Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_150000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_200000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_250000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_300000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_350000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_400000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_450000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_500000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/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_103639/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_103639/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,-0.134661379852989,0.10937709507377723,-0.1345329568922793,0.014164350233702088,18.123991195968692,21.975999999997512,0.18,10999.58,-1.24,-693.32,437.52,1.2593972635269166,150000
|
| 3 |
+
0.0,0.0,-0.07585795706703459,-0.014075406358252513,-0.07267561097613208,0.08263556310296005,22.562611121968704,18.549999999997965,0.34,32267.76,-0.88,-518.56,369.0,1.0607236814498902,200000
|
| 4 |
+
0.0,0.0,-0.07326103287353859,0.04804643990190737,-0.07109954354373692,0.035933126365884645,23.657339239077583,12.59699999999863,0.6,49062.7,-0.56,-366.38,249.94,0.7245305776596069,250000
|
| 5 |
+
0.0,0.0,-0.06546673174502798,0.08171762814680322,-0.06433850966926245,0.028495575677165277,28.640551525194777,11.183999999998866,0.66,61392.9,-0.5,-330.28,221.68,0.662751693725586,300000
|
| 6 |
+
0.0,0.0,-0.05561211470543549,0.04114122682993105,-0.0524820670632247,0.05138706368435286,31.912290966914405,6.538999999999478,0.86,69877.78,-0.2,-197.74,128.78,0.40421002864837646,350000
|
| 7 |
+
0.0,0.0,-0.07339177230375057,0.05153569667688545,-0.07025951213962732,0.04059363542565007,32.875027191356764,4.978999999999662,0.92,76150.22,-0.12,-145.92,97.58,0.2981424331665039,400000
|
| 8 |
+
0.0,0.0,-0.06476899424653548,0.04172430333182566,-0.06228380112692244,0.03537567672041694,32.12106784661134,7.258999999999325,0.82,83179.16,-0.26,-214.7,143.18,0.44871801376342774,450000
|
| 9 |
+
0.0,0.0,-0.061469205649811516,0.05195934137961183,-0.057720861465483365,0.05740201447051761,35.10708203731403,3.3279999999998933,0.98,88363.24,-0.04,-101.34,64.56,0.20850870609283448,500000
|
| 10 |
+
0.0,0.0,-0.06796379770957457,0.0475349722856109,-0.06533278784144055,0.04013879405405066,31.146328836360507,5.704999999999525,0.86,94593.58,-0.2,-164.7,112.1,0.33276928424835206,550000
|
| 11 |
+
0.0,0.0,-0.07507963023442439,0.03506493715598263,-0.07122925899821765,0.04483508777680548,33.765849046864815,4.173999999999722,0.92,98276.64,-0.12,-122.18,81.48,0.4249086618423462,600000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/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,-0.134661379852989,0.10937709507377723,-0.1345329568922793,0.014164350233702088,18.123991195968692,21.975999999997512,0.18,10999.58,-1.24,-693.32,437.52,1.2593972635269166,150000
|
| 3 |
+
0.0,0.0,-0.07585795706703459,-0.014075406358252513,-0.07267561097613208,0.08263556310296005,22.562611121968704,18.549999999997965,0.34,32267.76,-0.88,-518.56,369.0,1.0607236814498902,200000
|
| 4 |
+
0.0,0.0,-0.07326103287353859,0.04804643990190737,-0.07109954354373692,0.035933126365884645,23.657339239077583,12.59699999999863,0.6,49062.7,-0.56,-366.38,249.94,0.7245305776596069,250000
|
| 5 |
+
0.0,0.0,-0.06546673174502798,0.08171762814680322,-0.06433850966926245,0.028495575677165277,28.640551525194777,11.183999999998866,0.66,61392.9,-0.5,-330.28,221.68,0.662751693725586,300000
