Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_1000000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_650000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_700000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_750000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_800000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_850000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_900000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_950000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/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/cgql/20260319_092737/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/cgql/20260319_092737/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 |
+
0.0,0.0,0.003303770665748923,0.004966377706022315,0.004070427899841782,0.010499359085670306,27.366538083331662,16.71199999999943,0.72,8480.42,-0.36,-493.88,332.24,1.1297484016418458,550000
|
| 3 |
+
0.0,0.0,-0.022197049373652876,0.011916089490098763,-0.02223653673957267,-0.0047502091247305705,32.04991132818944,13.05499999999952,0.88,24119.14,-0.18,-404.14,259.1,0.8728262042999267,600000
|
| 4 |
+
0.0,0.0,-0.0034333115563433786,-0.02029582740110814,-0.003986418221872824,-0.02929124214211782,34.27566788201305,11.509999999999806,0.96,36477.64,-0.06,-346.26,228.2,0.8475271081924438,650000
|
| 5 |
+
0.0,0.0,0.012428712096659526,-0.05069684624482239,0.01141308679893075,-0.037721149506997155,33.98303819145856,9.975999999999537,0.94,47951.26,-0.08,-295.06,197.52,0.669064736366272,700000
|
| 6 |
+
0.0,0.0,0.027366799790828233,-0.043524850981707,0.025470915894425968,-0.04909195646874034,35.24587462549398,9.69099999999979,0.98,57540.62,-0.04,-277.64,191.82,0.6460059976577759,750000
|
| 7 |
+
0.0,0.0,0.0162057713446201,-0.05560522209683606,0.014461127166744059,-0.06193337063608493,36.01401873569532,6.9709999999995595,1.0,66065.68,0.0,-198.36,137.42,0.48297184467315674,800000
|
| 8 |
+
0.0,0.0,0.02869997554766912,-0.053869989826773254,0.027023289699897358,-0.05911394978251556,35.95408292465961,7.3439999999996255,1.0,73610.24,0.0,-208.52,144.88,0.5019793891906739,850000
|
| 9 |
+
0.0,0.0,0.03932273298667816,-0.05463833263033036,0.03777821216785575,-0.06327391308611845,35.954543906605196,7.791999999999633,1.0,81596.4,0.0,-226.18,153.84,0.5337522125244141,900000
|
| 10 |
+
0.0,0.0,0.03022560217609325,-0.05624747267199048,0.02932161839670793,-0.06277526877360515,36.044753467073996,7.0419999999996525,1.0,88738.3,0.0,-198.36,138.84,0.4807722806930542,950000
|
| 11 |
+
0.0,0.0,0.03711647251136687,-0.05246640641203855,0.03582023391333244,-0.058717974548359725,35.56909134173009,7.03999999999957,1.0,96004.5,0.0,-197.34,138.8,0.4889055633544922,1000000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/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 |
+
0.0,0.0,0.003303770665748923,0.004966377706022315,0.004070427899841782,0.010499359085670306,27.366538083331662,16.71199999999943,0.72,8480.42,-0.36,-493.88,332.24,1.1297484016418458,550000
|
| 3 |
+
0.0,0.0,-0.022197049373652876,0.011916089490098763,-0.02223653673957267,-0.0047502091247305705,32.04991132818944,13.05499999999952,0.88,24119.14,-0.18,-404.14,259.1,0.8728262042999267,600000
|
| 4 |
+
0.0,0.0,-0.0034333115563433786,-0.02029582740110814,-0.003986418221872824,-0.02929124214211782,34.27566788201305,11.509999999999806,0.96,36477.64,-0.06,-346.26,228.2,0.8475271081924438,650000
