Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_450000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_500000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_650000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_700000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_750000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_800000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_850000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_900000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/env.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/env_sv.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/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,-0.1830390388965553,0.17882963685762968,-0.18480767227706923,-0.04435296691850929,16.762341553175204,24.37299999999707,0.04,12535.12,-1.64,-867.88,485.46,1.3707727146148683,450000
|
| 3 |
+
0.0,0.0,-0.09101416897531013,0.03759138255623504,-0.09251354474524257,-0.04422243411850497,14.968318420010768,20.70299999999761,0.22,36049.22,-1.16,-642.34,412.06,1.1738760042190552,500000
|
| 4 |
+
0.0,0.0,-0.0762696701733227,-0.05297451030407334,-0.07471494861127112,0.05454637312600712,18.871781856266985,19.203999999997887,0.3,56373.32,-1.0,-556.82,382.08,1.0970215749740602,550000
|
| 5 |
+
0.0,0.0,-0.05061032701544821,0.029942551510206146,-0.048432178118029745,0.0282190094473619,21.314077885008327,13.601999999998565,0.58,72380.18,-0.6,-394.3,270.04,0.7789096975326538,600000
|
| 6 |
+
0.0,0.0,-0.07808710587090983,0.028519984217176948,-0.07619087039668253,0.024828205456641748,22.080924827733128,13.61499999999859,0.56,87230.9,-0.56,-362.04,270.3,0.7815701341629029,650000
|
| 7 |
+
0.0,0.0,-0.05724048219813156,-0.0023517001817970197,-0.05467017369687974,0.024267472700447202,25.897484372704806,9.326999999999122,0.76,99615.06,-0.32,-263.22,184.54,0.5515214681625367,700000
|
| 8 |
+
0.0,0.0,-0.0605537250787815,0.00769079295388793,-0.0594231824396226,0.011644665231878959,26.278911281193498,7.001999999999441,0.84,108492.9,-0.28,-222.12,138.04,0.41531283378601075,750000
|
| 9 |
+
0.0,0.0,-0.05941214006644921,0.044216745351695244,-0.057088341055689,0.01755474839390676,26.450497834802498,10.440999999999057,0.7,116992.88,-0.4,-288.26,206.82,0.6081548118591309,800000
|
| 10 |
+
0.0,0.0,-0.0666803950752521,0.05407671932703887,-0.06339293413417553,0.0431152602659191,29.2633371391649,5.535999999999641,0.9,125463.28,-0.14,-151.32,108.72,0.33326385498046873,850000
|
| 11 |
+
0.0,0.0,-0.06318695180721452,0.05167758776315443,-0.05870482464207813,0.07374018790427096,32.35159562372776,5.729999999999589,0.88,130721.58,-0.18,-164.84,112.6,0.3366214179992676,900000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/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,-0.1830390388965553,0.17882963685762968,-0.18480767227706923,-0.04435296691850929,16.762341553175204,24.37299999999707,0.04,12535.12,-1.64,-867.88,485.46,1.3707727146148683,450000
|
| 3 |
+
0.0,0.0,-0.09101416897531013,0.03759138255623504,-0.09251354474524257,-0.04422243411850497,14.968318420010768,20.70299999999761,0.22,36049.22,-1.16,-642.34,412.06,1.1738760042190552,500000
|
| 4 |
+
0.0,0.0,-0.0762696701733227,-0.05297451030407334,-0.07471494861127112,0.05454637312600712,18.871781856266985,19.203999999997887,0.3,56373.32,-1.0,-556.82,382.08,1.0970215749740602,550000
|
| 5 |
+
0.0,0.0,-0.05061032701544821,0.029942551510206146,-0.048432178118029745,0.0282190094473619,21.314077885008327,13.601999999998565,0.58,72380.18,-0.6,-394.3,270.04,0.7789096975326538,600000
|