|
| 6 |
+
0.0,0.0,-0.05561211470543549,0.04114122682993105,-0.0524820670632247,0.05138706368435286,31.912290966914405,6.538999999999478,0.86,69877.78,-0.2,-197.74,128.78,0.40421002864837646,350000
|
| 7 |
+
0.0,0.0,-0.07339177230375057,0.05153569667688545,-0.07025951213962732,0.04059363542565007,32.875027191356764,4.978999999999662,0.92,76150.22,-0.12,-145.92,97.58,0.2981424331665039,400000
|
| 8 |
+
0.0,0.0,-0.06476899424653548,0.04172430333182566,-0.06228380112692244,0.03537567672041694,32.12106784661134,7.258999999999325,0.82,83179.16,-0.26,-214.7,143.18,0.44871801376342774,450000
|
| 9 |
+
0.0,0.0,-0.061469205649811516,0.05195934137961183,-0.057720861465483365,0.05740201447051761,35.10708203731403,3.3279999999998933,0.98,88363.24,-0.04,-101.34,64.56,0.20850870609283448,500000
|
| 10 |
+
0.0,0.0,-0.06796379770957457,0.0475349722856109,-0.06533278784144055,0.04013879405405066,31.146328836360507,5.704999999999525,0.86,94593.58,-0.2,-164.7,112.1,0.33276928424835206,550000
|
| 11 |
+
0.0,0.0,-0.07507963023442439,0.03506493715598263,-0.07122925899821765,0.04483508777680548,33.765849046864815,4.173999999999722,0.92,98276.64,-0.12,-122.18,81.48,0.4249086618423462,600000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/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 |
+
532.73004,1.612279,1.2356589,-14.074883,-60.815094,-93.16784,1.1652855,-1.1973733,81.19976,105000
|
| 3 |
+
572.29736,1.119405,0.98333913,-12.695934,-64.53304,-106.757484,2.5792994,-2.604918,90.145515,110000
|
| 4 |
+
620.46014,0.83249897,1.6567067,-19.713017,-68.83099,-119.52719,2.382471,-2.2497063,83.81483,115000
|
| 5 |
+
617.427,0.83160436,3.8199556,-7.1711845,-68.714294,-122.50962,1.709029,-1.8846923,80.801704,120000
|
| 6 |
+
633.6846,0.75174177,1.4558687,-23.775019,-70.32864,-133.9981,9.841821,-17.021717,397.6302,125000
|
| 7 |
+
634.66296,0.75865114,1.9672712,-18.550982,-70.57148,-139.80377,1.6556549,-1.6004655,84.188156,130000
|
| 8 |
+
653.52783,1.0006838,1.100941,-12.350674,-72.21116,-145.93307,0.9777727,-0.96476656,47.2984,135000
|
| 9 |
+
688.5626,0.89530087,1.7241217,-27.0243,-75.91384,-149.38731,1.0779545,-1.242517,55.575077,140000
|
| 10 |
+
708.9878,1.1365474,1.4898739,-21.537447,-77.6831,-147.37614,2.0775409,-3.2665174,106.348564,145000
|
| 11 |
+
712.8549,0.75117666,4.3722405,-18.004627,-78.344635,-154.13533,1.7219217,-1.7909911,86.46887,150000
|
| 12 |
+
709.7714,0.8750385,3.6301434,-17.08589,-78.017845,-147.45273,3.1160278,-2.9403563,115.65989,155000
|
| 13 |
+
719.008,0.7807923,3.7325408,-17.037033,-78.898445,-155.436,1.1767164,-1.3643104,84.71432,160000
|
| 14 |
+
748.87317,0.77412105,1.4085902,-19.405024,-81.496216,-155.34938,1.7461262,-1.9363968,86.59869,165000
|
| 15 |
+
707.49756,0.88531363,1.5119059,-7.1120706,-76.919945,-150.88605,1.7871968,-1.6870209,64.69835,170000
|
| 16 |
+
744.985,0.9390261,3.5946252,-28.785412,-81.47388,-154.45375,2.2785096,-1.8053795,102.643036,175000
|
| 17 |
+
807.96826,0.87782955,1.4946188,-15.981386,-87.44357,-152.84494,6.223656,-6.248329,144.86241,180000
|
| 18 |
+
801.5866,1.4272316,3.7240484,-25.47863,-84.91932,-147.9622,2.6368225,-2.4897046,99.50035,185000
|
| 19 |
+
775.8485,0.9509458,2.0706627,0.22833706,-84.05885,-153.05247,1.131698,-1.0080624,59.517864,190000
|
| 20 |
+
767.10864,0.89354265,3.0659368,-6.9287567,-83.536095,-160.81912,0.9448277,-0.91304064,61.441868,195000
|
| 21 |
+
754.4682,0.79176474,2.1706402,-13.644045,-81.53235,-165.74817,1.3443137,-1.3004097,66.626686,200000
|
| 22 |
+
