Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_1000000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_650000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_700000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_750000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_800000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_850000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_900000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_950000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/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_152035/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_152035/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,-0.114905569908874,0.0966387590178643,-0.11786952055012989,-0.07340766515952761,17.444846301234126,24.83599999999704,0.02,12713.04,-1.84,-935.0,494.72,1.400816240310669,550000
|
| 3 |
+
0.0,0.0,-0.10020809524237496,-0.09047573474290983,-0.0988958858149892,0.012558130274513114,18.834221781667583,18.24099999999804,0.36,34756.0,-0.88,-517.7,362.82,1.0435595655441283,600000
|
| 4 |
+
0.0,0.0,-0.07440191544977202,-0.008309078587908369,-0.07425046851485058,0.0022315838987599455,24.959090768307,13.507999999998518,0.56,51485.1,-0.56,-373.78,268.16,0.7911075019836425,650000
|
| 5 |
+
0.0,0.0,-0.09252863707130177,-0.006315674640673463,-0.09238863411108209,-0.013227407748618183,25.784344137728407,10.748999999998942,0.7,64292.08,-0.42,-299.96,212.98,0.6231187438964844,700000
|
| 6 |
+
0.0,0.0,-0.11366039215340554,0.01462099911754362,-0.11266125704612376,0.02898236826371212,23.33345188369187,13.342999999998659,0.58,77728.28,-0.56,-367.46,264.86,0.7602690553665161,750000
|
| 7 |
+
0.0,0.0,-0.0979220644676609,-0.015600949986369394,-0.09674056711251014,0.015533188433250416,26.789701636692346,8.832999999999231,0.76,87543.26,-0.28,-221.18,174.66,0.5103612852096557,800000
|
| 8 |
+
0.0,0.0,-0.10988397289969269,0.03678519284056649,-0.10875559572659492,0.052651708947003655,25.455105460122784,10.564999999998983,0.68,99247.52,-0.38,-276.18,209.3,0.6024122619628907,850000
|
| 9 |
+
0.0,0.0,-0.11322017416311332,0.011259390487536818,-0.11092618053620981,0.04863478771754904,26.391929947407636,11.269999999998795,0.62,109813.06,-0.48,-305.3,223.4,0.6545119762420655,900000
|
| 10 |
+
0.0,0.0,-0.09229196421978941,0.039751049147008916,-0.08855407194746986,0.09207928142788163,32.25221076183134,6.273999999999522,0.86,119605.96,-0.16,-165.6,123.48,0.37300356388092043,950000
|
| 11 |
+
0.0,0.0,-0.09225493541175764,0.05585587024595849,-0.08999874243470221,0.049695346874352425,31.82959455573425,6.669999999999399,0.82,125485.1,-0.2,-163.64,131.4,0.38932892322540286,1000000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/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,-0.114905569908874,0.0966387590178643,-0.11786952055012989,-0.07340766515952761,17.444846301234126,24.83599999999704,0.02,12713.04,-1.84,-935.0,494.72,1.400816240310669,550000
|
| 3 |
+
0.0,0.0,-0.10020809524237496,-0.09047573474290983,-0.0988958858149892,0.012558130274513114,18.834221781667583,18.24099999999804,0.36,34756.0,-0.88,-517.7,362.82,1.0435595655441283,600000
|
| 4 |
+
0.0,0.0,-0.07440191544977202,-0.008309078587908369,-0.07425046851485058,0.0022315838987599455,24.959090768307,13.507999999998518,0.56,51485.1,-0.56,-373.78,268.16,0.7911075019836425,650000
|
| 5 |
+
0.0,0.0,-0.09252863707130177,-0.006315674640673463,-0.09238863411108209,-0.013227407748618183,25.784344137728407,10.748999999998942,0.7,64292.08,-0.42,-299.96,212.98,0.6231187438964844,700000