| 6 |
+
0.0,0.0,-0.07808710587090983,0.028519984217176948,-0.07619087039668253,0.024828205456641748,22.080924827733128,13.61499999999859,0.56,87230.9,-0.56,-362.04,270.3,0.7815701341629029,650000
|
| 7 |
+
0.0,0.0,-0.05724048219813156,-0.0023517001817970197,-0.05467017369687974,0.024267472700447202,25.897484372704806,9.326999999999122,0.76,99615.06,-0.32,-263.22,184.54,0.5515214681625367,700000
|
| 8 |
+
0.0,0.0,-0.0605537250787815,0.00769079295388793,-0.0594231824396226,0.011644665231878959,26.278911281193498,7.001999999999441,0.84,108492.9,-0.28,-222.12,138.04,0.41531283378601075,750000
|
| 9 |
+
0.0,0.0,-0.05941214006644921,0.044216745351695244,-0.057088341055689,0.01755474839390676,26.450497834802498,10.440999999999057,0.7,116992.88,-0.4,-288.26,206.82,0.6081548118591309,800000
|
| 10 |
+
0.0,0.0,-0.0666803950752521,0.05407671932703887,-0.06339293413417553,0.0431152602659191,29.2633371391649,5.535999999999641,0.9,125463.28,-0.14,-151.32,108.72,0.33326385498046873,850000
|
| 11 |
+
0.0,0.0,-0.06318695180721452,0.05167758776315443,-0.05870482464207813,0.07374018790427096,32.35159562372776,5.729999999999589,0.88,130721.58,-0.18,-164.84,112.6,0.3366214179992676,900000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/online_agent.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/actor_loss,actor/bc_flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
405.5173,1.1828893,0.6193251,-6.5233727,-48.532043,-78.69454,6.224837,-4.9778852,138.01532,405000
|
| 3 |
+
553.44727,0.9759586,1.1916183,-10.8670635,-62.435658,-104.28729,3.402227,-6.261418,93.273056,410000
|
| 4 |
+
611.7244,0.8813144,0.87109417,-13.039156,-68.137115,-131.80515,1.0430986,-0.82726634,57.54377,415000
|
| 5 |
+
616.45935,0.94943666,4.365664,-10.350101,-68.45347,-146.45921,2.8948386,-2.4536178,117.94323,420000
|
| 6 |
+
612.12695,0.9843923,0.8227914,-21.192245,-68.28709,-146.4553,1.1111751,-2.371766,51.902096,425000
|
| 7 |
+
621.77124,1.0079112,1.6308746,-16.042809,-69.16213,-155.23404,3.8052528,-3.1675098,91.999435,430000
|
| 8 |
+
654.7377,0.9135764,1.2405709,-16.268578,-72.30464,-155.52457,4.3848443,-5.3688774,115.0289,435000
|
| 9 |
+
700.0309,0.8952791,1.2456467,-23.46333,-76.59756,-159.6681,3.0429864,-4.312281,124.93967,440000
|
| 10 |
+
706.5258,0.7953591,1.1515021,-20.834385,-77.22875,-162.21953,2.7123802,-2.3554149,67.5392,445000
|
| 11 |
+
701.6892,0.9831395,1.5390975,-20.14615,-77.15319,-163.81442,3.6747239,-2.9714723,84.747086,450000
|
| 12 |
+
693.19025,0.85479134,2.3406026,-16.609892,-76.53892,-156.24994,1.087691,-1.0896039,88.27988,455000
|
| 13 |
+
690.9803,0.91972756,1.057938,-13.034582,-76.07487,-159.38873,1.8622348,-1.512023,71.344185,460000
|
| 14 |
+
723.5849,0.7736198,1.0100605,-20.833832,-78.705956,-168.78249,1.6069379,-1.6039205,55.739334,465000
|
| 15 |
+
702.2522,0.91952145,1.2634242,-13.205126,-76.48404,-173.06982,0.82422554,-1.9155583,61.23185,470000
|
| 16 |
+
767.74146,0.814485,8.067024,-22.066322,-82.16866,-159.01257,38.27067,-37.08725,658.536,475000
|
| 17 |
+
810.9961,1.0575887,1.7156086,-15.389393,-88.10691,-172.34651,2.5419261,-2.7845821,97.81464,480000
|
| 18 |
+
771.65405,0.8758485,2.2880425,-19.492527,-83.41003,-167.33078,5.4509873,-4.2317867,103.20671,485000
|
| 19 |
+
795.43994,0.8974532,1.8856564,-11.320294,-85.70304,-182.55484,3.0867615,-2.5826583,109.25818,490000
|
| 20 |
+
819.33734,2.0581667,1.6751908,-21.30584,-88.04157,-171.66406,7.2345433,-5.6289515,162.71785,495000
|
| 21 |
+
791.3065,0.870018,1.8310757,-18.026022,-85.35964,-177.52219,6.63129,-4.256553,93.50964,500000
|
