Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_150000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_200000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_250000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_300000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_350000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_400000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_450000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_500000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/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_071109/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_071109/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,-0.07809314997205298,-0.01082047315269634,-0.07837033226274603,-0.01022845835398253,19.82355500337241,24.152999999997384,0.14,12317.08,-1.32,-840.06,481.06,1.4447380924224853,150000
|
| 3 |
+
0.0,0.0,-0.050342890595788066,0.006611278624519786,-0.0503635871586322,-0.009286025685616445,20.656463670323983,22.524999999997828,0.24,36342.98,-1.24,-782.2,448.5,1.3802689123153686,200000
|
| 4 |
+
0.0,0.0,-0.05123237606353348,-0.002249200657599011,-0.05091669482225137,0.004189182196134851,19.918299110875097,20.98499999999865,0.46,59174.74,-0.7,-673.18,417.7,1.298602113723755,250000
|
| 5 |
+
0.0,0.0,-0.051373243111003046,0.00045118111910678356,-0.05093916648921607,-0.002645963281451505,28.114419950066512,17.401999999999177,0.72,78616.52,-0.34,-521.12,346.04,1.1061526775360107,300000
|
| 6 |
+
0.0,0.0,-0.03938014041279516,-0.0222302809602018,-0.03966171400423419,0.0048451187355446216,30.73803280348981,11.987999999999788,0.92,93415.98,-0.1,-357.26,237.76,0.7788176584243774,350000
|
| 7 |
+
0.0,0.0,-0.03870176697036318,-0.01812500024604946,-0.038955330873978934,-0.015035900208398317,32.15259746878813,12.7569999999996,0.92,106754.34,-0.12,-399.92,253.14,0.823464035987854,400000
|
| 8 |
+
0.0,0.0,-0.0074726300367719475,-0.013484579792810215,-0.007954875776644723,-0.0295934972131096,33.893234967425656,10.007999999999832,0.96,118266.84,-0.08,-301.98,198.16,0.6723643112182617,450000
|
| 9 |
+
0.0,0.0,-0.028530740217567886,-0.03637381711914293,-0.029738077712884774,-0.03951431079368652,34.10562766093108,10.140999999999858,0.98,128829.94,-0.04,-307.92,200.82,0.6742624711990356,500000
|
| 10 |
+
0.0,0.0,-0.011952270553988146,-0.04349646921279102,-0.013453050681094822,-0.04539225836387273,35.098887509201795,8.61999999999976,1.0,138062.76,0.0,-246.72,170.4,0.5715101432800292,550000
|
| 11 |
+
0.0,0.0,-0.005501827008398235,-0.03227316338295174,-0.0063975071437703795,-0.029648157767806056,34.15342719235918,8.908999999999516,0.98,147221.3,-0.02,-260.28,176.18,0.5952225160598755,600000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/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,-0.07809314997205298,-0.01082047315269634,-0.07837033226274603,-0.01022845835398253,19.82355500337241,24.152999999997384,0.14,12317.08,-1.32,-840.06,481.06,1.4447380924224853,150000
|
| 3 |
+
0.0,0.0,-0.050342890595788066,0.006611278624519786,-0.0503635871586322,-0.009286025685616445,20.656463670323983,22.524999999997828,0.24,36342.98,-1.24,-782.2,448.5,1.3802689123153686,200000
|
| 4 |
+
0.0,0.0,-0.05123237606353348,-0.002249200657599011,-0.05091669482225137,0.004189182196134851,19.918299110875097,20.98499999999865,0.46,59174.74,-0.7,-673.18,417.7,1.298602113723755,250000