|
| 6 |
+
0.0,0.0,-0.11366039215340554,0.01462099911754362,-0.11266125704612376,0.02898236826371212,23.33345188369187,13.342999999998659,0.58,77728.28,-0.56,-367.46,264.86,0.7602690553665161,750000
|
| 7 |
+
0.0,0.0,-0.0979220644676609,-0.015600949986369394,-0.09674056711251014,0.015533188433250416,26.789701636692346,8.832999999999231,0.76,87543.26,-0.28,-221.18,174.66,0.5103612852096557,800000
|
| 8 |
+
0.0,0.0,-0.10988397289969269,0.03678519284056649,-0.10875559572659492,0.052651708947003655,25.455105460122784,10.564999999998983,0.68,99247.52,-0.38,-276.18,209.3,0.6024122619628907,850000
|
| 9 |
+
0.0,0.0,-0.11322017416311332,0.011259390487536818,-0.11092618053620981,0.04863478771754904,26.391929947407636,11.269999999998795,0.62,109813.06,-0.48,-305.3,223.4,0.6545119762420655,900000
|
| 10 |
+
0.0,0.0,-0.09229196421978941,0.039751049147008916,-0.08855407194746986,0.09207928142788163,32.25221076183134,6.273999999999522,0.86,119605.96,-0.16,-165.6,123.48,0.37300356388092043,950000
|
| 11 |
+
0.0,0.0,-0.09225493541175764,0.05585587024595849,-0.08999874243470221,0.049695346874352425,31.82959455573425,6.669999999999399,0.82,125485.1,-0.2,-163.64,131.4,0.38932892322540286,1000000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/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 |
+
452.64963,1.3365817,1.2069706,-12.485567,-52.933075,-80.61363,8.783501,-8.928215,181.71524,505000
|
| 3 |
+
559.66284,1.0443755,0.92943305,-8.129159,-63.30897,-108.81358,3.6967893,-4.202759,109.349525,510000
|
| 4 |
+
622.093,1.0110067,2.2279537,-14.656605,-68.86446,-128.44435,3.2290697,-2.4222085,127.03331,515000
|
| 5 |
+
619.937,0.9812181,4.8216796,-7.247258,-68.91629,-137.88098,1.6995468,-2.2213764,99.16235,520000
|
| 6 |
+
630.8488,1.083922,1.0856203,-22.498034,-70.02803,-143.04993,1.4073087,-0.9642714,48.787415,525000
|
| 7 |
+
626.36786,0.8056767,1.4185972,-15.357644,-69.67832,-137.90758,1.9520855,-1.3586434,73.00691,530000
|
| 8 |
+
657.28033,0.8454031,1.3148359,-18.310362,-72.402725,-166.06557,1.9898548,-1.1056539,67.9273,535000
|
| 9 |
+
686.59454,0.86820596,2.326125,-23.615171,-75.42804,-149.55359,1.1452193,-1.7089608,80.87784,540000
|
| 10 |
+
713.48645,0.8825395,0.9496853,-20.256691,-78.071625,-161.07913,2.298263,-1.3884568,51.700264,545000
|
| 11 |
+
688.1092,0.9321668,6.517915,-17.382526,-75.841934,-152.99513,1.3055468,-1.0212194,70.02578,550000
|
| 12 |
+
684.44495,0.9688769,2.0982056,-15.546474,-75.494316,-159.8163,1.5294067,-1.3878953,83.16202,555000
|
| 13 |
+
678.7258,0.83121765,14.1827135,-11.263893,-75.110085,-148.79855,2.7857358,-2.1162496,151.11133,560000
|
| 14 |
+
709.09564,0.8433461,1.7338623,-15.733488,-77.09317,-159.87814,6.4007363,-6.7011356,125.485214,565000
|
| 15 |
+
693.79486,0.8908032,1.515094,-6.5018826,-75.721855,-154.91469,1.8115747,-2.9767485,77.54168,570000
|
| 16 |
+
741.0875,0.8446889,3.4812584,-14.633865,-80.82051,-149.60175,2.7435834,-2.8581104,143.67911,575000
|
| 17 |
+
800.3168,0.9172359,2.4218976,-16.861435,-86.89566,-168.53708,4.771409,-5.0321984,187.97726,580000
|
| 18 |
+
786.84784,0.87580293,1.3891503,-30.73769,-84.64697,-163.71417,1.9244152,-0.9103417,67.65885,585000
|
| 19 |
+
794.47705,1.0227067,2.38917,-11.371363,-85.64825,-166.0282,2.8272905,-2.9474912,130.75114,590000
|
| 20 |
+
790.8795,1.1262503,2.3630512,-13.594788,-85.67608,-168.31313,1.505192,-2.1302314,74.73902,595000
|
| 21 |
+
800.93097,1.2703251,1.6120666,-20.139086,-86.10514,-166.01074,2.152046,-1.1901779,67.80056,600000
|
| 22 |
+
795.4496,0.7565539,1.7396263,-20.781033,-85.66836,-167.15536,1.4680107,-1.415065,63.816948,605000