749.311,0.84920526,2.175696,-21.028635,-81.64922,-156.93382,0.7912643,-0.86543924,83.66703,205000
|
| 23 |
+
761.3757,0.8403986,1.9724053,-9.276994,-82.73565,-158.72751,24.5068,-30.62516,579.45624,210000
|
| 24 |
+
752.4988,0.72031885,2.2944024,1.4939178,-81.51171,-159.4681,2.1494129,-2.051594,82.26197,215000
|
| 25 |
+
762.2126,0.77429056,1.6390518,-14.26193,-82.60909,-157.33415,1.261481,-0.8417234,51.645927,220000
|
| 26 |
+
774.36993,0.8973812,2.5276573,-19.51557,-83.752686,-165.3895,1.0636926,-1.228186,68.994194,225000
|
| 27 |
+
766.18054,0.82232016,2.602472,-14.00823,-82.85027,-160.92644,1.1792103,-1.2304653,62.695213,230000
|
| 28 |
+
782.2892,0.8134265,1.5674406,1.5456688,-84.76764,-163.11128,1.0756454,-0.92662317,59.775173,235000
|
| 29 |
+
734.3693,0.84612393,2.1822693,-11.321688,-80.12438,-161.90881,1.4011619,-1.3571502,63.65829,240000
|
| 30 |
+
776.5865,0.96221876,4.8814716,-3.543705,-84.13779,-158.46255,3.0403988,-2.957796,146.24191,245000
|
| 31 |
+
768.8976,0.92111576,1.4901267,-6.864043,-82.78597,-168.04237,0.5121897,-0.6653422,48.36862,250000
|
| 32 |
+
911.0012,2.2453992,2.406842,-16.586922,-93.81463,-166.22192,2.540069,-4.14067,96.30117,255000
|
| 33 |
+
804.7983,1.2043037,2.2694077,-18.94424,-86.5837,-169.03456,9.387879,-9.327156,158.59576,260000
|
| 34 |
+
758.38245,0.9104239,1.8774662,-1.8136218,-82.20886,-156.20985,0.59941673,-0.7452778,45.96265,265000
|
| 35 |
+
736.3976,1.0070106,1.8912706,-16.032389,-79.993164,-160.34766,0.9702305,-0.99451864,59.871037,270000
|
| 36 |
+
800.5093,0.9894822,1.7263387,0.4624666,-86.304245,-162.3125,1.394441,-1.4456801,66.42984,275000
|
| 37 |
+
798.7019,0.93494177,2.32116,2.044285,-85.989174,-159.21495,1.1098984,-1.6624966,78.445984,280000
|
| 38 |
+
789.3665,0.8174529,1.721783,-16.974344,-85.12765,-164.83804,1.7726749,-1.2145163,70.971985,285000
|
| 39 |
+
803.9125,1.0010045,2.5114686,-14.091061,-86.48239,-167.80466,2.443341,-2.4380875,92.35683,290000
|
| 40 |
+
765.8864,0.9504376,2.0929623,-13.161027,-83.11979,-156.15494,1.198735,-1.3984789,68.73314,295000
|
| 41 |
+
754.98083,0.84645826,1.755333,-0.7327634,-81.84847,-157.25989,2.4382312,-2.3109794,121.73953,300000
|
| 42 |
+
785.4074,1.2571144,2.708964,-11.928301,-85.14222,-164.45659,1.3560274,-1.5207659,74.65794,305000
|
| 43 |
+
799.48334,1.2099326,3.926876,-14.545426,-85.94317,-166.74414,2.5077677,-2.5521963,79.13495,310000
|
| 44 |
+
766.38336,0.8623982,3.345415,1.0123502,-82.87294,-155.91862,1.6648794,-1.5882119,85.11952,315000
|
| 45 |
+
775.42035,0.9610591,2.020657,-5.618218,-83.19885,-161.25826,2.0355654,-1.9477856,67.43962,320000
|
| 46 |
+
790.94653,0.94594264,2.4245636,-6.292482,-85.29717,-155.30002,1.3274281,-1.3855497,75.87586,325000
|
| 47 |
+
782.04834,0.91425395,2.6081243,0.48284337,-84.23528,-162.25836,0.936495,-0.9037081,68.58267,330000
|
| 48 |
+
785.9648,0.99502456,1.957872,2.3893723,-84.32137,-168.08775,1.6417913,-1.44776,73.95512,335000
|
| 49 |
+
778.00977,1.0789138,1.4566298,1.7852829,-83.57784,-163.60231,1.8766462,-1.2867653,68.42853,340000
|
| 50 |
+
764.96686,0.86531055,3.7531915,-11.221831,-83.219376,-165.15146,1.9472158,-1.9152151,119.4088,345000
|
| 51 |
+
760.3529,1.1102169,2.2755806,-12.483456,-82.032715,-159.0321,3.094267,-3.3703957,158.75813,350000
|
| 52 |
+
781.61194,1.0173773,2.6126976,-7.928951,-84.56344,-160.61696,1.4607972,-1.4548246,74.70691,355000
|
| 53 |
+
757.19037,1.0686917,3.1429362,2.1730723,-81.74611,-165.59503,1.0594424,-1.0653024,74.931435,360000
|
| 54 |
+
756.8827,0.91786706,2.8499815,-1.8427817,-82.08886,-163.35109,14.680158,-12.007941,249.07582,365000
