Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_1000000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_1050000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_1100000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_650000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_700000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_750000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_800000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_850000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_900000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_950000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/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_163056/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_163056/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,-0.06769850464229198,-0.0773070220360722,-0.06483343849760302,0.06170862831921828,25.36300466494119,22.472999999997427,0.18,11144.62,-1.48,-813.26,447.46,1.297273373603821,650000
|
| 3 |
+
0.0,0.0,-0.018926488318887026,-0.0020062017234185646,-0.017566524187541326,-0.012209125231132965,23.084346186321643,16.820999999998183,0.44,30615.58,-0.92,-535.0,334.42,0.9994024848937988,700000
|
| 4 |
+
0.0,0.0,-0.07941582896120487,0.022735294298023602,-0.07908624386426492,-0.008018658122330442,25.050270936744425,11.083999999999023,0.74,46656.14,-0.44,-339.12,219.68,0.6453950595855713,750000
|
| 5 |
+
0.0,0.0,-0.06295075310137291,0.0012214745979555316,-0.061082723400187625,0.015298132423262537,28.294647754359197,8.457999999999224,0.78,56603.08,-0.36,-261.54,167.16,0.49475409984588625,800000
|
| 6 |
+
0.0,0.0,-0.06636254682598411,0.03785484639080257,-0.06340210707545414,0.011042342724737602,29.56260792647675,7.532999999999351,0.82,65638.42,-0.26,-235.4,148.66,0.4405153942108154,850000
|
| 7 |
+
0.0,0.0,-0.08628831941280678,0.0713242331436033,-0.08319484203933769,0.0440165861973406,27.676723859049837,9.257999999999171,0.74,72587.68,-0.4,-281.2,183.16,0.5408564615249634,900000
|
| 8 |
+
0.0,0.0,-0.09132089214419742,0.039040325111332826,-0.08875474692752386,0.02653022222848566,29.570754172009572,7.4399999999994,0.82,80717.9,-0.3,-235.8,146.8,0.4508566427230835,950000
|
| 9 |
+
0.0,0.0,-0.0842196765447962,0.057287817525721894,-0.08241568458901202,0.030627761154687308,30.82480855847611,3.977999999999754,0.94,87073.12,-0.1,-120.8,77.56,0.24141863346099854,1000000
|
| 10 |
+
0.0,0.0,-0.061197051673542564,0.06919335143395793,-0.058031657565323067,0.10289402795225976,32.82999723614761,3.2499999999998663,0.98,90559.2,-0.04,-97.12,63.0,0.20756758689880372,1050000
|
| 11 |
+
0.0,0.0,-0.07162503290752935,0.0461177026415997,-0.06950057743295886,0.038357590506500665,33.20566905288123,3.6199999999998083,0.96,93902.1,-0.08,-117.46,70.4,0.22960326194763184,1100000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/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,-0.06769850464229198,-0.0773070220360722,-0.06483343849760302,0.06170862831921828,25.36300466494119,22.472999999997427,0.18,11144.62,-1.48,-813.26,447.46,1.297273373603821,650000
|
| 3 |
+
0.0,0.0,-0.018926488318887026,-0.0020062017234185646,-0.017566524187541326,-0.012209125231132965,23.084346186321643,16.820999999998183,0.44,30615.58,-0.92,-535.0,334.42,0.9994024848937988,700000
|
| 4 |
+
0.0,0.0,-0.07941582896120487,0.022735294298023602,-0.07908624386426492,-0.008018658122330442,25.050270936744425,11.083999999999023,0.74,46656.14,-0.44,-339.12,219.68,0.6453950595855713,750000
|
| 5 |
+
