Upload folder using huggingface_hub

.gitattributes

@@ -962,3 +962,13 @@ O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1300000.png filter=lfs diff=
 O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1350000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1400000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260317_150042/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1050000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1100000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1150000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1200000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1250000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1300000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1350000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1400000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1450000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_181920/visited_states_1500000.png filter=lfs diff=lfs merge=lfs -text

O2O-w-diff-ckpts/qam/20260317_181920/eval.csv

@@ -0,0 +1,11 @@
+avg_gripper_contact_length,num_gripper_contacts,xy,prev_qpos,prev_qvel,qpos,qvel,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
+0.0,0.0,34.32080388007807,4.633537296897307,0.08063764930400165,4.638596185267495,-0.008145397802175327,0.34,25083.94,-0.66,-976.56,976.9,1.4242752742767335,1050000
+0.0,0.0,34.804130597339196,4.7011921241535894,0.04776964591490494,4.707906007525057,0.04877170704240094,0.38,75254.46,-0.62,-962.34,962.72,1.409255428314209,1100000
+0.0,0.0,29.039983170508375,3.932920322008055,0.05165078113351679,3.9374827311830747,0.07555348510244243,0.38,124994.46,-0.62,-951.9,952.28,1.481986975669861,1150000
+0.0,0.0,32.76177020177033,4.439775423449897,0.01455391341753005,4.443390300452905,0.04676449401940465,0.42,174564.14,-0.58,-951.02,951.44,1.3766852378845216,1200000
+0.0,0.0,30.781943230219277,4.1770209065987185,0.0629809704085102,4.185866936477042,0.12368983543830304,0.36,224163.14,-0.64,-952.96,953.32,1.4042433500289917,1250000
+0.0,0.0,28.45019843372021,3.8736693694200186,0.10817822978548955,3.883169995992432,0.06710554340552027,0.3,273760.72,-0.7,-959.82,960.12,1.4874731063842774,1300000
+0.0,0.0,29.131707043928017,3.953310714434676,-0.0015710819625229025,3.955428101171661,0.06579066885736855,0.48,323051.58,-0.52,-934.46,934.94,1.3467175579071045,1350000
+0.0,0.0,30.794859607837342,4.19080674236822,0.12438401061942723,4.20657479812642,0.13819021475667273,0.46,371533.56,-0.54,-930.32,930.78,1.3413993835449218,1400000
+0.0,0.0,31.623885150959442,4.296253125457702,0.09333517679872337,4.303443257371022,0.02812704559611769,0.46,419084.56,-0.54,-918.48,918.94,1.4141149091720582,1450000
+0.0,0.0,29.259296318411046,3.9991084607476215,0.10396190851020971,4.005405779095402,0.0412477847794862,0.36,467817.48,-0.64,-940.6,940.96,1.358656029701233,1500000

O2O-w-diff-ckpts/qam/20260317_181920/eval_sv.csv

@@ -0,0 +1,11 @@
+avg_gripper_contact_length,num_gripper_contacts,xy,prev_qpos,prev_qvel,qpos,qvel,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
+0.0,0.0,34.32080388007807,4.633537296897307,0.08063764930400165,4.638596185267495,-0.008145397802175327,0.34,25083.94,-0.66,-976.56,976.9,1.4242752742767335,1050000
+0.0,0.0,34.804130597339196,4.7011921241535894,0.04776964591490494,4.707906007525057,0.04877170704240094,0.38,75254.46,-0.62,-962.34,962.72,1.409255428314209,1100000
+0.0,0.0,29.039983170508375,3.932920322008055,0.05165078113351679,3.9374827311830747,0.07555348510244243,0.38,124994.46,-0.62,-951.9,952.28,1.481986975669861,1150000
+0.0,0.0,32.76177020177033,4.439775423449897,0.01455391341753005,4.443390300452905,0.04676449401940465,0.42,174564.14,-0.58,-951.02,951.44,1.3766852378845216,1200000
+0.0,0.0,30.781943230219277,4.1770209065987185,0.0629809704085102,4.185866936477042,0.12368983543830304,0.36,224163.14,-0.64,-952.96,953.32,1.4042433500289917,1250000
+0.0,0.0,28.45019843372021,3.8736693694200186,0.10817822978548955,3.883169995992432,0.06710554340552027,0.3,273760.72,-0.7,-959.82,960.12,1.4874731063842774,1300000
+0.0,0.0,29.131707043928017,3.953310714434676,-0.0015710819625229025,3.955428101171661,0.06579066885736855,0.48,323051.58,-0.52,-934.46,934.94,1.3467175579071045,1350000
+0.0,0.0,30.794859607837342,4.19080674236822,0.12438401061942723,4.20657479812642,0.13819021475667273,0.46,371533.56,-0.54,-930.32,930.78,1.3413993835449218,1400000
+0.0,0.0,31.623885150959442,4.296253125457702,0.09333517679872337,4.303443257371022,0.02812704559611769,0.46,419084.56,-0.54,-918.48,918.94,1.4141149091720582,1450000
+0.0,0.0,29.259296318411046,3.9991084607476215,0.10396190851020971,4.005405779095402,0.0412477847794862,0.36,467817.48,-0.64,-940.6,940.96,1.358656029701233,1500000