|
| 5 |
+
0.0,0.0,-0.051373243111003046,0.00045118111910678356,-0.05093916648921607,-0.002645963281451505,28.114419950066512,17.401999999999177,0.72,78616.52,-0.34,-521.12,346.04,1.1061526775360107,300000
|
| 6 |
+
0.0,0.0,-0.03938014041279516,-0.0222302809602018,-0.03966171400423419,0.0048451187355446216,30.73803280348981,11.987999999999788,0.92,93415.98,-0.1,-357.26,237.76,0.7788176584243774,350000
|
| 7 |
+
0.0,0.0,-0.03870176697036318,-0.01812500024604946,-0.038955330873978934,-0.015035900208398317,32.15259746878813,12.7569999999996,0.92,106754.34,-0.12,-399.92,253.14,0.823464035987854,400000
|
| 8 |
+
0.0,0.0,-0.0074726300367719475,-0.013484579792810215,-0.007954875776644723,-0.0295934972131096,33.893234967425656,10.007999999999832,0.96,118266.84,-0.08,-301.98,198.16,0.6723643112182617,450000
|
| 9 |
+
0.0,0.0,-0.028530740217567886,-0.03637381711914293,-0.029738077712884774,-0.03951431079368652,34.10562766093108,10.140999999999858,0.98,128829.94,-0.04,-307.92,200.82,0.6742624711990356,500000
|
| 10 |
+
0.0,0.0,-0.011952270553988146,-0.04349646921279102,-0.013453050681094822,-0.04539225836387273,35.098887509201795,8.61999999999976,1.0,138062.76,0.0,-246.72,170.4,0.5715101432800292,550000
|
| 11 |
+
0.0,0.0,-0.005501827008398235,-0.03227316338295174,-0.0063975071437703795,-0.029648157767806056,34.15342719235918,8.908999999999516,0.98,147221.3,-0.02,-260.28,176.18,0.5952225160598755,600000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/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 |
+
0.22092481,9.287963,-72.698494,-176.78549,-204.99437,0.5292157,-0.414974,64.276596,105000
|
| 3 |
+
0.19701031,7.3101754,-88.38469,-176.46664,-203.82104,0.52423805,-0.58165616,39.519356,110000
|
| 4 |
+
0.19824064,9.64664,-71.58293,-176.34717,-203.20862,0.3167134,-0.32797456,42.66682,115000
|
| 5 |
+
0.19987543,15.964348,-65.60533,-175.54305,-205.91777,0.35642958,-0.36007658,46.7584,120000
|
| 6 |
+
0.19257039,10.686086,-67.452065,-175.29951,-204.26228,0.7803737,-0.51402444,43.205826,125000
|
| 7 |
+
0.19607829,11.677277,-79.066895,-174.4506,-204.84097,0.5510604,-0.5177986,42.03445,130000
|
| 8 |
+
0.17403497,11.408183,-69.20124,-174.7244,-204.03308,0.29208687,-0.28723472,35.406803,135000
|
| 9 |
+
0.18232375,9.695179,-78.89477,-175.37813,-204.7559,0.741723,-0.834034,53.369385,140000
|
| 10 |
+
0.18205333,9.046303,-100.57324,-175.66747,-205.29921,0.3836621,-0.4328657,42.09436,145000
|
| 11 |
+
0.20899731,13.442453,-80.50185,-175.91206,-205.36751,2.6700213,-2.4787269,92.74145,150000
|
| 12 |
+
0.20751202,20.056906,-45.66265,-173.00142,-205.80132,1.4312441,-1.400476,105.44922,155000
|
| 13 |
+
0.22284232,11.10527,-49.123505,-173.59863,-204.36197,0.41861588,-0.42289627,41.605705,160000
|
| 14 |
+
0.17248967,12.759401,-66.97452,-173.83913,-204.91524,2.3952131,-2.170273,69.789154,165000
|
| 15 |
+
0.18833905,17.671616,-22.833368,-170.35132,-204.45074,1.1385738,-1.2136694,75.15944,170000
|
| 16 |
+
0.19357392,12.221278,-83.23754,-172.48996,-204.47643,0.64108163,-0.61478114,53.75587,175000
|
| 17 |
+
0.17727455,15.053647,-66.75508,-174.28981,-206.03188,1.2258148,-1.3396889,85.351234,180000
|
| 18 |
+
0.1703769,15.113681,-73.55383,-173.9215,-204.91302,0.5257943,-0.52761436,48.92303,185000
|
| 19 |
+
0.19346173,10.43468,-59.431496,-171.022,-204.9839,0.42396036,-0.3546123,47.50184,190000
