Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1000000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1050000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1100000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1150000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1200000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1250000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1300000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1350000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1400000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_950000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/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_200522/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_200522/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,-0.0032285203612893694,0.13118671442877936,-0.004553498270494471,-0.04905744945796195,23.74403840915723,25.099999999996967,0.0,12750.0,-1.8,-943.8,500.0,1.4415213346481324,950000
|
| 3 |
+
0.0,0.0,-0.07269128254104258,-0.0004949075876802885,-0.07023890438832477,0.026813624679567837,21.008732252235223,19.536999999997914,0.32,35811.3,-1.1,-636.16,388.74,1.123866729736328,1000000
|
| 4 |
+
0.0,0.0,-0.0873056202519602,0.037281201706342734,-0.08702940754988939,0.00839073842203974,28.5902734764348,12.369999999999,0.7,52438.76,-0.4,-347.74,245.4,0.7305111122131348,1050000
|
| 5 |
+
0.0,0.0,-0.06412202787113169,0.047620809431052166,-0.060558330115730856,0.041247540217366506,33.30757699842941,9.335999999999101,0.74,63412.58,-0.36,-270.56,184.72,0.5582216835021973,1100000
|
| 6 |
+
0.0,0.0,-0.07699509934469922,0.029477254000703425,-0.0749104216434124,0.04756845448969699,33.314286274304834,5.517999999999588,0.9,71134.82,-0.16,-165.06,108.36,0.33946521759033205,1150000
|
| 7 |
+
0.0,0.0,-0.08360115572429276,0.036493672396817965,-0.08243970351593702,-0.002914532240157827,31.24464867909536,5.553999999999593,0.9,76870.84,-0.2,-183.68,109.08,0.34408227920532225,1200000
|
| 8 |
+
0.0,0.0,-0.07077124563596372,0.06277627773800623,-0.06963080727481098,0.05083285166445061,32.48658574235881,7.463999999999304,0.82,83612.26,-0.3,-236.26,147.28,0.46343604564666746,1250000
|
| 9 |
+
0.0,0.0,-0.07388741775044387,0.06747325438128507,-0.0726371921099116,0.05809014466535653,34.236325090705535,3.218999999999858,0.98,88573.38,-0.02,-90.18,62.38,0.20591286659240723,1300000
|
| 10 |
+
0.0,0.0,-0.08182536966053779,0.06048299347484094,-0.07808953983275263,0.060032334301378866,35.71472410316577,3.001999999999881,0.98,91630.52,-0.02,-81.82,58.04,0.1918998622894287,1350000
|
| 11 |
+
0.0,0.0,-0.06632230114158083,0.07566512016618664,-0.06338428499262558,0.06774459895036536,35.709010852081676,3.247999999999915,0.98,94665.56,-0.02,-90.36,62.96,0.21293963432312013,1400000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/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,-0.0032285203612893694,0.13118671442877936,-0.004553498270494471,-0.04905744945796195,23.74403840915723,25.099999999996967,0.0,12750.0,-1.8,-943.8,500.0,1.4415213346481324,950000
|
| 3 |
+
0.0,0.0,-0.07269128254104258,-0.0004949075876802885,-0.07023890438832477,0.026813624679567837,21.008732252235223,19.536999999997914,0.32,35811.3,-1.1,-636.16,388.74,1.123866729736328,1000000
|
| 4 |
+
0.0,0.0,-0.0873056202519602,0.037281201706342734,-0.08702940754988939,0.00839073842203974,28.5902734764348,12.369999999999,0.7,52438.76,-0.4,-347.74,245.4,0.7305111122131348,1050000
|
| 5 |
+
0.0,0.0,-0.06412202787113169,0.047620809431052166,-0.060558330115730856,0.041247540217366506,33.30757699842941,9.335999999999101,0.74,63412.58,-0.36,-270.56,184.72,0.5582216835021973,1100000