|
| 5 |
+
0.0,0.0,0.012428712096659526,-0.05069684624482239,0.01141308679893075,-0.037721149506997155,33.98303819145856,9.975999999999537,0.94,47951.26,-0.08,-295.06,197.52,0.669064736366272,700000
|
| 6 |
+
0.0,0.0,0.027366799790828233,-0.043524850981707,0.025470915894425968,-0.04909195646874034,35.24587462549398,9.69099999999979,0.98,57540.62,-0.04,-277.64,191.82,0.6460059976577759,750000
|
| 7 |
+
0.0,0.0,0.0162057713446201,-0.05560522209683606,0.014461127166744059,-0.06193337063608493,36.01401873569532,6.9709999999995595,1.0,66065.68,0.0,-198.36,137.42,0.48297184467315674,800000
|
| 8 |
+
0.0,0.0,0.02869997554766912,-0.053869989826773254,0.027023289699897358,-0.05911394978251556,35.95408292465961,7.3439999999996255,1.0,73610.24,0.0,-208.52,144.88,0.5019793891906739,850000
|
| 9 |
+
0.0,0.0,0.03932273298667816,-0.05463833263033036,0.03777821216785575,-0.06327391308611845,35.954543906605196,7.791999999999633,1.0,81596.4,0.0,-226.18,153.84,0.5337522125244141,900000
|
| 10 |
+
0.0,0.0,0.03022560217609325,-0.05624747267199048,0.02932161839670793,-0.06277526877360515,36.044753467073996,7.0419999999996525,1.0,88738.3,0.0,-198.36,138.84,0.4807722806930542,950000
|
| 11 |
+
0.0,0.0,0.03711647251136687,-0.05246640641203855,0.03582023391333244,-0.058717974548359725,35.56909134173009,7.03999999999957,1.0,96004.5,0.0,-197.34,138.8,0.4889055633544922,1000000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/online_agent.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.20566803,5.110677,-73.12663,-179.45189,-203.61758,0.22142653,-0.23599018,19.25538,505000
|
| 3 |
+
0.2250425,9.059847,-71.92152,-175.47856,-203.1067,1.276209,-1.2214391,34.004097,510000
|
| 4 |
+
0.16932982,11.166118,-68.08083,-176.32138,-203.47983,0.43729627,-0.317221,34.374126,515000
|
| 5 |
+
0.17819636,16.805952,-65.42261,-174.59349,-203.47504,4.190076,-3.2183583,94.83454,520000
|
| 6 |
+
0.1722812,8.942349,-72.37749,-174.54308,-203.0009,0.35377336,-0.30577564,28.177853,525000
|
| 7 |
+
0.18364018,14.670789,-88.528625,-175.52774,-203.91237,4.1011844,-3.6807687,77.101395,530000
|
| 8 |
+
0.20521235,12.645774,-16.193739,-173.64854,-203.86273,0.22208874,-0.43939197,36.293564,535000
|
| 9 |
+
0.16835752,9.959799,-53.9744,-172.37384,-203.5259,0.27665028,-0.44127274,36.121014,540000
|
| 10 |
+
0.19698068,8.888588,-88.38606,-171.79369,-204.41869,0.57204884,-0.5381174,31.467728,545000
|
| 11 |
+
0.15572037,12.835947,-21.759287,-167.89372,-203.82889,0.69213164,-0.58809876,36.45994,550000
|
| 12 |
+
0.1954141,37.409393,-27.22268,-163.64323,-204.19447,1.6427501,-1.4318419,102.830574,555000
|
| 13 |
+
0.19255297,26.639893,-51.6152,-163.10672,-204.03114,0.45613933,-0.49051055,46.799038,560000
|
| 14 |
+
0.18367049,12.12156,-39.12962,-164.82045,-204.23233,1.062097,-1.0115552,45.36061,565000
|
| 15 |
+
0.17549372,19.61974,-28.350443,-161.28569,-204.11583,0.59141445,-0.5516618,53.70257,570000
|
| 16 |
+
0.20685051,12.2783985,-72.48462,-166.39575,-205.47327,0.3385271,-0.4601435,35.04776,575000
|
| 17 |
+
0.16643554,13.28646,-48.332752,-163.54066,-204.52322,0.73259604,-0.6885179,49.288322,580000
|
| 18 |
+
0.1801559,16.009888,-43.995087,-161.78589,-204.0759,0.4388525,-0.54398805,45.13157,585000
|
| 19 |
+
0.17249452,25.270279,-50.510937,-158.8568,-204.94019,1.1012672,-1.230733,74.603424,590000
|
| 20 |
+
