Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_250000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_300000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_350000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_400000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_450000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_500000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_650000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_700000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/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_114727/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_114727/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,-0.05699617164448793,0.06464115899720767,-0.06090479169976698,-0.10711785075664973,15.40709305360641,25.099999999996967,0.0,12750.0,-1.8,-936.48,500.0,1.4133911657333373,250000
|
| 3 |
+
0.0,0.0,-0.07566058452007268,-0.0026265863008170733,-0.07480821590802755,-0.019343030951510392,21.666904777586,14.342999999998613,0.56,33471.1,-0.64,-440.6,284.86,0.8303242683410644,300000
|
| 4 |
+
0.0,0.0,-0.04856043980943617,-0.020984773521005785,-0.04786937942097952,-0.004547285998156984,24.557080427273032,14.501999999998425,0.5,48176.02,-0.62,-372.88,288.04,0.8221420097351074,350000
|
| 5 |
+
0.0,0.0,-0.06530644518786256,0.018157823149944668,-0.06293958929493493,0.02944069928888288,30.040927957585332,9.208999999999087,0.74,59622.12,-0.38,-269.54,182.18,0.5322904396057129,400000
|
| 6 |
+
0.0,0.0,-0.08206181704096192,0.04505139246553543,-0.07970731765983881,0.025021658864389073,25.411482897691727,11.634999999998762,0.62,69686.12,-0.56,-343.56,230.7,0.6591518592834472,450000
|
| 7 |
+
0.0,0.0,-0.07579096422092381,0.027439509267844723,-0.07289283722673706,0.04044241203100295,28.723548502733866,9.581999999999018,0.7,81524.3,-0.38,-262.26,189.64,0.5498211479187012,500000
|
| 8 |
+
0.0,0.0,-0.06894131610494213,0.07139315746445352,-0.06722288247317437,0.0074025231065940195,29.004100100217933,7.347999999999314,0.8,90107.48,-0.28,-213.94,144.96,0.42887416839599607,550000
|
| 9 |
+
0.0,0.0,-0.07346641406187444,0.024352794947629694,-0.07197463862665744,0.03661250161703644,31.134592059984673,7.070999999999409,0.82,97698.64,-0.3,-226.0,139.42,0.41810898303985594,600000
|
| 10 |
+
0.0,0.0,-0.08568885651160255,0.03338808492081609,-0.08332221068890887,0.05344110350323892,32.74773407015043,4.477999999999746,0.94,103403.76,-0.08,-125.76,87.56,0.2720853567123413,650000
|
| 11 |
+
0.0,0.0,-0.07537963203055899,0.04379842602796201,-0.07358803138567031,0.03390372599060939,31.334385017403932,7.095999999999342,0.8,110136.16,-0.34,-230.42,139.92,0.41614169120788574,700000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/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,-0.05699617164448793,0.06464115899720767,-0.06090479169976698,-0.10711785075664973,15.40709305360641,25.099999999996967,0.0,12750.0,-1.8,-936.48,500.0,1.4133911657333373,250000
|
| 3 |
+
0.0,0.0,-0.07566058452007268,-0.0026265863008170733,-0.07480821590802755,-0.019343030951510392,21.666904777586,14.342999999998613,0.56,33471.1,-0.64,-440.6,284.86,0.8303242683410644,300000
|
| 4 |
+
0.0,0.0,-0.04856043980943617,-0.020984773521005785,-0.04786937942097952,-0.004547285998156984,24.557080427273032,14.501999999998425,0.5,48176.02,-0.62,-372.88,288.04,0.8221420097351074,350000
|
| 5 |
+
0.0,0.0,-0.06530644518786256,0.018157823149944668,-0.06293958929493493,0.02944069928888288,30.040927957585332,9.208999999999087,0.74,59622.12,-0.38,-269.54,182.18,0.5322904396057129,400000