|
| 23 |
+
806.39026,0.8593606,3.3986886,-12.396617,-86.973564,-170.70992,1.714979,-1.1813933,80.12377,610000
|
| 24 |
+
811.3909,0.9197198,1.4346079,2.2689922,-87.18085,-170.09056,21.346859,-11.140747,123.7889,615000
|
| 25 |
+
841.4316,1.1305273,2.40654,-24.35551,-90.41176,-167.7204,3.1437163,-4.788018,125.13218,620000
|
| 26 |
+
832.0072,0.9796524,1.6525596,-18.366638,-89.20034,-170.35107,1.6371228,-1.5151939,72.6409,625000
|
| 27 |
+
827.8084,0.96790683,1.7014748,-22.37032,-88.77531,-167.83813,1.6562937,-2.0322208,74.937775,630000
|
| 28 |
+
812.9805,0.9067867,4.1661854,1.8191855,-87.74334,-169.17377,14.925431,-15.634887,185.35074,635000
|
| 29 |
+
801.98566,0.8905717,2.635463,-11.380878,-87.09883,-169.01581,142.1382,-160.08507,1794.8265,640000
|
| 30 |
+
863.3928,0.8611659,1.6370811,-21.974714,-92.18876,-168.93178,3.8006785,-5.043507,140.21938,645000
|
| 31 |
+
811.8284,0.9076445,1.7756379,-6.5885825,-87.11571,-166.10995,2.0374637,-2.583291,81.8782,650000
|
| 32 |
+
830.8817,0.9805214,3.1536007,-19.459953,-89.14821,-169.83282,1.885306,-1.8152032,85.64246,655000
|
| 33 |
+
846.4515,0.9691616,1.894246,-15.379924,-90.523186,-165.93822,4.9384556,-5.8031464,196.78716,660000
|
| 34 |
+
832.394,0.7463238,2.4937353,-1.3362442,-89.313965,-174.32054,2.54174,-2.314888,97.124886,665000
|
| 35 |
+
857.12476,1.1248933,1.9899939,-18.54427,-91.58545,-170.69395,1.5208448,-2.0596642,82.771805,670000
|
| 36 |
+
882.73065,0.91497755,1.8098654,-14.838122,-94.181946,-170.2052,2.5070875,-1.6607951,75.39378,675000
|
| 37 |
+
885.8963,0.94194716,2.4034226,1.5750592,-94.36911,-175.31862,1.2831758,-2.346087,87.42029,680000
|
| 38 |
+
842.83484,0.87256277,1.6620804,-7.067542,-90.26408,-174.48,3.9395485,-3.7543225,147.45769,685000
|
| 39 |
+
855.2505,1.4137268,2.1317623,-15.049857,-90.99187,-167.7689,2.1336272,-3.1357837,77.04313,690000
|
| 40 |
+
828.896,0.99673766,1.7208693,-6.7867336,-89.246666,-167.39319,1.6155621,-1.7980602,79.627365,695000
|
| 41 |
+
824.7718,1.1740718,2.851699,-6.425957,-88.896034,-166.8341,1.9901701,-1.2138644,76.39907,700000
|
| 42 |
+
801.10583,0.84609985,5.7224,-8.150567,-86.23565,-170.69954,1.6610544,-1.6840358,88.70253,705000
|
| 43 |
+
835.2165,0.9661324,2.1119974,7.0036235,-89.48669,-169.68478,5.7276387,-5.870732,164.70766,710000
|
| 44 |
+
829.1583,0.91421807,2.9157875,-11.530433,-88.83567,-164.93561,3.0674677,-2.209299,108.85877,715000
|
| 45 |
+
834.4785,0.933558,4.0387025,-17.722502,-89.060234,-167.13849,2.065936,-2.029795,93.05212,720000
|
| 46 |
+
823.8249,0.97333866,2.0913923,-10.910155,-88.010704,-169.37535,4.346704,-2.9795053,121.17865,725000
|
| 47 |
+
869.6754,1.018669,2.6037614,-9.088565,-92.77956,-178.25774,1.9959351,-2.7608998,110.08645,730000
|
| 48 |
+
837.49066,1.0975605,2.2229931,-7.314997,-89.05057,-170.30344,1.7513056,-1.9577307,77.72645,735000
|
| 49 |
+
844.6756,0.98526174,2.561698,3.2040234,-90.37677,-170.2428,2.1542602,-2.0420065,108.90471,740000
|
| 50 |
+
834.62756,0.8856017,2.8447888,-17.605774,-89.54949,-170.67075,2.184103,-1.4687946,81.08256,745000
|
| 51 |
+
843.3474,0.9462594,2.0133414,-2.9813843,-89.99675,-170.59314,1.3591676,-1.2178811,63.303104,750000
|
| 52 |
+
865.6819,0.8642385,1.540855,-7.904732,-92.51087,-176.39827,40.306606,-43.125336,862.72437,755000
|
| 53 |
+
823.4364,0.95787597,4.0166316,1.397245,-88.14186,-175.07172,1.045937,-1.6492885,95.69548,760000
|
| 54 |
+
830.4806,0.96795976,2.0310984,-6.9945292,-88.60498,-168.77669,6.750961,-3.5699325,103.53765,765000
|
| 55 |
+
