237821865,34.59759496027192,8.717999999999444,0.94,35439.06,-0.08,-261.12,172.36,0.5558805274963379,650000
5
+ 0.0,0.0,-0.01191526818400421,-0.0023680869235649495,-0.011552095152660173,-0.0024082902096243214,35.08093480859642,7.5739999999995,0.96,43805.68,-0.06,-201.14,149.48,0.48268651008605956,700000
6
+ 0.0,0.0,-0.018465557677737377,-0.00197346516686753,-0.018242402189354943,-0.002410030489796426,35.78190532911201,6.762999999999621,1.0,51093.54,0.0,-187.62,133.26,0.43434730052948,750000
7
+ 0.0,0.0,-0.011080140917169285,0.005232061979744675,-0.010170162933486812,0.0035193533089336853,35.890048170248754,5.984999999999577,1.0,57647.74,0.0,-161.9,117.7,0.38916958808898927,800000
8
+ 0.0,0.0,-0.013959008388810616,0.00017343851055458606,-0.012970906234943526,-0.0024050242369721385,35.82168312380342,6.542999999999548,0.98,63938.78,-0.02,-184.14,128.86,0.4197626256942749,850000
9
+ 0.0,0.0,-0.03455892293373485,0.011379755551324176,-0.033157210607302666,0.0070523042836518465,35.84337818325878,5.445999999999623,1.0,70178.1,0.0,-147.7,106.92,0.35422301292419434,900000
10
+ 0.0,0.0,-0.013115179118446346,0.024918138578309535,-0.01100833343712233,0.04868535042021669,35.90617896323714,5.519999999999633,1.0,75767.46,0.0,-150.98,108.4,0.35133440494537355,950000
11
+ 0.0,0.0,-0.024247860510539097,0.019189046702536634,-0.02186849635628987,0.01721655699064539,35.12364501944059,5.651999999999656,0.98,81536.52,-0.02,-155.34,111.04,0.36151604652404784,1000000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/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
+ 166.5218,0.20748326,0.0068096803,6.619413,-60.070095,-166.68425,-204.48402,2.422592,-1.9576313,66.14717,505000
3
+ 164.31563,0.2250216,0.00700772,5.732899,-58.79256,-164.0827,-204.16925,1.7108012,-1.7522299,65.62773,510000
4
+ 165.29913,0.17137557,0.006376105,5.0586133,-52.771385,-165.32349,-203.41557,1.3747152,-1.3988771,65.6624,515000
5
+ 163.5229,0.1782758,0.007847391,7.557927,-31.002913,-163.9033,-206.54733,1.4952543,-1.3982507,68.358154,520000
6
+ 162.25117,0.17560524,0.006589155,6.0897636,-49.468014,-162.21002,-205.89598,1.0299759,-0.9675002,65.00014,525000
7
+ 162.36725,0.18355837,0.0059517385,4.8316536,-43.040222,-162.54027,-205.41733,0.8304766,-0.726861,55.03625,530000
8
+ 160.81677,0.20616008,0.005799729,4.890676,-57.6717,-161.01201,-203.68654,0.8950794,-0.8815994,44.642567,535000
9
+ 160.32861,0.17140076,0.008046914,6.720807,-49.072166,-160.88983,-205.19868,1.2066498,-1.2159265,63.782364,540000
10
+ 159.32564,0.19638297,0.007980976,4.652099,-63.072514,-159.30862,-204.59422,1.1939626,-1.2823656,59.363976,545000
11
+ 157.9882,0.16185543,0.008038209,5.442474,-26.559725,-158.32161,-204.50128,1.2616746,-1.168115,63.956963,550000
12
+ 152.93129,0.19482744,0.006991844,22.855251,-34.22967,-153.43106,-204.79384,1.3126396,-1.0643812,80.648224,555000
13
+ 150.69153,0.19156432,0.007946965,4.980285,-24.621868,-150.63383,-205.14622,2.4637897,-2.2888057,71.18353,560000
14
+ 152.6548,0.18948328,0.008026904,7.6956897,-30.475845,-152.5458,-205.15317,1.2719519,-1.2882636,78.669266,565000
15
+ 145.56583,0.17985855,0.007039245,7.8166823,-4.4266396,-146.17786,-205.60149,0.8503579,-1.1023912,73.64653,570000
16
+ 151.23058,0.20146024,0.009048472,5.783426,-40.58798,-151.84868,-205.50847,0.75749004,-0.70625013,62.894745,575000