|
| 6 |
+
0.0,0.0,-0.07699509934469922,0.029477254000703425,-0.0749104216434124,0.04756845448969699,33.314286274304834,5.517999999999588,0.9,71134.82,-0.16,-165.06,108.36,0.33946521759033205,1150000
|
| 7 |
+
0.0,0.0,-0.08360115572429276,0.036493672396817965,-0.08243970351593702,-0.002914532240157827,31.24464867909536,5.553999999999593,0.9,76870.84,-0.2,-183.68,109.08,0.34408227920532225,1200000
|
| 8 |
+
0.0,0.0,-0.07077124563596372,0.06277627773800623,-0.06963080727481098,0.05083285166445061,32.48658574235881,7.463999999999304,0.82,83612.26,-0.3,-236.26,147.28,0.46343604564666746,1250000
|
| 9 |
+
0.0,0.0,-0.07388741775044387,0.06747325438128507,-0.0726371921099116,0.05809014466535653,34.236325090705535,3.218999999999858,0.98,88573.38,-0.02,-90.18,62.38,0.20591286659240723,1300000
|
| 10 |
+
0.0,0.0,-0.08182536966053779,0.06048299347484094,-0.07808953983275263,0.060032334301378866,35.71472410316577,3.001999999999881,0.98,91630.52,-0.02,-81.82,58.04,0.1918998622894287,1350000
|
| 11 |
+
0.0,0.0,-0.06632230114158083,0.07566512016618664,-0.06338428499262558,0.06774459895036536,35.709010852081676,3.247999999999915,0.98,94665.56,-0.02,-90.36,62.96,0.21293963432312013,1400000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/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 |
+
529.73773,1.1239815,0.57534665,-14.895223,-60.350353,-93.30334,4.121672,-3.6855874,88.415504,905000
|
| 3 |
+
590.989,0.9862016,0.8494673,-11.663432,-66.19964,-120.9171,4.541003,-3.524241,77.095245,910000
|
| 4 |
+
671.704,0.84488505,1.7958821,-15.6507,-73.695816,-146.71265,12.899318,-27.286434,150.53629,915000
|
| 5 |
+
680.35095,1.0989952,1.8877472,-3.9798348,-74.86411,-148.91032,13.150928,-16.211184,191.2144,920000
|
| 6 |
+
673.13806,0.97862756,1.5317036,-21.087101,-74.28202,-166.98538,2.598018,-3.1848965,87.6682,925000
|
| 7 |
+
687.2353,0.80064905,1.385458,-16.315834,-75.336464,-171.73154,3.0437481,-3.9060752,92.70892,930000
|
| 8 |
+
724.09686,1.0927894,2.4035006,-19.777052,-78.8071,-160.5762,2.515453,-3.6652522,80.47922,935000
|
| 9 |
+
744.5599,0.78970826,2.640495,-21.895681,-81.28546,-174.04308,6.6136055,-2.5965798,101.52922,940000
|
| 10 |
+
760.5064,0.97382474,1.1241957,-22.835522,-82.32666,-181.88936,9.072872,-10.10233,111.13542,945000
|
| 11 |
+
755.42365,1.1060123,1.5013841,-29.149696,-82.26885,-176.47064,4.4014854,-2.253472,80.68268,950000
|
| 12 |
+
772.5241,0.95109904,1.6780596,-17.831615,-83.52621,-166.06073,5.270863,-7.4585776,139.20055,955000
|
| 13 |
+
733.395,0.8851695,1.5310433,-17.680984,-80.21348,-159.29625,4.541606,-3.0376775,85.12659,960000
|
| 14 |
+
785.859,1.2893121,1.1515487,-21.056166,-84.54095,-184.45457,9.0702305,-5.471699,112.72994,965000
|
| 15 |
+
752.7174,0.97154075,3.2663205,-7.3436704,-81.3892,-182.13614,2.8037894,-3.7279663,98.114,970000
|
| 16 |
+
806.5789,0.86178344,2.6974847,-23.933384,-87.38366,-176.76631,160.93117,-149.79637,1327.031,975000
|
| 17 |
+
887.39343,1.0961386,4.100405,-16.587902,-95.01095,-185.623,9.436003,-10.412239,150.8377,980000
|
| 18 |
+
862.0769,1.0081873,2.399611,-26.556921,-92.20605,-183.15642,8.512471,-6.6990685,163.43092,985000
|
| 19 |
+
859.5706,1.2339528,2.4647317,-19.060432,-91.90072,-185.37701,4.507363,-3.121995,106.24346,990000
|
| 20 |
+
865.3653,0.7856941,2.601734,-8.916185,-92.90645,-185.28455,10.303499,-9.792073,168.80595,995000
|
| 21 |
+
878.7382,0.91094744,2.0738592,-17.30088,-93.565285,-182.05693,56.84315,-54.094223,919.30383,1000000
|
| 22 |
+