|
| 6 |
+
0.0,0.0,-0.08206181704096192,0.04505139246553543,-0.07970731765983881,0.025021658864389073,25.411482897691727,11.634999999998762,0.62,69686.12,-0.56,-343.56,230.7,0.6591518592834472,450000
|
| 7 |
+
0.0,0.0,-0.07579096422092381,0.027439509267844723,-0.07289283722673706,0.04044241203100295,28.723548502733866,9.581999999999018,0.7,81524.3,-0.38,-262.26,189.64,0.5498211479187012,500000
|
| 8 |
+
0.0,0.0,-0.06894131610494213,0.07139315746445352,-0.06722288247317437,0.0074025231065940195,29.004100100217933,7.347999999999314,0.8,90107.48,-0.28,-213.94,144.96,0.42887416839599607,550000
|
| 9 |
+
0.0,0.0,-0.07346641406187444,0.024352794947629694,-0.07197463862665744,0.03661250161703644,31.134592059984673,7.070999999999409,0.82,97698.64,-0.3,-226.0,139.42,0.41810898303985594,600000
|
| 10 |
+
0.0,0.0,-0.08568885651160255,0.03338808492081609,-0.08332221068890887,0.05344110350323892,32.74773407015043,4.477999999999746,0.94,103403.76,-0.08,-125.76,87.56,0.2720853567123413,650000
|
| 11 |
+
0.0,0.0,-0.07537963203055899,0.04379842602796201,-0.07358803138567031,0.03390372599060939,31.334385017403932,7.095999999999342,0.8,110136.16,-0.34,-230.42,139.92,0.41614169120788574,700000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/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 |
+
307.83542,1.793665,2.7675521,14.658337,-39.88145,-75.928604,4.304818,-4.3877177,140.2789,205000
|
| 3 |
+
523.22437,0.96614903,0.80337393,-8.93338,-60.41825,-89.43572,1.0939847,-1.1289848,55.19023,210000
|
| 4 |
+
566.32306,0.6782825,1.0762153,-14.224123,-63.588905,-107.281525,2.1317894,-2.021386,79.5786,215000
|
| 5 |
+
578.84644,0.74034584,2.7977016,-5.670749,-64.89535,-110.983826,1.7395937,-1.849431,74.765945,220000
|
| 6 |
+
590.42694,0.8053446,1.1884961,-20.95797,-66.188286,-133.53497,0.7686094,-0.90649194,43.420246,225000
|
| 7 |
+
591.8493,0.95215124,1.1334,-13.742861,-66.71592,-131.16847,0.707565,-0.68699414,49.77237,230000
|
| 8 |
+
621.1783,0.7424199,0.95694274,-17.515377,-69.20687,-123.286545,0.67089754,-0.5433514,36.277115,235000
|
| 9 |
+
650.199,0.7801167,1.2859272,-22.80959,-72.05124,-140.2091,0.87777954,-0.863151,51.424824,240000
|
| 10 |
+
651.8649,0.73409414,1.0219921,-19.776747,-72.172035,-135.43947,0.91527236,-1.0669675,51.58935,245000
|
| 11 |
+
656.46497,0.7779803,1.6508417,-19.951185,-72.86702,-150.68822,2.0632205,-2.395191,73.39572,250000
|
| 12 |
+
644.9502,0.8613961,1.664691,-16.601467,-71.74284,-157.60094,1.8192812,-1.7890648,66.50876,255000
|
| 13 |
+
665.91895,0.8101858,1.1733614,-15.887938,-73.87853,-159.16853,2.9122672,-3.155864,96.05113,260000
|
| 14 |
+
683.9032,0.8830366,1.3788756,-18.329144,-74.86692,-146.2242,0.74097437,-0.65518636,44.35733,265000
|
| 15 |
+
666.3971,0.76082504,1.6316124,-8.590696,-72.85662,-161.64143,1.2410312,-1.1914666,59.15974,270000
|
| 16 |
+
695.3875,0.71524566,5.986065,-8.90675,-76.38079,-153.75552,1.2390528,-1.2227583,114.9651,275000
|
| 17 |
+
762.09735,0.91887367,1.6258595,-14.562922,-83.05414,-165.86906,2.5872478,-2.74089,97.749626,280000
|
| 18 |
+
755.8332,0.75963295,1.8623085,-29.944302,-81.824585,-164.98926,1.9632368,-1.4006493,75.434265,285000
|
| 19 |
+
746.2163,0.84899473,2.477015,-13.793045,-81.385826,-165.19899,3.3271608,-2.2117732,122.06877,290000
|
| 20 |
+
749.92,0.7301721,1.7219219,-20.853085,-81.93671,-169.8335,2.6929262,-2.5809112,105.53824,295000
|
| 21 |
+
747.33386,0.90590173,1.9565262,-16.494677,-80.9573,-171.36572,0.6200655,-0.6119353,53.403458,300000
|
