Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_350000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_400000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_450000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_500000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_650000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_700000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_750000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_800000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/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/cgql/20260318_202702/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/cgql/20260318_202702/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,-0.044088164848545476,-0.01077973188439914,-0.044092826999315944,-0.0026476256577957916,23.50955147128414,17.78099999999879,0.56,9180.4,-0.56,-540.06,353.62,1.1520432138442993,350000
|
| 3 |
+
0.0,0.0,0.016973526227002645,-0.006486546040241707,0.017335302777291648,0.018108735887752744,31.430684187553098,14.373999999999615,0.82,25440.68,-0.24,-442.9,285.48,0.9606283760070801,400000
|
| 4 |
+
0.0,0.0,0.009911075637317879,-0.018536330426186215,0.009287644048571969,-0.016618525276302618,33.485240770882285,8.77299999999975,1.0,37799.38,0.0,-245.48,173.46,0.627356333732605,450000
|
| 5 |
+
0.0,0.0,0.015311795999861303,-0.024481954545138872,0.014517153513151835,-0.03154217719839091,34.36720386403287,10.640999999999927,0.96,47682.34,-0.04,-313.64,210.82,0.7401925325393677,500000
|
| 6 |
+
0.0,0.0,0.0312606324277912,-0.040624776313474366,0.029445388737223754,-0.05240981521490503,34.00266626848915,9.605999999999499,0.94,58385.1,-0.06,-288.26,190.12,0.6924494600296021,550000
|
| 7 |
+
0.0,0.0,0.04231863916827076,-0.04620695682197926,0.040073644503078584,-0.046588417146291645,35.97492030698574,8.707999999999842,1.0,67460.42,0.0,-252.88,172.16,0.6085301399230957,600000
|
| 8 |
+
0.0,0.0,0.06087365539714472,-0.04599778343754079,0.058475302861784095,-0.04857853802142551,35.48513054438794,8.610999999999766,1.0,76782.24,0.0,-247.04,170.22,0.5884133434295654,650000
|
| 9 |
+
0.0,0.0,0.052633881185876766,-0.050029548735640916,0.049991119033899495,-0.054467462183511624,35.582101543411085,7.767999999999577,0.98,85029.78,-0.04,-229.04,153.36,0.5354673480987548,700000
|
| 10 |
+
0.0,0.0,0.053531588957268596,-0.055211463945725146,0.05138942370835695,-0.057326135984248745,35.45724896000008,8.479999999999524,0.94,93395.88,-0.06,-249.96,167.6,0.5801990127563477,750000
|
| 11 |
+
0.0,0.0,0.05817877686951945,-0.05734742220994463,0.05602061920185786,-0.03859110249138867,35.41307141588633,7.209999999999488,0.98,101273.44,-0.02,-209.84,142.2,0.49601695537567136,800000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/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,-0.044088164848545476,-0.01077973188439914,-0.044092826999315944,-0.0026476256577957916,23.50955147128414,17.78099999999879,0.56,9180.4,-0.56,-540.06,353.62,1.1520432138442993,350000
|
| 3 |
+
0.0,0.0,0.016973526227002645,-0.006486546040241707,0.017335302777291648,0.018108735887752744,31.430684187553098,14.373999999999615,0.82,25440.68,-0.24,-442.9,285.48,0.9606283760070801,400000
|
| 4 |
+
0.0,0.0,0.009911075637317879,-0.018536330426186215,0.009287644048571969,-0.016618525276302618,33.485240770882285,8.77299999999975,1.0,37799.38,0.0,-245.48,173.46,0.627356333732605,450000