853.398,0.8989228,3.8143709,-19.43287,-91.71944,-168.60202,2.4999058,-1.62605,108.59178,770000
|
| 56 |
+
837.32947,0.8742932,2.4443789,-10.354225,-89.355705,-172.91833,2.7920136,-2.444294,99.89055,775000
|
| 57 |
+
825.37695,0.8108789,1.8040494,-22.234043,-88.64682,-172.60814,1.2685694,-1.7725238,73.99518,780000
|
| 58 |
+
834.9493,0.87974745,4.6594505,-9.755031,-89.02943,-173.12967,1.5459992,-1.9022372,98.022644,785000
|
| 59 |
+
835.8155,0.9808848,2.3786786,-4.4766026,-89.70656,-169.13373,2.0308912,-1.4621853,84.27421,790000
|
| 60 |
+
825.7799,1.0094852,1.9454256,2.514319,-88.15456,-168.43456,2.5219135,-1.5603949,80.00997,795000
|
| 61 |
+
810.1505,0.97585106,2.3599782,-5.2248464,-86.82249,-163.14409,1.6278906,-2.4703374,99.11598,800000
|
| 62 |
+
830.2561,1.0600631,2.096319,-7.301257,-88.88532,-171.2025,2.104569,-1.9900638,78.26139,805000
|
| 63 |
+
781.01154,0.86187935,2.457574,-5.329166,-84.41592,-169.88176,3.5085466,-3.2495747,117.03455,810000
|
| 64 |
+
805.2872,1.0788982,1.9959229,-7.91649,-86.40298,-172.82289,1.629892,-1.5776672,84.104744,815000
|
| 65 |
+
806.8228,1.4261851,3.819041,-2.7516482,-86.49507,-168.86665,2.5267806,-3.991077,138.31314,820000
|
| 66 |
+
815.7944,0.84316385,2.5055788,-14.962046,-87.628265,-172.81747,1.9901514,-1.9031376,103.275314,825000
|
| 67 |
+
839.89526,0.8819242,2.9160244,-7.632332,-89.97591,-171.17154,11.44837,-5.3513885,251.10326,830000
|
| 68 |
+
828.8701,1.0396543,2.9199772,-5.8468714,-89.22056,-171.6347,4.2010136,-4.349566,147.76675,835000
|
| 69 |
+
802.44446,1.2260622,2.7373853,-4.7320795,-85.9732,-173.18636,15.0266485,-7.5679083,195.51721,840000
|
| 70 |
+
851.587,0.8350274,2.4026716,-16.216974,-90.704704,-174.6725,5.8195853,-5.8458643,192.25232,845000
|
| 71 |
+
836.9126,0.9494403,1.6226352,-9.252184,-89.28659,-170.9946,2.5941224,-2.645432,99.23658,850000
|
| 72 |
+
820.0114,0.8757168,4.197146,-3.4035044,-88.00152,-168.95016,5.415265,-5.1566286,205.88095,855000
|
| 73 |
+
830.8766,1.0826695,3.6053026,-4.762649,-89.02802,-173.3033,17.999834,-16.292881,434.2873,860000
|
| 74 |
+
820.1827,0.79232603,2.4003086,-10.408102,-87.87505,-171.25465,3.145259,-3.3863008,114.20823,865000
|
| 75 |
+
798.20746,1.073629,3.1260839,-6.8554606,-85.273155,-171.99446,2.5158257,-3.9859023,131.70937,870000
|
| 76 |
+
803.9436,1.0344411,2.9472833,0.70635754,-86.393364,-170.55739,2.1404986,-1.5383611,91.31928,875000
|
| 77 |
+
809.5135,1.1124703,3.2371228,-1.3667122,-86.96246,-166.76892,2.1527872,-1.8518515,110.8651,880000
|
| 78 |
+
806.88617,1.0281184,2.615375,-2.4812655,-86.650406,-174.88884,44.184464,-39.194473,944.93677,885000
|
| 79 |
+
835.2749,1.2188077,3.4557595,-12.149322,-89.59063,-169.17877,3.3488631,-2.908817,160.1271,890000
|
| 80 |
+
801.5713,1.1325834,3.395617,-0.372496,-85.96664,-170.52708,7.565752,-4.4560604,214.89963,895000
|
| 81 |
+
796.58044,0.9537481,2.7891617,0.2104977,-85.49447,-170.23819,2.5414846,-3.0271146,104.95488,900000
|
| 82 |
+
822.2539,1.0591143,2.1681106,-7.947759,-87.53568,-169.41902,3.393723,-2.0629334,93.421234,905000
|
| 83 |
+
830.15985,1.0695324,1.87052,-4.2740207,-88.22589,-175.53328,7.383498,-3.564857,127.134125,910000
|
| 84 |
+
810.5717,0.8823731,2.2745683,-16.248764,-87.18774,-173.26714,2.287677,-7.188812,98.22124,915000
|
| 85 |
+
790.987,1.0900512,2.913284,-5.3986926,-85.18459,-167.33855,3.29065,-12.664712,123.486145,920000
|
| 86 |
+
841.5321,1.0243094,2.4192255,1.27823,-89.989174,-168.72017,3.756138,-2.7391882,97.77069,925000
|
| 87 |
+
826.03845,1.0195193,1.9950218,-12.80754,-88.24143,-173.5585,2.029218,-1.7069951,85.33455,930000