0.0,0.0,-0.06295075310137291,0.0012214745979555316,-0.061082723400187625,0.015298132423262537,28.294647754359197,8.457999999999224,0.78,56603.08,-0.36,-261.54,167.16,0.49475409984588625,800000
|
| 6 |
+
0.0,0.0,-0.06636254682598411,0.03785484639080257,-0.06340210707545414,0.011042342724737602,29.56260792647675,7.532999999999351,0.82,65638.42,-0.26,-235.4,148.66,0.4405153942108154,850000
|
| 7 |
+
0.0,0.0,-0.08628831941280678,0.0713242331436033,-0.08319484203933769,0.0440165861973406,27.676723859049837,9.257999999999171,0.74,72587.68,-0.4,-281.2,183.16,0.5408564615249634,900000
|
| 8 |
+
0.0,0.0,-0.09132089214419742,0.039040325111332826,-0.08875474692752386,0.02653022222848566,29.570754172009572,7.4399999999994,0.82,80717.9,-0.3,-235.8,146.8,0.4508566427230835,950000
|
| 9 |
+
0.0,0.0,-0.0842196765447962,0.057287817525721894,-0.08241568458901202,0.030627761154687308,30.82480855847611,3.977999999999754,0.94,87073.12,-0.1,-120.8,77.56,0.24141863346099854,1000000
|
| 10 |
+
0.0,0.0,-0.061197051673542564,0.06919335143395793,-0.058031657565323067,0.10289402795225976,32.82999723614761,3.2499999999998663,0.98,90559.2,-0.04,-97.12,63.0,0.20756758689880372,1050000
|
| 11 |
+
0.0,0.0,-0.07162503290752935,0.0461177026415997,-0.06950057743295886,0.038357590506500665,33.20566905288123,3.6199999999998083,0.96,93902.1,-0.08,-117.46,70.4,0.22960326194763184,1100000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/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 |
+
434.14294,0.93425584,0.34796596,-9.083289,-51.265713,-76.166626,3.372315,-4.652626,115.69891,605000
|
| 3 |
+
562.87494,1.0036653,1.158358,-10.724568,-63.74832,-109.10415,2.956037,-2.283589,65.08718,610000
|
| 4 |
+
617.66876,0.83808124,0.91753656,-16.839571,-68.51613,-111.73221,13.127279,-12.497402,208.79256,615000
|
| 5 |
+
627.1068,0.93167114,2.5418222,-7.510864,-69.46161,-141.87454,6.6876855,-14.183579,191.34514,620000
|
| 6 |
+
654.5248,0.8101819,1.1747034,-25.6826,-72.26156,-160.46767,4.3902225,-3.9901485,89.1843,625000
|
| 7 |
+
658.9732,0.94644034,1.5387685,-13.056337,-72.74865,-148.03366,4.650146,-4.6667156,112.80083,630000
|
| 8 |
+
691.25183,0.9466008,1.3045913,-18.073982,-75.77899,-132.9818,2.151525,-4.0928307,101.787636,635000
|
| 9 |
+
715.65985,0.9442215,1.9547323,-22.292274,-78.225945,-144.26698,2.1533914,-3.2947783,83.921844,640000
|
| 10 |
+
748.174,1.0027481,1.3911537,-19.539383,-81.28954,-160.53761,3.2822127,-3.2338705,71.68933,645000
|
| 11 |
+
734.2968,1.0461617,2.6536336,-25.056152,-80.140144,-155.32794,7.5176234,-7.972514,132.20477,650000
|
| 12 |
+
722.59753,0.88574386,2.0695872,-18.685194,-79.00695,-159.547,5.5930314,-7.035993,135.0348,655000
|
| 13 |
+
729.24854,1.1262625,1.63672,-9.406507,-79.59984,-175.1855,2.3654516,-2.2804575,84.018936,660000
|
| 14 |
+
739.3651,0.8255472,2.2501352,-14.350083,-80.05552,-171.70909,4.625283,-4.809354,129.94293,665000
|
| 15 |
+
707.8151,0.9282313,1.9359524,-9.27391,-77.18297,-162.13004,1.9519492,-2.3652866,66.10638,670000
|
| 16 |
+
732.4702,0.8538679,2.6592872,-18.454182,-80.25321,-170.68063,2.036547,-4.261804,134.56395,675000
|
| 17 |
+
773.5324,1.0117173,1.5212322,-16.887371,-83.93245,-163.12166,3.626223,-4.163772,80.278694,680000
|
| 18 |
+
771.33887,1.0681928,1.814563,-25.605316,-83.38309,-172.13142,10.231879,-6.6918626,165.98227,685000
|
| 19 |
+
803.31635,1.1454105,2.6793993,-15.44661,-86.40189,-177.53757,2.109995,-4.9605846,84.391525,690000
|
| 20 |
+
803.2327,1.1991464,2.5442493,-18.707731,-86.53031,-174.0784,2.177446,-2.8869305,105.014435,695000
|
| 21 |
+
799.56006,1.2552981,1.8487877,-9.565937,-85.99082,-179.24622,3.368957,-2.2336822,90.79179,700000
|
| 22 |
+