|
| 5 |
+
0.0,0.0,0.015311795999861303,-0.024481954545138872,0.014517153513151835,-0.03154217719839091,34.36720386403287,10.640999999999927,0.96,47682.34,-0.04,-313.64,210.82,0.7401925325393677,500000
|
| 6 |
+
0.0,0.0,0.0312606324277912,-0.040624776313474366,0.029445388737223754,-0.05240981521490503,34.00266626848915,9.605999999999499,0.94,58385.1,-0.06,-288.26,190.12,0.6924494600296021,550000
|
| 7 |
+
0.0,0.0,0.04231863916827076,-0.04620695682197926,0.040073644503078584,-0.046588417146291645,35.97492030698574,8.707999999999842,1.0,67460.42,0.0,-252.88,172.16,0.6085301399230957,600000
|
| 8 |
+
0.0,0.0,0.06087365539714472,-0.04599778343754079,0.058475302861784095,-0.04857853802142551,35.48513054438794,8.610999999999766,1.0,76782.24,0.0,-247.04,170.22,0.5884133434295654,650000
|
| 9 |
+
0.0,0.0,0.052633881185876766,-0.050029548735640916,0.049991119033899495,-0.054467462183511624,35.582101543411085,7.767999999999577,0.98,85029.78,-0.04,-229.04,153.36,0.5354673480987548,700000
|
| 10 |
+
0.0,0.0,0.053531588957268596,-0.055211463945725146,0.05138942370835695,-0.057326135984248745,35.45724896000008,8.479999999999524,0.94,93395.88,-0.06,-249.96,167.6,0.5801990127563477,750000
|
| 11 |
+
0.0,0.0,0.05817877686951945,-0.05734742220994463,0.05602061920185786,-0.03859110249138867,35.41307141588633,7.209999999999488,0.98,101273.44,-0.02,-209.84,142.2,0.49601695537567136,800000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/online_agent.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.1696221,14.583948,-79.95071,-178.38101,-204.39644,0.5895841,-0.5857145,42.893295,305000
|
| 3 |
+
0.18361641,12.698093,-75.66108,-177.12514,-204.85342,4.076435,-4.5673385,79.254654,310000
|
| 4 |
+
0.15241197,9.307685,-53.732742,-177.01778,-203.61693,0.6676949,-0.69135505,36.93617,315000
|
| 5 |
+
0.17614792,10.689017,-74.97273,-175.46512,-203.96162,0.41295427,-0.46971756,43.70076,320000
|
| 6 |
+
0.20528771,9.139127,-88.39802,-176.06157,-204.15903,0.26543438,-0.27678084,28.116243,325000
|
| 7 |
+
0.18111812,9.802995,-96.875984,-175.7069,-203.6605,0.8934378,-0.8296731,38.629658,330000
|
| 8 |
+
0.18094087,13.112317,-77.616684,-173.896,-203.81169,1.2184672,-1.1817064,54.442448,335000
|
| 9 |
+
0.17527482,8.623652,-58.991634,-174.25865,-204.2566,0.50054723,-0.5392742,34.154976,340000
|
| 10 |
+
0.1782732,7.413428,-87.70643,-173.24712,-204.19954,0.9061889,-1.0457268,48.19983,345000
|
| 11 |
+
0.18817562,13.337958,-49.88276,-173.10806,-204.0674,1.4789039,-1.4624265,60.841053,350000
|
| 12 |
+
0.19097058,14.632636,-37.66665,-168.37805,-204.62366,0.5584149,-0.5696338,56.590733,355000
|
| 13 |
+
0.21729264,15.389261,-49.64505,-168.96758,-204.04582,0.44492918,-0.4719207,42.563087,360000
|
| 14 |
+
0.17480123,17.5778,-60.349113,-169.56606,-203.62173,1.9866745,-1.7389323,67.882286,365000
|
| 15 |
+
0.18452477,14.562655,-20.998083,-165.26804,-205.95522,0.80337447,-0.5890089,59.834198,370000
|
| 16 |
+
0.20209257,12.3149,-59.70119,-166.90889,-204.12088,1.9204735,-1.6029757,67.39909,375000
|
| 17 |
+
0.18105732,16.16329,-59.73273,-168.47961,-204.54456,1.0208077,-1.0860888,59.72648,380000
|
| 18 |
+
0.17266129,17.083044,-3.4680421,-163.85367,-204.83421,0.60509413,-0.4175795,57.458267,385000
|
| 19 |
+