|
| 20 |
+
0.15330458,10.672427,-61.211746,-170.59529,-204.26114,1.2538465,-1.1833152,59.889706,195000
|
| 21 |
+
0.17561394,11.918292,-46.745304,-168.81021,-205.13972,2.0793517,-1.9938055,63.181396,200000
|
| 22 |
+
0.19624406,15.911979,-49.925724,-171.03786,-205.22989,0.67325085,-0.6335746,57.026337,205000
|
| 23 |
+
0.18223408,15.319389,-63.07709,-169.2036,-205.20677,0.6306627,-0.6475238,60.161995,210000
|
| 24 |
+
0.16588482,7.3160386,1.9678297,-168.0948,-204.63075,0.86612034,-0.78443503,45.77465,215000
|
| 25 |
+
0.17754038,11.916513,-54.50445,-170.4549,-204.70215,0.48720792,-0.4011675,51.697235,220000
|
| 26 |
+
0.21230207,8.7748575,-39.523617,-173.61797,-206.22842,0.42282945,-0.37988377,46.960907,225000
|
| 27 |
+
0.17259403,17.908995,-65.43752,-169.91455,-206.12341,0.5738327,-0.45337152,53.121387,230000
|
| 28 |
+
0.19298583,6.8328476,3.4403803,-170.30562,-205.30467,0.30862644,-0.28094456,31.39479,235000
|
| 29 |
+
0.215051,9.235445,-46.74021,-167.17557,-205.18913,1.0628203,-1.0810939,50.573235,240000
|
| 30 |
+
0.18051845,12.522164,-19.907703,-168.32164,-205.05003,0.7336434,-0.7190554,55.53358,245000
|
| 31 |
+
0.19887272,17.059614,-26.836952,-166.93008,-205.16939,2.0463457,-2.0043929,79.76139,250000
|
| 32 |
+
0.16806358,6.888987,-55.043587,-166.7169,-204.46346,0.47028905,-0.49953404,50.79863,255000
|
| 33 |
+
0.19365948,18.585356,-16.366194,-167.75822,-205.23343,1.4476734,-1.2573347,92.17992,260000
|
| 34 |
+
0.18370354,19.937782,-0.9027337,-166.89195,-205.08635,3.0268297,-3.2723687,110.96749,265000
|
| 35 |
+
0.18805546,10.938647,-63.484325,-166.5656,-204.86238,1.2693896,-1.6382014,66.644714,270000
|
| 36 |
+
0.21178171,12.109989,-84.24983,-168.4367,-205.18292,1.0556457,-1.19839,62.781277,275000
|
| 37 |
+
0.18883261,9.986853,4.0408273,-169.19693,-204.77031,2.4359696,-2.4587653,73.40543,280000
|
| 38 |
+
0.18821584,10.757884,-5.842783,-165.64986,-205.3467,0.7416714,-0.65428615,69.160225,285000
|
| 39 |
+
0.1678991,12.683726,-49.195553,-166.27794,-205.29953,0.860694,-0.9170727,57.99099,290000
|
| 40 |
+
0.1857813,8.858765,-63.409245,-164.34497,-206.11893,0.8819759,-0.8438924,46.863335,295000
|
| 41 |
+
0.1935699,10.281029,-26.18455,-164.45758,-204.5761,1.2664256,-1.274539,61.30995,300000
|
| 42 |
+
0.16117023,11.902263,2.0229325,-160.96783,-204.34863,0.38283098,-0.37162685,44.826984,305000
|
| 43 |
+
0.16132948,13.533887,-35.50933,-159.95486,-203.90964,0.61349213,-0.5777253,56.382675,310000
|
| 44 |
+
0.17302398,13.296689,-46.909885,-163.18858,-205.14827,0.59393936,-0.5709367,64.84746,315000
|
| 45 |
+
0.16383103,12.364337,-39.602955,-160.89037,-204.66753,0.4068818,-0.5986005,57.252357,320000
|
| 46 |
+
0.19250327,22.9751,-16.616013,-157.02791,-202.54457,0.8030923,-1.3499603,79.09294,325000
|
| 47 |
+
0.20636632,10.714493,-36.606583,-162.16142,-205.67442,0.3665232,-0.40875527,39.90052,330000
|
| 48 |
+
0.17130359,14.955027,-18.311882,-158.53763,-204.73282,0.83865637,-0.8518282,62.375755,335000
|
| 49 |
+
0.17990717,11.725894,1.5723617,-159.14218,-203.9992,1.2888749,-0.82392836,53.95751,340000
|
| 50 |
+
0.18938322,10.544605,-9.631467,-157.28853,-204.89021,1.0004241,-1.1251612,50.97412,345000
|
| 51 |
+
0.17747933,20.549078,-8.564694,-150.07288,-205.09427,2.5099578,-2.4400594,102.397385,350000
|
| 52 |
+
0.1741857,10.704485,-23.65929,-158.84985,-203.52086,0.71439373,-0.75939345,46.650383,355000