| 22 |
+
748.35913,0.84598815,1.5198315,-13.069603,-81.00079,-156.5961,1.6914355,-1.7671801,71.657745,305000
|
| 23 |
+
769.9906,0.78907955,1.5606059,-20.896238,-83.55464,-167.31284,2.6264787,-2.7908702,87.71128,310000
|
| 24 |
+
741.8078,0.9730549,3.5216649,0.7255939,-80.548805,-161.14789,4.8148074,-4.695322,178.48187,315000
|
| 25 |
+
758.9595,0.91433394,1.5694095,-15.258568,-82.131645,-164.84064,2.204582,-2.3928683,79.386505,320000
|
| 26 |
+
781.9578,0.86858886,5.066304,-12.2236185,-84.701866,-161.69556,2.524811,-1.9152747,103.95055,325000
|
| 27 |
+
771.1138,0.794654,1.8843285,-17.528488,-83.468636,-173.04239,0.9568811,-0.86028856,60.22349,330000
|
| 28 |
+
759.1896,0.8494746,2.5856538,0.90867853,-82.72196,-167.34496,16.413382,-17.421421,464.075,335000
|
| 29 |
+
739.74084,0.7508485,1.5931369,-8.917828,-80.75937,-160.16693,0.64200664,-0.6338844,50.15498,340000
|
| 30 |
+
796.1317,0.9650283,2.5250852,-14.5802555,-86.05033,-173.83781,1.84056,-1.9503187,88.38152,345000
|
| 31 |
+
766.0113,0.9911655,1.6578312,-14.526748,-82.811134,-174.5528,0.80039024,-0.8957381,53.413868,350000
|
| 32 |
+
794.9009,1.0557842,2.259031,-20.034386,-85.78383,-160.28177,10.591969,-10.923729,238.83728,355000
|
| 33 |
+
780.94055,0.9715284,3.499096,-14.612205,-84.61382,-164.25626,10.578691,-13.06365,278.23816,360000
|
| 34 |
+
754.7522,0.9613766,2.498183,-0.82981884,-81.72204,-160.57509,16.319576,-13.153356,264.6828,365000
|
| 35 |
+
771.08484,0.8919723,1.7811209,-20.397013,-83.669365,-163.47224,1.391944,-1.3800358,60.10766,370000
|
| 36 |
+
772.6834,0.911255,2.0883012,-22.91697,-83.93684,-160.09778,2.359006,-2.2429192,79.61801,375000
|
| 37 |
+
794.80225,1.0568943,2.1284254,0.49107608,-85.64294,-161.24074,3.5865254,-3.555028,170.88725,380000
|
| 38 |
+
758.34906,1.708389,1.8339242,-10.24332,-82.032555,-164.0032,1.7107015,-1.7692294,66.9872,385000
|
| 39 |
+
798.93695,1.1128302,2.0244148,-9.805181,-85.66805,-162.21866,2.6629627,-3.8617377,109.5607,390000
|
| 40 |
+
772.98566,0.9724028,2.1282125,-11.910434,-83.43297,-155.22061,1.6631026,-1.3321999,90.95624,395000
|
| 41 |
+
746.1699,0.98203164,3.1937177,-15.985418,-81.25673,-159.07687,1.6415353,-1.5283307,104.28491,400000
|
| 42 |
+
747.69257,0.9173328,1.6401476,-11.058545,-81.13695,-154.8654,2.210377,-2.2705119,80.773865,405000
|
| 43 |
+
772.7285,0.94127893,2.7433205,-10.808118,-83.25367,-166.85974,2.8714716,-2.1163375,93.2899,410000
|
| 44 |
+
762.3127,0.9808898,7.805565,-20.002422,-82.308716,-154.5585,1.0629263,-1.0599253,116.22918,415000
|
| 45 |
+
768.2635,0.90388083,2.1835537,-5.238626,-82.92842,-159.1342,0.5306538,-0.7286174,55.811607,420000
|
| 46 |
+
762.5906,0.9534911,2.7586312,-8.651483,-82.647415,-171.8847,2.6092997,-2.2515383,88.78845,425000
|
| 47 |
+
768.0729,0.9708425,2.2048488,-6.430045,-83.12182,-171.23885,0.9212113,-0.908861,77.85809,430000
|
| 48 |
+
799.0898,0.9866633,2.2989678,0.59026945,-85.43897,-161.06929,1.9268559,-2.0553987,74.30763,435000
|
| 49 |
+
802.8656,1.0224797,1.8265755,1.5993512,-86.16832,-170.57097,4.130285,-3.7735674,93.527176,440000
|
| 50 |
+
763.7656,0.7663493,3.3064988,-14.390343,-82.69651,-165.11554,3.2577562,-2.3350217,163.0376,445000
|
| 51 |
+
786.2036,1.0760219,2.8084695,-13.294111,-84.6866,-168.08928,1.7716986,-1.9807835,89.733734,450000
|
| 52 |
+
763.69293,1.0321407,3.9577465,-1.1707848,-82.81768,-166.76517,4.057183,-4.6366754,123.28573,455000
|
| 53 |
+
772.68787,1.0329776,2.376705,2.361213,-83.43156,-170.10316,0.9231405,-0.88741374,83.52904,460000
|
| 54 |
+