0.16942412,19.799955,-31.70917,-162.2119,-205.12367,0.9153322,-0.94330066,61.34573,390000
|
| 20 |
+
0.1631334,8.917983,-15.729886,-162.4593,-204.33633,1.0673753,-0.9686627,37.29821,395000
|
| 21 |
+
0.15235226,19.439524,-16.701498,-154.4683,-204.7027,6.520432,-6.207141,148.9144,400000
|
| 22 |
+
0.18195046,15.115578,-21.70125,-160.66145,-204.73717,0.4369219,-0.50714713,47.49465,405000
|
| 23 |
+
0.1820166,15.757644,-20.29245,-156.83334,-204.62065,1.6882108,-2.519059,58.09859,410000
|
| 24 |
+
0.20026174,16.898695,-0.5821613,-154.11372,-204.52803,0.9052162,-0.91815704,65.60861,415000
|
| 25 |
+
0.15867245,21.176868,-31.02718,-159.37871,-204.69469,1.1542472,-0.72230273,74.715744,420000
|
| 26 |
+
0.19596313,14.45464,-9.645053,-158.10107,-203.88821,0.40580073,-0.43064925,49.15489,425000
|
| 27 |
+
0.19207102,27.437544,-15.506002,-157.02403,-203.99606,1.3209664,-1.396983,97.71727,430000
|
| 28 |
+
0.16363962,14.432573,1.9248976,-155.55515,-203.6856,1.2908555,-1.2056507,60.542343,435000
|
| 29 |
+
0.19360705,18.593092,-15.59631,-149.57988,-202.98074,0.53263026,-0.49755666,50.167713,440000
|
| 30 |
+
0.1804604,19.283072,-35.15772,-154.87334,-203.5556,0.7424414,-0.6354055,62.48025,445000
|
| 31 |
+
0.15794797,15.230838,-14.160645,-156.70695,-205.13951,2.0354626,-2.04286,74.8006,450000
|
| 32 |
+
0.17653254,11.160914,-36.12375,-152.2635,-204.44145,0.5996264,-0.44145483,53.836624,455000
|
| 33 |
+
0.19685045,11.857049,-24.05002,-155.31822,-205.1949,0.42385623,-0.4975845,51.204365,460000
|
| 34 |
+
0.16565561,15.8523245,-1.4899207,-150.696,-205.70462,1.8189476,-1.8160608,71.81787,465000
|
| 35 |
+
0.18354687,16.395113,-11.085676,-151.53893,-203.9599,2.7473981,-1.5788863,64.489296,470000
|
| 36 |
+
0.18747045,14.945442,-12.167648,-153.06302,-204.427,1.4258248,-1.505886,64.10987,475000
|
| 37 |
+
0.1899125,19.085308,2.1167467,-150.66943,-204.51181,1.4430156,-1.6041421,99.52258,480000
|
| 38 |
+
0.15787336,15.51738,-9.207779,-147.6374,-203.59097,1.3168116,-1.3993016,59.884644,485000
|
| 39 |
+
0.15209746,12.860207,-14.652618,-147.66634,-203.3097,0.907735,-0.894783,51.893066,490000
|
| 40 |
+
0.17848572,11.753514,-25.73645,-146.65648,-203.05176,0.55662084,-0.5979132,46.167477,495000
|
| 41 |
+
0.15783678,15.726062,-4.690777,-146.15869,-202.38481,0.6747658,-0.63552034,60.22393,500000
|
| 42 |
+
0.19301721,12.925788,-4.6279182,-151.5021,-201.53041,1.9976475,-2.2289078,55.247414,505000
|
| 43 |
+
0.20129535,11.145793,-4.901801,-145.15672,-201.29338,2.2503338,-2.383741,60.50036,510000
|
| 44 |
+
0.17523596,9.395565,-12.355534,-146.42041,-203.74481,0.8306545,-0.85612446,52.483208,515000
|
| 45 |
+
0.18491504,14.859448,-32.76616,-147.09628,-202.69374,1.085611,-1.2590259,57.2393,520000
|
| 46 |
+
0.16531608,28.60172,-16.873405,-143.09026,-199.89664,1.473506,-1.5240083,97.676094,525000
|
| 47 |
+
0.20389888,15.426389,-9.583631,-145.45044,-202.7411,1.3906136,-1.8463752,80.49508,530000
|
| 48 |
+
0.21080463,15.953618,-7.773838,-141.64867,-201.31378,0.6096132,-0.6952588,66.04927,535000
|
| 49 |
+
0.15959239,13.73925,3.5185866,-144.05534,-202.44987,0.95873237,-0.6710117,53.966167,540000
|
| 50 |
+
0.19825348,21.678839,-13.325268,-142.38802,-205.16466,7.793348,-5.240345,112.39647,545000
|
| 51 |
+
0.15674877,19.2363,-3.9659007,-136.35834,-201.19865,1.1024578,-1.045081,66.30255,550000
|
| 52 |
+
0.18476364,13.627559,-16.5586,-144.12749,-200.44739,0.71112,-0.69441015,57.06603,555000