17
+ 148.91629,0.17508309,0.0072668334,8.75602,-39.105846,-149.5543,-204.5968,1.0388274,-0.66895527,82.49553,580000
18
+ 147.16928,0.18105409,0.0069179214,6.9917145,0.6399143,-147.5811,-205.30368,1.5559683,-1.3546076,82.06183,585000
19
+ 145.74146,0.18065926,0.00731172,6.498562,-19.464043,-146.635,-206.47049,0.92860645,-0.9091873,80.98361,590000
20
+ 146.50188,0.16424981,0.008498847,8.853452,-26.55375,-146.9047,-205.19922,1.16657,-1.245795,60.325058,595000
21
+ 141.97646,0.1930753,0.0073928456,6.850709,-7.706395,-141.9793,-206.30367,1.4246017,-1.4894483,71.21469,600000
22
+ 145.37425,0.17739101,0.008345818,7.4535675,-35.759136,-145.9191,-204.98221,0.762427,-0.8037588,67.657104,605000
23
+ 143.38039,0.18841803,0.010037588,7.2064257,-7.883418,-142.93016,-206.01787,0.939676,-0.8968118,65.258095,610000
24
+ 138.98082,0.1561451,0.008567081,7.0705614,1.1745083,-140.03444,-205.85764,0.9824714,-1.1186332,77.62551,615000
25
+ 141.77406,0.17271763,0.0068140007,6.7961884,-1.8220332,-142.01794,-204.44736,1.3465353,-1.208942,81.953995,620000
26
+ 145.83495,0.16894947,0.007689125,6.392918,-23.07305,-145.60344,-205.64519,1.172403,-1.2191647,75.51995,625000
27
+ 140.0327,0.15687317,0.0078466395,5.1469607,0.30089337,-140.39783,-204.95923,1.0613123,-0.8971726,54.810516,630000
28
+ 139.57925,0.16413951,0.010316837,6.7176347,1.3929656,-140.71858,-205.22623,0.7228814,-0.74831146,61.306667,635000
29
+ 134.68864,0.1786459,0.00756677,9.050211,-1.5190578,-135.71252,-206.20598,0.96756464,-0.754621,71.28222,640000
30
+ 140.1516,0.1621275,0.008206757,7.379022,-11.07916,-141.19543,-205.59421,1.561644,-1.7521359,71.09219,645000
31
+ 137.84222,0.18932366,0.008376863,6.395865,2.8816447,-138.047,-205.9331,1.2307532,-1.3591601,71.87274,650000
32
+ 134.36858,0.21050474,0.008240202,6.351809,-2.4506776,-134.93033,-205.8044,1.7299888,-1.836239,70.29523,655000
33
+ 138.5572,0.18791889,0.007236007,7.092398,-18.314444,-139.07951,-205.53204,0.7006877,-1.0189695,60.082214,660000
34
+ 135.70801,0.18384363,0.0080038905,6.237934,-1.9456025,-136.69997,-206.10312,1.8338084,-1.6880748,66.80395,665000
35
+ 135.4642,0.1752526,0.0067462325,5.245669,-4.2588882,-135.88696,-207.52367,0.6699073,-0.7414518,58.707405,670000
36
+ 138.1036,0.19750008,0.008036039,6.613917,-5.173925,-137.87239,-208.96786,1.5908755,-2.5873287,75.63443,675000
37
+ 136.43507,0.17533946,0.008133958,7.6594515,2.289565,-137.08098,-206.21744,0.8040997,-0.81005317,70.88228,680000
38
+ 131.42802,0.1722506,0.007881626,6.5052066,-1.827974,-132.05092,-206.00293,0.6473991,-0.7845952,57.720207,685000
39
+ 132.88928,0.16545074,0.00955064,8.576665,-3.745032,-133.34868,-206.7009,0.7078985,-1.4510707,75.34433,690000
40
+ 134.15869,0.20014729,0.0075719603,5.279677,-7.4672136,-134.29263,-206.29095,1.892294,-1.697996,62.53632,695000
41
+ 131.75374,0.19199282,0.007885276,9.394301,-2.1798503,-132.62907,-205.37497,1.4919528,-3.1277113,100.75363,700000
42
+ 131.36867,0.17609769,0.006572296,5.4809847,2.035563,-131.90446,-204.95128,0.86584324,-0.85989827,64.47684,705000
43
+ 132.05164,0.16841641,0.008896918,6.6889153,-3.3114412,-132.47913,-205.11143,1.1456574,-1.7695111,72.1646,710000
44
+ 133.58696,0.1782682,0.008681855,5.000232,-6.0609503,-134.40865,-207.29204,2.3413424,-1.756267,79.23225,715000
45