801.7547,1.223191,2.7570071,-17.264582,-86.40015,-164.65283,2.357706,-3.0991344,103.11526,705000
|
| 23 |
+
804.0228,1.0594566,2.3583622,-17.115955,-86.77403,-176.81104,2.042641,-5.87693,93.22948,710000
|
| 24 |
+
786.1158,1.0996914,2.0062516,1.7243636,-84.71233,-178.5611,4.575255,-2.6275804,105.57688,715000
|
| 25 |
+
815.9678,1.2073476,2.5276048,-21.406124,-87.75828,-161.33339,5.487659,-3.9841204,96.76759,720000
|
| 26 |
+
841.8824,1.2322485,2.5796163,-16.692787,-90.4934,-178.6417,4.91563,-3.1081803,121.37596,725000
|
| 27 |
+
841.6898,1.4972546,2.6909368,-12.403051,-90.12391,-167.85252,4.345421,-4.411536,204.63362,730000
|
| 28 |
+
814.4505,1.4320481,2.6777642,2.1957095,-88.126,-179.76704,11.9109535,-13.900737,344.23477,735000
|
| 29 |
+
803.1835,0.99325204,2.8357065,-9.620932,-87.1233,-167.66325,3.3375905,-5.9353423,103.67445,740000
|
| 30 |
+
825.0029,1.1997471,2.662199,3.0394554,-88.49059,-163.09502,2.8977292,-2.8358483,106.551926,745000
|
| 31 |
+
824.07965,0.8780776,2.7778974,-2.296451,-88.263626,-172.04301,31.746737,-50.73118,416.25494,750000
|
| 32 |
+
838.1435,0.9271937,2.597803,-22.856857,-90.44594,-182.2891,2.5641322,-3.5319417,111.061745,755000
|
| 33 |
+
827.8906,1.3438593,3.65747,-17.253311,-88.81103,-170.1269,5.419157,-3.7391944,152.15582,760000
|
| 34 |
+
832.93823,0.98937744,2.3719716,-1.4812765,-89.26675,-165.33052,3.5563703,-3.1113791,99.60062,765000
|
| 35 |
+
814.02893,1.0987337,2.288025,-17.829672,-87.627884,-169.17267,1.9600296,-1.9967555,81.706375,770000
|
| 36 |
+
858.59955,0.8650442,2.9448705,-1.0174873,-92.287384,-173.1364,3.3141274,-3.0848532,91.81235,775000
|
| 37 |
+
859.87054,1.0578227,2.0045278,1.5572424,-91.77232,-172.2334,10.498485,-10.378243,297.062,780000
|
| 38 |
+
813.2576,1.1372912,3.7929597,-8.762899,-87.62809,-172.64711,6.670669,-6.7598953,232.49794,785000
|
| 39 |
+
829.99603,1.0165147,3.7226799,-11.057379,-88.82849,-168.43489,10.661511,-15.699259,271.04984,790000
|
| 40 |
+
853.2582,1.0363536,3.9094841,-20.587511,-91.51975,-172.34135,7.4725957,-13.710127,236.58095,795000
|
| 41 |
+
806.813,0.9284691,2.9028049,-3.637452,-86.94954,-167.1083,4.3336186,-3.8052776,135.07693,800000
|
| 42 |
+
817.75195,1.0335014,3.060678,-9.333281,-88.151535,-173.84474,75.76068,-76.15399,521.94147,805000
|
| 43 |
+
832.9491,0.95495236,3.2198243,-17.773157,-88.96404,-176.20564,2.025281,-2.9704292,103.18617,810000
|
| 44 |
+
788.8141,1.116118,5.744355,3.7929301,-84.638954,-179.98354,16.709278,-16.671154,280.70645,815000
|
| 45 |
+
819.13763,1.4454439,2.8896084,-6.861808,-87.54414,-173.59114,4.6355834,-3.7618158,104.34439,820000
|
| 46 |
+
819.373,0.9689402,4.034754,-11.826736,-87.86853,-174.5298,5.058416,-3.3457558,133.83577,825000
|
| 47 |
+
857.43207,1.0935688,2.0180333,-8.783673,-91.89794,-172.60512,2.7706566,-2.0706503,92.22322,830000
|
| 48 |
+
841.6701,1.628108,3.109014,-7.477362,-89.43697,-166.62456,7.454136,-15.044071,248.54562,835000
|
| 49 |
+
835.72974,1.3041837,2.9065053,1.4860642,-89.12907,-174.62029,6.1255,-5.0326877,148.09718,840000
|
| 50 |
+
817.0528,0.87435794,4.1297593,-16.402893,-88.02538,-170.94254,15.196315,-12.659268,379.89047,845000
|
| 51 |
+
816.6266,1.1834238,4.2415566,-8.160686,-87.56773,-174.24188,8.548012,-12.015875,263.65,850000
|
| 52 |
+
868.43646,0.90215164,2.8287115,-13.43597,-92.590126,-171.72284,8.8849535,-9.808154,176.01334,855000
|
| 53 |
+
801.5735,0.96204567,3.0947475,1.9366653,-86.06125,-169.38718,4.8837967,-5.2922835,161.39854,860000
|
| 54 |
+
832.1422,0.86473715,2.3683858,-2.0353105,-89.104774,-179.94505,6.6306744,-5.197513,143.25517,865000
|
| 55 |
+