|
| 53 |
+
0.16479439,17.110744,1.5934964,-139.01973,-201.90445,1.0462892,-1.1026694,55.65805,560000
|
| 54 |
+
0.1998527,17.471342,-3.546574,-144.50316,-201.96507,0.87839025,-0.96019894,55.035065,565000
|
| 55 |
+
0.17844418,19.145868,-8.449066,-139.81677,-201.15881,0.9005922,-0.7813469,66.92517,570000
|
| 56 |
+
0.21550211,17.37438,-5.1330705,-139.03108,-202.7133,0.629131,-1.1771924,69.60122,575000
|
| 57 |
+
0.17290212,23.506765,-20.623684,-143.37325,-203.82355,0.50479823,-0.65054655,62.13573,580000
|
| 58 |
+
0.16338338,14.702765,1.9475734,-136.46696,-202.50076,1.4972112,-0.9761119,56.226906,585000
|
| 59 |
+
0.15905508,18.760458,-1.8821013,-134.80443,-201.89224,0.5877921,-0.62909347,50.5141,590000
|
| 60 |
+
0.1669834,14.577278,1.688434,-136.8439,-207.37949,0.3596966,-0.37433982,46.1361,595000
|
| 61 |
+
0.15903653,27.727768,0.8390779,-139.1934,-201.15698,2.0343044,-1.8770529,99.33508,600000
|
| 62 |
+
0.17227295,15.979433,-7.5333548,-141.34846,-204.80283,0.890558,-0.45060268,50.41317,605000
|
| 63 |
+
0.17214987,19.322712,-13.529199,-137.13596,-203.11992,0.8661846,-0.5430204,55.60134,610000
|
| 64 |
+
0.16429755,21.948248,-8.48888,-138.83945,-200.8272,3.727535,-3.217524,96.74706,615000
|
| 65 |
+
0.16387501,15.262244,-4.9828033,-139.95775,-200.84503,3.6881835,-3.5457213,80.860504,620000
|
| 66 |
+
0.15286675,22.802526,-9.532267,-138.71556,-205.07216,0.74097705,-0.68002665,63.372322,625000
|
| 67 |
+
0.14820218,12.877565,-0.33360338,-136.78505,-202.67961,1.199309,-0.8634275,51.756813,630000
|
| 68 |
+
0.16244161,20.166365,-5.0059223,-135.81244,-204.13391,1.0018194,-0.9403141,70.98638,635000
|
| 69 |
+
0.17238021,13.810279,-10.944619,-139.70518,-203.40564,5.297089,-9.884139,85.05505,640000
|
| 70 |
+
0.15259793,12.130202,-8.3649435,-145.23294,-203.44064,1.9900649,-2.2065873,53.592384,645000
|
| 71 |
+
0.18421765,21.023924,-4.1243577,-131.88014,-204.72888,1.595141,-1.3518763,65.179634,650000
|
| 72 |
+
0.18636665,15.180315,-0.25296938,-138.55986,-201.70969,0.59568787,-0.6038515,44.124706,655000
|
| 73 |
+
0.19085574,16.073084,-2.732079,-135.06831,-203.3064,0.5680857,-0.61217284,61.968254,660000
|
| 74 |
+
0.18606299,13.84265,-16.766804,-139.9102,-205.19458,0.81670886,-1.1667701,75.48669,665000
|
| 75 |
+
0.15941751,13.22879,-2.7820768,-136.11374,-203.85223,1.0818052,-1.0609747,53.318832,670000
|
| 76 |
+
0.17459995,16.74568,0.8633211,-136.0753,-203.1712,0.68902296,-0.9633679,57.974396,675000
|
| 77 |
+
0.15865266,8.202517,0.14747877,-135.54068,-202.17743,1.1033105,-0.9799423,53.16801,680000
|
| 78 |
+
0.15486117,14.184583,-6.4659786,-132.95308,-203.83658,2.141078,-2.443536,57.71408,685000
|
| 79 |
+
0.1620773,19.552803,-8.780789,-138.38298,-203.22128,0.6721744,-0.77972615,58.96795,690000
|
| 80 |
+
0.19234538,17.495077,-5.8026037,-138.55624,-204.15546,1.2369518,-1.2301173,50.25677,695000
|
| 81 |
+
0.18428501,13.220229,-4.3890452,-132.44695,-201.61772,2.2543335,-1.5633534,58.821854,700000
|
| 82 |
+
0.18528937,16.835001,-10.880981,-133.58157,-203.53413,0.71514183,-0.73040843,56.616505,705000
|
| 83 |
+
0.16834393,17.631384,-5.20528,-138.8546,-201.85152,0.88982624,-0.8321296,66.94229,710000
|
| 84 |
+
0.1645082,13.971068,-5.2518725,-134.11966,-202.95575,2.313042,-2.0532305,56.798733,715000
|
| 85 |
+