+ 130.26068,0.17297438,0.007500497,6.203588,-10.338069,-130.46304,-205.99069,1.5919691,-1.8033642,65.79251,720000
46
+ 127.86684,0.15953943,0.0066857827,4.218212,-3.044785,-128.00386,-203.62187,1.0645288,-0.9230371,58.85525,725000
47
+ 131.42366,0.19301072,0.007776755,4.3784637,-0.5162743,-131.51219,-204.63426,1.7343754,-1.2761334,62.447998,730000
48
+ 129.34,0.19049877,0.0059848027,8.806047,-6.660486,-129.51222,-205.64581,1.6748475,-1.7897872,71.41674,735000
49
+ 125.273285,0.1457266,0.006478453,6.283852,1.6836936,-126.0333,-205.8054,0.68714094,-1.1180186,53.048462,740000
50
+ 128.65175,0.15678273,0.007809092,6.012171,0.48736215,-129.38257,-205.40898,0.74195945,-0.7285278,58.076073,745000
51
+ 120.6052,0.152136,0.006587132,6.3089895,-1.7709466,-121.05226,-204.74132,0.90740716,-0.97659296,62.595413,750000
52
+ 129.90562,0.16844666,0.0076739173,6.811792,-0.8375003,-130.8292,-204.11601,1.1574748,-1.1344916,81.66695,755000
53
+ 128.7339,0.19275725,0.00946365,8.717203,1.3040975,-129.27495,-204.45059,2.0662344,-1.9322214,88.722046,760000
54
+ 130.38031,0.17798938,0.008315503,4.7833953,-5.8009396,-130.36441,-205.5788,0.91399276,-1.0227433,59.15385,765000
55
+ 127.606316,0.17794245,0.0073523843,7.6489983,-0.264432,-127.913086,-205.63214,1.4343784,-1.2009773,95.50861,770000
56
+ 125.49583,0.1743324,0.0063023716,6.518682,-1.2783539,-126.05016,-205.46864,1.0191936,-0.957045,59.337276,775000
57
+ 129.15167,0.18540642,0.008371419,14.581675,-1.5505717,-130.14415,-205.38196,2.4627612,-2.1010523,165.85419,780000
58
+ 127.561844,0.18297982,0.00749687,6.212988,-8.488341,-128.18457,-206.6536,2.941416,-2.916381,89.98254,785000
59
+ 118.50928,0.17005599,0.0070027797,5.3881335,2.6239028,-119.01119,-204.53226,1.0554775,-1.660014,56.44802,790000
60
+ 121.64215,0.16012597,0.00651214,9.065615,3.3598802,-122.32788,-206.21072,0.8646723,-0.9278997,88.48897,795000
61
+ 126.858734,0.16309792,0.0065758447,11.003285,-7.487739,-127.41864,-205.33484,1.2968928,-1.36476,97.22938,800000
62
+ 125.96331,0.16668373,0.0069152745,5.8065095,-5.183187,-127.20003,-204.45486,1.444077,-1.7261181,68.55229,805000
63
+ 122.13812,0.17873943,0.0066028005,5.6726584,-1.090616,-122.76233,-204.12654,1.718991,-1.6122967,55.254433,810000
64
+ 122.66204,0.18367346,0.007020498,4.132024,-6.9758615,-122.97725,-203.5027,0.5045378,-0.6315088,45.222103,815000
65
+ 120.719,0.166908,0.008111222,6.1106906,-5.5405393,-121.66192,-204.32925,0.49973053,-0.6925161,50.918533,820000
66
+ 128.75484,0.16075233,0.006556637,5.6456985,-2.6131516,-129.15237,-206.37206,1.101054,-1.127568,61.518635,825000
67
+ 120.14458,0.1844497,0.006575374,6.2410493,-3.0688229,-120.592735,-205.21234,0.57648087,-0.58076835,65.50957,830000
68
+ 121.70195,0.17782468,0.007374693,4.9904995,0.05546537,-122.27775,-205.13652,1.9676663,-1.1865261,51.787323,835000
69
+ 125.31092,0.1878092,0.007619705,6.4286447,-1.0957571,-125.13766,-206.56995,2.1471083,-2.431331,73.6617,840000
70
+ 127.74588,0.16085848,0.008637991,5.578689,4.8539104,-128.01501,-205.0502,1.7152689,-1.6218858,64.86983,845000
71
+ 118.960075,0.16248497,0.0065502953,6.4874315,-0.06215509,-119.56593,-204.714,2.219815,-2.2722511,84.34273,850000
72
+ 123.557846,0.15150529,0.007849493,6.5396132,-0.36886722,-123.374535,-203.84967,1.0845523,-1.1087285,79.35518,855000
73