|
| 55 |
+
780.8634,0.8564004,1.808143,-2.8796864,-84.45306,-165.98724,1.7143936,-1.7037318,82.513504,370000
|
| 56 |
+
740.79065,0.9431271,2.5501919,-9.931754,-80.123436,-168.08376,1.3406699,-1.7134389,82.826416,375000
|
| 57 |
+
780.39,1.3166406,2.1415117,-14.435116,-84.627625,-159.43674,14.334722,-16.238836,482.7994,380000
|
| 58 |
+
739.4073,0.9960417,2.740817,-3.1101987,-79.72305,-157.30879,1.542518,-1.6686764,81.880585,385000
|
| 59 |
+
736.5362,0.91973925,2.6497684,-2.3113022,-80.01458,-159.68898,4.6432433,-4.591917,132.88861,390000
|
| 60 |
+
736.24066,0.96964717,2.6292164,1.4451824,-79.61797,-155.55959,1.4922361,-1.4918987,75.1024,395000
|
| 61 |
+
720.3597,1.3214844,2.3386028,-6.5598664,-77.74652,-159.73907,17.63623,-19.265816,475.91083,400000
|
| 62 |
+
750.0218,1.097013,2.721522,2.1961198,-81.78375,-158.13177,1.6456122,-1.5842665,88.72279,405000
|
| 63 |
+
727.65894,1.0218561,2.2979639,-9.211834,-79.23727,-162.75127,11.421657,-12.266369,214.35422,410000
|
| 64 |
+
759.1844,1.0714461,3.82556,-13.699823,-82.097435,-166.02592,1.9897377,-2.112662,107.693985,415000
|
| 65 |
+
762.63824,1.0710069,2.2970302,-8.735412,-82.80169,-162.44781,1.1742245,-1.2411549,78.32302,420000
|
| 66 |
+
731.07794,1.121125,3.4816644,-5.331164,-79.65846,-162.3243,3.119001,-3.4715555,150.24318,425000
|
| 67 |
+
754.44226,1.2009938,2.8196628,1.3298839,-81.54751,-166.6286,2.2582958,-2.065135,104.58055,430000
|
| 68 |
+
750.5494,1.4678179,1.917379,-5.4158015,-81.09847,-155.39183,1.9316764,-1.0808848,59.947723,435000
|
| 69 |
+
740.3757,1.2717991,2.2770514,-6.1835814,-80.178276,-168.10289,10.786521,-11.85406,208.69019,440000
|
| 70 |
+
763.8217,0.99121857,3.6511738,-17.097286,-82.54383,-157.00081,3.343996,-3.33841,142.62834,445000
|
| 71 |
+
746.7277,1.4920075,1.9213692,-9.865403,-80.55709,-163.80458,1.2269628,-1.4863474,72.69878,450000
|
| 72 |
+
755.59106,1.1427376,2.340308,-3.423368,-81.364395,-160.60735,1.3791789,-1.4819514,79.711,455000
|
| 73 |
+
755.0363,1.1128514,2.308622,-0.84330374,-82.005714,-160.25421,1.4752438,-1.3456199,70.731064,460000
|
| 74 |
+
741.70105,0.9626326,2.422341,-4.855369,-80.38669,-160.88622,1.1071941,-0.98294735,76.432175,465000
|
| 75 |
+
730.27875,1.0535195,3.6505146,-2.6114206,-78.922676,-159.26395,3.2113395,-3.3205798,177.95154,470000
|
| 76 |
+
724.7168,1.0136492,2.9353018,1.948243,-78.64575,-162.76277,1.6119708,-1.6104273,117.4419,475000
|
| 77 |
+
757.2055,1.0713372,2.1329024,-4.3293204,-81.52063,-166.66487,6.445052,-6.5669928,129.68153,480000
|
| 78 |
+
728.2905,0.8978506,3.653106,-10.781619,-79.00358,-168.54521,3.4721158,-3.3140619,122.65883,485000
|
| 79 |
+
739.1283,0.9675709,2.415306,-1.0297188,-79.85716,-165.48059,2.2997448,-2.0353682,87.708336,490000
|
| 80 |
+
768.23254,1.1489208,2.3090398,-11.337375,-82.930305,-162.29504,1.4481468,-1.3906267,77.54994,495000
|
| 81 |
+
732.4012,1.4142635,2.183485,-2.414194,-79.072716,-163.57713,1.6722283,-1.3846357,81.17019,500000
|
| 82 |
+
771.5399,1.473253,3.385405,-3.953732,-82.90501,-164.79277,12.138949,-17.13814,211.81886,505000
|
| 83 |
+
767.7275,1.4721124,2.300256,-6.4675136,-82.71315,-162.91354,4.9500613,-7.2116737,127.021805,510000
|
| 84 |
+
730.07404,1.0179327,3.3818588,-7.6256104,-79.03155,-158.94748,3.5797422,-3.817349,105.001816,515000
|
| 85 |
+
695.1459,1.022006,3.6603189,-4.5188966,-75.703514,-159.23969,0.9975054,-1.8481138,87.81513,520000
|
| 86 |
+
734.0053,1.2350473,2.5223024,-7.5021024,-79.19636,-171.76852,2.925165,-2.9543543,79.21494,525000
|
| 87 |
+