|
| 88 |
+
826.6436,1.5481858,3.4172776,-1.2493749,-88.51531,-170.77412,6.0322227,-4.5311513,119.47271,935000
|
| 89 |
+
845.3411,0.9855307,2.2982352,-13.420368,-90.253784,-174.82991,6.042174,-14.008944,253.48697,940000
|
| 90 |
+
837.6029,0.9770358,1.75698,-6.9110055,-89.70809,-167.33548,3.686094,-7.9052134,141.80229,945000
|
| 91 |
+
818.10376,1.2165756,3.8992386,-20.466585,-86.964714,-177.19876,2.9556532,-2.7774448,122.41441,950000
|
| 92 |
+
789.369,0.9422753,2.3559747,-5.3739595,-84.5356,-175.43356,1.5495585,-1.5200168,77.11247,955000
|
| 93 |
+
778.21155,0.88381106,3.2056253,2.2821937,-83.27264,-170.13472,3.345886,-2.9419494,130.44833,960000
|
| 94 |
+
803.87823,1.136049,2.645036,1.5247736,-86.30334,-175.45966,4.1095643,-3.8860106,133.3895,965000
|
| 95 |
+
807.3643,1.1149331,2.5425806,-6.083763,-86.40845,-177.87917,2.5025368,-3.449123,116.470856,970000
|
| 96 |
+
815.3836,0.9387916,3.2293808,-4.255764,-87.22314,-177.06943,2.641368,-2.4293084,107.57158,975000
|
| 97 |
+
771.7642,1.2422258,2.0660152,5.5934353,-82.710594,-175.24602,4.6641383,-4.3158293,111.14106,980000
|
| 98 |
+
787.93475,1.4284303,2.3168874,-3.7008362,-84.14573,-170.40321,2.1015804,-2.280247,92.02365,985000
|
| 99 |
+
800.28186,0.99890554,2.7984169,-4.4291334,-85.42901,-174.39833,5.4585724,-5.5037565,124.474,990000
|
| 100 |
+
770.62354,1.0012851,5.4210176,6.397098,-82.72852,-161.03716,7.579869,-7.768574,286.90207,995000
|
| 101 |
+
814.572,1.2654238,4.69839,-1.9654229,-86.72782,-169.88919,5.1653013,-4.590702,161.02144,1000000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/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 |
+
452.64963,1.3365817,1.2069706,-12.485567,-52.933075,-80.61363,8.783501,-8.928215,181.71524,505000
|
| 3 |
+
559.66284,1.0443755,0.92943305,-8.129159,-63.30897,-108.81358,3.6967893,-4.202759,109.349525,510000
|
| 4 |
+
622.093,1.0110067,2.2279537,-14.656605,-68.86446,-128.44435,3.2290697,-2.4222085,127.03331,515000
|
| 5 |
+
619.937,0.9812181,4.8216796,-7.247258,-68.91629,-137.88098,1.6995468,-2.2213764,99.16235,520000
|
| 6 |
+
630.8488,1.083922,1.0856203,-22.498034,-70.02803,-143.04993,1.4073087,-0.9642714,48.787415,525000
|
| 7 |
+
626.36786,0.8056767,1.4185972,-15.357644,-69.67832,-137.90758,1.9520855,-1.3586434,73.00691,530000
|
| 8 |
+
657.28033,0.8454031,1.3148359,-18.310362,-72.402725,-166.06557,1.9898548,-1.1056539,67.9273,535000
|
| 9 |
+
686.59454,0.86820596,2.326125,-23.615171,-75.42804,-149.55359,1.1452193,-1.7089608,80.87784,540000
|
| 10 |
+
713.48645,0.8825395,0.9496853,-20.256691,-78.071625,-161.07913,2.298263,-1.3884568,51.700264,545000
|
| 11 |
+
688.1092,0.9321668,6.517915,-17.382526,-75.841934,-152.99513,1.3055468,-1.0212194,70.02578,550000
|
| 12 |
+
684.44495,0.9688769,2.0982056,-15.546474,-75.494316,-159.8163,1.5294067,-1.3878953,83.16202,555000
|
| 13 |
+
678.7258,0.83121765,14.1827135,-11.263893,-75.110085,-148.79855,2.7857358,-2.1162496,151.11133,560000
|
| 14 |
+
709.09564,0.8433461,1.7338623,-15.733488,-77.09317,-159.87814,6.4007363,-6.7011356,125.485214,565000
|
| 15 |
+
693.79486,0.8908032,1.515094,-6.5018826,-75.721855,-154.91469,1.8115747,-2.9767485,77.54168,570000
|
| 16 |
+
741.0875,0.8446889,3.4812584,-14.633865,-80.82051,-149.60175,2.7435834,-2.8581104,143.67911,575000
|
| 17 |
+
800.3168,0.9172359,2.4218976,-16.861435,-86.89566,-168.53708,4.771409,-5.0321984,187.97726,580000
|
| 18 |
+
786.84784,0.87580293,1.3891503,-30.73769,-84.64697,-163.71417,1.9244152,-0.9103417,67.65885,585000
|
| 19 |
+
794.47705,1.0227067,2.38917,-11.371363,-85.64825,-166.0282,2.8272905,-2.9474912,130.75114,590000