+ 117.039734,0.16404904,0.0068482407,6.007574,3.502732,-118.02351,-204.32057,0.8559219,-0.9870076,64.16542,860000
74
+ 124.57399,0.16699484,0.0087474,4.731914,-3.245717,-125.04348,-207.16895,1.6128016,-1.5123146,59.74136,865000
75
+ 121.711716,0.12767239,0.006910123,6.5898547,0.966691,-122.37459,-204.60338,0.7092211,-0.6879251,62.50541,870000
76
+ 118.0822,0.14509878,0.008217927,5.161196,1.1204474,-119.27876,-203.43231,0.9029107,-1.3754536,56.854034,875000
77
+ 117.04352,0.15905538,0.007378138,4.735679,-4.0913005,-117.78469,-204.92143,0.94224316,-0.93244606,74.14639,880000
78
+ 121.08336,0.12470487,0.0075852405,6.7289047,-3.9572515,-122.28883,-206.277,2.5228095,-3.2846751,107.84764,885000
79
+ 121.06717,0.18317983,0.007656805,6.060302,-3.4560008,-121.44202,-206.44019,1.3586857,-1.2742635,78.41884,890000
80
+ 120.30422,0.14392698,0.007849237,4.0327663,-3.0741627,-121.25254,-204.8295,4.5677915,-4.8448544,93.83548,895000
81
+ 118.50156,0.1764293,0.007638925,5.142563,-1.3810589,-118.455215,-207.40471,1.4946325,-1.4864384,61.014847,900000
82
+ 120.93931,0.17401282,0.0060407883,9.152859,6.1863065,-121.163284,-205.32027,1.2496396,-1.4294966,67.980934,905000
83
+ 120.91707,0.15649039,0.008563802,6.46223,-4.290752,-121.15564,-201.75842,2.636629,-2.6154048,117.15733,910000
84
+ 117.243385,0.17634611,0.006853453,3.87054,-1.6067694,-118.2492,-203.9798,1.0513705,-1.0546068,47.94529,915000
85
+ 116.76192,0.16762558,0.007520787,4.8842134,5.875246,-117.522194,-204.37843,1.062924,-1.3655668,51.608856,920000
86
+ 115.6531,0.15459329,0.0066032503,6.0176234,-3.0577707,-116.93469,-205.25687,2.6834238,-2.7210238,79.60943,925000
87
+ 113.82699,0.1560736,0.0076613897,7.8168564,-1.4658872,-114.140335,-203.99881,1.0471091,-1.0111188,99.85576,930000
88
+ 117.81987,0.1762259,0.005894056,6.0363426,-6.1093307,-118.333374,-205.34381,0.866666,-0.86983687,67.48644,935000
89
+ 113.22659,0.19882146,0.0075526866,5.933759,-4.8166404,-113.61299,-205.60382,1.7072988,-1.8268111,76.57216,940000
90
+ 117.954765,0.17373596,0.006560946,4.7602677,-3.8026423,-118.7183,-206.64941,1.0095962,-1.0488683,71.79688,945000
91
+ 113.25496,0.1826435,0.0067786914,10.062365,-3.1509595,-114.30778,-206.13974,1.9749994,-1.9320332,137.42839,950000
92
+ 115.347206,0.15795147,0.007588198,6.05331,5.3709154,-115.5198,-204.00873,2.8452694,-3.5317638,99.48747,955000
93
+ 114.81619,0.15499566,0.006378074,6.8485093,-0.3749362,-115.252235,-206.53482,0.9138383,-0.95301586,74.726425,960000
94
+ 114.97985,0.17602533,0.0072607105,6.038507,-2.1881385,-115.332695,-202.18312,0.7743522,-0.62826204,56.3636,965000
95
+ 111.13982,0.17803866,0.006056064,5.8114886,5.1205096,-112.00423,-201.5938,0.541172,-0.60353035,51.335052,970000
96
+ 112.88629,0.14722873,0.0071546654,7.7515717,-2.7658374,-112.85238,-206.11218,1.3605978,-1.9291384,79.38382,975000
97
+ 112.625916,0.15376326,0.008273376,6.952541,2.941209,-113.03894,-203.73897,2.0905352,-2.0617201,91.255394,980000
98
+ 113.59849,0.15310055,0.0067876447,4.260574,-2.6479971,-114.06411,-204.5438,0.87353516,-1.2501167,52.92022,985000
99
+ 110.28074,0.15410972,0.0066639567,5.8290024,-4.3232675,-111.052956,-203.84453,1.3144221,-1.4927942,72.99801,990000
100
+ 108.24418,0.16326335,0.0060323547,6.922821,-4.519434,-109.19602,-204.65303,1.2939167,-1.1549381,78.92921,995000
101