815.28613,1.1185197,2.9591653,-5.825882,-87.87494,-175.91504,7.609048,-7.8541613,153.23647,870000
|
| 56 |
+
839.7625,0.96920156,4.897299,-14.285614,-89.71207,-174.78426,16.85096,-17.28326,188.12784,875000
|
| 57 |
+
827.3715,1.2070332,5.9105124,-3.2723565,-89.04259,-181.97359,6.369671,-6.4119945,204.88661,880000
|
| 58 |
+
847.51,1.2418157,5.0148845,-4.771305,-90.932976,-171.86447,15.210716,-17.427809,374.9498,885000
|
| 59 |
+
828.5773,0.9201516,6.5825915,-1.3984616,-88.93126,-174.97887,2.6879122,-3.8230338,132.56664,890000
|
| 60 |
+
816.5826,1.0807669,2.5439765,0.8674401,-87.33587,-180.66853,2.4891243,-3.911482,127.46078,895000
|
| 61 |
+
809.88135,0.777575,3.7239063,-2.7504222,-87.128105,-177.43625,2.162445,-2.8349667,125.79939,900000
|
| 62 |
+
835.81104,0.9220474,5.3694015,-19.801233,-90.107025,-171.15932,1.95555,-2.6898525,133.82626,905000
|
| 63 |
+
786.69556,0.93782645,2.9915636,-4.7470794,-84.72421,-177.2414,8.249756,-9.197311,245.10114,910000
|
| 64 |
+
800.97363,0.7963799,4.3470225,3.3174238,-86.528244,-179.94398,4.9625955,-4.878296,190.7142,915000
|
| 65 |
+
773.68665,1.2021322,2.554643,-2.7729769,-83.35835,-164.97299,2.5162208,-2.3636503,88.58694,920000
|
| 66 |
+
851.37085,1.1202109,3.1057508,-11.103623,-90.84154,-175.01796,15.801125,-10.794919,150.59232,925000
|
| 67 |
+
848.56104,1.1741846,4.8058176,2.4353776,-90.370766,-172.28932,4.262996,-4.3017297,120.82619,930000
|
| 68 |
+
804.47186,1.2191849,4.2312226,-2.3178427,-86.385315,-169.76813,3.5890493,-2.6031528,128.7398,935000
|
| 69 |
+
775.2834,1.019462,4.7494087,-2.5926795,-83.73118,-165.79121,5.4812155,-6.669617,214.70851,940000
|
| 70 |
+
816.0254,0.9324888,2.5895777,-3.0106914,-87.95562,-169.08266,5.2864895,-5.810695,131.47894,945000
|
| 71 |
+
820.9521,1.3975497,3.5530572,1.9439282,-87.89941,-171.1765,12.887703,-6.180868,230.5586,950000
|
| 72 |
+
842.69775,0.9060603,3.3419473,-0.60015,-89.73,-174.69157,8.635907,-10.340825,184.24852,955000
|
| 73 |
+
812.13947,0.9475347,5.3957667,-0.76084363,-87.03115,-179.63292,7.0227475,-6.5819974,215.40375,960000
|
| 74 |
+
816.1321,0.9601753,2.7452054,-9.955758,-87.45429,-173.4077,3.7399244,-3.4863563,132.2075,965000
|
| 75 |
+
827.1425,1.5089625,4.0468855,0.43516773,-88.249535,-165.88693,5.616756,-5.0160346,181.34515,970000
|
| 76 |
+
770.55914,1.1447656,4.5371337,1.3463888,-82.73242,-175.7278,3.2809901,-4.9042687,136.02914,975000
|
| 77 |
+
815.4869,1.0558323,5.2122397,-3.2427416,-87.60265,-173.0432,62.672005,-84.45174,674.4756,980000
|
| 78 |
+
798.94653,1.3630441,2.725444,-6.98343,-85.665276,-174.30391,6.985837,-4.5512505,155.42564,985000
|
| 79 |
+
814.97797,1.0302389,1.9031929,-10.6490965,-87.44713,-172.41122,2.7446873,-3.7003555,109.99562,990000
|
| 80 |
+
818.97656,0.9140985,2.9580414,-1.5252699,-88.13249,-167.2146,4.9237146,-4.805582,162.28679,995000
|
| 81 |
+
768.8554,1.2453926,3.8138351,-0.65682137,-82.57149,-173.83777,3.2080934,-3.0009108,138.21237,1000000
|
| 82 |
+
815.5199,1.2022153,3.4152787,-1.5532421,-86.74057,-180.76889,17.12318,-21.43623,467.35248,1005000
|
| 83 |
+
810.69104,1.1544406,4.0620303,1.386386,-86.744255,-167.44606,5.95604,-6.180534,132.29893,1010000
|
| 84 |
+
804.5585,1.110605,2.9948177,-3.595895,-86.23385,-173.51172,6.7196712,-7.142971,185.05328,1015000
|
| 85 |
+
777.5281,1.179712,2.6551006,5.529713,-83.92607,-173.94182,1.8251935,-2.8517032,99.77095,1020000
|
| 86 |
+
816.5834,0.9963535,3.258868,-7.7505884,-87.40513,-174.07115,20.417871,-58.26588,512.2823,1025000
|
| 87 |
+
785.1731,0.8939949,3.3176625,6.098199,-84.386955,-166.07643,14.474429,-13.945319,259.13934,1030000
|
| 88 |