734.01276,1.0565096,2.1623154,-1.9208133,-79.54805,-166.01118,1.8662999,-1.2221721,76.618454,530000
|
| 88 |
+
689.91003,1.1446695,2.3295462,1.9046888,-75.30996,-151.09679,3.1683238,-2.7704723,117.14613,535000
|
| 89 |
+
718.1642,1.1006856,3.6175287,-5.1985526,-78.07416,-167.0765,4.9706783,-5.9418397,157.70131,540000
|
| 90 |
+
763.04504,1.0891105,1.8280461,-9.788375,-82.34464,-168.36325,6.501297,-5.811725,147.52266,545000
|
| 91 |
+
704.7875,1.2084054,2.6930616,-2.6293066,-76.66201,-162.28757,1.1129798,-0.957596,78.26945,550000
|
| 92 |
+
704.7596,1.1657288,2.3212206,-11.997178,-76.34248,-160.2213,5.3999925,-5.7863836,199.02081,555000
|
| 93 |
+
694.71155,1.1557916,8.708527,5.049887,-75.421684,-164.67632,3.2478156,-3.7125306,139.75937,560000
|
| 94 |
+
700.2244,1.0393803,1.6813834,-8.989307,-75.89603,-166.0865,1.5042154,-1.6274116,70.81188,565000
|
| 95 |
+
693.46423,1.0978,2.5616913,0.77971995,-75.58993,-160.4688,2.4885519,-2.0695336,84.270645,570000
|
| 96 |
+
725.1448,1.1335306,5.048302,-6.2774496,-78.64412,-177.96118,1.3181614,-1.0589892,95.65219,575000
|
| 97 |
+
701.4881,1.0753562,2.919995,1.269795,-76.29647,-162.92691,1.1894044,-1.2247031,78.44476,580000
|
| 98 |
+
689.9801,1.0314443,3.7530828,0.9478364,-75.46993,-178.01794,2.3233113,-2.3756871,100.56516,585000
|
| 99 |
+
741.98914,1.0263093,3.9152985,-7.749998,-79.94545,-159.77705,1.5027927,-1.4320745,106.87279,590000
|
| 100 |
+
676.6479,1.3152738,3.0359085,-0.55182046,-73.442986,-163.53403,2.4120574,-2.416573,95.080444,595000
|
| 101 |
+
669.2046,1.4332885,2.3218434,0.27920997,-72.78036,-162.09523,2.0679262,-3.0092747,84.13901,600000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/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 |
+
532.73004,1.612279,1.2356589,-14.074883,-60.815094,-93.16784,1.1652855,-1.1973733,81.19976,105000
|
| 3 |
+
572.29736,1.119405,0.98333913,-12.695934,-64.53304,-106.757484,2.5792994,-2.604918,90.145515,110000
|
| 4 |
+
620.46014,0.83249897,1.6567067,-19.713017,-68.83099,-119.52719,2.382471,-2.2497063,83.81483,115000
|
| 5 |
+
617.427,0.83160436,3.8199556,-7.1711845,-68.714294,-122.50962,1.709029,-1.8846923,80.801704,120000
|
| 6 |
+
633.6846,0.75174177,1.4558687,-23.775019,-70.32864,-133.9981,9.841821,-17.021717,397.6302,125000
|
| 7 |
+
634.66296,0.75865114,1.9672712,-18.550982,-70.57148,-139.80377,1.6556549,-1.6004655,84.188156,130000
|
| 8 |
+
653.52783,1.0006838,1.100941,-12.350674,-72.21116,-145.93307,0.9777727,-0.96476656,47.2984,135000
|
| 9 |
+
688.5626,0.89530087,1.7241217,-27.0243,-75.91384,-149.38731,1.0779545,-1.242517,55.575077,140000
|
| 10 |
+
708.9878,1.1365474,1.4898739,-21.537447,-77.6831,-147.37614,2.0775409,-3.2665174,106.348564,145000
|
| 11 |
+
712.8549,0.75117666,4.3722405,-18.004627,-78.344635,-154.13533,1.7219217,-1.7909911,86.46887,150000
|
| 12 |
+
709.7714,0.8750385,3.6301434,-17.08589,-78.017845,-147.45273,3.1160278,-2.9403563,115.65989,155000
|
| 13 |
+
719.008,0.7807923,3.7325408,-17.037033,-78.898445,-155.436,1.1767164,-1.3643104,84.71432,160000
|
| 14 |
+
748.87317,0.77412105,1.4085902,-19.405024,-81.496216,-155.34938,1.7461262,-1.9363968,86.59869,165000
|
| 15 |
+
707.49756,0.88531363,1.5119059,-7.1120706,-76.919945,-150.88605,1.7871968,-1.6870209,64.69835,170000
|
| 16 |
+
744.985,0.9390261,3.5946252,-28.785412,-81.47388,-154.45375,2.2785096,-1.8053795,102.643036,175000
|
| 17 |
+
807.96826,0.87782955,1.4946188,-15.981386,-87.44357,-152.84494,6.223656,-6.248329,144.86241,180000
|
| 18 |
+
801.5866,1.4272316,3.7240484,-25.47863,-84.91932,-147.9622,2.6368225,-2.4897046,99.50035,185000