0.15666306,16.27174,-36.677277,-160.54138,-204.03716,1.0948342,-1.0939605,41.94873,595000
|
| 21 |
+
0.19297245,19.256468,-21.627161,-154.55284,-203.80296,0.5846042,-0.63321394,51.47951,600000
|
| 22 |
+
0.18215103,11.736672,-45.44688,-159.09502,-205.13307,0.74325377,-0.6711486,46.419,605000
|
| 23 |
+
0.18784031,20.716288,-39.975956,-153.83015,-203.73938,0.6608016,-0.7067684,49.96794,610000
|
| 24 |
+
0.16215727,10.715085,2.1705005,-150.5094,-204.17896,1.3537142,-1.6073018,54.05764,615000
|
| 25 |
+
0.17303324,13.208338,-29.6961,-156.46396,-205.18839,0.7878483,-0.73783183,46.174683,620000
|
| 26 |
+
0.16602579,27.703257,-32.58668,-154.58769,-202.96054,0.7985654,-0.80906004,56.15025,625000
|
| 27 |
+
0.15611237,18.12496,-46.88384,-155.2082,-204.15376,0.8786886,-0.90878373,62.375313,630000
|
| 28 |
+
0.16161524,12.926068,3.088586,-154.67468,-204.69948,0.48457962,-0.71018004,46.2227,635000
|
| 29 |
+
0.17938894,17.544287,-29.482773,-148.32384,-201.60298,0.79231113,-0.77717656,56.840576,640000
|
| 30 |
+
0.16222373,25.938505,-28.240393,-151.2465,-203.89647,0.8903465,-0.850017,61.339806,645000
|
| 31 |
+
0.19187292,12.910105,-9.11895,-148.80208,-204.14496,0.7650809,-0.73558205,44.848988,650000
|
| 32 |
+
0.20996657,15.410697,-7.288761,-151.61943,-204.38197,0.5965687,-0.4602733,46.117016,655000
|
| 33 |
+
0.18960157,17.222998,-23.542465,-149.58118,-204.59146,2.2771595,-2.1334667,48.260048,660000
|
| 34 |
+
0.18364385,17.466696,1.5797184,-149.45886,-204.84885,0.5929509,-0.82026637,53.902145,665000
|
| 35 |
+
0.1696206,12.829656,-4.008024,-149.29083,-203.60889,0.6415093,-0.6237316,46.46586,670000
|
| 36 |
+
0.19804734,14.335022,-7.413153,-150.88414,-204.16646,0.689401,-0.7187595,48.7769,675000
|
| 37 |
+
0.17449117,20.371546,2.5581908,-149.5919,-203.94086,0.9196676,-0.8439001,62.9606,680000
|
| 38 |
+
0.17332101,18.588964,-17.49788,-147.54393,-203.03539,0.79254264,-0.9416936,76.58604,685000
|
| 39 |
+
0.16070896,24.520195,-20.431978,-145.90898,-202.24486,1.1409044,-1.0309751,81.443016,690000
|
| 40 |
+
0.20384756,16.685019,-7.2251096,-145.1892,-202.61761,0.58344895,-0.3957181,53.10576,695000
|
| 41 |
+
0.19963089,11.409919,-10.923604,-144.06644,-203.68452,1.0427814,-0.9438096,45.17065,700000
|
| 42 |
+
0.18104927,20.39068,-4.7607503,-145.24388,-201.574,0.44935983,-0.5296516,60.633423,705000
|
| 43 |
+
0.16611281,23.309597,-2.529027,-142.5005,-202.20909,0.71147645,-0.8462647,62.373535,710000
|
| 44 |
+
0.18311203,17.027493,-10.483625,-147.04388,-203.48883,0.6471176,-0.39923036,54.374157,715000
|
| 45 |
+
0.17484075,20.359911,-8.469924,-144.68907,-200.27666,1.3133475,-1.1496165,70.97615,720000
|
| 46 |
+
0.16159269,15.254886,-2.1809375,-141.70189,-203.94514,0.5898609,-0.84784067,64.39255,725000
|
| 47 |
+
0.19942284,21.431952,-8.299704,-142.05325,-204.37785,0.8852629,-0.8556647,59.66687,730000
|
| 48 |
+
0.19127601,12.016114,-5.0704546,-139.07619,-204.06389,0.74963856,-0.8542583,42.54686,735000
|
| 49 |
+
0.14877728,17.753191,1.9998504,-140.90872,-201.8382,2.849966,-1.7264401,52.442055,740000
|
| 50 |
+
0.15849599,16.768353,-3.2734382,-141.8522,-204.35588,0.6998075,-0.59482425,48.736237,745000
|
| 51 |
+
0.15797818,14.1616,-9.655507,-132.37993,-203.13571,0.55767494,-0.60660505,45.03371,750000
|
| 52 |
+
0.16840333,13.4676485,-11.877489,-145.27701,-202.78534,0.8772593,-1.0089743,54.600945,755000
|
| 53 |
+