+
799.0207,1.3814907,3.1565964,-3.5394108,-85.896324,-180.74792,12.283465,-10.228398,259.51447,1035000
|
| 89 |
+
812.1297,0.9257755,2.9513485,-1.3816719,-87.24784,-178.9357,5.024671,-8.403029,174.36877,1040000
|
| 90 |
+
848.8009,1.194016,3.0832303,-6.3031654,-90.60148,-175.63234,6.343365,-4.4395947,132.43408,1045000
|
| 91 |
+
824.2469,1.0114899,3.4455101,-0.2425049,-88.38389,-178.48918,4.4904995,-4.3165584,154.74953,1050000
|
| 92 |
+
802.2786,0.8633478,12.966987,0.6125128,-86.142876,-181.17772,10.915232,-27.051268,287.21875,1055000
|
| 93 |
+
813.95605,1.0677556,5.3992624,-4.3106065,-87.160576,-175.26782,3.3200955,-4.3457317,173.91496,1060000
|
| 94 |
+
775.7184,0.9680231,4.3713083,-4.6616135,-83.48939,-174.9847,32.448997,-31.001192,417.94653,1065000
|
| 95 |
+
770.3447,1.4640088,4.17556,-0.094278276,-83.37023,-187.43849,5.797046,-2.5507314,145.9885,1070000
|
| 96 |
+
781.67706,0.9995682,2.8630593,1.0851294,-83.80535,-165.96536,25.423273,-17.975815,370.42523,1075000
|
| 97 |
+
753.9105,0.93571955,2.7480805,2.0991611,-81.39345,-171.96637,6.2909956,-7.9497213,191.81776,1080000
|
| 98 |
+
761.72797,1.0621315,2.3539588,-0.014353871,-81.969536,-168.3485,1.8296916,-2.5411644,90.46594,1085000
|
| 99 |
+
810.48444,0.8363762,5.123904,-2.0782027,-86.46462,-166.0178,11.410303,-5.4818153,232.72687,1090000
|
| 100 |
+
760.75916,1.0387887,4.469214,0.09100434,-82.0076,-165.29402,13.026721,-11.782981,227.50327,1095000
|
| 101 |
+
781.7133,1.2383239,2.700714,-1.6973774,-83.52551,-175.96962,117.17309,-342.26715,1853.3307,1100000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/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 |
+
434.14294,0.93425584,0.34796596,-9.083289,-51.265713,-76.166626,3.372315,-4.652626,115.69891,605000
|
| 3 |
+
562.87494,1.0036653,1.158358,-10.724568,-63.74832,-109.10415,2.956037,-2.283589,65.08718,610000
|
| 4 |
+
617.66876,0.83808124,0.91753656,-16.839571,-68.51613,-111.73221,13.127279,-12.497402,208.79256,615000
|
| 5 |
+
627.1068,0.93167114,2.5418222,-7.510864,-69.46161,-141.87454,6.6876855,-14.183579,191.34514,620000
|
| 6 |
+
654.5248,0.8101819,1.1747034,-25.6826,-72.26156,-160.46767,4.3902225,-3.9901485,89.1843,625000
|
| 7 |
+
658.9732,0.94644034,1.5387685,-13.056337,-72.74865,-148.03366,4.650146,-4.6667156,112.80083,630000
|
| 8 |
+
691.25183,0.9466008,1.3045913,-18.073982,-75.77899,-132.9818,2.151525,-4.0928307,101.787636,635000
|
| 9 |
+
715.65985,0.9442215,1.9547323,-22.292274,-78.225945,-144.26698,2.1533914,-3.2947783,83.921844,640000
|
| 10 |
+
748.174,1.0027481,1.3911537,-19.539383,-81.28954,-160.53761,3.2822127,-3.2338705,71.68933,645000
|
| 11 |
+
734.2968,1.0461617,2.6536336,-25.056152,-80.140144,-155.32794,7.5176234,-7.972514,132.20477,650000
|
| 12 |
+
722.59753,0.88574386,2.0695872,-18.685194,-79.00695,-159.547,5.5930314,-7.035993,135.0348,655000
|
| 13 |
+
729.24854,1.1262625,1.63672,-9.406507,-79.59984,-175.1855,2.3654516,-2.2804575,84.018936,660000
|
| 14 |
+
739.3651,0.8255472,2.2501352,-14.350083,-80.05552,-171.70909,4.625283,-4.809354,129.94293,665000
|
| 15 |
+
707.8151,0.9282313,1.9359524,-9.27391,-77.18297,-162.13004,1.9519492,-2.3652866,66.10638,670000
|
| 16 |
+
732.4702,0.8538679,2.6592872,-18.454182,-80.25321,-170.68063,2.036547,-4.261804,134.56395,675000
|
| 17 |
+
773.5324,1.0117173,1.5212322,-16.887371,-83.93245,-163.12166,3.626223,-4.163772,80.278694,680000
|
| 18 |
+
771.33887,1.0681928,1.814563,-25.605316,-83.38309,-172.13142,10.231879,-6.6918626,165.98227,685000
|
| 19 |
+
803.31635,1.1454105,2.6793993,-15.44661,-86.40189,-177.53757,2.109995,-4.9605846,84.391525,690000