+ 106.39088,0.13631198,0.00652132,5.984836,1.5058433,-107.38535,-207.12848,1.2072271,-1.0943193,64.757065,1000000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/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
+ 166.5218,0.20748326,0.0068096803,6.619413,-60.070095,-166.68425,-204.48402,2.422592,-1.9576313,66.14717,505000
3
+ 164.31563,0.2250216,0.00700772,5.732899,-58.79256,-164.0827,-204.16925,1.7108012,-1.7522299,65.62773,510000
4
+ 165.29913,0.17137557,0.006376105,5.0586133,-52.771385,-165.32349,-203.41557,1.3747152,-1.3988771,65.6624,515000
5
+ 163.5229,0.1782758,0.007847391,7.557927,-31.002913,-163.9033,-206.54733,1.4952543,-1.3982507,68.358154,520000
6
+ 162.25117,0.17560524,0.006589155,6.0897636,-49.468014,-162.21002,-205.89598,1.0299759,-0.9675002,65.00014,525000
7
+ 162.36725,0.18355837,0.0059517385,4.8316536,-43.040222,-162.54027,-205.41733,0.8304766,-0.726861,55.03625,530000
8
+ 160.81677,0.20616008,0.005799729,4.890676,-57.6717,-161.01201,-203.68654,0.8950794,-0.8815994,44.642567,535000
9
+ 160.32861,0.17140076,0.008046914,6.720807,-49.072166,-160.88983,-205.19868,1.2066498,-1.2159265,63.782364,540000
10
+ 159.32564,0.19638297,0.007980976,4.652099,-63.072514,-159.30862,-204.59422,1.1939626,-1.2823656,59.363976,545000
11
+ 157.9882,0.16185543,0.008038209,5.442474,-26.559725,-158.32161,-204.50128,1.2616746,-1.168115,63.956963,550000
12
+ 152.93129,0.19482744,0.006991844,22.855251,-34.22967,-153.43106,-204.79384,1.3126396,-1.0643812,80.648224,555000
13
+ 150.69153,0.19156432,0.007946965,4.980285,-24.621868,-150.63383,-205.14622,2.4637897,-2.2888057,71.18353,560000
14
+ 152.6548,0.18948328,0.008026904,7.6956897,-30.475845,-152.5458,-205.15317,1.2719519,-1.2882636,78.669266,565000
15
+ 145.56583,0.17985855,0.007039245,7.8166823,-4.4266396,-146.17786,-205.60149,0.8503579,-1.1023912,73.64653,570000
16
+ 151.23058,0.20146024,0.009048472,5.783426,-40.58798,-151.84868,-205.50847,0.75749004,-0.70625013,62.894745,575000
17
+ 148.91629,0.17508309,0.0072668334,8.75602,-39.105846,-149.5543,-204.5968,1.0388274,-0.66895527,82.49553,580000
18
+ 147.16928,0.18105409,0.0069179214,6.9917145,0.6399143,-147.5811,-205.30368,1.5559683,-1.3546076,82.06183,585000
19
+ 145.74146,0.18065926,0.00731172,6.498562,-19.464043,-146.635,-206.47049,0.92860645,-0.9091873,80.98361,590000
20
+ 146.50188,0.16424981,0.008498847,8.853452,-26.55375,-146.9047,-205.19922,1.16657,-1.245795,60.325058,595000
21
+ 141.97646,0.1930753,0.0073928456,6.850709,-7.706395,-141.9793,-206.30367,1.4246017,-1.4894483,71.21469,600000
22
+ 145.37425,0.17739101,0.008345818,7.4535675,-35.759136,-145.9191,-204.98221,0.762427,-0.8037588,67.657104,605000
23
+ 143.38039,0.18841803,0.010037588,7.2064257,-7.883418,-142.93016,-206.01787,0.939676,-0.8968118,65.258095,610000
24
+ 138.98082,0.1561451,0.008567081,7.0705614,1.1745083,-140.03444,-205.85764,0.9824714,-1.1186332,77.62551,615000
25
+ 141.77406,0.17271763,0.0068140007,6.7961884,-1.8220332,-142.01794,-204.44736,1.3465353,-1.208942,81.953995,620000
26
+ 145.83495,0.16894947,0.007689125,6.392918,-23.07305,-145.60344,-205.64519,1.172403,-1.2191647,75.51995,625000
27
+ 140.0327,0.15687317,0.0078466395,5.1469607,0.30089337,-140.39783,-204.95923,1.0613123,-0.8971726,54.810516,630000
28
+ 139.57925,0.16413951,0.010316837,6.7176347,1.3929656,-140.71858,-205.22623,0.7228814,-0.74831146,61.306667,635000