0.20070918,19.792334,2.1166937,-139.10991,-202.05222,0.49715358,-0.5373625,52.138588,760000
|
| 54 |
+
0.18192849,10.095213,-10.67541,-141.31204,-203.40642,3.5511296,-3.8602796,56.66836,765000
|
| 55 |
+
0.18078843,13.938334,-7.760792,-136.52077,-201.90285,1.0523647,-1.2054632,65.229,770000
|
| 56 |
+
0.18183675,23.46391,-2.6011903,-137.47803,-203.9655,0.7151897,-0.75863814,63.505882,775000
|
| 57 |
+
0.17884183,19.194773,0.39754874,-142.38707,-202.35033,1.2965966,-1.0110936,75.09224,780000
|
| 58 |
+
0.18403237,27.61637,-8.001782,-137.46289,-200.56467,0.49351478,-0.559817,54.69496,785000
|
| 59 |
+
0.17848617,24.73358,-9.332264,-132.98448,-201.87773,0.6652241,-0.50930893,53.470795,790000
|
| 60 |
+
0.16427842,16.23123,1.817133,-135.62332,-204.57756,0.90239376,-0.53135395,57.941315,795000
|
| 61 |
+
0.16155425,16.284563,-9.194742,-141.14062,-201.71518,0.85177755,-0.8215203,47.509613,800000
|
| 62 |
+
0.16602425,8.328747,-4.3643885,-136.75658,-202.55081,0.3415836,-0.3336187,34.023834,805000
|
| 63 |
+
0.1743149,25.364897,-8.887951,-134.67302,-200.30852,1.0598027,-1.1452687,80.011314,810000
|
| 64 |
+
0.19449773,15.558542,-8.456966,-136.06505,-200.27019,0.51718193,-0.48751932,54.561615,815000
|
| 65 |
+
0.16617954,15.823067,-2.984804,-138.42395,-199.49597,0.7974013,-0.87779844,45.192055,820000
|
| 66 |
+
0.16289836,17.932865,-0.7679078,-135.77032,-204.486,1.3965622,-1.3726783,55.828896,825000
|
| 67 |
+
0.1809396,11.507446,3.843368,-130.39734,-202.51524,0.88868845,-0.9208092,50.562355,830000
|
| 68 |
+
0.17535426,10.462753,-1.1687212,-134.7661,-201.47809,0.7491093,-1.1554656,51.343197,835000
|
| 69 |
+
0.18958125,18.943789,-12.288729,-137.79002,-201.39345,0.5737777,-0.5632078,56.033092,840000
|
| 70 |
+
0.1634078,14.0271635,-6.9966736,-139.04524,-202.37915,1.3867223,-1.2557281,56.750053,845000
|
| 71 |
+
0.16627136,17.048716,1.7746447,-129.41043,-205.93011,0.7848844,-0.93137515,66.40256,850000
|
| 72 |
+
0.15264544,17.482555,3.6996229,-135.35118,-202.52048,0.7926187,-0.76327294,56.34529,855000
|
| 73 |
+
0.17051777,16.864414,3.138114,-129.88853,-202.73994,0.9764274,-1.106148,56.737415,860000
|
| 74 |
+
0.1733315,21.130417,-1.4282693,-132.7655,-205.20236,1.4397427,-1.5489992,80.72945,865000
|
| 75 |
+
0.13914573,24.038872,-3.5544577,-136.40018,-203.0152,1.4605868,-1.9756727,84.29962,870000
|
| 76 |
+
0.14436974,17.468794,18.26893,-132.07643,-203.118,4.9887176,-3.5575895,125.817856,875000
|
| 77 |
+
0.16389282,16.294622,-4.9914317,-131.27733,-203.22824,1.3005617,-1.1565778,59.3302,880000
|
| 78 |
+
0.13228564,14.0862875,-6.6787667,-135.0751,-204.50111,0.5194781,-0.44081974,44.60755,885000
|
| 79 |
+
0.1776802,21.527426,-1.0939099,-135.17339,-203.49399,1.2740924,-2.574737,77.69024,890000
|
| 80 |
+
0.14309555,16.486021,-8.768705,-134.33519,-201.52061,3.6996768,-4.883682,127.28819,895000
|
| 81 |
+
0.17265815,19.084253,0.65107274,-128.75833,-203.61635,1.4767836,-1.5384986,63.492203,900000
|
| 82 |
+
0.17832702,19.180925,3.5831013,-130.2824,-202.28436,2.685244,-1.3061078,86.052666,905000
|
| 83 |
+
0.15585211,16.10821,2.5865293,-134.98828,-200.81145,0.46009806,-0.49597698,40.925663,910000
|
| 84 |
+
0.17207897,12.185086,6.1804323,-129.83862,-199.91946,0.43543243,-0.53793013,39.379425,915000
|
| 85 |
+
0.16567516,18.877089,4.424414,-130.39897,-202.7771,1.6114975,-1.8736048,92.151306,920000
|
| 86 |
+
0.16090353,12.246615,-1.5225828,-128.98692,-203.34203,0.8944234,-0.6646631,46.30623,925000