|
| 53 |
+
0.20360872,12.218505,3.8688087,-155.2239,-203.84627,1.8746895,-1.8302611,55.630234,360000
|
| 54 |
+
0.17780855,12.166137,-0.115344405,-157.23808,-203.76492,1.2565371,-1.459961,69.65971,365000
|
| 55 |
+
0.1915835,13.565509,-41.27767,-157.09904,-203.53992,7.514668,-7.3040924,154.9455,370000
|
| 56 |
+
0.19873807,27.976297,-8.725239,-149.11588,-204.31017,0.8582652,-0.9020294,97.52704,375000
|
| 57 |
+
0.18509158,14.358655,-25.886257,-154.3051,-203.52338,0.70012087,-0.6153304,54.808365,380000
|
| 58 |
+
0.17208579,11.653882,-17.879198,-152.93617,-204.99586,3.1058517,-2.901954,111.338104,385000
|
| 59 |
+
0.16387504,13.174601,-31.716242,-151.58589,-204.63347,0.80794233,-0.8557665,57.246445,390000
|
| 60 |
+
0.1693985,10.34274,2.8635259,-148.93498,-203.55034,1.8103368,-2.0835514,71.203926,395000
|
| 61 |
+
0.14395839,11.315379,-10.344255,-154.63806,-203.4481,0.5112778,-0.42888555,48.53271,400000
|
| 62 |
+
0.17669731,12.82786,-6.860077,-151.10735,-205.12766,0.91178876,-0.8558712,55.38537,405000
|
| 63 |
+
0.1736899,32.63975,-9.816763,-149.19444,-205.0469,2.551077,-2.300282,136.11876,410000
|
| 64 |
+
0.19666165,25.100983,-5.914399,-150.12798,-204.33638,0.78100866,-1.1693001,74.20615,415000
|
| 65 |
+
0.17845182,16.660269,-17.202824,-150.31673,-202.1858,0.91258186,-0.77550465,59.720985,420000
|
| 66 |
+
0.17995435,18.065,-19.94416,-149.84198,-205.08606,0.7379911,-0.9508023,75.554214,425000
|
| 67 |
+
0.19468638,15.089368,-13.727713,-147.455,-201.98788,2.8881977,-2.2163248,84.19322,430000
|
| 68 |
+
0.16630888,17.00386,-10.484803,-144.66718,-205.36748,1.5724155,-1.5583748,79.363434,435000
|
| 69 |
+
0.2006185,16.267847,-6.422451,-148.19478,-204.62263,1.760887,-0.8931064,65.340164,440000
|
| 70 |
+
0.1769982,23.125439,-25.33821,-153.18161,-205.58893,0.99193215,-1.147973,68.68703,445000
|
| 71 |
+
0.16783291,14.762225,-8.685497,-142.40428,-203.9729,1.7226423,-1.5442352,68.27591,450000
|
| 72 |
+
0.1601775,15.044601,-6.3886924,-149.14217,-202.86728,0.49294826,-0.54519874,52.404755,455000
|
| 73 |
+
0.19984612,14.821555,-10.549817,-146.25047,-203.34647,1.1325419,-1.163919,78.334885,460000
|
| 74 |
+
0.17011987,20.116175,-5.670882,-148.40532,-205.85457,1.1522771,-1.017202,65.84053,465000
|
| 75 |
+
0.17113456,16.203615,-7.4791384,-147.56133,-205.0818,1.3447672,-1.0404904,78.220085,470000
|
| 76 |
+
0.16878115,14.095054,0.91044635,-146.09393,-203.90372,0.5266623,-0.8467189,59.731712,475000
|
| 77 |
+
0.16855535,21.034767,-6.546904,-146.37366,-205.52354,1.6067731,-2.1851058,72.11552,480000
|
| 78 |
+
0.13643093,11.311225,-17.975323,-147.35307,-204.99973,0.76408046,-0.71859866,52.55117,485000
|
| 79 |
+
0.16845313,15.313593,1.1718853,-149.45319,-205.59831,1.2008618,-1.1560233,78.39767,490000
|
| 80 |
+
0.16753086,13.154602,-9.3515835,-148.03166,-204.56816,3.8802574,-1.4018462,92.55007,495000
|
| 81 |
+
0.15511365,18.62321,-0.51702714,-138.93468,-205.58101,1.8734133,-2.082345,77.44471,500000
|
| 82 |
+
0.18307279,14.80513,-14.79918,-143.26125,-205.22914,0.5821623,-0.626914,50.575882,505000
|
| 83 |
+
0.20010404,15.086049,-9.288646,-148.34123,-204.29936,3.2019358,-3.1412187,84.882935,510000
|
| 84 |
+
0.16482002,16.93778,-15.545438,-141.50223,-201.8327,2.1281056,-0.94277143,64.08988,515000
|
| 85 |
+
0.17558344,9.635551,-27.16997,-140.92027,-203.81122,0.5076295,-0.74564487,46.951244,520000