29
+ 134.68864,0.1786459,0.00756677,9.050211,-1.5190578,-135.71252,-206.20598,0.96756464,-0.754621,71.28222,640000
30
+ 140.1516,0.1621275,0.008206757,7.379022,-11.07916,-141.19543,-205.59421,1.561644,-1.7521359,71.09219,645000
31
+ 137.84222,0.18932366,0.008376863,6.395865,2.8816447,-138.047,-205.9331,1.2307532,-1.3591601,71.87274,650000
32
+ 134.36858,0.21050474,0.008240202,6.351809,-2.4506776,-134.93033,-205.8044,1.7299888,-1.836239,70.29523,655000
33
+ 138.5572,0.18791889,0.007236007,7.092398,-18.314444,-139.07951,-205.53204,0.7006877,-1.0189695,60.082214,660000
34
+ 135.70801,0.18384363,0.0080038905,6.237934,-1.9456025,-136.69997,-206.10312,1.8338084,-1.6880748,66.80395,665000
35
+ 135.4642,0.1752526,0.0067462325,5.245669,-4.2588882,-135.88696,-207.52367,0.6699073,-0.7414518,58.707405,670000
36
+ 138.1036,0.19750008,0.008036039,6.613917,-5.173925,-137.87239,-208.96786,1.5908755,-2.5873287,75.63443,675000
37
+ 136.43507,0.17533946,0.008133958,7.6594515,2.289565,-137.08098,-206.21744,0.8040997,-0.81005317,70.88228,680000
38
+ 131.42802,0.1722506,0.007881626,6.5052066,-1.827974,-132.05092,-206.00293,0.6473991,-0.7845952,57.720207,685000
39
+ 132.88928,0.16545074,0.00955064,8.576665,-3.745032,-133.34868,-206.7009,0.7078985,-1.4510707,75.34433,690000
40
+ 134.15869,0.20014729,0.0075719603,5.279677,-7.4672136,-134.29263,-206.29095,1.892294,-1.697996,62.53632,695000
41
+ 131.75374,0.19199282,0.007885276,9.394301,-2.1798503,-132.62907,-205.37497,1.4919528,-3.1277113,100.75363,700000
42
+ 131.36867,0.17609769,0.006572296,5.4809847,2.035563,-131.90446,-204.95128,0.86584324,-0.85989827,64.47684,705000
43
+ 132.05164,0.16841641,0.008896918,6.6889153,-3.3114412,-132.47913,-205.11143,1.1456574,-1.7695111,72.1646,710000
44
+ 133.58696,0.1782682,0.008681855,5.000232,-6.0609503,-134.40865,-207.29204,2.3413424,-1.756267,79.23225,715000
45
+ 130.26068,0.17297438,0.007500497,6.203588,-10.338069,-130.46304,-205.99069,1.5919691,-1.8033642,65.79251,720000
46
+ 127.86684,0.15953943,0.0066857827,4.218212,-3.044785,-128.00386,-203.62187,1.0645288,-0.9230371,58.85525,725000
47
+ 131.42366,0.19301072,0.007776755,4.3784637,-0.5162743,-131.51219,-204.63426,1.7343754,-1.2761334,62.447998,730000
48
+ 129.34,0.19049877,0.0059848027,8.806047,-6.660486,-129.51222,-205.64581,1.6748475,-1.7897872,71.41674,735000
49
+ 125.273285,0.1457266,0.006478453,6.283852,1.6836936,-126.0333,-205.8054,0.68714094,-1.1180186,53.048462,740000
50
+ 128.65175,0.15678273,0.007809092,6.012171,0.48736215,-129.38257,-205.40898,0.74195945,-0.7285278,58.076073,745000
51
+ 120.6052,0.152136,0.006587132,6.3089895,-1.7709466,-121.05226,-204.74132,0.90740716,-0.97659296,62.595413,750000
52
+ 129.90562,0.16844666,0.0076739173,6.811792,-0.8375003,-130.8292,-204.11601,1.1574748,-1.1344916,81.66695,755000
53
+ 128.7339,0.19275725,0.00946365,8.717203,1.3040975,-129.27495,-204.45059,2.0662344,-1.9322214,88.722046,760000
54
+ 130.38031,0.17798938,0.008315503,4.7833953,-5.8009396,-130.36441,-205.5788,0.91399276,-1.0227433,59.15385,765000
55
+ 127.606316,0.17794245,0.0073523843,7.6489983,-0.264432,-127.913086,-205.63214,1.4343784,-1.2009773,95.50861,770000
56
+ 125.49583,0.1743324,0.0063023716,6.518682,-1.2783539,-126.05016,-205.46864,1.0191936,-0.957045,59.337276,775000
57