|
| 19 |
+
775.8485,0.9509458,2.0706627,0.22833706,-84.05885,-153.05247,1.131698,-1.0080624,59.517864,190000
|
| 20 |
+
767.10864,0.89354265,3.0659368,-6.9287567,-83.536095,-160.81912,0.9448277,-0.91304064,61.441868,195000
|
| 21 |
+
754.4682,0.79176474,2.1706402,-13.644045,-81.53235,-165.74817,1.3443137,-1.3004097,66.626686,200000
|
| 22 |
+
749.311,0.84920526,2.175696,-21.028635,-81.64922,-156.93382,0.7912643,-0.86543924,83.66703,205000
|
| 23 |
+
761.3757,0.8403986,1.9724053,-9.276994,-82.73565,-158.72751,24.5068,-30.62516,579.45624,210000
|
| 24 |
+
752.4988,0.72031885,2.2944024,1.4939178,-81.51171,-159.4681,2.1494129,-2.051594,82.26197,215000
|
| 25 |
+
762.2126,0.77429056,1.6390518,-14.26193,-82.60909,-157.33415,1.261481,-0.8417234,51.645927,220000
|
| 26 |
+
774.36993,0.8973812,2.5276573,-19.51557,-83.752686,-165.3895,1.0636926,-1.228186,68.994194,225000
|
| 27 |
+
766.18054,0.82232016,2.602472,-14.00823,-82.85027,-160.92644,1.1792103,-1.2304653,62.695213,230000
|
| 28 |
+
782.2892,0.8134265,1.5674406,1.5456688,-84.76764,-163.11128,1.0756454,-0.92662317,59.775173,235000
|
| 29 |
+
734.3693,0.84612393,2.1822693,-11.321688,-80.12438,-161.90881,1.4011619,-1.3571502,63.65829,240000
|
| 30 |
+
776.5865,0.96221876,4.8814716,-3.543705,-84.13779,-158.46255,3.0403988,-2.957796,146.24191,245000
|
| 31 |
+
768.8976,0.92111576,1.4901267,-6.864043,-82.78597,-168.04237,0.5121897,-0.6653422,48.36862,250000
|
| 32 |
+
911.0012,2.2453992,2.406842,-16.586922,-93.81463,-166.22192,2.540069,-4.14067,96.30117,255000
|
| 33 |
+
804.7983,1.2043037,2.2694077,-18.94424,-86.5837,-169.03456,9.387879,-9.327156,158.59576,260000
|
| 34 |
+
758.38245,0.9104239,1.8774662,-1.8136218,-82.20886,-156.20985,0.59941673,-0.7452778,45.96265,265000
|
| 35 |
+
736.3976,1.0070106,1.8912706,-16.032389,-79.993164,-160.34766,0.9702305,-0.99451864,59.871037,270000
|
| 36 |
+
800.5093,0.9894822,1.7263387,0.4624666,-86.304245,-162.3125,1.394441,-1.4456801,66.42984,275000
|
| 37 |
+
798.7019,0.93494177,2.32116,2.044285,-85.989174,-159.21495,1.1098984,-1.6624966,78.445984,280000
|
| 38 |
+
789.3665,0.8174529,1.721783,-16.974344,-85.12765,-164.83804,1.7726749,-1.2145163,70.971985,285000
|
| 39 |
+
803.9125,1.0010045,2.5114686,-14.091061,-86.48239,-167.80466,2.443341,-2.4380875,92.35683,290000
|
| 40 |
+
765.8864,0.9504376,2.0929623,-13.161027,-83.11979,-156.15494,1.198735,-1.3984789,68.73314,295000
|
| 41 |
+
754.98083,0.84645826,1.755333,-0.7327634,-81.84847,-157.25989,2.4382312,-2.3109794,121.73953,300000
|
| 42 |
+
785.4074,1.2571144,2.708964,-11.928301,-85.14222,-164.45659,1.3560274,-1.5207659,74.65794,305000
|
| 43 |
+
799.48334,1.2099326,3.926876,-14.545426,-85.94317,-166.74414,2.5077677,-2.5521963,79.13495,310000
|
| 44 |
+
766.38336,0.8623982,3.345415,1.0123502,-82.87294,-155.91862,1.6648794,-1.5882119,85.11952,315000
|
| 45 |
+
775.42035,0.9610591,2.020657,-5.618218,-83.19885,-161.25826,2.0355654,-1.9477856,67.43962,320000
|
| 46 |
+
790.94653,0.94594264,2.4245636,-6.292482,-85.29717,-155.30002,1.3274281,-1.3855497,75.87586,325000
|
| 47 |
+
782.04834,0.91425395,2.6081243,0.48284337,-84.23528,-162.25836,0.936495,-0.9037081,68.58267,330000
|
| 48 |
+
785.9648,0.99502456,1.957872,2.3893723,-84.32137,-168.08775,1.6417913,-1.44776,73.95512,335000
|
| 49 |
+
778.00977,1.0789138,1.4566298,1.7852829,-83.57784,-163.60231,1.8766462,-1.2867653,68.42853,340000
|
| 50 |
+
764.96686,0.86531055,3.7531915,-11.221831,-83.219376,-165.15146,1.9472158,-1.9152151,119.4088,345000
|
| 51 |
+