O2O-w-diff-ckpts/qam/20260317_181920/online_agent.csv

@@ -0,0 +1,101 @@
+actor/adj_loss,actor/adj_max,actor/adj_mean,actor/adj_std,actor/fast_loss,actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
+24.053583,11.416684,0.4137994,0.74002093,24.053583,0.2683622,0.49191594,-5.9619665,-177.29106,-219.35425,63.97785,-68.54767,459.96042,1005000
+25.655807,6.7525406,0.44540626,0.6574334,25.655807,0.2757206,0.36778307,-10.46353,-174.7085,-214.2866,128.15623,-96.48595,489.03748,1010000
+17.491636,7.9249125,0.3651009,0.6130472,17.491636,0.3299815,0.3253989,-10.0960865,-181.08417,-217.23824,33.108246,-58.461838,329.55743,1015000
+12.976393,6.2365847,0.39547804,0.6325385,12.976393,0.29245433,0.29446617,-19.68103,-179.18309,-211.62968,45.378937,-63.785324,296.0389,1020000
+56.67389,9.181837,0.4318375,0.65023726,56.67389,0.31896207,0.4979473,0.43735224,-176.78978,-218.5623,60.281544,-88.258354,568.83905,1025000
+13.649202,7.3755636,0.37932807,0.586568,13.649202,0.2918892,0.41033497,0.3824906,-176.6591,-214.85904,56.503963,-58.47045,355.3679,1030000
+22.614159,11.025528,0.39412123,0.71844923,22.614159,0.33817303,0.3680289,0.96891207,-176.91528,-216.20015,71.09589,-67.76231,375.36847,1035000
+14.802422,10.177118,0.40101564,0.721759,14.802422,0.26246276,0.32778308,-10.037554,-176.22134,-215.53569,84.82708,-53.263115,360.30252,1040000
+25.343029,15.9279585,0.4154485,0.809764,25.343029,0.3126763,0.41046104,-18.774488,-180.0783,-237.55899,42.1129,-66.3568,377.21054,1045000
+13.90407,4.4865003,0.37714148,0.5478736,13.90407,0.32330456,0.5843158,0.6388816,-178.8322,-213.77165,57.374813,-55.775352,388.29523,1050000
+16.938072,9.977825,0.40378517,0.6958985,16.938072,0.29595512,0.38194656,0.8812933,-176.08778,-236.08698,72.30664,-67.4977,433.77356,1055000
+22.233307,7.2894354,0.4051507,0.67468596,22.233307,0.30641663,0.5100822,-43.432877,-180.57976,-218.82051,94.221664,-66.806656,469.67838,1060000
+10.308928,6.2228136,0.3373704,0.5214709,10.308928,0.3049242,0.21890989,-24.484362,-184.1034,-215.84082,40.688225,-62.27069,306.12128,1065000
+21.399437,10.734043,0.38680965,0.6973657,21.399437,0.35412738,0.48768583,-18.132734,-180.43039,-211.00247,83.23067,-120.83323,433.2458,1070000
+18.342852,6.9879427,0.36207888,0.6172443,18.342852,0.31676257,0.30169162,-0.22732607,-183.38292,-212.94144,76.90894,-49.114666,350.8566,1075000
+16.524727,16.660717,0.399638,0.89535326,16.524727,0.30096555,0.3807828,-15.828323,-181.7397,-215.47241,36.781555,-60.681656,373.49927,1080000
+13.440106,6.137291,0.33441374,0.52428347,13.440106,0.3277539,0.34690508,-9.332224,-183.19263,-216.98216,72.86182,-63.810646,368.4379,1085000
+24.124094,6.263713,0.37394816,0.61331016,24.124094,0.31898817,0.45926744,-23.621746,-180.55046,-210.385,99.98787,-90.8852,503.21918,1090000
+20.6125,8.51436,0.38337898,0.6621284,20.6125,0.32579458,0.48078987,1.2199218,-178.20024,-212.12556,81.20235,-49.432335,430.56842,1095000