+ 129.15167,0.18540642,0.008371419,14.581675,-1.5505717,-130.14415,-205.38196,2.4627612,-2.1010523,165.85419,780000
58
+ 127.561844,0.18297982,0.00749687,6.212988,-8.488341,-128.18457,-206.6536,2.941416,-2.916381,89.98254,785000
59
+ 118.50928,0.17005599,0.0070027797,5.3881335,2.6239028,-119.01119,-204.53226,1.0554775,-1.660014,56.44802,790000
60
+ 121.64215,0.16012597,0.00651214,9.065615,3.3598802,-122.32788,-206.21072,0.8646723,-0.9278997,88.48897,795000
61
+ 126.858734,0.16309792,0.0065758447,11.003285,-7.487739,-127.41864,-205.33484,1.2968928,-1.36476,97.22938,800000
62
+ 125.96331,0.16668373,0.0069152745,5.8065095,-5.183187,-127.20003,-204.45486,1.444077,-1.7261181,68.55229,805000
63
+ 122.13812,0.17873943,0.0066028005,5.6726584,-1.090616,-122.76233,-204.12654,1.718991,-1.6122967,55.254433,810000
64
+ 122.66204,0.18367346,0.007020498,4.132024,-6.9758615,-122.97725,-203.5027,0.5045378,-0.6315088,45.222103,815000
65
+ 120.719,0.166908,0.008111222,6.1106906,-5.5405393,-121.66192,-204.32925,0.49973053,-0.6925161,50.918533,820000
66
+ 128.75484,0.16075233,0.006556637,5.6456985,-2.6131516,-129.15237,-206.37206,1.101054,-1.127568,61.518635,825000
67
+ 120.14458,0.1844497,0.006575374,6.2410493,-3.0688229,-120.592735,-205.21234,0.57648087,-0.58076835,65.50957,830000
68
+ 121.70195,0.17782468,0.007374693,4.9904995,0.05546537,-122.27775,-205.13652,1.9676663,-1.1865261,51.787323,835000
69
+ 125.31092,0.1878092,0.007619705,6.4286447,-1.0957571,-125.13766,-206.56995,2.1471083,-2.431331,73.6617,840000
70
+ 127.74588,0.16085848,0.008637991,5.578689,4.8539104,-128.01501,-205.0502,1.7152689,-1.6218858,64.86983,845000
71
+ 118.960075,0.16248497,0.0065502953,6.4874315,-0.06215509,-119.56593,-204.714,2.219815,-2.2722511,84.34273,850000
72
+ 123.557846,0.15150529,0.007849493,6.5396132,-0.36886722,-123.374535,-203.84967,1.0845523,-1.1087285,79.35518,855000
73
+ 117.039734,0.16404904,0.0068482407,6.007574,3.502732,-118.02351,-204.32057,0.8559219,-0.9870076,64.16542,860000
74
+ 124.57399,0.16699484,0.0087474,4.731914,-3.245717,-125.04348,-207.16895,1.6128016,-1.5123146,59.74136,865000
75
+ 121.711716,0.12767239,0.006910123,6.5898547,0.966691,-122.37459,-204.60338,0.7092211,-0.6879251,62.50541,870000
76
+ 118.0822,0.14509878,0.008217927,5.161196,1.1204474,-119.27876,-203.43231,0.9029107,-1.3754536,56.854034,875000
77
+ 117.04352,0.15905538,0.007378138,4.735679,-4.0913005,-117.78469,-204.92143,0.94224316,-0.93244606,74.14639,880000
78
+ 121.08336,0.12470487,0.0075852405,6.7289047,-3.9572515,-122.28883,-206.277,2.5228095,-3.2846751,107.84764,885000
79
+ 121.06717,0.18317983,0.007656805,6.060302,-3.4560008,-121.44202,-206.44019,1.3586857,-1.2742635,78.41884,890000
80
+ 120.30422,0.14392698,0.007849237,4.0327663,-3.0741627,-121.25254,-204.8295,4.5677915,-4.8448544,93.83548,895000
81
+ 118.50156,0.1764293,0.007638925,5.142563,-1.3810589,-118.455215,-207.40471,1.4946325,-1.4864384,61.014847,900000
82
+ 120.93931,0.17401282,0.0060407883,9.152859,6.1863065,-121.163284,-205.32027,1.2496396,-1.4294966,67.980934,905000
83
+ 120.91707,0.15649039,0.008563802,6.46223,-4.290752,-121.15564,-201.75842,2.636629,-2.6154048,117.15733,910000
84
+ 117.243385,0.17634611,0.006853453,3.87054,-1.6067694,-118.2492,-203.9798,1.0513705,-1.0546068,47.94529,915000
85