| 22 |
+
784.9463,1.0570296,1.631774,-16.287521,-84.624954,-182.05196,3.579713,-4.217913,132.94453,505000
|
| 23 |
+
811.5731,0.9412776,2.4994054,-17.300537,-87.70357,-172.00488,1.9758644,-2.2393298,79.87335,510000
|
| 24 |
+
778.8394,0.76775503,2.3972661,1.3497155,-84.21362,-179.74518,1.2653642,-1.4476131,75.93214,515000
|
| 25 |
+
833.84015,0.93853843,2.08703,-19.295513,-89.419,-174.08385,3.1956053,-3.8373582,75.62886,520000
|
| 26 |
+
829.8172,1.4053024,1.8786768,-15.357582,-88.96261,-181.15042,1.842871,-1.7965221,97.60041,525000
|
| 27 |
+
825.4426,0.89122236,1.5599514,-15.550449,-88.734344,-184.80579,1.4850925,-2.0979486,75.08842,530000
|
| 28 |
+
820.65094,0.9942925,2.402785,2.866313,-88.97576,-167.48108,3.5288882,-3.7726164,120.20134,535000
|
| 29 |
+
791.1899,0.9429517,2.071338,-8.559671,-86.127205,-182.87436,1.2384876,-1.6217775,70.88561,540000
|
| 30 |
+
844.2694,0.8634976,2.8016307,-16.165453,-90.239334,-174.38837,4.299239,-4.1553893,103.04955,545000
|
| 31 |
+
823.01465,1.0181566,2.0253334,-9.931633,-87.988396,-171.14146,0.9603729,-1.2953712,69.338615,550000
|
| 32 |
+
875.91925,1.002027,2.359529,-25.69041,-94.08648,-178.34683,1.5924159,-1.9039496,86.58127,555000
|
| 33 |
+
853.8223,0.8989929,2.889457,-18.441406,-91.64233,-178.74802,2.3864517,-1.5250547,89.93282,560000
|
| 34 |
+
848.87714,0.9340024,1.5665897,-1.7245891,-90.827866,-174.5781,2.5994942,-2.3202055,78.91778,565000
|
| 35 |
+
839.2001,1.239326,1.9509125,-19.615383,-89.933235,-183.21208,2.611184,-2.1626356,94.245445,570000
|
| 36 |
+
861.40454,1.093623,2.2997627,-18.445978,-92.01444,-179.48512,5.568317,-6.6700296,117.33326,575000
|
| 37 |
+
913.5953,1.0607095,1.974197,4.012268,-97.162224,-178.76349,11.364053,-9.06149,150.15344,580000
|
| 38 |
+
876.5191,0.92081213,2.4455063,-15.069168,-93.58721,-181.67505,5.5704026,-6.660349,185.59348,585000
|
| 39 |
+
906.0771,1.1061343,2.4134903,-10.805757,-96.065056,-181.37328,2.736781,-1.7754436,81.64987,590000
|
| 40 |
+
853.3981,1.0172004,1.8761818,-18.424398,-91.145874,-184.5671,1.532626,-1.5621828,78.248085,595000
|
| 41 |
+
859.1976,1.1882166,2.1120973,-13.956669,-92.059814,-178.71732,1.777087,-1.6558865,93.4738,600000
|
| 42 |
+
853.19305,1.2737784,2.4939046,-17.18291,-91.39129,-183.79515,4.715182,-6.972207,230.44655,605000
|
| 43 |
+
841.13165,1.290658,2.256624,-12.254558,-89.71447,-183.95168,2.3532858,-3.5178468,89.30494,610000
|
| 44 |
+
863.2068,0.8537529,3.6691067,-7.9386744,-92.242424,-188.92592,2.9518201,-3.028882,101.901634,615000
|
| 45 |
+
883.09534,0.9538759,2.9165075,-18.822979,-94.01812,-181.84673,6.380039,-7.0452714,223.48132,620000
|
| 46 |
+
861.3251,1.751997,4.247812,-0.9777489,-91.81894,-184.02786,5.7575336,-6.0648084,105.07429,625000
|
| 47 |
+
864.012,1.1714046,1.8585209,-10.891997,-92.32582,-182.91017,2.5652256,-2.1374056,107.161446,630000
|
| 48 |
+
869.3221,1.0161569,2.0236518,-15.721817,-92.28839,-182.7884,2.9458556,-3.0418954,77.486145,635000
|
| 49 |
+
875.4143,1.0951133,1.9161316,2.4231286,-93.31616,-182.44691,1.8345355,-1.8759037,75.865974,640000
|
| 50 |
+
855.80505,1.0814366,2.0280888,-16.261116,-91.72052,-181.43443,1.9894372,-1.3480873,90.553215,645000
|
| 51 |
+
871.11914,1.1125317,3.208903,-14.425922,-92.831726,-181.1703,1.755453,-1.7751014,102.382866,650000
|
| 52 |
+
878.78735,0.9958947,1.9923,-19.909973,-94.01026,-173.92148,11.709573,-13.616155,154.54803,655000
|
| 53 |
+
833.4301,1.4270897,3.518226,1.6097902,-89.21017,-179.94276,5.4020553,-5.5737767,201.89629,660000
|
| 54 |
+
851.809,1.211338,12.910367,-4.423285,-91.13261,-183.61504,1.7414786,-1.8760995,172.58846,665000