|
| 20 |
+
790.8795,1.1262503,2.3630512,-13.594788,-85.67608,-168.31313,1.505192,-2.1302314,74.73902,595000
|
| 21 |
+
800.93097,1.2703251,1.6120666,-20.139086,-86.10514,-166.01074,2.152046,-1.1901779,67.80056,600000
|
| 22 |
+
795.4496,0.7565539,1.7396263,-20.781033,-85.66836,-167.15536,1.4680107,-1.415065,63.816948,605000
|
| 23 |
+
806.39026,0.8593606,3.3986886,-12.396617,-86.973564,-170.70992,1.714979,-1.1813933,80.12377,610000
|
| 24 |
+
811.3909,0.9197198,1.4346079,2.2689922,-87.18085,-170.09056,21.346859,-11.140747,123.7889,615000
|
| 25 |
+
841.4316,1.1305273,2.40654,-24.35551,-90.41176,-167.7204,3.1437163,-4.788018,125.13218,620000
|
| 26 |
+
832.0072,0.9796524,1.6525596,-18.366638,-89.20034,-170.35107,1.6371228,-1.5151939,72.6409,625000
|
| 27 |
+
827.8084,0.96790683,1.7014748,-22.37032,-88.77531,-167.83813,1.6562937,-2.0322208,74.937775,630000
|
| 28 |
+
812.9805,0.9067867,4.1661854,1.8191855,-87.74334,-169.17377,14.925431,-15.634887,185.35074,635000
|
| 29 |
+
801.98566,0.8905717,2.635463,-11.380878,-87.09883,-169.01581,142.1382,-160.08507,1794.8265,640000
|
| 30 |
+
863.3928,0.8611659,1.6370811,-21.974714,-92.18876,-168.93178,3.8006785,-5.043507,140.21938,645000
|
| 31 |
+
811.8284,0.9076445,1.7756379,-6.5885825,-87.11571,-166.10995,2.0374637,-2.583291,81.8782,650000
|
| 32 |
+
830.8817,0.9805214,3.1536007,-19.459953,-89.14821,-169.83282,1.885306,-1.8152032,85.64246,655000
|
| 33 |
+
846.4515,0.9691616,1.894246,-15.379924,-90.523186,-165.93822,4.9384556,-5.8031464,196.78716,660000
|
| 34 |
+
832.394,0.7463238,2.4937353,-1.3362442,-89.313965,-174.32054,2.54174,-2.314888,97.124886,665000
|
| 35 |
+
857.12476,1.1248933,1.9899939,-18.54427,-91.58545,-170.69395,1.5208448,-2.0596642,82.771805,670000
|
| 36 |
+
882.73065,0.91497755,1.8098654,-14.838122,-94.181946,-170.2052,2.5070875,-1.6607951,75.39378,675000
|
| 37 |
+
885.8963,0.94194716,2.4034226,1.5750592,-94.36911,-175.31862,1.2831758,-2.346087,87.42029,680000
|
| 38 |
+
842.83484,0.87256277,1.6620804,-7.067542,-90.26408,-174.48,3.9395485,-3.7543225,147.45769,685000
|
| 39 |
+
855.2505,1.4137268,2.1317623,-15.049857,-90.99187,-167.7689,2.1336272,-3.1357837,77.04313,690000
|
| 40 |
+
828.896,0.99673766,1.7208693,-6.7867336,-89.246666,-167.39319,1.6155621,-1.7980602,79.627365,695000
|
| 41 |
+
824.7718,1.1740718,2.851699,-6.425957,-88.896034,-166.8341,1.9901701,-1.2138644,76.39907,700000
|
| 42 |
+
801.10583,0.84609985,5.7224,-8.150567,-86.23565,-170.69954,1.6610544,-1.6840358,88.70253,705000
|
| 43 |
+
835.2165,0.9661324,2.1119974,7.0036235,-89.48669,-169.68478,5.7276387,-5.870732,164.70766,710000
|
| 44 |
+
829.1583,0.91421807,2.9157875,-11.530433,-88.83567,-164.93561,3.0674677,-2.209299,108.85877,715000
|
| 45 |
+
834.4785,0.933558,4.0387025,-17.722502,-89.060234,-167.13849,2.065936,-2.029795,93.05212,720000
|
| 46 |
+
823.8249,0.97333866,2.0913923,-10.910155,-88.010704,-169.37535,4.346704,-2.9795053,121.17865,725000
|
| 47 |
+
869.6754,1.018669,2.6037614,-9.088565,-92.77956,-178.25774,1.9959351,-2.7608998,110.08645,730000
|
| 48 |
+
837.49066,1.0975605,2.2229931,-7.314997,-89.05057,-170.30344,1.7513056,-1.9577307,77.72645,735000
|
| 49 |
+
844.6756,0.98526174,2.561698,3.2040234,-90.37677,-170.2428,2.1542602,-2.0420065,108.90471,740000
|
| 50 |
+
834.62756,0.8856017,2.8447888,-17.605774,-89.54949,-170.67075,2.184103,-1.4687946,81.08256,745000
|
| 51 |
+
843.3474,0.9462594,2.0133414,-2.9813843,-89.99675,-170.59314,1.3591676,-1.2178811,63.303104,750000
|
| 52 |
+