859.1072,1.0628116,2.4486434,-23.457129,-92.061485,-182.71066,3.7802258,-4.9334903,113.59428,1005000
|
| 23 |
+
847.15674,1.1386906,2.7500782,-24.901834,-91.293175,-181.17264,36.278553,-38.05639,629.7894,1010000
|
| 24 |
+
835.9802,1.0608826,2.382687,1.8974187,-89.25759,-181.80652,7.396956,-11.02375,129.81429,1015000
|
| 25 |
+
835.6116,1.2700231,4.1120806,-19.343403,-90.01288,-172.66591,7.7812533,-9.094308,215.69748,1020000
|
| 26 |
+
853.09216,0.84802294,2.15412,-1.3696216,-91.259056,-170.76959,4.382492,-5.0275865,125.80205,1025000
|
| 27 |
+
855.1376,1.5331178,2.2800815,-29.733152,-91.333755,-186.03691,4.446479,-10.85311,127.92987,1030000
|
| 28 |
+
848.06,1.0316741,3.1091692,2.0877497,-91.135635,-186.7053,10.515394,-11.545498,201.62764,1035000
|
| 29 |
+
838.8811,0.9846709,2.9790123,-18.605692,-90.44418,-181.50363,11.085675,-3.842167,124.5608,1040000
|
| 30 |
+
864.5513,1.3629082,2.7921665,-14.668187,-92.55952,-188.27954,19.577717,-55.231995,335.98956,1045000
|
| 31 |
+
872.5928,1.1444007,3.0258615,-10.533497,-92.896614,-186.5116,4.485779,-5.2876573,122.34554,1050000
|
| 32 |
+
899.2144,1.8516923,3.1204708,-23.03796,-95.90315,-183.07578,22.178661,-25.827873,476.64935,1055000
|
| 33 |
+
856.37964,1.3022561,6.384587,-16.065191,-91.95335,-176.33522,28.07654,-14.802348,310.54877,1060000
|
| 34 |
+
835.3684,0.9347148,3.2171094,-1.3406588,-89.55384,-192.89214,149.0268,-31.811531,520.1793,1065000
|
| 35 |
+
854.8366,1.0921836,7.521979,-10.825726,-91.68912,-190.3353,17.15585,-16.636333,530.79913,1070000
|
| 36 |
+
857.4304,1.3807089,3.5335,-17.706747,-91.69512,-185.4318,6.8683987,-7.5585546,164.5089,1075000
|
| 37 |
+
897.22003,1.2862914,4.764435,3.015536,-95.33997,-193.6926,19.801302,-12.623305,313.46252,1080000
|
| 38 |
+
850.8642,1.3847233,2.2187982,-11.908224,-91.02335,-184.09529,9.350732,-6.040883,132.21484,1085000
|
| 39 |
+
890.9172,0.8582536,4.30185,-11.159658,-94.76059,-190.4023,20.153925,-8.616067,223.06131,1090000
|
| 40 |
+
847.37177,1.1157299,3.6793492,-4.694198,-90.5198,-186.02046,7.761747,-5.2187915,177.68732,1095000
|
| 41 |
+
840.5717,1.2245293,2.923281,-4.4475365,-90.086555,-181.82713,9.535239,-11.922213,234.20418,1100000
|
| 42 |
+
841.86884,0.9626122,5.7062387,-4.030562,-90.605125,-183.14752,30.029224,-38.443184,710.8964,1105000
|
| 43 |
+
878.9264,1.0949142,3.310513,3.156085,-93.62519,-185.04408,13.18896,-11.710232,284.5283,1110000
|
| 44 |
+
880.38544,1.0097021,7.86787,-3.5572278,-94.247345,-186.54904,6.425876,-10.032601,205.99765,1115000
|
| 45 |
+
874.58185,1.0689504,5.0414023,5.1732645,-93.316956,-185.0386,11.71009,-28.783522,288.71722,1120000
|
| 46 |
+
839.11176,1.1081588,3.1176221,-12.776054,-89.434074,-183.97348,6.6465187,-5.321152,139.39665,1125000
|
| 47 |
+
886.94366,1.06813,15.54043,1.2815125,-94.70196,-194.25897,6.624905,-10.034806,237.96353,1130000
|
| 48 |
+
877.2438,1.2892964,4.2621226,-9.4684305,-93.50179,-191.55215,11.932098,-4.486093,139.925,1135000
|
| 49 |
+
897.5011,1.1557504,4.1133957,2.3158576,-95.41094,-188.86739,166.34334,-124.92731,2217.2852,1140000
|
| 50 |
+
851.8779,1.6829429,4.4406714,-4.1670685,-91.44974,-184.51288,43.225933,-58.401157,626.768,1145000
|
| 51 |
+
846.7982,1.0923215,6.9676094,-5.4920244,-90.58237,-186.54631,26.712574,-26.838432,390.51538,1150000
|
| 52 |
+
848.04047,1.2045741,5.78086,-0.39201206,-91.17055,-183.97945,30.092253,-13.200417,283.4049,1155000
|
| 53 |
+
835.5666,1.165648,2.8992693,1.5648222,-89.326454,-184.45432,9.595948,-6.3174715,163.93352,1160000
|
| 54 |
+
833.98444,1.1764876,3.2641556,-14.8080635,-89.21969,-188.96904,57.742542,-35.409466,414.26163,1165000
|
| 55 |
+