|
| 55 |
+
853.96436,1.0813706,3.782224,-5.6607256,-91.36271,-179.67184,10.4585495,-9.231908,207.48996,670000
|
| 56 |
+
855.0522,1.0111128,3.387923,-6.786969,-90.93738,-186.4468,1.4708258,-2.1750884,83.217766,675000
|
| 57 |
+
835.01996,1.1162512,2.079747,-20.211226,-89.521286,-176.0714,2.0232778,-2.0437682,79.52569,680000
|
| 58 |
+
854.4871,0.8492815,3.4173868,-2.6685135,-91.0479,-183.06303,2.021254,-2.3381076,108.71373,685000
|
| 59 |
+
865.11224,1.3525345,3.7040596,-9.81982,-92.202446,-178.94017,4.323018,-4.4026303,110.63461,690000
|
| 60 |
+
859.1073,1.2398064,3.2265382,1.4086223,-91.4229,-182.08463,11.887332,-14.021603,364.97882,695000
|
| 61 |
+
842.78864,1.3021393,8.671099,-6.856566,-90.01481,-182.59245,12.366944,-9.611695,228.92181,700000
|
| 62 |
+
864.5784,1.0380597,2.118567,-4.01817,-92.482864,-181.16032,5.7464566,-5.8166723,88.96546,705000
|
| 63 |
+
825.99756,1.470089,2.3270068,-21.8268,-88.66416,-181.59328,2.0427656,-2.3894062,96.5998,710000
|
| 64 |
+
850.93463,1.3219068,2.2841623,-3.9948843,-90.628075,-179.93471,4.4329395,-4.035535,101.18606,715000
|
| 65 |
+
851.2941,0.9316455,2.0691803,-5.1876383,-91.120094,-185.83374,2.8931043,-1.9822888,73.051865,720000
|
| 66 |
+
866.3687,0.9177872,1.9993991,-1.6574137,-92.72323,-181.66428,10.856943,-9.940129,252.06494,725000
|
| 67 |
+
888.7033,1.23261,3.3960457,-5.138755,-94.43185,-184.17073,2.025364,-1.9348748,101.65339,730000
|
| 68 |
+
819.2075,1.3089654,3.9414012,-6.262308,-88.114105,-176.71646,12.620558,-20.74654,258.98834,735000
|
| 69 |
+
827.2156,0.9051831,1.9511757,-6.733506,-88.92184,-183.58678,4.6448793,-3.4170206,95.93685,740000
|
| 70 |
+
864.8499,1.0449886,2.284281,-15.23907,-92.01973,-178.46556,14.790496,-10.064911,142.64897,745000
|
| 71 |
+
843.5594,1.0753766,2.8177767,-4.198795,-90.099785,-180.45197,6.1800647,-6.115022,185.98001,750000
|
| 72 |
+
848.3844,1.1066825,2.708183,-8.298423,-90.380844,-181.84799,42.9232,-48.44292,504.03363,755000
|
| 73 |
+
896.0244,1.4142863,4.8361955,-17.118921,-95.33398,-181.07468,3.923565,-8.7311,141.83987,760000
|
| 74 |
+
855.85345,1.2450225,2.609563,-10.793397,-91.60753,-174.71857,3.383151,-2.4522977,139.23917,765000
|
| 75 |
+
850.1688,1.3676667,6.3990016,-5.4482255,-90.639175,-180.36147,3.0635347,-2.7351825,155.11197,770000
|
| 76 |
+
827.9858,0.95389146,11.956375,0.83159983,-88.732025,-182.03482,14.106418,-17.53877,328.0995,775000
|
| 77 |
+
857.0714,1.0673869,6.5560737,5.065036,-91.11155,-181.49942,7.14958,-8.380975,153.06216,780000
|
| 78 |
+
845.76227,1.2512995,2.2230413,-6.166675,-90.175316,-183.51869,2.2973557,-3.0349877,117.24575,785000
|
| 79 |
+
850.8814,1.1252806,2.9875572,-14.144508,-90.841255,-170.73894,8.477725,-6.0458894,172.89397,790000
|
| 80 |
+
847.69586,1.0627763,2.9458816,-1.5725431,-90.41707,-180.2329,2.4375954,-3.0666442,134.95522,795000
|
| 81 |
+
841.7671,1.2452507,3.1712255,-6.166974,-89.61352,-183.07936,9.768958,-7.7855916,291.05148,800000
|
| 82 |
+
867.00806,1.5954748,2.0830007,0.1475657,-92.039665,-182.49678,15.277546,-6.096374,143.21915,805000
|
| 83 |
+
863.702,1.0262603,3.0072505,0.86500454,-92.55033,-181.21506,2.6962154,-2.4217372,117.69165,810000
|
| 84 |
+
839.4958,1.4205643,3.100447,-10.911906,-90.016075,-179.2228,3.4032013,-5.0459323,163.68692,815000
|
| 85 |
+
844.43945,1.2360103,2.843272,-12.19417,-90.16204,-183.43881,2.668967,-2.4536614,98.90971,820000
|
| 86 |
+
854.5465,1.1572297,3.0341783,-4.9063644,-90.961876,-179.8996,3.9401693,-3.8576853,156.30907,825000
|
| 87 |
+