+ 116.76192,0.16762558,0.007520787,4.8842134,5.875246,-117.522194,-204.37843,1.062924,-1.3655668,51.608856,920000
86
+ 115.6531,0.15459329,0.0066032503,6.0176234,-3.0577707,-116.93469,-205.25687,2.6834238,-2.7210238,79.60943,925000
87
+ 113.82699,0.1560736,0.0076613897,7.8168564,-1.4658872,-114.140335,-203.99881,1.0471091,-1.0111188,99.85576,930000
88
+ 117.81987,0.1762259,0.005894056,6.0363426,-6.1093307,-118.333374,-205.34381,0.866666,-0.86983687,67.48644,935000
89
+ 113.22659,0.19882146,0.0075526866,5.933759,-4.8166404,-113.61299,-205.60382,1.7072988,-1.8268111,76.57216,940000
90
+ 117.954765,0.17373596,0.006560946,4.7602677,-3.8026423,-118.7183,-206.64941,1.0095962,-1.0488683,71.79688,945000
91
+ 113.25496,0.1826435,0.0067786914,10.062365,-3.1509595,-114.30778,-206.13974,1.9749994,-1.9320332,137.42839,950000
92
+ 115.347206,0.15795147,0.007588198,6.05331,5.3709154,-115.5198,-204.00873,2.8452694,-3.5317638,99.48747,955000
93
+ 114.81619,0.15499566,0.006378074,6.8485093,-0.3749362,-115.252235,-206.53482,0.9138383,-0.95301586,74.726425,960000
94
+ 114.97985,0.17602533,0.0072607105,6.038507,-2.1881385,-115.332695,-202.18312,0.7743522,-0.62826204,56.3636,965000
95
+ 111.13982,0.17803866,0.006056064,5.8114886,5.1205096,-112.00423,-201.5938,0.541172,-0.60353035,51.335052,970000
96
+ 112.88629,0.14722873,0.0071546654,7.7515717,-2.7658374,-112.85238,-206.11218,1.3605978,-1.9291384,79.38382,975000
97
+ 112.625916,0.15376326,0.008273376,6.952541,2.941209,-113.03894,-203.73897,2.0905352,-2.0617201,91.255394,980000
98
+ 113.59849,0.15310055,0.0067876447,4.260574,-2.6479971,-114.06411,-204.5438,0.87353516,-1.2501167,52.92022,985000
99
+ 110.28074,0.15410972,0.0066639567,5.8290024,-4.3232675,-111.052956,-203.84453,1.3144221,-1.4927942,72.99801,990000
100
+ 108.24418,0.16326335,0.0060323547,6.922821,-4.519434,-109.19602,-204.65303,1.2939167,-1.1549381,78.92921,995000
101
+ 106.39088,0.13631198,0.00652132,5.984836,1.5058433,-107.38535,-207.12848,1.2072271,-1.0943193,64.757065,1000000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c2ed7c3dfafc27ea51ba563769f79001d866c266877c18dd9b9d25dd1291146
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c3a16e26bee4dcff4cc54af4e52bf3158c417620a9cc0e44cfe625152b5556
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a4f72d86265b7f7a00eb4c6095bb793b65aabb6a776d48cfaec4c1c76d36d2
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2827f9a036aa800663aea221f1381f775092358ab0c797aa5dac23c8055112e7
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb1bde33e183f248e64bf618bbc2a514a366f46109e4f3cecc31bd5d2c69201
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147aeb9059a601033ab625a9f5081954ed9615c81ec444de9aaabb4e6a8daf82
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6224b6bf0beef4ca5c87c0351f2e1ea0fda88758ced7faa0dd2028aa1f6ce67
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35ced9f934e0bf7afbae7025b27095b2d5d10f5070cb84931879f17c4e0b2574
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ac4a843bc81ec7e80c2cfdfeb6cf60b7ccdd8681fb7b296fc933ae325c350a
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3923bcafaa245e8d5218823e0f48d83be831d44a6839791193a09fc06f20d9da
3
+ size 217969454
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/fql/20260319_132025/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/5wh15fst