839.6985,1.0989468,5.9573617,-8.822609,-90.154305,-195.1231,6.8192005,-6.429243,169.79922,1170000
|
| 56 |
+
817.2386,1.1801713,4.3467546,-15.652009,-87.331566,-192.78221,10.217662,-12.093464,216.28178,1175000
|
| 57 |
+
843.0786,1.0969515,2.8627331,-10.947356,-90.06526,-185.14677,10.039758,-11.2754965,217.42122,1180000
|
| 58 |
+
846.71924,1.2242494,6.662314,-1.1502105,-89.87441,-182.21974,46.647705,-30.677185,452.3341,1185000
|
| 59 |
+
845.85645,1.1993555,4.3917975,-3.3379786,-90.0248,-181.32697,12.991261,-16.46101,360.21838,1190000
|
| 60 |
+
848.0706,1.2234585,3.8366578,2.7461758,-90.68756,-178.05975,17.923677,-16.21649,312.93823,1195000
|
| 61 |
+
842.16785,1.302697,4.4179764,-3.682687,-89.71581,-188.96298,5.00801,-4.6198654,139.15302,1200000
|
| 62 |
+
844.8174,1.276632,3.6669095,-9.212246,-90.562645,-184.29912,6.1420546,-8.749104,173.17871,1205000
|
| 63 |
+
809.7005,1.7837508,4.8101,2.1333973,-87.21442,-183.57666,7.2830257,-8.737421,181.2959,1210000
|
| 64 |
+
821.2088,0.9794543,17.41058,-1.1052865,-87.9537,-171.11003,48.966908,-54.876556,911.9551,1215000
|
| 65 |
+
845.7203,1.2992618,3.8811123,-7.938998,-90.60166,-184.43478,18.604618,-13.859921,347.90692,1220000
|
| 66 |
+
843.26215,1.2694743,5.161241,-9.915523,-90.12367,-184.4372,20.07414,-19.189602,500.8282,1225000
|
| 67 |
+
802.12384,1.6715852,5.2612185,-1.6704376,-85.54542,-177.21487,20.035343,-17.189531,463.04678,1230000
|
| 68 |
+
809.69366,1.4216834,6.610106,-3.1801372,-87.31398,-188.89392,21.125544,-51.158165,337.97958,1235000
|
| 69 |
+
804.4163,1.5077261,3.453015,-11.997812,-86.05489,-182.01157,26.909695,-8.535657,252.33704,1240000
|
| 70 |
+
829.51447,1.2324959,3.09355,-4.144488,-88.747025,-180.16602,106.46615,-373.31155,1554.8094,1245000
|
| 71 |
+
835.8643,1.1781621,4.5302672,-6.6890063,-89.14446,-175.59354,5.580744,-5.6059265,159.418,1250000
|
| 72 |
+
864.00696,1.231953,4.2894006,-7.8804607,-92.04069,-187.17924,5.5075197,-7.7363796,184.46341,1255000
|
| 73 |
+
815.6958,1.6146867,4.3334517,-5.25567,-87.239525,-183.44153,10.750787,-12.2386265,222.32928,1260000
|
| 74 |
+
834.6027,1.3930118,4.0616336,-2.2735448,-89.25478,-179.0797,9.775192,-10.034666,165.69699,1265000
|
| 75 |
+
807.5225,1.023347,5.3095984,-5.132805,-86.47607,-178.67847,6.638727,-5.7441754,154.97206,1270000
|
| 76 |
+
798.46466,1.4338866,3.4764924,1.7663107,-85.64404,-176.12556,14.37551,-12.067902,255.45332,1275000
|
| 77 |
+
795.9509,1.974474,4.037731,4.714282,-85.03263,-175.65717,8.0025,-12.8118305,225.05193,1280000
|
| 78 |
+
828.43665,1.5468549,11.090686,-4.1673765,-88.370636,-178.2203,22.856966,-9.341936,265.70938,1285000
|
| 79 |
+
824.5251,1.4262931,4.286548,-6.9874983,-88.24877,-175.28857,32.974186,-32.355198,609.1817,1290000
|
| 80 |
+
807.5725,1.1088331,4.687932,-0.7530472,-86.55769,-179.74925,82.80721,-69.29715,791.7608,1295000
|
| 81 |
+
788.01904,1.6393946,3.820723,-2.7140293,-84.58376,-182.63405,8.339349,-7.742512,218.0419,1300000
|
| 82 |
+
824.90894,1.8257035,4.7413216,-5.340042,-87.84995,-181.81625,11.303514,-12.863511,283.6858,1305000
|
| 83 |
+
796.95557,0.97827816,4.1882052,-3.048204,-85.6824,-189.3053,11.221253,-25.400686,281.0424,1310000
|
| 84 |
+
778.5136,1.0354636,5.6548586,-6.3093348,-83.68795,-174.4057,17.313705,-46.836086,477.24597,1315000
|
| 85 |
+
788.4215,1.2144843,5.4683757,1.0480313,-85.1158,-169.43651,16.448341,-51.55784,380.0426,1320000
|
| 86 |
+
785.4594,1.6161323,5.3539596,0.5403999,-84.48286,-186.1796,7.895142,-10.254237,190.10315,1325000
|
| 87 |
+
805.9726,1.9006667,4.578637,-2.3776264,-86.347466,-180.85675,20.781897,-19.16184,269.7621,1330000
|
| 88 |
+