849.19836,1.4351622,3.5302582,-7.9944177,-90.636696,-180.59254,39.07237,-65.302376,560.9809,830000
|
| 88 |
+
818.0216,1.4584904,7.443971,0.232506,-87.411804,-176.51999,8.37828,-7.2504044,195.78642,835000
|
| 89 |
+
872.2223,1.303232,3.1579182,-0.9761186,-92.60017,-182.82495,5.1887,-4.5341973,125.92915,840000
|
| 90 |
+
880.89557,1.2498702,2.809859,-1.2116644,-93.873726,-185.21275,3.8479548,-2.3700984,110.74429,845000
|
| 91 |
+
863.5201,1.1105629,3.1891382,-5.8922577,-92.22932,-183.64648,11.044283,-13.284296,173.31265,850000
|
| 92 |
+
843.59454,0.93264806,3.9638488,-7.3891363,-89.979225,-177.89691,22.390408,-15.959525,214.46553,855000
|
| 93 |
+
843.49316,1.00933,5.530874,-14.6034155,-90.096245,-187.44092,4.775937,-3.5360823,124.88133,860000
|
| 94 |
+
785.4719,0.8394935,2.6629045,-0.15924957,-85.013435,-181.9364,1.8166537,-1.7409055,87.77231,865000
|
| 95 |
+
851.897,1.1587814,1.9136189,-4.6792345,-90.98287,-178.08318,5.5873456,-4.5463696,91.79373,870000
|
| 96 |
+
829.0326,0.871061,2.692888,-6.8574753,-88.408066,-180.70676,5.9819326,-4.3834004,138.5816,875000
|
| 97 |
+
792.89655,0.9727788,3.3963144,2.296708,-85.24032,-179.88692,8.069695,-5.346298,156.37071,880000
|
| 98 |
+
830.35187,1.1397145,2.5159168,-4.170389,-88.81994,-179.71054,1.8548334,-1.8477014,98.39159,885000
|
| 99 |
+
817.86035,0.8743218,5.585834,-3.2773447,-87.67862,-178.32149,4.7771273,-4.8394823,183.63963,890000
|
| 100 |
+
797.1675,1.1467475,3.6835084,-5.353954,-85.43017,-172.8087,5.5785365,-7.621479,149.1793,895000
|
| 101 |
+
803.80145,0.90684414,2.2726142,-2.0050902,-85.621284,-182.5734,17.757315,-16.180202,226.22112,900000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/online_agent_sv.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/actor_loss,actor/bc_flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
405.5173,1.1828893,0.6193251,-6.5233727,-48.532043,-78.69454,6.224837,-4.9778852,138.01532,405000
|
| 3 |
+
553.44727,0.9759586,1.1916183,-10.8670635,-62.435658,-104.28729,3.402227,-6.261418,93.273056,410000
|
| 4 |
+
611.7244,0.8813144,0.87109417,-13.039156,-68.137115,-131.80515,1.0430986,-0.82726634,57.54377,415000
|
| 5 |
+
616.45935,0.94943666,4.365664,-10.350101,-68.45347,-146.45921,2.8948386,-2.4536178,117.94323,420000
|
| 6 |
+
612.12695,0.9843923,0.8227914,-21.192245,-68.28709,-146.4553,1.1111751,-2.371766,51.902096,425000
|
| 7 |
+
621.77124,1.0079112,1.6308746,-16.042809,-69.16213,-155.23404,3.8052528,-3.1675098,91.999435,430000
|
| 8 |
+
654.7377,0.9135764,1.2405709,-16.268578,-72.30464,-155.52457,4.3848443,-5.3688774,115.0289,435000
|
| 9 |
+
700.0309,0.8952791,1.2456467,-23.46333,-76.59756,-159.6681,3.0429864,-4.312281,124.93967,440000
|
| 10 |
+
706.5258,0.7953591,1.1515021,-20.834385,-77.22875,-162.21953,2.7123802,-2.3554149,67.5392,445000
|
| 11 |
+
701.6892,0.9831395,1.5390975,-20.14615,-77.15319,-163.81442,3.6747239,-2.9714723,84.747086,450000
|
| 12 |
+
693.19025,0.85479134,2.3406026,-16.609892,-76.53892,-156.24994,1.087691,-1.0896039,88.27988,455000
|
| 13 |
+
690.9803,0.91972756,1.057938,-13.034582,-76.07487,-159.38873,1.8622348,-1.512023,71.344185,460000
|
| 14 |
+
723.5849,0.7736198,1.0100605,-20.833832,-78.705956,-168.78249,1.6069379,-1.6039205,55.739334,465000
|
| 15 |
+
702.2522,0.91952145,1.2634242,-13.205126,-76.48404,-173.06982,0.82422554,-1.9155583,61.23185,470000
|
| 16 |
+
767.74146,0.814485,8.067024,-22.066322,-82.16866,-159.01257,38.27067,-37.08725,658.536,475000
|
| 17 |
+
810.9961,1.0575887,1.7156086,-15.389393,-88.10691,-172.34651,2.5419261,-2.7845821,97.81464,480000
|
| 18 |
+