|
| 86 |
+
0.14962634,19.996252,-3.4638743,-142.38506,-205.61143,1.0720803,-1.1673537,79.38329,525000
|
| 87 |
+
0.18658563,14.354998,-3.3265474,-140.10579,-203.86919,2.0966635,-2.1351779,98.48299,530000
|
| 88 |
+
0.19385192,13.825721,-11.926594,-143.67148,-203.27689,1.1784276,-1.1861335,70.788086,535000
|
| 89 |
+
0.16254464,10.414416,-14.309663,-139.05876,-205.82198,0.85614634,-0.851205,54.730385,540000
|
| 90 |
+
0.18687478,14.16727,2.1077356,-147.41467,-204.478,2.42912,-2.574473,75.34223,545000
|
| 91 |
+
0.14285475,14.087343,5.150196,-140.18578,-202.881,9.65044,-10.355306,155.4137,550000
|
| 92 |
+
0.17680348,14.711786,-14.649434,-141.9928,-205.2442,0.7941604,-0.55256003,59.610004,555000
|
| 93 |
+
0.16168137,13.578119,-8.728877,-138.47614,-204.37636,1.0434266,-1.0818772,49.65183,560000
|
| 94 |
+
0.17742407,15.749619,-18.824987,-141.3557,-203.45052,1.3525028,-1.4493562,72.988174,565000
|
| 95 |
+
0.16459876,13.394078,-2.7536285,-139.2121,-205.35576,0.5309417,-0.49380222,53.522675,570000
|
| 96 |
+
0.18491665,15.368978,-9.940787,-139.82193,-204.16661,1.3199847,-1.2507542,70.05089,575000
|
| 97 |
+
0.16017559,13.985965,1.2212728,-141.1325,-204.6753,2.611091,-2.6376853,98.87508,580000
|
| 98 |
+
0.18684411,17.027042,-16.596285,-141.69121,-204.94807,0.6193341,-0.6434937,63.358273,585000
|
| 99 |
+
0.17875308,21.912985,-5.8353405,-137.43993,-204.64542,0.72354645,-0.9426311,59.53319,590000
|
| 100 |
+
0.1471212,22.019758,-4.1366434,-132.95097,-203.39864,1.9643474,-2.7956858,112.4468,595000
|
| 101 |
+
0.1833157,19.090971,-3.592376,-133.0115,-205.0381,1.1136949,-0.9819796,80.57759,600000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/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 |
+
0.22092481,9.287963,-72.698494,-176.78549,-204.99437,0.5292157,-0.414974,64.276596,105000
|
| 3 |
+
0.19701031,7.3101754,-88.38469,-176.46664,-203.82104,0.52423805,-0.58165616,39.519356,110000
|
| 4 |
+
0.19824064,9.64664,-71.58293,-176.34717,-203.20862,0.3167134,-0.32797456,42.66682,115000
|
| 5 |
+
0.19987543,15.964348,-65.60533,-175.54305,-205.91777,0.35642958,-0.36007658,46.7584,120000
|
| 6 |
+
0.19257039,10.686086,-67.452065,-175.29951,-204.26228,0.7803737,-0.51402444,43.205826,125000
|
| 7 |
+
0.19607829,11.677277,-79.066895,-174.4506,-204.84097,0.5510604,-0.5177986,42.03445,130000
|
| 8 |
+
0.17403497,11.408183,-69.20124,-174.7244,-204.03308,0.29208687,-0.28723472,35.406803,135000
|
| 9 |
+
0.18232375,9.695179,-78.89477,-175.37813,-204.7559,0.741723,-0.834034,53.369385,140000
|
| 10 |
+
0.18205333,9.046303,-100.57324,-175.66747,-205.29921,0.3836621,-0.4328657,42.09436,145000
|
| 11 |
+
0.20899731,13.442453,-80.50185,-175.91206,-205.36751,2.6700213,-2.4787269,92.74145,150000
|
| 12 |
+
0.20751202,20.056906,-45.66265,-173.00142,-205.80132,1.4312441,-1.400476,105.44922,155000
|
| 13 |
+
0.22284232,11.10527,-49.123505,-173.59863,-204.36197,0.41861588,-0.42289627,41.605705,160000
|
| 14 |
+
0.17248967,12.759401,-66.97452,-173.83913,-204.91524,2.3952131,-2.170273,69.789154,165000
|
| 15 |
+
0.18833905,17.671616,-22.833368,-170.35132,-204.45074,1.1385738,-1.2136694,75.15944,170000
|
| 16 |
+
0.19357392,12.221278,-83.23754,-172.48996,-204.47643,0.64108163,-0.61478114,53.75587,175000
|
| 17 |
+
0.17727455,15.053647,-66.75508,-174.28981,-206.03188,1.2258148,-1.3396889,85.351234,180000
|