865.6819,0.8642385,1.540855,-7.904732,-92.51087,-176.39827,40.306606,-43.125336,862.72437,755000
|
| 53 |
+
823.4364,0.95787597,4.0166316,1.397245,-88.14186,-175.07172,1.045937,-1.6492885,95.69548,760000
|
| 54 |
+
830.4806,0.96795976,2.0310984,-6.9945292,-88.60498,-168.77669,6.750961,-3.5699325,103.53765,765000
|
| 55 |
+
853.398,0.8989228,3.8143709,-19.43287,-91.71944,-168.60202,2.4999058,-1.62605,108.59178,770000
|
| 56 |
+
837.32947,0.8742932,2.4443789,-10.354225,-89.355705,-172.91833,2.7920136,-2.444294,99.89055,775000
|
| 57 |
+
825.37695,0.8108789,1.8040494,-22.234043,-88.64682,-172.60814,1.2685694,-1.7725238,73.99518,780000
|
| 58 |
+
834.9493,0.87974745,4.6594505,-9.755031,-89.02943,-173.12967,1.5459992,-1.9022372,98.022644,785000
|
| 59 |
+
835.8155,0.9808848,2.3786786,-4.4766026,-89.70656,-169.13373,2.0308912,-1.4621853,84.27421,790000
|
| 60 |
+
825.7799,1.0094852,1.9454256,2.514319,-88.15456,-168.43456,2.5219135,-1.5603949,80.00997,795000
|
| 61 |
+
810.1505,0.97585106,2.3599782,-5.2248464,-86.82249,-163.14409,1.6278906,-2.4703374,99.11598,800000
|
| 62 |
+
830.2561,1.0600631,2.096319,-7.301257,-88.88532,-171.2025,2.104569,-1.9900638,78.26139,805000
|
| 63 |
+
781.01154,0.86187935,2.457574,-5.329166,-84.41592,-169.88176,3.5085466,-3.2495747,117.03455,810000
|
| 64 |
+
805.2872,1.0788982,1.9959229,-7.91649,-86.40298,-172.82289,1.629892,-1.5776672,84.104744,815000
|
| 65 |
+
806.8228,1.4261851,3.819041,-2.7516482,-86.49507,-168.86665,2.5267806,-3.991077,138.31314,820000
|
| 66 |
+
815.7944,0.84316385,2.5055788,-14.962046,-87.628265,-172.81747,1.9901514,-1.9031376,103.275314,825000
|
| 67 |
+
839.89526,0.8819242,2.9160244,-7.632332,-89.97591,-171.17154,11.44837,-5.3513885,251.10326,830000
|
| 68 |
+
828.8701,1.0396543,2.9199772,-5.8468714,-89.22056,-171.6347,4.2010136,-4.349566,147.76675,835000
|
| 69 |
+
802.44446,1.2260622,2.7373853,-4.7320795,-85.9732,-173.18636,15.0266485,-7.5679083,195.51721,840000
|
| 70 |
+
851.587,0.8350274,2.4026716,-16.216974,-90.704704,-174.6725,5.8195853,-5.8458643,192.25232,845000
|
| 71 |
+
836.9126,0.9494403,1.6226352,-9.252184,-89.28659,-170.9946,2.5941224,-2.645432,99.23658,850000
|
| 72 |
+
820.0114,0.8757168,4.197146,-3.4035044,-88.00152,-168.95016,5.415265,-5.1566286,205.88095,855000
|
| 73 |
+
830.8766,1.0826695,3.6053026,-4.762649,-89.02802,-173.3033,17.999834,-16.292881,434.2873,860000
|
| 74 |
+
820.1827,0.79232603,2.4003086,-10.408102,-87.87505,-171.25465,3.145259,-3.3863008,114.20823,865000
|
| 75 |
+
798.20746,1.073629,3.1260839,-6.8554606,-85.273155,-171.99446,2.5158257,-3.9859023,131.70937,870000
|
| 76 |
+
803.9436,1.0344411,2.9472833,0.70635754,-86.393364,-170.55739,2.1404986,-1.5383611,91.31928,875000
|
| 77 |
+
809.5135,1.1124703,3.2371228,-1.3667122,-86.96246,-166.76892,2.1527872,-1.8518515,110.8651,880000
|
| 78 |
+
806.88617,1.0281184,2.615375,-2.4812655,-86.650406,-174.88884,44.184464,-39.194473,944.93677,885000
|
| 79 |
+
835.2749,1.2188077,3.4557595,-12.149322,-89.59063,-169.17877,3.3488631,-2.908817,160.1271,890000
|
| 80 |
+
801.5713,1.1325834,3.395617,-0.372496,-85.96664,-170.52708,7.565752,-4.4560604,214.89963,895000
|
| 81 |
+
796.58044,0.9537481,2.7891617,0.2104977,-85.49447,-170.23819,2.5414846,-3.0271146,104.95488,900000
|
| 82 |
+
822.2539,1.0591143,2.1681106,-7.947759,-87.53568,-169.41902,3.393723,-2.0629334,93.421234,905000
|
| 83 |
+
830.15985,1.0695324,1.87052,-4.2740207,-88.22589,-175.53328,7.383498,-3.564857,127.134125,910000
|
| 84 |
+
810.5717,0.8823731,2.2745683,-16.248764,-87.18774,-173.26714,2.287677,-7.188812,98.22124,915000