786.27136,1.1654917,5.0007358,-6.730015,-84.665565,-169.92557,9.794573,-14.002338,213.70953,1335000
|
| 89 |
+
803.5603,1.4156464,4.8757358,-2.7662172,-85.971306,-183.56229,16.658968,-13.875982,307.59256,1340000
|
| 90 |
+
825.92224,1.1445241,3.7664688,-1.9342167,-88.5688,-171.18608,5.9364195,-4.063361,154.84738,1345000
|
| 91 |
+
807.8155,1.3918705,4.1307883,0.40382263,-86.815636,-186.24886,17.035069,-13.425815,251.22932,1350000
|
| 92 |
+
761.87335,1.1212673,13.019752,3.2980723,-81.89827,-170.20624,13.03722,-7.569277,287.31976,1355000
|
| 93 |
+
779.6027,1.0449848,13.185511,-7.8632793,-83.62462,-172.78032,15.319895,-10.279707,298.19818,1360000
|
| 94 |
+
774.6073,1.9618204,6.1973257,-4.6022873,-83.66063,-190.65079,7.1743803,-6.016455,171.97461,1365000
|
| 95 |
+
749.41656,1.8706529,3.541277,-3.9875805,-80.86755,-170.99579,10.475526,-11.073045,240.37617,1370000
|
| 96 |
+
801.5738,1.3461816,4.5600686,-7.0214324,-85.56036,-183.83504,4.7116766,-8.6128435,154.14238,1375000
|
| 97 |
+
761.36786,1.3044049,9.591812,1.24937,-82.253136,-180.91196,12.928739,-16.239376,333.67523,1380000
|
| 98 |
+
723.4231,1.2835685,5.20868,-4.1289043,-78.105644,-183.35156,10.431582,-11.669026,263.35382,1385000
|
| 99 |
+
796.0945,1.2067084,3.4422333,2.4992158,-84.81533,-173.12097,15.311869,-11.010423,379.4691,1390000
|
| 100 |
+
708.79504,1.465425,3.3042753,4.0558696,-76.65652,-174.81006,22.759779,-50.124493,346.97586,1395000
|
| 101 |
+
731.9763,2.0533206,3.955804,2.890226,-78.99318,-171.20412,11.705644,-30.574497,376.52832,1400000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/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 |
+
529.73773,1.1239815,0.57534665,-14.895223,-60.350353,-93.30334,4.121672,-3.6855874,88.415504,905000
|
| 3 |
+
590.989,0.9862016,0.8494673,-11.663432,-66.19964,-120.9171,4.541003,-3.524241,77.095245,910000
|
| 4 |
+
671.704,0.84488505,1.7958821,-15.6507,-73.695816,-146.71265,12.899318,-27.286434,150.53629,915000
|
| 5 |
+
680.35095,1.0989952,1.8877472,-3.9798348,-74.86411,-148.91032,13.150928,-16.211184,191.2144,920000
|
| 6 |
+
673.13806,0.97862756,1.5317036,-21.087101,-74.28202,-166.98538,2.598018,-3.1848965,87.6682,925000
|
| 7 |
+
687.2353,0.80064905,1.385458,-16.315834,-75.336464,-171.73154,3.0437481,-3.9060752,92.70892,930000
|
| 8 |
+
724.09686,1.0927894,2.4035006,-19.777052,-78.8071,-160.5762,2.515453,-3.6652522,80.47922,935000
|
| 9 |
+
744.5599,0.78970826,2.640495,-21.895681,-81.28546,-174.04308,6.6136055,-2.5965798,101.52922,940000
|
| 10 |
+
760.5064,0.97382474,1.1241957,-22.835522,-82.32666,-181.88936,9.072872,-10.10233,111.13542,945000
|
| 11 |
+
755.42365,1.1060123,1.5013841,-29.149696,-82.26885,-176.47064,4.4014854,-2.253472,80.68268,950000
|
| 12 |
+
772.5241,0.95109904,1.6780596,-17.831615,-83.52621,-166.06073,5.270863,-7.4585776,139.20055,955000
|
| 13 |
+
733.395,0.8851695,1.5310433,-17.680984,-80.21348,-159.29625,4.541606,-3.0376775,85.12659,960000
|
| 14 |
+
785.859,1.2893121,1.1515487,-21.056166,-84.54095,-184.45457,9.0702305,-5.471699,112.72994,965000
|
| 15 |
+
752.7174,0.97154075,3.2663205,-7.3436704,-81.3892,-182.13614,2.8037894,-3.7279663,98.114,970000
|
| 16 |
+
806.5789,0.86178344,2.6974847,-23.933384,-87.38366,-176.76631,160.93117,-149.79637,1327.031,975000
|
| 17 |
+
887.39343,1.0961386,4.100405,-16.587902,-95.01095,-185.623,9.436003,-10.412239,150.8377,980000
|
| 18 |
+
862.0769,1.0081873,2.399611,-26.556921,-92.20605,-183.15642,8.512471,-6.6990685,163.43092,985000
|
| 19 |
+
859.5706,1.2339528,2.4647317,-19.060432,-91.90072,-185.37701,4.507363,-3.121995,106.24346,990000
|
| 20 |
+