| 18 |
+
0.1703769,15.113681,-73.55383,-173.9215,-204.91302,0.5257943,-0.52761436,48.92303,185000
|
| 19 |
+
0.19346173,10.43468,-59.431496,-171.022,-204.9839,0.42396036,-0.3546123,47.50184,190000
|
| 20 |
+
0.15330458,10.672427,-61.211746,-170.59529,-204.26114,1.2538465,-1.1833152,59.889706,195000
|
| 21 |
+
0.17561394,11.918292,-46.745304,-168.81021,-205.13972,2.0793517,-1.9938055,63.181396,200000
|
| 22 |
+
0.19624406,15.911979,-49.925724,-171.03786,-205.22989,0.67325085,-0.6335746,57.026337,205000
|
| 23 |
+
0.18223408,15.319389,-63.07709,-169.2036,-205.20677,0.6306627,-0.6475238,60.161995,210000
|
| 24 |
+
0.16588482,7.3160386,1.9678297,-168.0948,-204.63075,0.86612034,-0.78443503,45.77465,215000
|
| 25 |
+
0.17754038,11.916513,-54.50445,-170.4549,-204.70215,0.48720792,-0.4011675,51.697235,220000
|
| 26 |
+
0.21230207,8.7748575,-39.523617,-173.61797,-206.22842,0.42282945,-0.37988377,46.960907,225000
|
| 27 |
+
0.17259403,17.908995,-65.43752,-169.91455,-206.12341,0.5738327,-0.45337152,53.121387,230000
|
| 28 |
+
0.19298583,6.8328476,3.4403803,-170.30562,-205.30467,0.30862644,-0.28094456,31.39479,235000
|
| 29 |
+
0.215051,9.235445,-46.74021,-167.17557,-205.18913,1.0628203,-1.0810939,50.573235,240000
|
| 30 |
+
0.18051845,12.522164,-19.907703,-168.32164,-205.05003,0.7336434,-0.7190554,55.53358,245000
|
| 31 |
+
0.19887272,17.059614,-26.836952,-166.93008,-205.16939,2.0463457,-2.0043929,79.76139,250000
|
| 32 |
+
0.16806358,6.888987,-55.043587,-166.7169,-204.46346,0.47028905,-0.49953404,50.79863,255000
|
| 33 |
+
0.19365948,18.585356,-16.366194,-167.75822,-205.23343,1.4476734,-1.2573347,92.17992,260000
|
| 34 |
+
0.18370354,19.937782,-0.9027337,-166.89195,-205.08635,3.0268297,-3.2723687,110.96749,265000
|
| 35 |
+
0.18805546,10.938647,-63.484325,-166.5656,-204.86238,1.2693896,-1.6382014,66.644714,270000
|
| 36 |
+
0.21178171,12.109989,-84.24983,-168.4367,-205.18292,1.0556457,-1.19839,62.781277,275000
|
| 37 |
+
0.18883261,9.986853,4.0408273,-169.19693,-204.77031,2.4359696,-2.4587653,73.40543,280000
|
| 38 |
+
0.18821584,10.757884,-5.842783,-165.64986,-205.3467,0.7416714,-0.65428615,69.160225,285000
|
| 39 |
+
0.1678991,12.683726,-49.195553,-166.27794,-205.29953,0.860694,-0.9170727,57.99099,290000
|
| 40 |
+
0.1857813,8.858765,-63.409245,-164.34497,-206.11893,0.8819759,-0.8438924,46.863335,295000
|
| 41 |
+
0.1935699,10.281029,-26.18455,-164.45758,-204.5761,1.2664256,-1.274539,61.30995,300000
|
| 42 |
+
0.16117023,11.902263,2.0229325,-160.96783,-204.34863,0.38283098,-0.37162685,44.826984,305000
|
| 43 |
+
0.16132948,13.533887,-35.50933,-159.95486,-203.90964,0.61349213,-0.5777253,56.382675,310000
|
| 44 |
+
0.17302398,13.296689,-46.909885,-163.18858,-205.14827,0.59393936,-0.5709367,64.84746,315000
|
| 45 |
+
0.16383103,12.364337,-39.602955,-160.89037,-204.66753,0.4068818,-0.5986005,57.252357,320000
|
| 46 |
+
0.19250327,22.9751,-16.616013,-157.02791,-202.54457,0.8030923,-1.3499603,79.09294,325000
|
| 47 |
+
0.20636632,10.714493,-36.606583,-162.16142,-205.67442,0.3665232,-0.40875527,39.90052,330000
|
| 48 |
+
0.17130359,14.955027,-18.311882,-158.53763,-204.73282,0.83865637,-0.8518282,62.375755,335000
|
| 49 |
+
0.17990717,11.725894,1.5723617,-159.14218,-203.9992,1.2888749,-0.82392836,53.95751,340000
|
| 50 |
+
0.18938322,10.544605,-9.631467,-157.28853,-204.89021,1.0004241,-1.1251612,50.97412,345000