760.3529,1.1102169,2.2755806,-12.483456,-82.032715,-159.0321,3.094267,-3.3703957,158.75813,350000
|
| 52 |
+
781.61194,1.0173773,2.6126976,-7.928951,-84.56344,-160.61696,1.4607972,-1.4548246,74.70691,355000
|
| 53 |
+
757.19037,1.0686917,3.1429362,2.1730723,-81.74611,-165.59503,1.0594424,-1.0653024,74.931435,360000
|
| 54 |
+
756.8827,0.91786706,2.8499815,-1.8427817,-82.08886,-163.35109,14.680158,-12.007941,249.07582,365000
|
| 55 |
+
780.8634,0.8564004,1.808143,-2.8796864,-84.45306,-165.98724,1.7143936,-1.7037318,82.513504,370000
|
| 56 |
+
740.79065,0.9431271,2.5501919,-9.931754,-80.123436,-168.08376,1.3406699,-1.7134389,82.826416,375000
|
| 57 |
+
780.39,1.3166406,2.1415117,-14.435116,-84.627625,-159.43674,14.334722,-16.238836,482.7994,380000
|
| 58 |
+
739.4073,0.9960417,2.740817,-3.1101987,-79.72305,-157.30879,1.542518,-1.6686764,81.880585,385000
|
| 59 |
+
736.5362,0.91973925,2.6497684,-2.3113022,-80.01458,-159.68898,4.6432433,-4.591917,132.88861,390000
|
| 60 |
+
736.24066,0.96964717,2.6292164,1.4451824,-79.61797,-155.55959,1.4922361,-1.4918987,75.1024,395000
|
| 61 |
+
720.3597,1.3214844,2.3386028,-6.5598664,-77.74652,-159.73907,17.63623,-19.265816,475.91083,400000
|
| 62 |
+
750.0218,1.097013,2.721522,2.1961198,-81.78375,-158.13177,1.6456122,-1.5842665,88.72279,405000
|
| 63 |
+
727.65894,1.0218561,2.2979639,-9.211834,-79.23727,-162.75127,11.421657,-12.266369,214.35422,410000
|
| 64 |
+
759.1844,1.0714461,3.82556,-13.699823,-82.097435,-166.02592,1.9897377,-2.112662,107.693985,415000
|
| 65 |
+
762.63824,1.0710069,2.2970302,-8.735412,-82.80169,-162.44781,1.1742245,-1.2411549,78.32302,420000
|
| 66 |
+
731.07794,1.121125,3.4816644,-5.331164,-79.65846,-162.3243,3.119001,-3.4715555,150.24318,425000
|
| 67 |
+
754.44226,1.2009938,2.8196628,1.3298839,-81.54751,-166.6286,2.2582958,-2.065135,104.58055,430000
|
| 68 |
+
750.5494,1.4678179,1.917379,-5.4158015,-81.09847,-155.39183,1.9316764,-1.0808848,59.947723,435000
|
| 69 |
+
740.3757,1.2717991,2.2770514,-6.1835814,-80.178276,-168.10289,10.786521,-11.85406,208.69019,440000
|
| 70 |
+
763.8217,0.99121857,3.6511738,-17.097286,-82.54383,-157.00081,3.343996,-3.33841,142.62834,445000
|
| 71 |
+
746.7277,1.4920075,1.9213692,-9.865403,-80.55709,-163.80458,1.2269628,-1.4863474,72.69878,450000
|
| 72 |
+
755.59106,1.1427376,2.340308,-3.423368,-81.364395,-160.60735,1.3791789,-1.4819514,79.711,455000
|
| 73 |
+
755.0363,1.1128514,2.308622,-0.84330374,-82.005714,-160.25421,1.4752438,-1.3456199,70.731064,460000
|
| 74 |
+
741.70105,0.9626326,2.422341,-4.855369,-80.38669,-160.88622,1.1071941,-0.98294735,76.432175,465000
|
| 75 |
+
730.27875,1.0535195,3.6505146,-2.6114206,-78.922676,-159.26395,3.2113395,-3.3205798,177.95154,470000
|
| 76 |
+
724.7168,1.0136492,2.9353018,1.948243,-78.64575,-162.76277,1.6119708,-1.6104273,117.4419,475000
|
| 77 |
+
757.2055,1.0713372,2.1329024,-4.3293204,-81.52063,-166.66487,6.445052,-6.5669928,129.68153,480000
|
| 78 |
+
728.2905,0.8978506,3.653106,-10.781619,-79.00358,-168.54521,3.4721158,-3.3140619,122.65883,485000
|
| 79 |
+
739.1283,0.9675709,2.415306,-1.0297188,-79.85716,-165.48059,2.2997448,-2.0353682,87.708336,490000
|
| 80 |
+
768.23254,1.1489208,2.3090398,-11.337375,-82.930305,-162.29504,1.4481468,-1.3906267,77.54994,495000
|
| 81 |
+
732.4012,1.4142635,2.183485,-2.414194,-79.072716,-163.57713,1.6722283,-1.3846357,81.17019,500000
|
| 82 |
+
771.5399,1.473253,3.385405,-3.953732,-82.90501,-164.79277,12.138949,-17.13814,211.81886,505000
|
| 83 |
+
767.7275,1.4721124,2.300256,-6.4675136,-82.71315,-162.91354,4.9500613,-7.2116737,127.021805,510000