0.16054824,15.725547,0.6779158,-135.49689,-204.81287,0.5686581,-0.77207416,49.321365,720000
|
| 86 |
+
0.1491563,17.456259,-4.246301,-133.60574,-206.24084,2.4076474,-4.427112,122.78345,725000
|
| 87 |
+
0.16079646,16.841867,-6.844969,-132.2475,-203.1409,4.7036242,-5.624679,141.34317,730000
|
| 88 |
+
0.16163519,28.642698,-0.14387359,-135.76419,-203.49684,1.0516877,-1.0124618,77.85248,735000
|
| 89 |
+
0.14247933,12.830912,-6.187802,-129.5087,-202.77928,0.5814253,-0.5530016,46.045864,740000
|
| 90 |
+
0.15155612,11.725707,-2.1626968,-134.79646,-203.18723,0.48475522,-0.7916965,43.120502,745000
|
| 91 |
+
0.1580571,13.731763,-4.5915837,-132.56407,-203.98233,3.2809741,-6.9024606,97.14336,750000
|
| 92 |
+
0.16237563,10.4581,-5.9840574,-134.63326,-199.56299,1.2898166,-1.1343324,50.79565,755000
|
| 93 |
+
0.17952779,14.334867,-2.583793,-131.73604,-202.41971,0.41173753,-0.79415286,46.76423,760000
|
| 94 |
+
0.17100899,15.988879,9.459294,-131.5031,-202.23398,2.0992823,-1.5421213,56.33833,765000
|
| 95 |
+
0.16990149,15.605838,-0.9761844,-130.60046,-205.0716,0.59087837,-1.0438545,72.077286,770000
|
| 96 |
+
0.15314235,13.088864,-2.155512,-127.212845,-202.78,3.003752,-3.406925,76.05948,775000
|
| 97 |
+
0.1611397,18.274605,0.03270328,-131.7419,-202.98756,0.5749098,-0.6857718,50.68961,780000
|
| 98 |
+
0.17635565,11.094909,-4.5655446,-129.43378,-203.76486,0.76659346,-0.8964755,59.88378,785000
|
| 99 |
+
0.15973097,18.6037,-1.6363375,-128.27432,-204.37305,0.53064334,-0.37403008,47.62345,790000
|
| 100 |
+
0.14848945,22.945013,-1.4848025,-124.38544,-203.4258,8.255608,-8.137012,160.84332,795000
|
| 101 |
+
0.15807825,17.878492,0.3447596,-123.93926,-205.58302,1.0028296,-0.950502,68.75777,800000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/online_agent_sv.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.1696221,14.583948,-79.95071,-178.38101,-204.39644,0.5895841,-0.5857145,42.893295,305000
|
| 3 |
+
0.18361641,12.698093,-75.66108,-177.12514,-204.85342,4.076435,-4.5673385,79.254654,310000
|
| 4 |
+
0.15241197,9.307685,-53.732742,-177.01778,-203.61693,0.6676949,-0.69135505,36.93617,315000
|
| 5 |
+
0.17614792,10.689017,-74.97273,-175.46512,-203.96162,0.41295427,-0.46971756,43.70076,320000
|
| 6 |
+
0.20528771,9.139127,-88.39802,-176.06157,-204.15903,0.26543438,-0.27678084,28.116243,325000
|
| 7 |
+
0.18111812,9.802995,-96.875984,-175.7069,-203.6605,0.8934378,-0.8296731,38.629658,330000
|
| 8 |
+
0.18094087,13.112317,-77.616684,-173.896,-203.81169,1.2184672,-1.1817064,54.442448,335000
|
| 9 |
+
0.17527482,8.623652,-58.991634,-174.25865,-204.2566,0.50054723,-0.5392742,34.154976,340000
|
| 10 |
+
0.1782732,7.413428,-87.70643,-173.24712,-204.19954,0.9061889,-1.0457268,48.19983,345000
|
| 11 |
+
0.18817562,13.337958,-49.88276,-173.10806,-204.0674,1.4789039,-1.4624265,60.841053,350000
|
| 12 |
+
0.19097058,14.632636,-37.66665,-168.37805,-204.62366,0.5584149,-0.5696338,56.590733,355000
|
| 13 |
+
0.21729264,15.389261,-49.64505,-168.96758,-204.04582,0.44492918,-0.4719207,42.563087,360000
|
| 14 |
+
0.17480123,17.5778,-60.349113,-169.56606,-203.62173,1.9866745,-1.7389323,67.882286,365000
|
| 15 |
+
0.18452477,14.562655,-20.998083,-165.26804,-205.95522,0.80337447,-0.5890089,59.834198,370000
|
| 16 |
+
0.20209257,12.3149,-59.70119,-166.90889,-204.12088,1.9204735,-1.6029757,67.39909,375000
|
| 17 |
+