|
| 87 |
+
0.15609518,9.450595,4.580974,-127.03284,-203.38896,0.6955127,-0.6717838,47.243362,930000
|
| 88 |
+
0.16821508,19.396168,-4.5124083,-133.06183,-204.2938,0.98031604,-0.7347524,62.25898,935000
|
| 89 |
+
0.19899519,12.72849,-3.4284725,-127.00173,-203.70036,0.4245919,-0.66957265,46.52172,940000
|
| 90 |
+
0.16834307,14.100878,-0.9320762,-131.88159,-202.08862,0.434805,-0.71628624,49.708225,945000
|
| 91 |
+
0.17673849,16.692053,4.3999977,-125.01891,-203.98111,0.7370554,-0.69245315,60.623085,950000
|
| 92 |
+
0.15658207,15.9711,0.01352492,-130.42699,-202.79799,1.1694291,-0.670781,48.42834,955000
|
| 93 |
+
0.16231695,10.718351,1.1705865,-129.41682,-204.47519,0.9204243,-1.0117134,45.5894,960000
|
| 94 |
+
0.17960864,21.843128,0.12891328,-130.8596,-201.63226,1.3396517,-0.7459913,70.10545,965000
|
| 95 |
+
0.18104786,29.098383,-3.144074,-129.56049,-200.19524,1.184074,-0.6953975,74.60333,970000
|
| 96 |
+
0.14773096,11.88752,2.3300188,-128.70247,-203.48528,0.44930115,-0.61248326,49.85585,975000
|
| 97 |
+
0.16161032,11.939612,1.6975546,-130.32237,-202.08061,1.4425445,-1.479039,63.26365,980000
|
| 98 |
+
0.15711072,14.122367,3.2696037,-127.64113,-203.73878,0.9431156,-0.8844055,52.604782,985000
|
| 99 |
+
0.15902841,18.554762,6.704783,-126.4449,-201.55714,1.3296425,-1.1997738,75.470764,990000
|
| 100 |
+
0.16208376,12.772144,1.9101351,-122.565025,-204.11597,0.99128395,-1.1938636,68.18968,995000
|
| 101 |
+
0.1455262,8.824849,4.3799644,-122.600174,-203.38554,0.6558775,-0.719639,40.324806,1000000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/online_agent_sv.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.20566803,5.110677,-73.12663,-179.45189,-203.61758,0.22142653,-0.23599018,19.25538,505000
|
| 3 |
+
0.2250425,9.059847,-71.92152,-175.47856,-203.1067,1.276209,-1.2214391,34.004097,510000
|
| 4 |
+
0.16932982,11.166118,-68.08083,-176.32138,-203.47983,0.43729627,-0.317221,34.374126,515000
|
| 5 |
+
0.17819636,16.805952,-65.42261,-174.59349,-203.47504,4.190076,-3.2183583,94.83454,520000
|
| 6 |
+
0.1722812,8.942349,-72.37749,-174.54308,-203.0009,0.35377336,-0.30577564,28.177853,525000
|
| 7 |
+
0.18364018,14.670789,-88.528625,-175.52774,-203.91237,4.1011844,-3.6807687,77.101395,530000
|
| 8 |
+
0.20521235,12.645774,-16.193739,-173.64854,-203.86273,0.22208874,-0.43939197,36.293564,535000
|
| 9 |
+
0.16835752,9.959799,-53.9744,-172.37384,-203.5259,0.27665028,-0.44127274,36.121014,540000
|
| 10 |
+
0.19698068,8.888588,-88.38606,-171.79369,-204.41869,0.57204884,-0.5381174,31.467728,545000
|
| 11 |
+
0.15572037,12.835947,-21.759287,-167.89372,-203.82889,0.69213164,-0.58809876,36.45994,550000
|
| 12 |
+
0.1954141,37.409393,-27.22268,-163.64323,-204.19447,1.6427501,-1.4318419,102.830574,555000
|
| 13 |
+
0.19255297,26.639893,-51.6152,-163.10672,-204.03114,0.45613933,-0.49051055,46.799038,560000
|
| 14 |
+
0.18367049,12.12156,-39.12962,-164.82045,-204.23233,1.062097,-1.0115552,45.36061,565000
|
| 15 |
+
0.17549372,19.61974,-28.350443,-161.28569,-204.11583,0.59141445,-0.5516618,53.70257,570000
|
| 16 |
+
0.20685051,12.2783985,-72.48462,-166.39575,-205.47327,0.3385271,-0.4601435,35.04776,575000
|
| 17 |
+
0.16643554,13.28646,-48.332752,-163.54066,-204.52322,0.73259604,-0.6885179,49.288322,580000
|
| 18 |
+
0.1801559,16.009888,-43.995087,-161.78589,-204.0759,0.4388525,-0.54398805,45.13157,585000