|
| 20 |
+
803.2327,1.1991464,2.5442493,-18.707731,-86.53031,-174.0784,2.177446,-2.8869305,105.014435,695000
|
| 21 |
+
799.56006,1.2552981,1.8487877,-9.565937,-85.99082,-179.24622,3.368957,-2.2336822,90.79179,700000
|
| 22 |
+
801.7547,1.223191,2.7570071,-17.264582,-86.40015,-164.65283,2.357706,-3.0991344,103.11526,705000
|
| 23 |
+
804.0228,1.0594566,2.3583622,-17.115955,-86.77403,-176.81104,2.042641,-5.87693,93.22948,710000
|
| 24 |
+
786.1158,1.0996914,2.0062516,1.7243636,-84.71233,-178.5611,4.575255,-2.6275804,105.57688,715000
|
| 25 |
+
815.9678,1.2073476,2.5276048,-21.406124,-87.75828,-161.33339,5.487659,-3.9841204,96.76759,720000
|
| 26 |
+
841.8824,1.2322485,2.5796163,-16.692787,-90.4934,-178.6417,4.91563,-3.1081803,121.37596,725000
|
| 27 |
+
841.6898,1.4972546,2.6909368,-12.403051,-90.12391,-167.85252,4.345421,-4.411536,204.63362,730000
|
| 28 |
+
814.4505,1.4320481,2.6777642,2.1957095,-88.126,-179.76704,11.9109535,-13.900737,344.23477,735000
|
| 29 |
+
803.1835,0.99325204,2.8357065,-9.620932,-87.1233,-167.66325,3.3375905,-5.9353423,103.67445,740000
|
| 30 |
+
825.0029,1.1997471,2.662199,3.0394554,-88.49059,-163.09502,2.8977292,-2.8358483,106.551926,745000
|
| 31 |
+
824.07965,0.8780776,2.7778974,-2.296451,-88.263626,-172.04301,31.746737,-50.73118,416.25494,750000
|
| 32 |
+
838.1435,0.9271937,2.597803,-22.856857,-90.44594,-182.2891,2.5641322,-3.5319417,111.061745,755000
|
| 33 |
+
827.8906,1.3438593,3.65747,-17.253311,-88.81103,-170.1269,5.419157,-3.7391944,152.15582,760000
|
| 34 |
+
832.93823,0.98937744,2.3719716,-1.4812765,-89.26675,-165.33052,3.5563703,-3.1113791,99.60062,765000
|
| 35 |
+
814.02893,1.0987337,2.288025,-17.829672,-87.627884,-169.17267,1.9600296,-1.9967555,81.706375,770000
|
| 36 |
+
858.59955,0.8650442,2.9448705,-1.0174873,-92.287384,-173.1364,3.3141274,-3.0848532,91.81235,775000
|
| 37 |
+
859.87054,1.0578227,2.0045278,1.5572424,-91.77232,-172.2334,10.498485,-10.378243,297.062,780000
|
| 38 |
+
813.2576,1.1372912,3.7929597,-8.762899,-87.62809,-172.64711,6.670669,-6.7598953,232.49794,785000
|
| 39 |
+
829.99603,1.0165147,3.7226799,-11.057379,-88.82849,-168.43489,10.661511,-15.699259,271.04984,790000
|
| 40 |
+
853.2582,1.0363536,3.9094841,-20.587511,-91.51975,-172.34135,7.4725957,-13.710127,236.58095,795000
|
| 41 |
+
806.813,0.9284691,2.9028049,-3.637452,-86.94954,-167.1083,4.3336186,-3.8052776,135.07693,800000
|
| 42 |
+
817.75195,1.0335014,3.060678,-9.333281,-88.151535,-173.84474,75.76068,-76.15399,521.94147,805000
|
| 43 |
+
832.9491,0.95495236,3.2198243,-17.773157,-88.96404,-176.20564,2.025281,-2.9704292,103.18617,810000
|
| 44 |
+
788.8141,1.116118,5.744355,3.7929301,-84.638954,-179.98354,16.709278,-16.671154,280.70645,815000
|
| 45 |
+
819.13763,1.4454439,2.8896084,-6.861808,-87.54414,-173.59114,4.6355834,-3.7618158,104.34439,820000
|
| 46 |
+
819.373,0.9689402,4.034754,-11.826736,-87.86853,-174.5298,5.058416,-3.3457558,133.83577,825000
|
| 47 |
+
857.43207,1.0935688,2.0180333,-8.783673,-91.89794,-172.60512,2.7706566,-2.0706503,92.22322,830000
|
| 48 |
+
841.6701,1.628108,3.109014,-7.477362,-89.43697,-166.62456,7.454136,-15.044071,248.54562,835000
|
| 49 |
+
835.72974,1.3041837,2.9065053,1.4860642,-89.12907,-174.62029,6.1255,-5.0326877,148.09718,840000
|
| 50 |
+
817.0528,0.87435794,4.1297593,-16.402893,-88.02538,-170.94254,15.196315,-12.659268,379.89047,845000
|
| 51 |
+
816.6266,1.1834238,4.2415566,-8.160686,-87.56773,-174.24188,8.548012,-12.015875,263.65,850000
|
| 52 |
+
868.43646,0.90215164,2.8287115,-13.43597,-92.590126,-171.72284,8.8849535,-9.808154,176.01334,855000