0.18105732,16.16329,-59.73273,-168.47961,-204.54456,1.0208077,-1.0860888,59.72648,380000
|
| 18 |
+
0.17266129,17.083044,-3.4680421,-163.85367,-204.83421,0.60509413,-0.4175795,57.458267,385000
|
| 19 |
+
0.16942412,19.799955,-31.70917,-162.2119,-205.12367,0.9153322,-0.94330066,61.34573,390000
|
| 20 |
+
0.1631334,8.917983,-15.729886,-162.4593,-204.33633,1.0673753,-0.9686627,37.29821,395000
|
| 21 |
+
0.15235226,19.439524,-16.701498,-154.4683,-204.7027,6.520432,-6.207141,148.9144,400000
|
| 22 |
+
0.18195046,15.115578,-21.70125,-160.66145,-204.73717,0.4369219,-0.50714713,47.49465,405000
|
| 23 |
+
0.1820166,15.757644,-20.29245,-156.83334,-204.62065,1.6882108,-2.519059,58.09859,410000
|
| 24 |
+
0.20026174,16.898695,-0.5821613,-154.11372,-204.52803,0.9052162,-0.91815704,65.60861,415000
|
| 25 |
+
0.15867245,21.176868,-31.02718,-159.37871,-204.69469,1.1542472,-0.72230273,74.715744,420000
|
| 26 |
+
0.19596313,14.45464,-9.645053,-158.10107,-203.88821,0.40580073,-0.43064925,49.15489,425000
|
| 27 |
+
0.19207102,27.437544,-15.506002,-157.02403,-203.99606,1.3209664,-1.396983,97.71727,430000
|
| 28 |
+
0.16363962,14.432573,1.9248976,-155.55515,-203.6856,1.2908555,-1.2056507,60.542343,435000
|
| 29 |
+
0.19360705,18.593092,-15.59631,-149.57988,-202.98074,0.53263026,-0.49755666,50.167713,440000
|
| 30 |
+
0.1804604,19.283072,-35.15772,-154.87334,-203.5556,0.7424414,-0.6354055,62.48025,445000
|
| 31 |
+
0.15794797,15.230838,-14.160645,-156.70695,-205.13951,2.0354626,-2.04286,74.8006,450000
|
| 32 |
+
0.17653254,11.160914,-36.12375,-152.2635,-204.44145,0.5996264,-0.44145483,53.836624,455000
|
| 33 |
+
0.19685045,11.857049,-24.05002,-155.31822,-205.1949,0.42385623,-0.4975845,51.204365,460000
|
| 34 |
+
0.16565561,15.8523245,-1.4899207,-150.696,-205.70462,1.8189476,-1.8160608,71.81787,465000
|
| 35 |
+
0.18354687,16.395113,-11.085676,-151.53893,-203.9599,2.7473981,-1.5788863,64.489296,470000
|
| 36 |
+
0.18747045,14.945442,-12.167648,-153.06302,-204.427,1.4258248,-1.505886,64.10987,475000
|
| 37 |
+
0.1899125,19.085308,2.1167467,-150.66943,-204.51181,1.4430156,-1.6041421,99.52258,480000
|
| 38 |
+
0.15787336,15.51738,-9.207779,-147.6374,-203.59097,1.3168116,-1.3993016,59.884644,485000
|
| 39 |
+
0.15209746,12.860207,-14.652618,-147.66634,-203.3097,0.907735,-0.894783,51.893066,490000
|
| 40 |
+
0.17848572,11.753514,-25.73645,-146.65648,-203.05176,0.55662084,-0.5979132,46.167477,495000
|
| 41 |
+
0.15783678,15.726062,-4.690777,-146.15869,-202.38481,0.6747658,-0.63552034,60.22393,500000
|
| 42 |
+
0.19301721,12.925788,-4.6279182,-151.5021,-201.53041,1.9976475,-2.2289078,55.247414,505000
|
| 43 |
+
0.20129535,11.145793,-4.901801,-145.15672,-201.29338,2.2503338,-2.383741,60.50036,510000
|
| 44 |
+
0.17523596,9.395565,-12.355534,-146.42041,-203.74481,0.8306545,-0.85612446,52.483208,515000
|
| 45 |
+
0.18491504,14.859448,-32.76616,-147.09628,-202.69374,1.085611,-1.2590259,57.2393,520000
|
| 46 |
+
0.16531608,28.60172,-16.873405,-143.09026,-199.89664,1.473506,-1.5240083,97.676094,525000
|
| 47 |
+
0.20389888,15.426389,-9.583631,-145.45044,-202.7411,1.3906136,-1.8463752,80.49508,530000
|
| 48 |
+
0.21080463,15.953618,-7.773838,-141.64867,-201.31378,0.6096132,-0.6952588,66.04927,535000
|
| 49 |
+
0.15959239,13.73925,3.5185866,-144.05534,-202.44987,0.95873237,-0.6710117,53.966167,540000
|
| 50 |
+