779.2358,0.8745657,1.9190731,-6.2075853,-83.95597,-164.62248,3.6426702,-4.0028486,122.73597,465000
|
| 55 |
+
770.9371,1.031793,1.8604239,-6.239957,-83.38439,-166.38364,1.894074,-1.8563211,73.384796,470000
|
| 56 |
+
775.4998,0.9292489,2.0963008,-5.373879,-83.00736,-169.97318,3.5684755,-3.9034228,120.93565,475000
|
| 57 |
+
770.16016,0.95176584,2.798187,-6.372719,-83.27926,-163.10226,1.8452024,-1.9095354,76.04393,480000
|
| 58 |
+
794.0695,0.86886036,1.8031464,-0.43163857,-85.04821,-171.34076,5.233616,-5.2427425,119.80111,485000
|
| 59 |
+
763.2033,0.95936286,3.070649,-5.591586,-82.26265,-167.68565,14.17649,-15.711923,352.4126,490000
|
| 60 |
+
745.59924,1.0256393,2.336327,1.5840414,-80.739395,-162.12631,1.4295558,-1.2649778,80.047714,495000
|
| 61 |
+
735.8148,0.9515474,2.2841165,-7.735282,-80.24558,-156.81343,8.265721,-8.193528,184.37581,500000
|
| 62 |
+
777.70496,0.9672977,3.0193431,-19.557632,-83.89147,-164.06381,1.6335236,-3.2753358,113.68937,505000
|
| 63 |
+
747.4667,1.1585672,1.9787432,-1.5425113,-81.419876,-156.06587,0.98202586,-0.9223322,55.46113,510000
|
| 64 |
+
763.8452,0.90029675,1.8833016,-7.3374987,-82.01514,-162.95271,2.2953386,-2.22655,104.3707,515000
|
| 65 |
+
761.4081,0.93714845,1.3539032,-8.572325,-82.1323,-164.15619,1.2797341,-1.0839049,78.09419,520000
|
| 66 |
+
789.4384,1.0234425,2.4678173,-6.4653277,-84.99938,-164.29033,1.1962557,-1.2663237,82.31457,525000
|
| 67 |
+
762.8968,1.1679704,3.188115,-13.659868,-82.27193,-159.99469,1.1029567,-1.0956413,96.79672,530000
|
| 68 |
+
760.76575,1.172574,3.0082371,-7.3762817,-82.06045,-168.96298,118.958015,-129.6369,1931.786,535000
|
| 69 |
+
740.8473,1.0818167,2.9773412,-10.748354,-80.204185,-163.53171,8.717296,-6.914601,163.84671,540000
|
| 70 |
+
766.45764,0.90390444,2.5999181,-8.499114,-83.106316,-163.78673,2.3480215,-2.0769427,86.69771,545000
|
| 71 |
+
770.36035,1.0449016,2.070336,0.20556438,-82.51815,-166.81909,1.6504345,-1.6947577,67.43655,550000
|
| 72 |
+
802.01825,1.1170733,1.7890667,-1.6000022,-86.04614,-170.20479,1.1755295,-1.3392719,79.772865,555000
|
| 73 |
+
753.88666,1.5055323,2.6022732,-4.0792236,-81.65893,-165.38313,4.1257367,-4.342637,119.07138,560000
|
| 74 |
+
758.0267,1.0742437,2.3054419,-12.47301,-81.83133,-161.25655,3.806193,-3.7439253,198.44547,565000
|
| 75 |
+
773.2891,1.006701,2.5553026,-4.7478647,-83.30486,-168.1766,5.3362055,-4.87416,102.66571,570000
|
| 76 |
+
728.9005,1.1875477,3.0569103,1.1514593,-78.9178,-165.26512,1.1024479,-0.95818233,75.35169,575000
|
| 77 |
+
779.2055,1.0934572,3.5659082,-10.569957,-83.73431,-162.67047,1.8698443,-1.8977673,139.38995,580000
|
| 78 |
+
760.942,1.1929655,2.0766122,1.5686362,-82.379364,-164.83224,14.964014,-16.35613,217.57841,585000
|
| 79 |
+
759.35785,1.072459,2.3157418,-6.454669,-82.0476,-164.67218,1.0277828,-1.0223048,87.62096,590000
|
| 80 |
+
782.9371,1.1136749,2.7583902,-2.2587664,-83.83715,-162.03552,3.6491,-3.9602597,182.15161,595000
|
| 81 |
+
759.4783,1.4979874,2.7130039,-3.8616192,-81.33665,-163.00156,3.152574,-3.1613262,137.50581,600000
|
| 82 |
+
797.4717,1.246209,1.6508642,-6.0683036,-85.565704,-164.58829,1.4336586,-1.4896069,78.48396,605000
|
| 83 |
+
790.25183,1.0559512,1.8501667,-4.544305,-84.8751,-168.11516,8.067504,-7.079412,253.73181,610000
|
| 84 |
+
797.997,1.1225172,2.8006673,-6.191342,-85.570984,-171.33176,1.2615389,-1.0344052,78.71173,615000
|
| 85 |
+
740.7397,0.95345396,6.4575725,-2.8066897,-80.51119,-169.12813,2.2727175,-2.277347,165.09853,620000
|
| 86 |
+
757.31555,0.9848627,7.769878,-4.9074636,-81.689896,-162.79956,2.7197886,-2.551484,169.67732,625000