+21.493513,7.090083,0.39960685,0.6859983,21.493513,0.30451325,0.62393343,-7.563723,-181.63225,-217.29233,104.08113,-95.369446,468.3804,1100000
+21.888512,9.320791,0.39173472,0.64291584,21.888512,0.35664195,0.4891337,-21.811665,-182.52272,-228.51239,69.947334,-120.76936,536.7847,1105000
+31.55491,7.427208,0.39681756,0.6696737,31.55491,0.26664644,0.5343031,-17.806759,-179.55319,-217.68242,188.90503,-120.37823,598.9484,1110000
+29.190165,5.479189,0.34140527,0.5699353,29.190165,0.27275467,0.4098969,-15.169944,-184.19351,-217.38115,101.510445,-115.47577,541.6714,1115000
+16.872005,7.0805984,0.3420713,0.589407,16.872005,0.31487,0.69547933,-0.5326252,-181.4555,-223.16551,62.92398,-62.601616,391.7257,1120000
+13.541498,5.18156,0.33990398,0.55171824,13.541498,0.34523284,0.41076085,-21.44351,-183.89622,-217.3108,57.66825,-55.238297,353.84808,1125000
+14.516006,5.9874835,0.35198882,0.566091,14.516006,0.3125421,0.46484986,-19.2453,-183.57458,-215.52649,44.58857,-56.773773,345.2204,1130000
+14.802598,5.301402,0.34682098,0.583379,14.802598,0.3437723,0.36835513,-59.38504,-184.09471,-214.55447,23.998405,-42.59326,315.40305,1135000
+24.922337,12.521458,0.33511567,0.6627384,24.922337,0.290289,0.67729324,-2.0271668,-183.35,-216.25768,301.48224,-166.24982,849.1623,1140000
+19.11364,7.593748,0.3593455,0.611358,19.11364,0.34383762,0.34029746,-24.493994,-178.47879,-209.34708,93.77597,-100.04336,432.7758,1145000
+17.839388,8.728241,0.34008718,0.6082963,17.839388,0.32201993,0.35550252,-3.3090708,-182.50595,-232.39047,109.74577,-32.087322,354.70953,1150000
+15.421583,9.460504,0.3330061,0.59802353,15.421583,0.3285662,0.36493516,-24.63506,-185.70406,-224.74852,65.23112,-53.36161,420.79578,1155000
+13.9464855,12.674206,0.36453438,0.7710948,13.9464855,0.3231025,0.544296,-0.09403837,-179.84683,-230.45032,45.835926,-76.1012,353.14874,1160000
+20.333067,5.76051,0.32718235,0.5513508,20.333067,0.30301744,0.42544833,-11.7021885,-183.66641,-215.48317,68.45408,-81.74828,452.5905,1165000
+15.704923,10.382608,0.33455148,0.6323106,15.704923,0.2961579,0.35042503,0.88313675,-182.2292,-215.53516,66.45413,-184.30771,519.6419,1170000
+11.166485,9.996065,0.3396886,0.65164375,11.166485,0.2776364,0.7567703,-12.209002,-181.43803,-212.84845,38.071606,-76.11424,390.2139,1175000
+22.920717,6.9746284,0.37124726,0.62419194,22.920717,0.33702847,0.64210266,-1.2297196,-178.83023,-217.41197,253.2004,-84.24035,646.158,1180000
+13.022151,8.643882,0.35051537,0.6508596,13.022151,0.32112765,0.40961733,-14.86686,-184.16808,-216.539,73.6053,-72.520676,457.5015,1185000
+14.253891,6.9553146,0.3649599,0.6140741,14.253891,0.30040237,0.40278408,-40.28539,-182.47472,-215.2205,69.92546,-42.30809,366.93985,1190000
+41.979904,8.596763,0.31921512,0.6039357,41.979904,0.32890683,0.5685987,0.5492133,-186.95792,-240.91133,332.28992,-690.48694,1326.9727,1195000
+25.088814,12.504887,0.38948357,0.8405885,25.088814,0.3197922,0.5451253,0.71870166,-180.28532,-241.74915,55.974564,-92.95025,505.58466,1200000