0.19825348,21.678839,-13.325268,-142.38802,-205.16466,7.793348,-5.240345,112.39647,545000
|
| 51 |
+
0.15674877,19.2363,-3.9659007,-136.35834,-201.19865,1.1024578,-1.045081,66.30255,550000
|
| 52 |
+
0.18476364,13.627559,-16.5586,-144.12749,-200.44739,0.71112,-0.69441015,57.06603,555000
|
| 53 |
+
0.16479439,17.110744,1.5934964,-139.01973,-201.90445,1.0462892,-1.1026694,55.65805,560000
|
| 54 |
+
0.1998527,17.471342,-3.546574,-144.50316,-201.96507,0.87839025,-0.96019894,55.035065,565000
|
| 55 |
+
0.17844418,19.145868,-8.449066,-139.81677,-201.15881,0.9005922,-0.7813469,66.92517,570000
|
| 56 |
+
0.21550211,17.37438,-5.1330705,-139.03108,-202.7133,0.629131,-1.1771924,69.60122,575000
|
| 57 |
+
0.17290212,23.506765,-20.623684,-143.37325,-203.82355,0.50479823,-0.65054655,62.13573,580000
|
| 58 |
+
0.16338338,14.702765,1.9475734,-136.46696,-202.50076,1.4972112,-0.9761119,56.226906,585000
|
| 59 |
+
0.15905508,18.760458,-1.8821013,-134.80443,-201.89224,0.5877921,-0.62909347,50.5141,590000
|
| 60 |
+
0.1669834,14.577278,1.688434,-136.8439,-207.37949,0.3596966,-0.37433982,46.1361,595000
|
| 61 |
+
0.15903653,27.727768,0.8390779,-139.1934,-201.15698,2.0343044,-1.8770529,99.33508,600000
|
| 62 |
+
0.17227295,15.979433,-7.5333548,-141.34846,-204.80283,0.890558,-0.45060268,50.41317,605000
|
| 63 |
+
0.17214987,19.322712,-13.529199,-137.13596,-203.11992,0.8661846,-0.5430204,55.60134,610000
|
| 64 |
+
0.16429755,21.948248,-8.48888,-138.83945,-200.8272,3.727535,-3.217524,96.74706,615000
|
| 65 |
+
0.16387501,15.262244,-4.9828033,-139.95775,-200.84503,3.6881835,-3.5457213,80.860504,620000
|
| 66 |
+
0.15286675,22.802526,-9.532267,-138.71556,-205.07216,0.74097705,-0.68002665,63.372322,625000
|
| 67 |
+
0.14820218,12.877565,-0.33360338,-136.78505,-202.67961,1.199309,-0.8634275,51.756813,630000
|
| 68 |
+
0.16244161,20.166365,-5.0059223,-135.81244,-204.13391,1.0018194,-0.9403141,70.98638,635000
|
| 69 |
+
0.17238021,13.810279,-10.944619,-139.70518,-203.40564,5.297089,-9.884139,85.05505,640000
|
| 70 |
+
0.15259793,12.130202,-8.3649435,-145.23294,-203.44064,1.9900649,-2.2065873,53.592384,645000
|
| 71 |
+
0.18421765,21.023924,-4.1243577,-131.88014,-204.72888,1.595141,-1.3518763,65.179634,650000
|
| 72 |
+
0.18636665,15.180315,-0.25296938,-138.55986,-201.70969,0.59568787,-0.6038515,44.124706,655000
|
| 73 |
+
0.19085574,16.073084,-2.732079,-135.06831,-203.3064,0.5680857,-0.61217284,61.968254,660000
|
| 74 |
+
0.18606299,13.84265,-16.766804,-139.9102,-205.19458,0.81670886,-1.1667701,75.48669,665000
|
| 75 |
+
0.15941751,13.22879,-2.7820768,-136.11374,-203.85223,1.0818052,-1.0609747,53.318832,670000
|
| 76 |
+
0.17459995,16.74568,0.8633211,-136.0753,-203.1712,0.68902296,-0.9633679,57.974396,675000
|
| 77 |
+
0.15865266,8.202517,0.14747877,-135.54068,-202.17743,1.1033105,-0.9799423,53.16801,680000
|
| 78 |
+
0.15486117,14.184583,-6.4659786,-132.95308,-203.83658,2.141078,-2.443536,57.71408,685000
|
| 79 |
+
0.1620773,19.552803,-8.780789,-138.38298,-203.22128,0.6721744,-0.77972615,58.96795,690000
|
| 80 |
+
0.19234538,17.495077,-5.8026037,-138.55624,-204.15546,1.2369518,-1.2301173,50.25677,695000
|
| 81 |
+
0.18428501,13.220229,-4.3890452,-132.44695,-201.61772,2.2543335,-1.5633534,58.821854,700000
|
| 82 |
+
0.18528937,16.835001,-10.880981,-133.58157,-203.53413,0.71514183,-0.73040843,56.616505,705000
|
| 83 |
+