|
| 87 |
+
776.70483,1.2583416,2.3394315,-4.739601,-83.38695,-169.48222,1.7846217,-1.6328516,82.985435,630000
|
| 88 |
+
768.4716,0.8690716,2.6547892,-15.549565,-83.25967,-166.12439,1.1104459,-1.1505758,91.876144,635000
|
| 89 |
+
743.7819,1.1649928,2.9275048,-4.372989,-80.1354,-163.19379,3.8882377,-4.07357,117.90549,640000
|
| 90 |
+
801.7695,1.1988668,1.7456799,-1.7380884,-85.90453,-169.55591,7.299335,-7.9418526,104.485275,645000
|
| 91 |
+
782.03094,1.0477923,3.265155,-9.246789,-84.08828,-160.4854,3.8902333,-4.2040915,182.41928,650000
|
| 92 |
+
759.28143,1.1031941,1.9905663,0.6463961,-81.70992,-161.9456,1.9183719,-1.6918088,82.273,655000
|
| 93 |
+
759.0354,1.1815293,2.8303201,-3.9455237,-81.82238,-163.74663,6.940129,-6.7698474,258.32797,660000
|
| 94 |
+
758.0263,1.0065646,2.6815834,-5.3801885,-81.5498,-164.1728,7.2875266,-6.736727,125.48337,665000
|
| 95 |
+
742.72363,1.2090406,3.1084487,-4.3865223,-79.99974,-164.82199,1.9812262,-1.8997487,93.46996,670000
|
| 96 |
+
786.0614,1.4881375,2.4436584,-10.691938,-83.95382,-166.8836,8.564134,-8.224987,188.41699,675000
|
| 97 |
+
721.8196,1.2791996,3.1089513,1.1417885,-77.90663,-164.81308,1.5548667,-1.7478564,99.95951,680000
|
| 98 |
+
746.4883,0.9347684,2.249754,5.4471645,-80.5205,-169.04373,8.528228,-7.668897,107.263115,685000
|
| 99 |
+
757.95074,1.2179521,3.6762636,-5.5792246,-81.3787,-164.65039,2.5425625,-2.5779877,134.94673,690000
|
| 100 |
+
753.7887,1.1508981,3.0582745,-4.5014453,-81.50567,-164.27362,1.5473884,-1.4327343,107.405106,695000
|
| 101 |
+
750.93677,1.3527396,1.9100201,-7.3977113,-80.66726,-169.68169,6.238197,-6.080919,148.49457,700000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/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 |
+
307.83542,1.793665,2.7675521,14.658337,-39.88145,-75.928604,4.304818,-4.3877177,140.2789,205000
|
| 3 |
+
523.22437,0.96614903,0.80337393,-8.93338,-60.41825,-89.43572,1.0939847,-1.1289848,55.19023,210000
|
| 4 |
+
566.32306,0.6782825,1.0762153,-14.224123,-63.588905,-107.281525,2.1317894,-2.021386,79.5786,215000
|
| 5 |
+
578.84644,0.74034584,2.7977016,-5.670749,-64.89535,-110.983826,1.7395937,-1.849431,74.765945,220000
|
| 6 |
+
590.42694,0.8053446,1.1884961,-20.95797,-66.188286,-133.53497,0.7686094,-0.90649194,43.420246,225000
|
| 7 |
+
591.8493,0.95215124,1.1334,-13.742861,-66.71592,-131.16847,0.707565,-0.68699414,49.77237,230000
|
| 8 |
+
621.1783,0.7424199,0.95694274,-17.515377,-69.20687,-123.286545,0.67089754,-0.5433514,36.277115,235000
|
| 9 |
+
650.199,0.7801167,1.2859272,-22.80959,-72.05124,-140.2091,0.87777954,-0.863151,51.424824,240000
|
| 10 |
+
651.8649,0.73409414,1.0219921,-19.776747,-72.172035,-135.43947,0.91527236,-1.0669675,51.58935,245000
|
| 11 |
+
656.46497,0.7779803,1.6508417,-19.951185,-72.86702,-150.68822,2.0632205,-2.395191,73.39572,250000
|
| 12 |
+
644.9502,0.8613961,1.664691,-16.601467,-71.74284,-157.60094,1.8192812,-1.7890648,66.50876,255000
|
| 13 |
+
665.91895,0.8101858,1.1733614,-15.887938,-73.87853,-159.16853,2.9122672,-3.155864,96.05113,260000
|
| 14 |
+
683.9032,0.8830366,1.3788756,-18.329144,-74.86692,-146.2242,0.74097437,-0.65518636,44.35733,265000
|
| 15 |
+
666.3971,0.76082504,1.6316124,-8.590696,-72.85662,-161.64143,1.2410312,-1.1914666,59.15974,270000
|
| 16 |
+
695.3875,0.71524566,5.986065,-8.90675,-76.38079,-153.75552,1.2390528,-1.2227583,114.9651,275000
|
| 17 |
+
762.09735,0.91887367,1.6258595,-14.562922,-83.05414,-165.86906,2.5872478,-2.74089,97.749626,280000
|
| 18 |
+