|
| 19 |
+
0.17249452,25.270279,-50.510937,-158.8568,-204.94019,1.1012672,-1.230733,74.603424,590000
|
| 20 |
+
0.15666306,16.27174,-36.677277,-160.54138,-204.03716,1.0948342,-1.0939605,41.94873,595000
|
| 21 |
+
0.19297245,19.256468,-21.627161,-154.55284,-203.80296,0.5846042,-0.63321394,51.47951,600000
|
| 22 |
+
0.18215103,11.736672,-45.44688,-159.09502,-205.13307,0.74325377,-0.6711486,46.419,605000
|
| 23 |
+
0.18784031,20.716288,-39.975956,-153.83015,-203.73938,0.6608016,-0.7067684,49.96794,610000
|
| 24 |
+
0.16215727,10.715085,2.1705005,-150.5094,-204.17896,1.3537142,-1.6073018,54.05764,615000
|
| 25 |
+
0.17303324,13.208338,-29.6961,-156.46396,-205.18839,0.7878483,-0.73783183,46.174683,620000
|
| 26 |
+
0.16602579,27.703257,-32.58668,-154.58769,-202.96054,0.7985654,-0.80906004,56.15025,625000
|
| 27 |
+
0.15611237,18.12496,-46.88384,-155.2082,-204.15376,0.8786886,-0.90878373,62.375313,630000
|
| 28 |
+
0.16161524,12.926068,3.088586,-154.67468,-204.69948,0.48457962,-0.71018004,46.2227,635000
|
| 29 |
+
0.17938894,17.544287,-29.482773,-148.32384,-201.60298,0.79231113,-0.77717656,56.840576,640000
|
| 30 |
+
0.16222373,25.938505,-28.240393,-151.2465,-203.89647,0.8903465,-0.850017,61.339806,645000
|
| 31 |
+
0.19187292,12.910105,-9.11895,-148.80208,-204.14496,0.7650809,-0.73558205,44.848988,650000
|
| 32 |
+
0.20996657,15.410697,-7.288761,-151.61943,-204.38197,0.5965687,-0.4602733,46.117016,655000
|
| 33 |
+
0.18960157,17.222998,-23.542465,-149.58118,-204.59146,2.2771595,-2.1334667,48.260048,660000
|
| 34 |
+
0.18364385,17.466696,1.5797184,-149.45886,-204.84885,0.5929509,-0.82026637,53.902145,665000
|
| 35 |
+
0.1696206,12.829656,-4.008024,-149.29083,-203.60889,0.6415093,-0.6237316,46.46586,670000
|
| 36 |
+
0.19804734,14.335022,-7.413153,-150.88414,-204.16646,0.689401,-0.7187595,48.7769,675000
|
| 37 |
+
0.17449117,20.371546,2.5581908,-149.5919,-203.94086,0.9196676,-0.8439001,62.9606,680000
|
| 38 |
+
0.17332101,18.588964,-17.49788,-147.54393,-203.03539,0.79254264,-0.9416936,76.58604,685000
|
| 39 |
+
0.16070896,24.520195,-20.431978,-145.90898,-202.24486,1.1409044,-1.0309751,81.443016,690000
|
| 40 |
+
0.20384756,16.685019,-7.2251096,-145.1892,-202.61761,0.58344895,-0.3957181,53.10576,695000
|
| 41 |
+
0.19963089,11.409919,-10.923604,-144.06644,-203.68452,1.0427814,-0.9438096,45.17065,700000
|
| 42 |
+
0.18104927,20.39068,-4.7607503,-145.24388,-201.574,0.44935983,-0.5296516,60.633423,705000
|
| 43 |
+
0.16611281,23.309597,-2.529027,-142.5005,-202.20909,0.71147645,-0.8462647,62.373535,710000
|
| 44 |
+
0.18311203,17.027493,-10.483625,-147.04388,-203.48883,0.6471176,-0.39923036,54.374157,715000
|
| 45 |
+
0.17484075,20.359911,-8.469924,-144.68907,-200.27666,1.3133475,-1.1496165,70.97615,720000
|
| 46 |
+
0.16159269,15.254886,-2.1809375,-141.70189,-203.94514,0.5898609,-0.84784067,64.39255,725000
|
| 47 |
+
0.19942284,21.431952,-8.299704,-142.05325,-204.37785,0.8852629,-0.8556647,59.66687,730000
|
| 48 |
+
0.19127601,12.016114,-5.0704546,-139.07619,-204.06389,0.74963856,-0.8542583,42.54686,735000
|
| 49 |
+
0.14877728,17.753191,1.9998504,-140.90872,-201.8382,2.849966,-1.7264401,52.442055,740000
|
| 50 |
+
0.15849599,16.768353,-3.2734382,-141.8522,-204.35588,0.6998075,-0.59482425,48.736237,745000
|
| 51 |
+
0.15797818,14.1616,-9.655507,-132.37993,-203.13571,0.55767494,-0.60660505,45.03371,750000
|
| 52 |