0.16834393,17.631384,-5.20528,-138.8546,-201.85152,0.88982624,-0.8321296,66.94229,710000
|
| 84 |
+
0.1645082,13.971068,-5.2518725,-134.11966,-202.95575,2.313042,-2.0532305,56.798733,715000
|
| 85 |
+
0.16054824,15.725547,0.6779158,-135.49689,-204.81287,0.5686581,-0.77207416,49.321365,720000
|
| 86 |
+
0.1491563,17.456259,-4.246301,-133.60574,-206.24084,2.4076474,-4.427112,122.78345,725000
|
| 87 |
+
0.16079646,16.841867,-6.844969,-132.2475,-203.1409,4.7036242,-5.624679,141.34317,730000
|
| 88 |
+
0.16163519,28.642698,-0.14387359,-135.76419,-203.49684,1.0516877,-1.0124618,77.85248,735000
|
| 89 |
+
0.14247933,12.830912,-6.187802,-129.5087,-202.77928,0.5814253,-0.5530016,46.045864,740000
|
| 90 |
+
0.15155612,11.725707,-2.1626968,-134.79646,-203.18723,0.48475522,-0.7916965,43.120502,745000
|
| 91 |
+
0.1580571,13.731763,-4.5915837,-132.56407,-203.98233,3.2809741,-6.9024606,97.14336,750000
|
| 92 |
+
0.16237563,10.4581,-5.9840574,-134.63326,-199.56299,1.2898166,-1.1343324,50.79565,755000
|
| 93 |
+
0.17952779,14.334867,-2.583793,-131.73604,-202.41971,0.41173753,-0.79415286,46.76423,760000
|
| 94 |
+
0.17100899,15.988879,9.459294,-131.5031,-202.23398,2.0992823,-1.5421213,56.33833,765000
|
| 95 |
+
0.16990149,15.605838,-0.9761844,-130.60046,-205.0716,0.59087837,-1.0438545,72.077286,770000
|
| 96 |
+
0.15314235,13.088864,-2.155512,-127.212845,-202.78,3.003752,-3.406925,76.05948,775000
|
| 97 |
+
0.1611397,18.274605,0.03270328,-131.7419,-202.98756,0.5749098,-0.6857718,50.68961,780000
|
| 98 |
+
0.17635565,11.094909,-4.5655446,-129.43378,-203.76486,0.76659346,-0.8964755,59.88378,785000
|
| 99 |
+
0.15973097,18.6037,-1.6363375,-128.27432,-204.37305,0.53064334,-0.37403008,47.62345,790000
|
| 100 |
+
0.14848945,22.945013,-1.4848025,-124.38544,-203.4258,8.255608,-8.137012,160.84332,795000
|
| 101 |
+
0.15807825,17.878492,0.3447596,-123.93926,-205.58302,1.0028296,-0.950502,68.75777,800000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:849aff9d8ee1e237959db6a4b7721f19e93b8ace74b593f2792b0aaa0c5e6a8e
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ec1b7e3bb17b6b52d68025c419a0207df17ffae11ceabb9304ca8c6b82525e9
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8996e9781e4539bce7ee70c4ff517ed0335ebc1d57268d507e80c00f5a3e198
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0682eabffda87b4cc5e7778b7e803569afe96c7cca038acda80cfddb6352aef2
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c909dbeee447649aa0d48e66ce6c0b74ddbdc255005af7f153b5a751eb01f39
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b9a8f0754ab1e3a4ba25cfc751c8fad6c46405848d50eb78d422e11e0a119e0
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:167a2b917399dc5c1550f64ff5276a80ac7ce5b257f96b6528e8e4b65685aa0f
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47feab9d2bc301834e5de4c21d51fc10472a93b62fae36445d6aabdd8838b6f2
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_750000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3541bd288832491aba7955d6c426b961dcdabc270d30581a1ad34e1447e56df9
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/params_800000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62e484b26e825827cc2474790d861b4af26f0329e027da0333770b28087e3560
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_202702/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/idmgazax
|