755.8332,0.75963295,1.8623085,-29.944302,-81.824585,-164.98926,1.9632368,-1.4006493,75.434265,285000
|
| 19 |
+
746.2163,0.84899473,2.477015,-13.793045,-81.385826,-165.19899,3.3271608,-2.2117732,122.06877,290000
|
| 20 |
+
749.92,0.7301721,1.7219219,-20.853085,-81.93671,-169.8335,2.6929262,-2.5809112,105.53824,295000
|
| 21 |
+
747.33386,0.90590173,1.9565262,-16.494677,-80.9573,-171.36572,0.6200655,-0.6119353,53.403458,300000
|
| 22 |
+
748.35913,0.84598815,1.5198315,-13.069603,-81.00079,-156.5961,1.6914355,-1.7671801,71.657745,305000
|
| 23 |
+
769.9906,0.78907955,1.5606059,-20.896238,-83.55464,-167.31284,2.6264787,-2.7908702,87.71128,310000
|
| 24 |
+
741.8078,0.9730549,3.5216649,0.7255939,-80.548805,-161.14789,4.8148074,-4.695322,178.48187,315000
|
| 25 |
+
758.9595,0.91433394,1.5694095,-15.258568,-82.131645,-164.84064,2.204582,-2.3928683,79.386505,320000
|
| 26 |
+
781.9578,0.86858886,5.066304,-12.2236185,-84.701866,-161.69556,2.524811,-1.9152747,103.95055,325000
|
| 27 |
+
771.1138,0.794654,1.8843285,-17.528488,-83.468636,-173.04239,0.9568811,-0.86028856,60.22349,330000
|
| 28 |
+
759.1896,0.8494746,2.5856538,0.90867853,-82.72196,-167.34496,16.413382,-17.421421,464.075,335000
|
| 29 |
+
739.74084,0.7508485,1.5931369,-8.917828,-80.75937,-160.16693,0.64200664,-0.6338844,50.15498,340000
|
| 30 |
+
796.1317,0.9650283,2.5250852,-14.5802555,-86.05033,-173.83781,1.84056,-1.9503187,88.38152,345000
|
| 31 |
+
766.0113,0.9911655,1.6578312,-14.526748,-82.811134,-174.5528,0.80039024,-0.8957381,53.413868,350000
|
| 32 |
+
794.9009,1.0557842,2.259031,-20.034386,-85.78383,-160.28177,10.591969,-10.923729,238.83728,355000
|
| 33 |
+
780.94055,0.9715284,3.499096,-14.612205,-84.61382,-164.25626,10.578691,-13.06365,278.23816,360000
|
| 34 |
+
754.7522,0.9613766,2.498183,-0.82981884,-81.72204,-160.57509,16.319576,-13.153356,264.6828,365000
|
| 35 |
+
771.08484,0.8919723,1.7811209,-20.397013,-83.669365,-163.47224,1.391944,-1.3800358,60.10766,370000
|
| 36 |
+
772.6834,0.911255,2.0883012,-22.91697,-83.93684,-160.09778,2.359006,-2.2429192,79.61801,375000
|
| 37 |
+
794.80225,1.0568943,2.1284254,0.49107608,-85.64294,-161.24074,3.5865254,-3.555028,170.88725,380000
|
| 38 |
+
758.34906,1.708389,1.8339242,-10.24332,-82.032555,-164.0032,1.7107015,-1.7692294,66.9872,385000
|
| 39 |
+
798.93695,1.1128302,2.0244148,-9.805181,-85.66805,-162.21866,2.6629627,-3.8617377,109.5607,390000
|
| 40 |
+
772.98566,0.9724028,2.1282125,-11.910434,-83.43297,-155.22061,1.6631026,-1.3321999,90.95624,395000
|
| 41 |
+
746.1699,0.98203164,3.1937177,-15.985418,-81.25673,-159.07687,1.6415353,-1.5283307,104.28491,400000
|
| 42 |
+
747.69257,0.9173328,1.6401476,-11.058545,-81.13695,-154.8654,2.210377,-2.2705119,80.773865,405000
|
| 43 |
+
772.7285,0.94127893,2.7433205,-10.808118,-83.25367,-166.85974,2.8714716,-2.1163375,93.2899,410000
|
| 44 |
+
762.3127,0.9808898,7.805565,-20.002422,-82.308716,-154.5585,1.0629263,-1.0599253,116.22918,415000
|
| 45 |
+
768.2635,0.90388083,2.1835537,-5.238626,-82.92842,-159.1342,0.5306538,-0.7286174,55.811607,420000
|
| 46 |
+
762.5906,0.9534911,2.7586312,-8.651483,-82.647415,-171.8847,2.6092997,-2.2515383,88.78845,425000
|
| 47 |
+
768.0729,0.9708425,2.2048488,-6.430045,-83.12182,-171.23885,0.9212113,-0.908861,77.85809,430000
|
| 48 |
+
799.0898,0.9866633,2.2989678,0.59026945,-85.43897,-161.06929,1.9268559,-2.0553987,74.30763,435000
|
| 49 |
+
802.8656,1.0224797,1.8265755,1.5993512,-86.16832,-170.57097,4.130285,-3.7735674,93.527176,440000
|
| 50 |
+