|
| 84 |
+
730.07404,1.0179327,3.3818588,-7.6256104,-79.03155,-158.94748,3.5797422,-3.817349,105.001816,515000
|
| 85 |
+
695.1459,1.022006,3.6603189,-4.5188966,-75.703514,-159.23969,0.9975054,-1.8481138,87.81513,520000
|
| 86 |
+
734.0053,1.2350473,2.5223024,-7.5021024,-79.19636,-171.76852,2.925165,-2.9543543,79.21494,525000
|
| 87 |
+
734.01276,1.0565096,2.1623154,-1.9208133,-79.54805,-166.01118,1.8662999,-1.2221721,76.618454,530000
|
| 88 |
+
689.91003,1.1446695,2.3295462,1.9046888,-75.30996,-151.09679,3.1683238,-2.7704723,117.14613,535000
|
| 89 |
+
718.1642,1.1006856,3.6175287,-5.1985526,-78.07416,-167.0765,4.9706783,-5.9418397,157.70131,540000
|
| 90 |
+
763.04504,1.0891105,1.8280461,-9.788375,-82.34464,-168.36325,6.501297,-5.811725,147.52266,545000
|
| 91 |
+
704.7875,1.2084054,2.6930616,-2.6293066,-76.66201,-162.28757,1.1129798,-0.957596,78.26945,550000
|
| 92 |
+
704.7596,1.1657288,2.3212206,-11.997178,-76.34248,-160.2213,5.3999925,-5.7863836,199.02081,555000
|
| 93 |
+
694.71155,1.1557916,8.708527,5.049887,-75.421684,-164.67632,3.2478156,-3.7125306,139.75937,560000
|
| 94 |
+
700.2244,1.0393803,1.6813834,-8.989307,-75.89603,-166.0865,1.5042154,-1.6274116,70.81188,565000
|
| 95 |
+
693.46423,1.0978,2.5616913,0.77971995,-75.58993,-160.4688,2.4885519,-2.0695336,84.270645,570000
|
| 96 |
+
725.1448,1.1335306,5.048302,-6.2774496,-78.64412,-177.96118,1.3181614,-1.0589892,95.65219,575000
|
| 97 |
+
701.4881,1.0753562,2.919995,1.269795,-76.29647,-162.92691,1.1894044,-1.2247031,78.44476,580000
|
| 98 |
+
689.9801,1.0314443,3.7530828,0.9478364,-75.46993,-178.01794,2.3233113,-2.3756871,100.56516,585000
|
| 99 |
+
741.98914,1.0263093,3.9152985,-7.749998,-79.94545,-159.77705,1.5027927,-1.4320745,106.87279,590000
|
| 100 |
+
676.6479,1.3152738,3.0359085,-0.55182046,-73.442986,-163.53403,2.4120574,-2.416573,95.080444,595000
|
| 101 |
+
669.2046,1.4332885,2.3218434,0.27920997,-72.78036,-162.09523,2.0679262,-3.0092747,84.13901,600000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_150000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc36a247f6aacf9d1a5315c92ac02f1be71650fd2aafb021c653aabb6cdcb80
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_200000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1594711e74ff032fe1bc4bba8803ecebc8a223ca2652e052433786510d6b219e
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_250000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76c5be1572716be493e9581c9237d83cd05bd9fcd063cf3d8814d7a3b946803a
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_300000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6ecaa36fedcd41ff07faa7332c1517df548cec605a8f611a97f193f544de11e
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5576b8c8b3953320289c1c0f4335ba60bf347caab66b2d31091c78f75e5b0dd3
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dbcfd0c0171a9c35e45209befca58486ca481a6b8f89f2b191c528809ed55b3
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8116ae95a6de581b13d9ff86409fd6c531ce415f4b366e2a0a57fa63a991e8d1
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb42c4e7ccd0b1f83d8a41d21ed34b7e82f3c0f98c4c9bf18811dc2bd96736cc
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77eb862a9f574b7942ca6ea0d59db9447e5ca0e7bdd7e4aa0aa14d278125244e
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:133e2ab3861f49102144c834e7591237f69803e91010d4cc8f0491225d3e5992
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_103639/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/vbjfnund
|