865.3653,0.7856941,2.601734,-8.916185,-92.90645,-185.28455,10.303499,-9.792073,168.80595,995000
|
| 21 |
+
878.7382,0.91094744,2.0738592,-17.30088,-93.565285,-182.05693,56.84315,-54.094223,919.30383,1000000
|
| 22 |
+
859.1072,1.0628116,2.4486434,-23.457129,-92.061485,-182.71066,3.7802258,-4.9334903,113.59428,1005000
|
| 23 |
+
847.15674,1.1386906,2.7500782,-24.901834,-91.293175,-181.17264,36.278553,-38.05639,629.7894,1010000
|
| 24 |
+
835.9802,1.0608826,2.382687,1.8974187,-89.25759,-181.80652,7.396956,-11.02375,129.81429,1015000
|
| 25 |
+
835.6116,1.2700231,4.1120806,-19.343403,-90.01288,-172.66591,7.7812533,-9.094308,215.69748,1020000
|
| 26 |
+
853.09216,0.84802294,2.15412,-1.3696216,-91.259056,-170.76959,4.382492,-5.0275865,125.80205,1025000
|
| 27 |
+
855.1376,1.5331178,2.2800815,-29.733152,-91.333755,-186.03691,4.446479,-10.85311,127.92987,1030000
|
| 28 |
+
848.06,1.0316741,3.1091692,2.0877497,-91.135635,-186.7053,10.515394,-11.545498,201.62764,1035000
|
| 29 |
+
838.8811,0.9846709,2.9790123,-18.605692,-90.44418,-181.50363,11.085675,-3.842167,124.5608,1040000
|
| 30 |
+
864.5513,1.3629082,2.7921665,-14.668187,-92.55952,-188.27954,19.577717,-55.231995,335.98956,1045000
|
| 31 |
+
872.5928,1.1444007,3.0258615,-10.533497,-92.896614,-186.5116,4.485779,-5.2876573,122.34554,1050000
|
| 32 |
+
899.2144,1.8516923,3.1204708,-23.03796,-95.90315,-183.07578,22.178661,-25.827873,476.64935,1055000
|
| 33 |
+
856.37964,1.3022561,6.384587,-16.065191,-91.95335,-176.33522,28.07654,-14.802348,310.54877,1060000
|
| 34 |
+
835.3684,0.9347148,3.2171094,-1.3406588,-89.55384,-192.89214,149.0268,-31.811531,520.1793,1065000
|
| 35 |
+
854.8366,1.0921836,7.521979,-10.825726,-91.68912,-190.3353,17.15585,-16.636333,530.79913,1070000
|
| 36 |
+
857.4304,1.3807089,3.5335,-17.706747,-91.69512,-185.4318,6.8683987,-7.5585546,164.5089,1075000
|
| 37 |
+
897.22003,1.2862914,4.764435,3.015536,-95.33997,-193.6926,19.801302,-12.623305,313.46252,1080000
|
| 38 |
+
850.8642,1.3847233,2.2187982,-11.908224,-91.02335,-184.09529,9.350732,-6.040883,132.21484,1085000
|
| 39 |
+
890.9172,0.8582536,4.30185,-11.159658,-94.76059,-190.4023,20.153925,-8.616067,223.06131,1090000
|
| 40 |
+
847.37177,1.1157299,3.6793492,-4.694198,-90.5198,-186.02046,7.761747,-5.2187915,177.68732,1095000
|
| 41 |
+
840.5717,1.2245293,2.923281,-4.4475365,-90.086555,-181.82713,9.535239,-11.922213,234.20418,1100000
|
| 42 |
+
841.86884,0.9626122,5.7062387,-4.030562,-90.605125,-183.14752,30.029224,-38.443184,710.8964,1105000
|
| 43 |
+
878.9264,1.0949142,3.310513,3.156085,-93.62519,-185.04408,13.18896,-11.710232,284.5283,1110000
|
| 44 |
+
880.38544,1.0097021,7.86787,-3.5572278,-94.247345,-186.54904,6.425876,-10.032601,205.99765,1115000
|
| 45 |
+
874.58185,1.0689504,5.0414023,5.1732645,-93.316956,-185.0386,11.71009,-28.783522,288.71722,1120000
|
| 46 |
+
839.11176,1.1081588,3.1176221,-12.776054,-89.434074,-183.97348,6.6465187,-5.321152,139.39665,1125000
|
| 47 |
+
886.94366,1.06813,15.54043,1.2815125,-94.70196,-194.25897,6.624905,-10.034806,237.96353,1130000
|
| 48 |
+
877.2438,1.2892964,4.2621226,-9.4684305,-93.50179,-191.55215,11.932098,-4.486093,139.925,1135000
|
| 49 |
+
897.5011,1.1557504,4.1133957,2.3158576,-95.41094,-188.86739,166.34334,-124.92731,2217.2852,1140000
|
| 50 |
+
851.8779,1.6829429,4.4406714,-4.1670685,-91.44974,-184.51288,43.225933,-58.401157,626.768,1145000
|
| 51 |
+
846.7982,1.0923215,6.9676094,-5.4920244,-90.58237,-186.54631,26.712574,-26.838432,390.51538,1150000
|
| 52 |
+
848.04047,1.2045741,5.78086,-0.39201206,-91.17055,-183.97945,30.092253,-13.200417,283.4049,1155000
|
| 53 |
+