+
0.16840333,13.4676485,-11.877489,-145.27701,-202.78534,0.8772593,-1.0089743,54.600945,755000
|
| 53 |
+
0.20070918,19.792334,2.1166937,-139.10991,-202.05222,0.49715358,-0.5373625,52.138588,760000
|
| 54 |
+
0.18192849,10.095213,-10.67541,-141.31204,-203.40642,3.5511296,-3.8602796,56.66836,765000
|
| 55 |
+
0.18078843,13.938334,-7.760792,-136.52077,-201.90285,1.0523647,-1.2054632,65.229,770000
|
| 56 |
+
0.18183675,23.46391,-2.6011903,-137.47803,-203.9655,0.7151897,-0.75863814,63.505882,775000
|
| 57 |
+
0.17884183,19.194773,0.39754874,-142.38707,-202.35033,1.2965966,-1.0110936,75.09224,780000
|
| 58 |
+
0.18403237,27.61637,-8.001782,-137.46289,-200.56467,0.49351478,-0.559817,54.69496,785000
|
| 59 |
+
0.17848617,24.73358,-9.332264,-132.98448,-201.87773,0.6652241,-0.50930893,53.470795,790000
|
| 60 |
+
0.16427842,16.23123,1.817133,-135.62332,-204.57756,0.90239376,-0.53135395,57.941315,795000
|
| 61 |
+
0.16155425,16.284563,-9.194742,-141.14062,-201.71518,0.85177755,-0.8215203,47.509613,800000
|
| 62 |
+
0.16602425,8.328747,-4.3643885,-136.75658,-202.55081,0.3415836,-0.3336187,34.023834,805000
|
| 63 |
+
0.1743149,25.364897,-8.887951,-134.67302,-200.30852,1.0598027,-1.1452687,80.011314,810000
|
| 64 |
+
0.19449773,15.558542,-8.456966,-136.06505,-200.27019,0.51718193,-0.48751932,54.561615,815000
|
| 65 |
+
0.16617954,15.823067,-2.984804,-138.42395,-199.49597,0.7974013,-0.87779844,45.192055,820000
|
| 66 |
+
0.16289836,17.932865,-0.7679078,-135.77032,-204.486,1.3965622,-1.3726783,55.828896,825000
|
| 67 |
+
0.1809396,11.507446,3.843368,-130.39734,-202.51524,0.88868845,-0.9208092,50.562355,830000
|
| 68 |
+
0.17535426,10.462753,-1.1687212,-134.7661,-201.47809,0.7491093,-1.1554656,51.343197,835000
|
| 69 |
+
0.18958125,18.943789,-12.288729,-137.79002,-201.39345,0.5737777,-0.5632078,56.033092,840000
|
| 70 |
+
0.1634078,14.0271635,-6.9966736,-139.04524,-202.37915,1.3867223,-1.2557281,56.750053,845000
|
| 71 |
+
0.16627136,17.048716,1.7746447,-129.41043,-205.93011,0.7848844,-0.93137515,66.40256,850000
|
| 72 |
+
0.15264544,17.482555,3.6996229,-135.35118,-202.52048,0.7926187,-0.76327294,56.34529,855000
|
| 73 |
+
0.17051777,16.864414,3.138114,-129.88853,-202.73994,0.9764274,-1.106148,56.737415,860000
|
| 74 |
+
0.1733315,21.130417,-1.4282693,-132.7655,-205.20236,1.4397427,-1.5489992,80.72945,865000
|
| 75 |
+
0.13914573,24.038872,-3.5544577,-136.40018,-203.0152,1.4605868,-1.9756727,84.29962,870000
|
| 76 |
+
0.14436974,17.468794,18.26893,-132.07643,-203.118,4.9887176,-3.5575895,125.817856,875000
|
| 77 |
+
0.16389282,16.294622,-4.9914317,-131.27733,-203.22824,1.3005617,-1.1565778,59.3302,880000
|
| 78 |
+
0.13228564,14.0862875,-6.6787667,-135.0751,-204.50111,0.5194781,-0.44081974,44.60755,885000
|
| 79 |
+
0.1776802,21.527426,-1.0939099,-135.17339,-203.49399,1.2740924,-2.574737,77.69024,890000
|
| 80 |
+
0.14309555,16.486021,-8.768705,-134.33519,-201.52061,3.6996768,-4.883682,127.28819,895000
|
| 81 |
+
0.17265815,19.084253,0.65107274,-128.75833,-203.61635,1.4767836,-1.5384986,63.492203,900000
|
| 82 |
+
0.17832702,19.180925,3.5831013,-130.2824,-202.28436,2.685244,-1.3061078,86.052666,905000
|
| 83 |
+
0.15585211,16.10821,2.5865293,-134.98828,-200.81145,0.46009806,-0.49597698,40.925663,910000
|
| 84 |
+
0.17207897,12.185086,6.1804323,-129.83862,-199.91946,0.43543243,-0.53793013,39.379425,915000
|
| 85 |
+