771.65405,0.8758485,2.2880425,-19.492527,-83.41003,-167.33078,5.4509873,-4.2317867,103.20671,485000
|
| 19 |
+
795.43994,0.8974532,1.8856564,-11.320294,-85.70304,-182.55484,3.0867615,-2.5826583,109.25818,490000
|
| 20 |
+
819.33734,2.0581667,1.6751908,-21.30584,-88.04157,-171.66406,7.2345433,-5.6289515,162.71785,495000
|
| 21 |
+
791.3065,0.870018,1.8310757,-18.026022,-85.35964,-177.52219,6.63129,-4.256553,93.50964,500000
|
| 22 |
+
784.9463,1.0570296,1.631774,-16.287521,-84.624954,-182.05196,3.579713,-4.217913,132.94453,505000
|
| 23 |
+
811.5731,0.9412776,2.4994054,-17.300537,-87.70357,-172.00488,1.9758644,-2.2393298,79.87335,510000
|
| 24 |
+
778.8394,0.76775503,2.3972661,1.3497155,-84.21362,-179.74518,1.2653642,-1.4476131,75.93214,515000
|
| 25 |
+
833.84015,0.93853843,2.08703,-19.295513,-89.419,-174.08385,3.1956053,-3.8373582,75.62886,520000
|
| 26 |
+
829.8172,1.4053024,1.8786768,-15.357582,-88.96261,-181.15042,1.842871,-1.7965221,97.60041,525000
|
| 27 |
+
825.4426,0.89122236,1.5599514,-15.550449,-88.734344,-184.80579,1.4850925,-2.0979486,75.08842,530000
|
| 28 |
+
820.65094,0.9942925,2.402785,2.866313,-88.97576,-167.48108,3.5288882,-3.7726164,120.20134,535000
|
| 29 |
+
791.1899,0.9429517,2.071338,-8.559671,-86.127205,-182.87436,1.2384876,-1.6217775,70.88561,540000
|
| 30 |
+
844.2694,0.8634976,2.8016307,-16.165453,-90.239334,-174.38837,4.299239,-4.1553893,103.04955,545000
|
| 31 |
+
823.01465,1.0181566,2.0253334,-9.931633,-87.988396,-171.14146,0.9603729,-1.2953712,69.338615,550000
|
| 32 |
+
875.91925,1.002027,2.359529,-25.69041,-94.08648,-178.34683,1.5924159,-1.9039496,86.58127,555000
|
| 33 |
+
853.8223,0.8989929,2.889457,-18.441406,-91.64233,-178.74802,2.3864517,-1.5250547,89.93282,560000
|
| 34 |
+
848.87714,0.9340024,1.5665897,-1.7245891,-90.827866,-174.5781,2.5994942,-2.3202055,78.91778,565000
|
| 35 |
+
839.2001,1.239326,1.9509125,-19.615383,-89.933235,-183.21208,2.611184,-2.1626356,94.245445,570000
|
| 36 |
+
861.40454,1.093623,2.2997627,-18.445978,-92.01444,-179.48512,5.568317,-6.6700296,117.33326,575000
|
| 37 |
+
913.5953,1.0607095,1.974197,4.012268,-97.162224,-178.76349,11.364053,-9.06149,150.15344,580000
|
| 38 |
+
876.5191,0.92081213,2.4455063,-15.069168,-93.58721,-181.67505,5.5704026,-6.660349,185.59348,585000
|
| 39 |
+
906.0771,1.1061343,2.4134903,-10.805757,-96.065056,-181.37328,2.736781,-1.7754436,81.64987,590000
|
| 40 |
+
853.3981,1.0172004,1.8761818,-18.424398,-91.145874,-184.5671,1.532626,-1.5621828,78.248085,595000
|
| 41 |
+
859.1976,1.1882166,2.1120973,-13.956669,-92.059814,-178.71732,1.777087,-1.6558865,93.4738,600000
|
| 42 |
+
853.19305,1.2737784,2.4939046,-17.18291,-91.39129,-183.79515,4.715182,-6.972207,230.44655,605000
|
| 43 |
+
841.13165,1.290658,2.256624,-12.254558,-89.71447,-183.95168,2.3532858,-3.5178468,89.30494,610000
|
| 44 |
+
863.2068,0.8537529,3.6691067,-7.9386744,-92.242424,-188.92592,2.9518201,-3.028882,101.901634,615000
|
| 45 |
+
883.09534,0.9538759,2.9165075,-18.822979,-94.01812,-181.84673,6.380039,-7.0452714,223.48132,620000
|
| 46 |
+
861.3251,1.751997,4.247812,-0.9777489,-91.81894,-184.02786,5.7575336,-6.0648084,105.07429,625000
|
| 47 |
+
864.012,1.1714046,1.8585209,-10.891997,-92.32582,-182.91017,2.5652256,-2.1374056,107.161446,630000
|
| 48 |
+
869.3221,1.0161569,2.0236518,-15.721817,-92.28839,-182.7884,2.9458556,-3.0418954,77.486145,635000
|
| 49 |
+
875.4143,1.0951133,1.9161316,2.4231286,-93.31616,-182.44691,1.8345355,-1.8759037,75.865974,640000
|
| 50 |
+
855.80505,1.0814366,2.0280888,-16.261116,-91.72052,-181.43443,1.9894372,-1.3480873,90.553215,645000