763.7656,0.7663493,3.3064988,-14.390343,-82.69651,-165.11554,3.2577562,-2.3350217,163.0376,445000
|
| 51 |
+
786.2036,1.0760219,2.8084695,-13.294111,-84.6866,-168.08928,1.7716986,-1.9807835,89.733734,450000
|
| 52 |
+
763.69293,1.0321407,3.9577465,-1.1707848,-82.81768,-166.76517,4.057183,-4.6366754,123.28573,455000
|
| 53 |
+
772.68787,1.0329776,2.376705,2.361213,-83.43156,-170.10316,0.9231405,-0.88741374,83.52904,460000
|
| 54 |
+
779.2358,0.8745657,1.9190731,-6.2075853,-83.95597,-164.62248,3.6426702,-4.0028486,122.73597,465000
|
| 55 |
+
770.9371,1.031793,1.8604239,-6.239957,-83.38439,-166.38364,1.894074,-1.8563211,73.384796,470000
|
| 56 |
+
775.4998,0.9292489,2.0963008,-5.373879,-83.00736,-169.97318,3.5684755,-3.9034228,120.93565,475000
|
| 57 |
+
770.16016,0.95176584,2.798187,-6.372719,-83.27926,-163.10226,1.8452024,-1.9095354,76.04393,480000
|
| 58 |
+
794.0695,0.86886036,1.8031464,-0.43163857,-85.04821,-171.34076,5.233616,-5.2427425,119.80111,485000
|
| 59 |
+
763.2033,0.95936286,3.070649,-5.591586,-82.26265,-167.68565,14.17649,-15.711923,352.4126,490000
|
| 60 |
+
745.59924,1.0256393,2.336327,1.5840414,-80.739395,-162.12631,1.4295558,-1.2649778,80.047714,495000
|
| 61 |
+
735.8148,0.9515474,2.2841165,-7.735282,-80.24558,-156.81343,8.265721,-8.193528,184.37581,500000
|
| 62 |
+
777.70496,0.9672977,3.0193431,-19.557632,-83.89147,-164.06381,1.6335236,-3.2753358,113.68937,505000
|
| 63 |
+
747.4667,1.1585672,1.9787432,-1.5425113,-81.419876,-156.06587,0.98202586,-0.9223322,55.46113,510000
|
| 64 |
+
763.8452,0.90029675,1.8833016,-7.3374987,-82.01514,-162.95271,2.2953386,-2.22655,104.3707,515000
|
| 65 |
+
761.4081,0.93714845,1.3539032,-8.572325,-82.1323,-164.15619,1.2797341,-1.0839049,78.09419,520000
|
| 66 |
+
789.4384,1.0234425,2.4678173,-6.4653277,-84.99938,-164.29033,1.1962557,-1.2663237,82.31457,525000
|
| 67 |
+
762.8968,1.1679704,3.188115,-13.659868,-82.27193,-159.99469,1.1029567,-1.0956413,96.79672,530000
|
| 68 |
+
760.76575,1.172574,3.0082371,-7.3762817,-82.06045,-168.96298,118.958015,-129.6369,1931.786,535000
|
| 69 |
+
740.8473,1.0818167,2.9773412,-10.748354,-80.204185,-163.53171,8.717296,-6.914601,163.84671,540000
|
| 70 |
+
766.45764,0.90390444,2.5999181,-8.499114,-83.106316,-163.78673,2.3480215,-2.0769427,86.69771,545000
|
| 71 |
+
770.36035,1.0449016,2.070336,0.20556438,-82.51815,-166.81909,1.6504345,-1.6947577,67.43655,550000
|
| 72 |
+
802.01825,1.1170733,1.7890667,-1.6000022,-86.04614,-170.20479,1.1755295,-1.3392719,79.772865,555000
|
| 73 |
+
753.88666,1.5055323,2.6022732,-4.0792236,-81.65893,-165.38313,4.1257367,-4.342637,119.07138,560000
|
| 74 |
+
758.0267,1.0742437,2.3054419,-12.47301,-81.83133,-161.25655,3.806193,-3.7439253,198.44547,565000
|
| 75 |
+
773.2891,1.006701,2.5553026,-4.7478647,-83.30486,-168.1766,5.3362055,-4.87416,102.66571,570000
|
| 76 |
+
728.9005,1.1875477,3.0569103,1.1514593,-78.9178,-165.26512,1.1024479,-0.95818233,75.35169,575000
|
| 77 |
+
779.2055,1.0934572,3.5659082,-10.569957,-83.73431,-162.67047,1.8698443,-1.8977673,139.38995,580000
|
| 78 |
+
760.942,1.1929655,2.0766122,1.5686362,-82.379364,-164.83224,14.964014,-16.35613,217.57841,585000
|
| 79 |
+
759.35785,1.072459,2.3157418,-6.454669,-82.0476,-164.67218,1.0277828,-1.0223048,87.62096,590000
|
| 80 |
+
782.9371,1.1136749,2.7583902,-2.2587664,-83.83715,-162.03552,3.6491,-3.9602597,182.15161,595000
|
| 81 |
+
759.4783,1.4979874,2.7130039,-3.8616192,-81.33665,-163.00156,3.152574,-3.1613262,137.50581,600000
|
| 82 |
+
797.4717,1.246209,1.6508642,-6.0683036,-85.565704,-164.58829,1.4336586,-1.4896069,78.48396,605000