0.16567516,18.877089,4.424414,-130.39897,-202.7771,1.6114975,-1.8736048,92.151306,920000
|
| 86 |
+
0.16090353,12.246615,-1.5225828,-128.98692,-203.34203,0.8944234,-0.6646631,46.30623,925000
|
| 87 |
+
0.15609518,9.450595,4.580974,-127.03284,-203.38896,0.6955127,-0.6717838,47.243362,930000
|
| 88 |
+
0.16821508,19.396168,-4.5124083,-133.06183,-204.2938,0.98031604,-0.7347524,62.25898,935000
|
| 89 |
+
0.19899519,12.72849,-3.4284725,-127.00173,-203.70036,0.4245919,-0.66957265,46.52172,940000
|
| 90 |
+
0.16834307,14.100878,-0.9320762,-131.88159,-202.08862,0.434805,-0.71628624,49.708225,945000
|
| 91 |
+
0.17673849,16.692053,4.3999977,-125.01891,-203.98111,0.7370554,-0.69245315,60.623085,950000
|
| 92 |
+
0.15658207,15.9711,0.01352492,-130.42699,-202.79799,1.1694291,-0.670781,48.42834,955000
|
| 93 |
+
0.16231695,10.718351,1.1705865,-129.41682,-204.47519,0.9204243,-1.0117134,45.5894,960000
|
| 94 |
+
0.17960864,21.843128,0.12891328,-130.8596,-201.63226,1.3396517,-0.7459913,70.10545,965000
|
| 95 |
+
0.18104786,29.098383,-3.144074,-129.56049,-200.19524,1.184074,-0.6953975,74.60333,970000
|
| 96 |
+
0.14773096,11.88752,2.3300188,-128.70247,-203.48528,0.44930115,-0.61248326,49.85585,975000
|
| 97 |
+
0.16161032,11.939612,1.6975546,-130.32237,-202.08061,1.4425445,-1.479039,63.26365,980000
|
| 98 |
+
0.15711072,14.122367,3.2696037,-127.64113,-203.73878,0.9431156,-0.8844055,52.604782,985000
|
| 99 |
+
0.15902841,18.554762,6.704783,-126.4449,-201.55714,1.3296425,-1.1997738,75.470764,990000
|
| 100 |
+
0.16208376,12.772144,1.9101351,-122.565025,-204.11597,0.99128395,-1.1938636,68.18968,995000
|
| 101 |
+
0.1455262,8.824849,4.3799644,-122.600174,-203.38554,0.6558775,-0.719639,40.324806,1000000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_1000000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a1531565324dfa81719cfb6f3e0c943c1beba9553f312dc7b88213c92030c94
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77305c9bd214eb6bc0dc6055aab8248104a83b765feeef2a2e3f0a69351bab59
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:488434def4a5fb53838886be9b89d590d7f8cb90cd661a9bc48888578fb139bc
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a8580c4925ae31dd4e2602ca04a29fef33f4592ae61e41dbbcdfec1dce57184
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e93455486eb0179159b978ba888c62ce2b36e4cd47373c7e848584343ab2d076
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_750000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2459226900c3c8354a02059eb1c29117dbbf3c269732be892e40a49803a2545
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_800000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c3b1430717ff638e7f304b5d4930c1b75950c6ac80bf275ea20acb92f566b53
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_850000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0140cb1c10320078fcbc7f4516ebbc7b26da91c96f03e3b9668a811754ccae5d
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_900000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:389e79c09a7b44e38deb90c1d656fcacb9bb9013e76a3a3b939de8247dfa0dc6
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/params_950000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2ab0804d84138d8d9bccdbed1b9b41fffedb925b2ed54560dcf3eddd1bc569c
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260319_092737/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/rt7bqnea
|