|
| 51 |
+
871.11914,1.1125317,3.208903,-14.425922,-92.831726,-181.1703,1.755453,-1.7751014,102.382866,650000
|
| 52 |
+
878.78735,0.9958947,1.9923,-19.909973,-94.01026,-173.92148,11.709573,-13.616155,154.54803,655000
|
| 53 |
+
833.4301,1.4270897,3.518226,1.6097902,-89.21017,-179.94276,5.4020553,-5.5737767,201.89629,660000
|
| 54 |
+
851.809,1.211338,12.910367,-4.423285,-91.13261,-183.61504,1.7414786,-1.8760995,172.58846,665000
|
| 55 |
+
853.96436,1.0813706,3.782224,-5.6607256,-91.36271,-179.67184,10.4585495,-9.231908,207.48996,670000
|
| 56 |
+
855.0522,1.0111128,3.387923,-6.786969,-90.93738,-186.4468,1.4708258,-2.1750884,83.217766,675000
|
| 57 |
+
835.01996,1.1162512,2.079747,-20.211226,-89.521286,-176.0714,2.0232778,-2.0437682,79.52569,680000
|
| 58 |
+
854.4871,0.8492815,3.4173868,-2.6685135,-91.0479,-183.06303,2.021254,-2.3381076,108.71373,685000
|
| 59 |
+
865.11224,1.3525345,3.7040596,-9.81982,-92.202446,-178.94017,4.323018,-4.4026303,110.63461,690000
|
| 60 |
+
859.1073,1.2398064,3.2265382,1.4086223,-91.4229,-182.08463,11.887332,-14.021603,364.97882,695000
|
| 61 |
+
842.78864,1.3021393,8.671099,-6.856566,-90.01481,-182.59245,12.366944,-9.611695,228.92181,700000
|
| 62 |
+
864.5784,1.0380597,2.118567,-4.01817,-92.482864,-181.16032,5.7464566,-5.8166723,88.96546,705000
|
| 63 |
+
825.99756,1.470089,2.3270068,-21.8268,-88.66416,-181.59328,2.0427656,-2.3894062,96.5998,710000
|
| 64 |
+
850.93463,1.3219068,2.2841623,-3.9948843,-90.628075,-179.93471,4.4329395,-4.035535,101.18606,715000
|
| 65 |
+
851.2941,0.9316455,2.0691803,-5.1876383,-91.120094,-185.83374,2.8931043,-1.9822888,73.051865,720000
|
| 66 |
+
866.3687,0.9177872,1.9993991,-1.6574137,-92.72323,-181.66428,10.856943,-9.940129,252.06494,725000
|
| 67 |
+
888.7033,1.23261,3.3960457,-5.138755,-94.43185,-184.17073,2.025364,-1.9348748,101.65339,730000
|
| 68 |
+
819.2075,1.3089654,3.9414012,-6.262308,-88.114105,-176.71646,12.620558,-20.74654,258.98834,735000
|
| 69 |
+
827.2156,0.9051831,1.9511757,-6.733506,-88.92184,-183.58678,4.6448793,-3.4170206,95.93685,740000
|
| 70 |
+
864.8499,1.0449886,2.284281,-15.23907,-92.01973,-178.46556,14.790496,-10.064911,142.64897,745000
|
| 71 |
+
843.5594,1.0753766,2.8177767,-4.198795,-90.099785,-180.45197,6.1800647,-6.115022,185.98001,750000
|
| 72 |
+
848.3844,1.1066825,2.708183,-8.298423,-90.380844,-181.84799,42.9232,-48.44292,504.03363,755000
|
| 73 |
+
896.0244,1.4142863,4.8361955,-17.118921,-95.33398,-181.07468,3.923565,-8.7311,141.83987,760000
|
| 74 |
+
855.85345,1.2450225,2.609563,-10.793397,-91.60753,-174.71857,3.383151,-2.4522977,139.23917,765000
|
| 75 |
+
850.1688,1.3676667,6.3990016,-5.4482255,-90.639175,-180.36147,3.0635347,-2.7351825,155.11197,770000
|
| 76 |
+
827.9858,0.95389146,11.956375,0.83159983,-88.732025,-182.03482,14.106418,-17.53877,328.0995,775000
|
| 77 |
+
857.0714,1.0673869,6.5560737,5.065036,-91.11155,-181.49942,7.14958,-8.380975,153.06216,780000
|
| 78 |
+
845.76227,1.2512995,2.2230413,-6.166675,-90.175316,-183.51869,2.2973557,-3.0349877,117.24575,785000
|
| 79 |
+
850.8814,1.1252806,2.9875572,-14.144508,-90.841255,-170.73894,8.477725,-6.0458894,172.89397,790000
|
| 80 |
+
847.69586,1.0627763,2.9458816,-1.5725431,-90.41707,-180.2329,2.4375954,-3.0666442,134.95522,795000
|
| 81 |
+
841.7671,1.2452507,3.1712255,-6.166974,-89.61352,-183.07936,9.768958,-7.7855916,291.05148,800000
|
| 82 |
+
867.00806,1.5954748,2.0830007,0.1475657,-92.039665,-182.49678,15.277546,-6.096374,143.21915,805000
|
| 83 |
+
863.702,1.0262603,3.0072505,0.86500454,-92.55033,-181.21506,2.6962154,-2.4217372,117.69165,810000