835.5666,1.165648,2.8992693,1.5648222,-89.326454,-184.45432,9.595948,-6.3174715,163.93352,1160000
|
| 54 |
+
833.98444,1.1764876,3.2641556,-14.8080635,-89.21969,-188.96904,57.742542,-35.409466,414.26163,1165000
|
| 55 |
+
839.6985,1.0989468,5.9573617,-8.822609,-90.154305,-195.1231,6.8192005,-6.429243,169.79922,1170000
|
| 56 |
+
817.2386,1.1801713,4.3467546,-15.652009,-87.331566,-192.78221,10.217662,-12.093464,216.28178,1175000
|
| 57 |
+
843.0786,1.0969515,2.8627331,-10.947356,-90.06526,-185.14677,10.039758,-11.2754965,217.42122,1180000
|
| 58 |
+
846.71924,1.2242494,6.662314,-1.1502105,-89.87441,-182.21974,46.647705,-30.677185,452.3341,1185000
|
| 59 |
+
845.85645,1.1993555,4.3917975,-3.3379786,-90.0248,-181.32697,12.991261,-16.46101,360.21838,1190000
|
| 60 |
+
848.0706,1.2234585,3.8366578,2.7461758,-90.68756,-178.05975,17.923677,-16.21649,312.93823,1195000
|
| 61 |
+
842.16785,1.302697,4.4179764,-3.682687,-89.71581,-188.96298,5.00801,-4.6198654,139.15302,1200000
|
| 62 |
+
844.8174,1.276632,3.6669095,-9.212246,-90.562645,-184.29912,6.1420546,-8.749104,173.17871,1205000
|
| 63 |
+
809.7005,1.7837508,4.8101,2.1333973,-87.21442,-183.57666,7.2830257,-8.737421,181.2959,1210000
|
| 64 |
+
821.2088,0.9794543,17.41058,-1.1052865,-87.9537,-171.11003,48.966908,-54.876556,911.9551,1215000
|
| 65 |
+
845.7203,1.2992618,3.8811123,-7.938998,-90.60166,-184.43478,18.604618,-13.859921,347.90692,1220000
|
| 66 |
+
843.26215,1.2694743,5.161241,-9.915523,-90.12367,-184.4372,20.07414,-19.189602,500.8282,1225000
|
| 67 |
+
802.12384,1.6715852,5.2612185,-1.6704376,-85.54542,-177.21487,20.035343,-17.189531,463.04678,1230000
|
| 68 |
+
809.69366,1.4216834,6.610106,-3.1801372,-87.31398,-188.89392,21.125544,-51.158165,337.97958,1235000
|
| 69 |
+
804.4163,1.5077261,3.453015,-11.997812,-86.05489,-182.01157,26.909695,-8.535657,252.33704,1240000
|
| 70 |
+
829.51447,1.2324959,3.09355,-4.144488,-88.747025,-180.16602,106.46615,-373.31155,1554.8094,1245000
|
| 71 |
+
835.8643,1.1781621,4.5302672,-6.6890063,-89.14446,-175.59354,5.580744,-5.6059265,159.418,1250000
|
| 72 |
+
864.00696,1.231953,4.2894006,-7.8804607,-92.04069,-187.17924,5.5075197,-7.7363796,184.46341,1255000
|
| 73 |
+
815.6958,1.6146867,4.3334517,-5.25567,-87.239525,-183.44153,10.750787,-12.2386265,222.32928,1260000
|
| 74 |
+
834.6027,1.3930118,4.0616336,-2.2735448,-89.25478,-179.0797,9.775192,-10.034666,165.69699,1265000
|
| 75 |
+
807.5225,1.023347,5.3095984,-5.132805,-86.47607,-178.67847,6.638727,-5.7441754,154.97206,1270000
|
| 76 |
+
798.46466,1.4338866,3.4764924,1.7663107,-85.64404,-176.12556,14.37551,-12.067902,255.45332,1275000
|
| 77 |
+
795.9509,1.974474,4.037731,4.714282,-85.03263,-175.65717,8.0025,-12.8118305,225.05193,1280000
|
| 78 |
+
828.43665,1.5468549,11.090686,-4.1673765,-88.370636,-178.2203,22.856966,-9.341936,265.70938,1285000
|
| 79 |
+
824.5251,1.4262931,4.286548,-6.9874983,-88.24877,-175.28857,32.974186,-32.355198,609.1817,1290000
|
| 80 |
+
807.5725,1.1088331,4.687932,-0.7530472,-86.55769,-179.74925,82.80721,-69.29715,791.7608,1295000
|
| 81 |
+
788.01904,1.6393946,3.820723,-2.7140293,-84.58376,-182.63405,8.339349,-7.742512,218.0419,1300000
|
| 82 |
+
824.90894,1.8257035,4.7413216,-5.340042,-87.84995,-181.81625,11.303514,-12.863511,283.6858,1305000
|
| 83 |
+
796.95557,0.97827816,4.1882052,-3.048204,-85.6824,-189.3053,11.221253,-25.400686,281.0424,1310000
|
| 84 |
+
778.5136,1.0354636,5.6548586,-6.3093348,-83.68795,-174.4057,17.313705,-46.836086,477.24597,1315000
|
| 85 |
+
788.4215,1.2144843,5.4683757,1.0480313,-85.1158,-169.43651,16.448341,-51.55784,380.0426,1320000
|
| 86 |
+