|
| 53 |
+
801.5735,0.96204567,3.0947475,1.9366653,-86.06125,-169.38718,4.8837967,-5.2922835,161.39854,860000
|
| 54 |
+
832.1422,0.86473715,2.3683858,-2.0353105,-89.104774,-179.94505,6.6306744,-5.197513,143.25517,865000
|
| 55 |
+
815.28613,1.1185197,2.9591653,-5.825882,-87.87494,-175.91504,7.609048,-7.8541613,153.23647,870000
|
| 56 |
+
839.7625,0.96920156,4.897299,-14.285614,-89.71207,-174.78426,16.85096,-17.28326,188.12784,875000
|
| 57 |
+
827.3715,1.2070332,5.9105124,-3.2723565,-89.04259,-181.97359,6.369671,-6.4119945,204.88661,880000
|
| 58 |
+
847.51,1.2418157,5.0148845,-4.771305,-90.932976,-171.86447,15.210716,-17.427809,374.9498,885000
|
| 59 |
+
828.5773,0.9201516,6.5825915,-1.3984616,-88.93126,-174.97887,2.6879122,-3.8230338,132.56664,890000
|
| 60 |
+
816.5826,1.0807669,2.5439765,0.8674401,-87.33587,-180.66853,2.4891243,-3.911482,127.46078,895000
|
| 61 |
+
809.88135,0.777575,3.7239063,-2.7504222,-87.128105,-177.43625,2.162445,-2.8349667,125.79939,900000
|
| 62 |
+
835.81104,0.9220474,5.3694015,-19.801233,-90.107025,-171.15932,1.95555,-2.6898525,133.82626,905000
|
| 63 |
+
786.69556,0.93782645,2.9915636,-4.7470794,-84.72421,-177.2414,8.249756,-9.197311,245.10114,910000
|
| 64 |
+
800.97363,0.7963799,4.3470225,3.3174238,-86.528244,-179.94398,4.9625955,-4.878296,190.7142,915000
|
| 65 |
+
773.68665,1.2021322,2.554643,-2.7729769,-83.35835,-164.97299,2.5162208,-2.3636503,88.58694,920000
|
| 66 |
+
851.37085,1.1202109,3.1057508,-11.103623,-90.84154,-175.01796,15.801125,-10.794919,150.59232,925000
|
| 67 |
+
848.56104,1.1741846,4.8058176,2.4353776,-90.370766,-172.28932,4.262996,-4.3017297,120.82619,930000
|
| 68 |
+
804.47186,1.2191849,4.2312226,-2.3178427,-86.385315,-169.76813,3.5890493,-2.6031528,128.7398,935000
|
| 69 |
+
775.2834,1.019462,4.7494087,-2.5926795,-83.73118,-165.79121,5.4812155,-6.669617,214.70851,940000
|
| 70 |
+
816.0254,0.9324888,2.5895777,-3.0106914,-87.95562,-169.08266,5.2864895,-5.810695,131.47894,945000
|
| 71 |
+
820.9521,1.3975497,3.5530572,1.9439282,-87.89941,-171.1765,12.887703,-6.180868,230.5586,950000
|
| 72 |
+
842.69775,0.9060603,3.3419473,-0.60015,-89.73,-174.69157,8.635907,-10.340825,184.24852,955000
|
| 73 |
+
812.13947,0.9475347,5.3957667,-0.76084363,-87.03115,-179.63292,7.0227475,-6.5819974,215.40375,960000
|
| 74 |
+
816.1321,0.9601753,2.7452054,-9.955758,-87.45429,-173.4077,3.7399244,-3.4863563,132.2075,965000
|
| 75 |
+
827.1425,1.5089625,4.0468855,0.43516773,-88.249535,-165.88693,5.616756,-5.0160346,181.34515,970000
|
| 76 |
+
770.55914,1.1447656,4.5371337,1.3463888,-82.73242,-175.7278,3.2809901,-4.9042687,136.02914,975000
|
| 77 |
+
815.4869,1.0558323,5.2122397,-3.2427416,-87.60265,-173.0432,62.672005,-84.45174,674.4756,980000
|
| 78 |
+
798.94653,1.3630441,2.725444,-6.98343,-85.665276,-174.30391,6.985837,-4.5512505,155.42564,985000
|
| 79 |
+
814.97797,1.0302389,1.9031929,-10.6490965,-87.44713,-172.41122,2.7446873,-3.7003555,109.99562,990000
|
| 80 |
+
818.97656,0.9140985,2.9580414,-1.5252699,-88.13249,-167.2146,4.9237146,-4.805582,162.28679,995000
|
| 81 |
+
768.8554,1.2453926,3.8138351,-0.65682137,-82.57149,-173.83777,3.2080934,-3.0009108,138.21237,1000000
|
| 82 |
+
815.5199,1.2022153,3.4152787,-1.5532421,-86.74057,-180.76889,17.12318,-21.43623,467.35248,1005000
|
| 83 |
+
810.69104,1.1544406,4.0620303,1.386386,-86.744255,-167.44606,5.95604,-6.180534,132.29893,1010000
|
| 84 |
+
804.5585,1.110605,2.9948177,-3.595895,-86.23385,-173.51172,6.7196712,-7.142971,185.05328,1015000
|
| 85 |
+
777.5281,1.179712,2.6551006,5.529713,-83.92607,-173.94182,1.8251935,-2.8517032,99.77095,1020000