|
| 51 |
+
0.17747933,20.549078,-8.564694,-150.07288,-205.09427,2.5099578,-2.4400594,102.397385,350000
|
| 52 |
+
0.1741857,10.704485,-23.65929,-158.84985,-203.52086,0.71439373,-0.75939345,46.650383,355000
|
| 53 |
+
0.20360872,12.218505,3.8688087,-155.2239,-203.84627,1.8746895,-1.8302611,55.630234,360000
|
| 54 |
+
0.17780855,12.166137,-0.115344405,-157.23808,-203.76492,1.2565371,-1.459961,69.65971,365000
|
| 55 |
+
0.1915835,13.565509,-41.27767,-157.09904,-203.53992,7.514668,-7.3040924,154.9455,370000
|
| 56 |
+
0.19873807,27.976297,-8.725239,-149.11588,-204.31017,0.8582652,-0.9020294,97.52704,375000
|
| 57 |
+
0.18509158,14.358655,-25.886257,-154.3051,-203.52338,0.70012087,-0.6153304,54.808365,380000
|
| 58 |
+
0.17208579,11.653882,-17.879198,-152.93617,-204.99586,3.1058517,-2.901954,111.338104,385000
|
| 59 |
+
0.16387504,13.174601,-31.716242,-151.58589,-204.63347,0.80794233,-0.8557665,57.246445,390000
|
| 60 |
+
0.1693985,10.34274,2.8635259,-148.93498,-203.55034,1.8103368,-2.0835514,71.203926,395000
|
| 61 |
+
0.14395839,11.315379,-10.344255,-154.63806,-203.4481,0.5112778,-0.42888555,48.53271,400000
|
| 62 |
+
0.17669731,12.82786,-6.860077,-151.10735,-205.12766,0.91178876,-0.8558712,55.38537,405000
|
| 63 |
+
0.1736899,32.63975,-9.816763,-149.19444,-205.0469,2.551077,-2.300282,136.11876,410000
|
| 64 |
+
0.19666165,25.100983,-5.914399,-150.12798,-204.33638,0.78100866,-1.1693001,74.20615,415000
|
| 65 |
+
0.17845182,16.660269,-17.202824,-150.31673,-202.1858,0.91258186,-0.77550465,59.720985,420000
|
| 66 |
+
0.17995435,18.065,-19.94416,-149.84198,-205.08606,0.7379911,-0.9508023,75.554214,425000
|
| 67 |
+
0.19468638,15.089368,-13.727713,-147.455,-201.98788,2.8881977,-2.2163248,84.19322,430000
|
| 68 |
+
0.16630888,17.00386,-10.484803,-144.66718,-205.36748,1.5724155,-1.5583748,79.363434,435000
|
| 69 |
+
0.2006185,16.267847,-6.422451,-148.19478,-204.62263,1.760887,-0.8931064,65.340164,440000
|
| 70 |
+
0.1769982,23.125439,-25.33821,-153.18161,-205.58893,0.99193215,-1.147973,68.68703,445000
|
| 71 |
+
0.16783291,14.762225,-8.685497,-142.40428,-203.9729,1.7226423,-1.5442352,68.27591,450000
|
| 72 |
+
0.1601775,15.044601,-6.3886924,-149.14217,-202.86728,0.49294826,-0.54519874,52.404755,455000
|
| 73 |
+
0.19984612,14.821555,-10.549817,-146.25047,-203.34647,1.1325419,-1.163919,78.334885,460000
|
| 74 |
+
0.17011987,20.116175,-5.670882,-148.40532,-205.85457,1.1522771,-1.017202,65.84053,465000
|
| 75 |
+
0.17113456,16.203615,-7.4791384,-147.56133,-205.0818,1.3447672,-1.0404904,78.220085,470000
|
| 76 |
+
0.16878115,14.095054,0.91044635,-146.09393,-203.90372,0.5266623,-0.8467189,59.731712,475000
|
| 77 |
+
0.16855535,21.034767,-6.546904,-146.37366,-205.52354,1.6067731,-2.1851058,72.11552,480000
|
| 78 |
+
0.13643093,11.311225,-17.975323,-147.35307,-204.99973,0.76408046,-0.71859866,52.55117,485000
|
| 79 |
+
0.16845313,15.313593,1.1718853,-149.45319,-205.59831,1.2008618,-1.1560233,78.39767,490000
|
| 80 |
+
0.16753086,13.154602,-9.3515835,-148.03166,-204.56816,3.8802574,-1.4018462,92.55007,495000
|
| 81 |
+
0.15511365,18.62321,-0.51702714,-138.93468,-205.58101,1.8734133,-2.082345,77.44471,500000
|
| 82 |
+
0.18307279,14.80513,-14.79918,-143.26125,-205.22914,0.5821623,-0.626914,50.575882,505000
|
| 83 |
+
0.20010404,15.086049,-9.288646,-148.34123,-204.29936,3.2019358,-3.1412187,84.882935,510000
|