|
| 84 |
+
839.4958,1.4205643,3.100447,-10.911906,-90.016075,-179.2228,3.4032013,-5.0459323,163.68692,815000
|
| 85 |
+
844.43945,1.2360103,2.843272,-12.19417,-90.16204,-183.43881,2.668967,-2.4536614,98.90971,820000
|
| 86 |
+
854.5465,1.1572297,3.0341783,-4.9063644,-90.961876,-179.8996,3.9401693,-3.8576853,156.30907,825000
|
| 87 |
+
849.19836,1.4351622,3.5302582,-7.9944177,-90.636696,-180.59254,39.07237,-65.302376,560.9809,830000
|
| 88 |
+
818.0216,1.4584904,7.443971,0.232506,-87.411804,-176.51999,8.37828,-7.2504044,195.78642,835000
|
| 89 |
+
872.2223,1.303232,3.1579182,-0.9761186,-92.60017,-182.82495,5.1887,-4.5341973,125.92915,840000
|
| 90 |
+
880.89557,1.2498702,2.809859,-1.2116644,-93.873726,-185.21275,3.8479548,-2.3700984,110.74429,845000
|
| 91 |
+
863.5201,1.1105629,3.1891382,-5.8922577,-92.22932,-183.64648,11.044283,-13.284296,173.31265,850000
|
| 92 |
+
843.59454,0.93264806,3.9638488,-7.3891363,-89.979225,-177.89691,22.390408,-15.959525,214.46553,855000
|
| 93 |
+
843.49316,1.00933,5.530874,-14.6034155,-90.096245,-187.44092,4.775937,-3.5360823,124.88133,860000
|
| 94 |
+
785.4719,0.8394935,2.6629045,-0.15924957,-85.013435,-181.9364,1.8166537,-1.7409055,87.77231,865000
|
| 95 |
+
851.897,1.1587814,1.9136189,-4.6792345,-90.98287,-178.08318,5.5873456,-4.5463696,91.79373,870000
|
| 96 |
+
829.0326,0.871061,2.692888,-6.8574753,-88.408066,-180.70676,5.9819326,-4.3834004,138.5816,875000
|
| 97 |
+
792.89655,0.9727788,3.3963144,2.296708,-85.24032,-179.88692,8.069695,-5.346298,156.37071,880000
|
| 98 |
+
830.35187,1.1397145,2.5159168,-4.170389,-88.81994,-179.71054,1.8548334,-1.8477014,98.39159,885000
|
| 99 |
+
817.86035,0.8743218,5.585834,-3.2773447,-87.67862,-178.32149,4.7771273,-4.8394823,183.63963,890000
|
| 100 |
+
797.1675,1.1467475,3.6835084,-5.353954,-85.43017,-172.8087,5.5785365,-7.621479,149.1793,895000
|
| 101 |
+
803.80145,0.90684414,2.2726142,-2.0050902,-85.621284,-182.5734,17.757315,-16.180202,226.22112,900000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae09ddfb626e087a39a61c6a67388f7d4314a1c4b2c4943301946a7582535364
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1973a8c86bdeeb958238a0f1f51d67ef911e1e2ebe7da3a37398b6fa039d848c
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06e82d7b0fc70b31ce26ae76fc868ad6d5dedee6eb517427de156064f37232d4
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:641e2cf03d96f20c7b078fdc2839c8f2ef75b3e9f7636d2057eadb2dd500bb51
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1310c737c03908f7e840c532a4fc352f0ded0848e10df4a57050603b2927c200
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20f46ad3e98735530428f01e53a088876607e62a4a62b7b4a3fe9ca7bec2bf91
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_750000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d5c0775f33579c9021a2c0ce0a86269e9ab4ee914935cf51f0fc01227ab8f4e
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_800000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e02ce72e3868bce1e00764b4c201ea61fbd4d28591dd2f3c917f2452da922329
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_850000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8d7b52d0d5f3ac7189adb9f617edaee80143a2859268ade0efaf6518fbf62fa
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/params_900000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:762bda996bc64dc4ffe7aea834d966c28f92b859514e504ccf337189d514beda
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_140918/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/hsxpy3my
|