|
| 83 |
+
790.25183,1.0559512,1.8501667,-4.544305,-84.8751,-168.11516,8.067504,-7.079412,253.73181,610000
|
| 84 |
+
797.997,1.1225172,2.8006673,-6.191342,-85.570984,-171.33176,1.2615389,-1.0344052,78.71173,615000
|
| 85 |
+
740.7397,0.95345396,6.4575725,-2.8066897,-80.51119,-169.12813,2.2727175,-2.277347,165.09853,620000
|
| 86 |
+
757.31555,0.9848627,7.769878,-4.9074636,-81.689896,-162.79956,2.7197886,-2.551484,169.67732,625000
|
| 87 |
+
776.70483,1.2583416,2.3394315,-4.739601,-83.38695,-169.48222,1.7846217,-1.6328516,82.985435,630000
|
| 88 |
+
768.4716,0.8690716,2.6547892,-15.549565,-83.25967,-166.12439,1.1104459,-1.1505758,91.876144,635000
|
| 89 |
+
743.7819,1.1649928,2.9275048,-4.372989,-80.1354,-163.19379,3.8882377,-4.07357,117.90549,640000
|
| 90 |
+
801.7695,1.1988668,1.7456799,-1.7380884,-85.90453,-169.55591,7.299335,-7.9418526,104.485275,645000
|
| 91 |
+
782.03094,1.0477923,3.265155,-9.246789,-84.08828,-160.4854,3.8902333,-4.2040915,182.41928,650000
|
| 92 |
+
759.28143,1.1031941,1.9905663,0.6463961,-81.70992,-161.9456,1.9183719,-1.6918088,82.273,655000
|
| 93 |
+
759.0354,1.1815293,2.8303201,-3.9455237,-81.82238,-163.74663,6.940129,-6.7698474,258.32797,660000
|
| 94 |
+
758.0263,1.0065646,2.6815834,-5.3801885,-81.5498,-164.1728,7.2875266,-6.736727,125.48337,665000
|
| 95 |
+
742.72363,1.2090406,3.1084487,-4.3865223,-79.99974,-164.82199,1.9812262,-1.8997487,93.46996,670000
|
| 96 |
+
786.0614,1.4881375,2.4436584,-10.691938,-83.95382,-166.8836,8.564134,-8.224987,188.41699,675000
|
| 97 |
+
721.8196,1.2791996,3.1089513,1.1417885,-77.90663,-164.81308,1.5548667,-1.7478564,99.95951,680000
|
| 98 |
+
746.4883,0.9347684,2.249754,5.4471645,-80.5205,-169.04373,8.528228,-7.668897,107.263115,685000
|
| 99 |
+
757.95074,1.2179521,3.6762636,-5.5792246,-81.3787,-164.65039,2.5425625,-2.5779877,134.94673,690000
|
| 100 |
+
753.7887,1.1508981,3.0582745,-4.5014453,-81.50567,-164.27362,1.5473884,-1.4327343,107.405106,695000
|
| 101 |
+
750.93677,1.3527396,1.9100201,-7.3977113,-80.66726,-169.68169,6.238197,-6.080919,148.49457,700000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_250000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c3d0fa048438bbaf2b04735e8fc945b9217254ea0d649189e35cd384d054bd0
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_300000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72eac7ea3b2f5671713b8b3b2de93d7ebfa8c7eefd9178727436cfcbfeae72f5
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12ce6d247a3363007aa143e47f42ca6b292c4f4d5e0881283b98891f0f313eed
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1804547a846744c0195f77461ff80215c9490d896259e2a650d62cd9015ead87
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f6691c378ba1c6f444953af49c22a8167e7499b9fbf9887a5931361fc1e3ef5
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a43dece5536f09386b3482dbcd49e6afad08b8aa47b38eace2041555d0a1d36f
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7234d725aa0446365dfa61f91fce426d80044082d8ea98a0a898041b45b50712
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8293d9dcb52de0a2fe2148cad63044b5b92a5f704d325f7fa1f0900c7953d5b6
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4990161e220a95e941b410cac46559a75bb3550dd49bccb4efa1725cf4109297
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e27d4b3d3f4d138fd3959d099ec72067ff473554fdeedb1f49fc06ed9566ed
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_114727/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/29kxftv4
|