| 84 |
+
0.16482002,16.93778,-15.545438,-141.50223,-201.8327,2.1281056,-0.94277143,64.08988,515000
|
| 85 |
+
0.17558344,9.635551,-27.16997,-140.92027,-203.81122,0.5076295,-0.74564487,46.951244,520000
|
| 86 |
+
0.14962634,19.996252,-3.4638743,-142.38506,-205.61143,1.0720803,-1.1673537,79.38329,525000
|
| 87 |
+
0.18658563,14.354998,-3.3265474,-140.10579,-203.86919,2.0966635,-2.1351779,98.48299,530000
|
| 88 |
+
0.19385192,13.825721,-11.926594,-143.67148,-203.27689,1.1784276,-1.1861335,70.788086,535000
|
| 89 |
+
0.16254464,10.414416,-14.309663,-139.05876,-205.82198,0.85614634,-0.851205,54.730385,540000
|
| 90 |
+
0.18687478,14.16727,2.1077356,-147.41467,-204.478,2.42912,-2.574473,75.34223,545000
|
| 91 |
+
0.14285475,14.087343,5.150196,-140.18578,-202.881,9.65044,-10.355306,155.4137,550000
|
| 92 |
+
0.17680348,14.711786,-14.649434,-141.9928,-205.2442,0.7941604,-0.55256003,59.610004,555000
|
| 93 |
+
0.16168137,13.578119,-8.728877,-138.47614,-204.37636,1.0434266,-1.0818772,49.65183,560000
|
| 94 |
+
0.17742407,15.749619,-18.824987,-141.3557,-203.45052,1.3525028,-1.4493562,72.988174,565000
|
| 95 |
+
0.16459876,13.394078,-2.7536285,-139.2121,-205.35576,0.5309417,-0.49380222,53.522675,570000
|
| 96 |
+
0.18491665,15.368978,-9.940787,-139.82193,-204.16661,1.3199847,-1.2507542,70.05089,575000
|
| 97 |
+
0.16017559,13.985965,1.2212728,-141.1325,-204.6753,2.611091,-2.6376853,98.87508,580000
|
| 98 |
+
0.18684411,17.027042,-16.596285,-141.69121,-204.94807,0.6193341,-0.6434937,63.358273,585000
|
| 99 |
+
0.17875308,21.912985,-5.8353405,-137.43993,-204.64542,0.72354645,-0.9426311,59.53319,590000
|
| 100 |
+
0.1471212,22.019758,-4.1366434,-132.95097,-203.39864,1.9643474,-2.7956858,112.4468,595000
|
| 101 |
+
0.1833157,19.090971,-3.592376,-133.0115,-205.0381,1.1136949,-0.9819796,80.57759,600000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_150000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b918a9061f87946018e037e5855f1760e406ba90c7fd8276277ced411006fd73
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_200000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f06e87581781f26cfeba399681c1cd0cf2973590ac5f66b2350cb956f305fd5f
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_250000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50ff01313da82e42ba33a9c2afa0ea0bb78ff5639a93d2db5d16ed37e44a23f4
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_300000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cbb995466eea2fdbc65f158c717aaf29bf7c622584ae91d9eb16e5858e7fa86
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:631d6260b4e99d64fb87cc85baf434050e556e49b3623b7e2560b0b8246c2887
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad53e55b4e68a1b7a1c4bf0c81e8ca2c41900b60824114049f531febe0dacc7
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c597b04fb1b72c43abbf21df10594e65935e77e9601416c3aa22825620a010f
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db71c926041b8d983f4003816ef5173a074090d971d9deda0e1fc5c7406e3213
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8863900792dd49cb2ad266a4d7abef2b0899063de317170699c9921cc1dc14b1
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2737c5b0c3968f5a81dc587ae9c9921cfb6f9a2e11d653cbe94231263976ed8
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_071109/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/2t9c3svw
|