|
| 86 |
+
816.5834,0.9963535,3.258868,-7.7505884,-87.40513,-174.07115,20.417871,-58.26588,512.2823,1025000
|
| 87 |
+
785.1731,0.8939949,3.3176625,6.098199,-84.386955,-166.07643,14.474429,-13.945319,259.13934,1030000
|
| 88 |
+
799.0207,1.3814907,3.1565964,-3.5394108,-85.896324,-180.74792,12.283465,-10.228398,259.51447,1035000
|
| 89 |
+
812.1297,0.9257755,2.9513485,-1.3816719,-87.24784,-178.9357,5.024671,-8.403029,174.36877,1040000
|
| 90 |
+
848.8009,1.194016,3.0832303,-6.3031654,-90.60148,-175.63234,6.343365,-4.4395947,132.43408,1045000
|
| 91 |
+
824.2469,1.0114899,3.4455101,-0.2425049,-88.38389,-178.48918,4.4904995,-4.3165584,154.74953,1050000
|
| 92 |
+
802.2786,0.8633478,12.966987,0.6125128,-86.142876,-181.17772,10.915232,-27.051268,287.21875,1055000
|
| 93 |
+
813.95605,1.0677556,5.3992624,-4.3106065,-87.160576,-175.26782,3.3200955,-4.3457317,173.91496,1060000
|
| 94 |
+
775.7184,0.9680231,4.3713083,-4.6616135,-83.48939,-174.9847,32.448997,-31.001192,417.94653,1065000
|
| 95 |
+
770.3447,1.4640088,4.17556,-0.094278276,-83.37023,-187.43849,5.797046,-2.5507314,145.9885,1070000
|
| 96 |
+
781.67706,0.9995682,2.8630593,1.0851294,-83.80535,-165.96536,25.423273,-17.975815,370.42523,1075000
|
| 97 |
+
753.9105,0.93571955,2.7480805,2.0991611,-81.39345,-171.96637,6.2909956,-7.9497213,191.81776,1080000
|
| 98 |
+
761.72797,1.0621315,2.3539588,-0.014353871,-81.969536,-168.3485,1.8296916,-2.5411644,90.46594,1085000
|
| 99 |
+
810.48444,0.8363762,5.123904,-2.0782027,-86.46462,-166.0178,11.410303,-5.4818153,232.72687,1090000
|
| 100 |
+
760.75916,1.0387887,4.469214,0.09100434,-82.0076,-165.29402,13.026721,-11.782981,227.50327,1095000
|
| 101 |
+
781.7133,1.2383239,2.700714,-1.6973774,-83.52551,-175.96962,117.17309,-342.26715,1853.3307,1100000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_1000000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba5f6d95f5da53e1c9ef1c086a189cfe4c8640180e0652b24ad2e7353debeeea
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_1050000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74d793c6e44279d840f88810ef8695ce331eb4f9fe24cd822f5523bdbb41940f
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_1100000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb9b8958750ca903c01c9227ca4de9eef47c677a57872ad5c3243e53c7d78cc2
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d54d6dbe97a1cbedcb8ac16dc450d537fbfc0c619c98b0145cd35d47bf15db2
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23b54c0e1a5ba827e14a80766765413c3b0b0efd6d8f5a38a7dd5c039c44592a
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_750000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60bc26dfc621fe67928d7397c7df431d2468fd84307a33da90bbcf790e8f564
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_800000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f12257c62799919afc28794d4b4e236a2cd4931c826541ade9ade32fd210f13b
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_850000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5e1d53404431917d240634e50aaea08f54a36a337b5775835d36854ae35f395
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_900000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6313409743caa078053ee7222e3740a4bc9d82c7cbac39ba85e9716760766435
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/params_950000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8273521257b0d10f4992d0c79d4c4047c46ea161f0790457f4bd12202cba0d8
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_163056/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/hm5ghxvt
|