|
| 85 |
+
790.987,1.0900512,2.913284,-5.3986926,-85.18459,-167.33855,3.29065,-12.664712,123.486145,920000
|
| 86 |
+
841.5321,1.0243094,2.4192255,1.27823,-89.989174,-168.72017,3.756138,-2.7391882,97.77069,925000
|
| 87 |
+
826.03845,1.0195193,1.9950218,-12.80754,-88.24143,-173.5585,2.029218,-1.7069951,85.33455,930000
|
| 88 |
+
826.6436,1.5481858,3.4172776,-1.2493749,-88.51531,-170.77412,6.0322227,-4.5311513,119.47271,935000
|
| 89 |
+
845.3411,0.9855307,2.2982352,-13.420368,-90.253784,-174.82991,6.042174,-14.008944,253.48697,940000
|
| 90 |
+
837.6029,0.9770358,1.75698,-6.9110055,-89.70809,-167.33548,3.686094,-7.9052134,141.80229,945000
|
| 91 |
+
818.10376,1.2165756,3.8992386,-20.466585,-86.964714,-177.19876,2.9556532,-2.7774448,122.41441,950000
|
| 92 |
+
789.369,0.9422753,2.3559747,-5.3739595,-84.5356,-175.43356,1.5495585,-1.5200168,77.11247,955000
|
| 93 |
+
778.21155,0.88381106,3.2056253,2.2821937,-83.27264,-170.13472,3.345886,-2.9419494,130.44833,960000
|
| 94 |
+
803.87823,1.136049,2.645036,1.5247736,-86.30334,-175.45966,4.1095643,-3.8860106,133.3895,965000
|
| 95 |
+
807.3643,1.1149331,2.5425806,-6.083763,-86.40845,-177.87917,2.5025368,-3.449123,116.470856,970000
|
| 96 |
+
815.3836,0.9387916,3.2293808,-4.255764,-87.22314,-177.06943,2.641368,-2.4293084,107.57158,975000
|
| 97 |
+
771.7642,1.2422258,2.0660152,5.5934353,-82.710594,-175.24602,4.6641383,-4.3158293,111.14106,980000
|
| 98 |
+
787.93475,1.4284303,2.3168874,-3.7008362,-84.14573,-170.40321,2.1015804,-2.280247,92.02365,985000
|
| 99 |
+
800.28186,0.99890554,2.7984169,-4.4291334,-85.42901,-174.39833,5.4585724,-5.5037565,124.474,990000
|
| 100 |
+
770.62354,1.0012851,5.4210176,6.397098,-82.72852,-161.03716,7.579869,-7.768574,286.90207,995000
|
| 101 |
+
814.572,1.2654238,4.69839,-1.9654229,-86.72782,-169.88919,5.1653013,-4.590702,161.02144,1000000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_1000000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd7a693ca507a1a1b24ad6a43994ed8eb80614cede62d764fe5fb6d44b51f7f1
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6b7e824c86eb020f920763adaee15d671cb0f55433e5b0091c6a951aa795975
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd8b0c16a8be3dfdbcfa9451f382c9aff422af3b2509c1c5f3cde3d7bd15665
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bee661d2d6f1fda827ad01e2814f6d665683718ec3e9447162a2d2ca3961dbea
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2904aa2d9711b88d8401c6bb74ece2ec41e0ea908eaf3f3afd86c2cf435e20de
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_750000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:141530a674d9844d2fff397fd297c04c4761530e388a9f61c1a0b969a98ee26e
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_800000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef5afe87cab353d0e395a5fb3ec5691d8820b3f9e3b7a5bca1fbd56be1eedf4a
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_850000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:791cd0809157e152b67b2545b542d26a0e056008826ac7918b087dfb5ca9fb75
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_900000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b23f1f9481195afcb1dab5b6e21406d566ede7738c18177187cbd402a4f6ba60
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/params_950000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e77d9de594b7b17fcd1f034be52e4d468e06ae794cd60c58e6cfb9cf58162104
|
| 3 |
+
size 207971010
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/20260311_152035/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/nh8qbp90
|