785.4594,1.6161323,5.3539596,0.5403999,-84.48286,-186.1796,7.895142,-10.254237,190.10315,1325000
|
| 87 |
+
805.9726,1.9006667,4.578637,-2.3776264,-86.347466,-180.85675,20.781897,-19.16184,269.7621,1330000
|
| 88 |
+
786.27136,1.1654917,5.0007358,-6.730015,-84.665565,-169.92557,9.794573,-14.002338,213.70953,1335000
|
| 89 |
+
803.5603,1.4156464,4.8757358,-2.7662172,-85.971306,-183.56229,16.658968,-13.875982,307.59256,1340000
|
| 90 |
+
825.92224,1.1445241,3.7664688,-1.9342167,-88.5688,-171.18608,5.9364195,-4.063361,154.84738,1345000
|
| 91 |
+
807.8155,1.3918705,4.1307883,0.40382263,-86.815636,-186.24886,17.035069,-13.425815,251.22932,1350000
|
| 92 |
+
761.87335,1.1212673,13.019752,3.2980723,-81.89827,-170.20624,13.03722,-7.569277,287.31976,1355000
|
| 93 |
+
779.6027,1.0449848,13.185511,-7.8632793,-83.62462,-172.78032,15.319895,-10.279707,298.19818,1360000
|
| 94 |
+
774.6073,1.9618204,6.1973257,-4.6022873,-83.66063,-190.65079,7.1743803,-6.016455,171.97461,1365000
|
| 95 |
+
749.41656,1.8706529,3.541277,-3.9875805,-80.86755,-170.99579,10.475526,-11.073045,240.37617,1370000
|
| 96 |
+
801.5738,1.3461816,4.5600686,-7.0214324,-85.56036,-183.83504,4.7116766,-8.6128435,154.14238,1375000
|
| 97 |
+
761.36786,1.3044049,9.591812,1.24937,-82.253136,-180.91196,12.928739,-16.239376,333.67523,1380000
|
| 98 |
+
723.4231,1.2835685,5.20868,-4.1289043,-78.105644,-183.35156,10.431582,-11.669026,263.35382,1385000
|
| 99 |
+
796.0945,1.2067084,3.4422333,2.4992158,-84.81533,-173.12097,15.311869,-11.010423,379.4691,1390000
|
| 100 |
+
708.79504,1.465425,3.3042753,4.0558696,-76.65652,-174.81006,22.759779,-50.124493,346.97586,1395000
|
| 101 |
+
731.9763,2.0533206,3.955804,2.890226,-78.99318,-171.20412,11.705644,-30.574497,376.52832,1400000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1000000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b38bf27909cd7506b65c55aa26da53274f109a2ec4c61ce9775d5ce5807e6ec
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1050000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00f37f6893ad67ed0ee14bc467336632c84c5f515684a03d986e24caf7a4a436
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1100000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dfbe2cd65548ab9993d5408986e21cb189605bdd758950b8ce23d841afd9f18
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1150000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edadce9497a01848d42a18d3f6a6b0890dfaa3ce1b4ba0c9f84c461d038aefdd
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1200000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59b81adafbd28496e383593a75d9a58c7027a9f46d51e4570037856b56ef38ef
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1250000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f8c5f435883ef194824d884c3d40aeab334a3818d5251cbe41ba1c3e87ce3b5
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1300000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6ba1ce45fa5e312119f512da55a8fad53345b677e1ed33aa456e7c1c66823d6
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ef67dea76c44de8f073ef691fd2be2225c18195484b6ace684910e21132dbc2
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_1400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ccfe03a8572aa5493ab4ae5c91757435335a6a752cde83fab38188ba043d31d
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/params_950000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:783bdeba467dad49d9662f51f804a8ed713a7f519889a03aa329de19e59dffbb
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_200522/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/sdbxbs3z
|