+150.53491,5.2242,0.34095305,0.54197156,150.53491,0.28663272,0.37301388,-24.929222,-179.41795,-242.54681,112.53007,-143.87312,845.6875,1205000
+20.876621,28.530052,0.40243813,1.1679446,20.876621,0.3009073,0.34019846,-36.682846,-185.65874,-213.02553,47.46687,-62.649563,449.00296,1210000
+11.78117,7.829261,0.3190478,0.58384377,11.78117,0.37477756,0.2412391,-0.17563623,-186.11412,-218.16173,76.026855,-61.845737,346.2193,1215000
+15.109015,9.04556,0.33632356,0.6011679,15.109015,0.33361727,0.26521298,0.16144481,-183.36034,-233.79454,81.15796,-71.1878,436.46262,1220000
+21.149422,9.612463,0.33475226,0.6438035,21.149422,0.34450403,0.38017014,0.67517525,-180.87627,-215.02739,183.95477,-385.55853,799.9033,1225000
+13.593729,5.1992435,0.33771157,0.5711954,13.593729,0.30750066,0.4756975,-2.6612444,-184.14554,-222.381,87.037285,-45.317467,377.52667,1230000
+10.351461,5.4282484,0.30705985,0.52706,10.351461,0.30402803,0.6066308,0.8881378,-182.341,-214.03087,51.781075,-58.416412,464.60986,1235000
+12.949773,14.869415,0.32163066,0.6876027,12.949773,0.37572956,0.26055768,-7.3144045,-187.031,-259.1927,68.777145,-41.521698,371.10742,1240000
+10.157741,8.825706,0.30466777,0.5353522,10.157741,0.34206352,0.32440522,-24.78978,-187.38097,-215.6499,50.306953,-46.854317,288.73502,1245000
+12.754471,6.500566,0.32818234,0.61222357,12.754471,0.32342595,0.46449095,-13.4869375,-185.45381,-263.37924,54.984924,-31.870201,322.67606,1250000
+26.729515,6.7954516,0.36825478,0.64621466,26.729515,0.3196206,0.5095401,-13.273157,-180.53346,-266.52087,304.12238,-86.47249,734.1753,1255000
+14.78716,8.935659,0.3176572,0.53863895,14.78716,0.31579572,0.3362088,-1.4323549,-182.93668,-263.069,57.674347,-110.26239,382.1859,1260000
+15.244109,4.8048034,0.30967227,0.5258454,15.244109,0.3287324,0.33510032,-18.380392,-187.57886,-262.35855,35.82089,-54.05519,360.40198,1265000
+21.508526,15.757578,0.35060623,0.7987446,21.508526,0.28954858,0.47451258,-16.434013,-182.64241,-259.84717,54.801277,-74.39519,432.48813,1270000
+45.217823,8.080565,0.35824153,0.65227026,45.217823,0.34000418,0.44573504,-17.620178,-180.59387,-234.19595,69.423485,-249.97586,730.4998,1275000
+11.624324,6.434434,0.3103066,0.59528273,11.624324,0.31897897,0.49483132,1.1902401,-184.81244,-223.43396,63.878113,-71.13687,315.2352,1280000
+13.48103,4.1116266,0.3359308,0.53184277,13.48103,0.30770218,0.4590459,-2.2935102,-182.59431,-214.16666,48.162487,-46.111465,352.45663,1285000
+11.784887,8.150109,0.29869708,0.5497626,11.784887,0.35183877,0.32627583,-14.85692,-187.3567,-216.4617,58.14784,-75.423996,419.2025,1290000
+13.102032,13.021348,0.34765583,0.68480664,13.102032,0.35734332,0.54197234,0.15911075,-182.18831,-256.43378,89.69271,-67.66,420.46793,1295000
+13.274937,10.316909,0.30804464,0.60139817,13.274937,0.3134747,0.28508782,-56.957417,-185.38316,-213.37946,46.489178,-44.734745,309.69028,1300000
+14.8218,7.964216,0.30419642,0.5657333,14.8218,0.30925995,0.40576106,-18.058186,-187.17314,-224.1631,97.23839,-61.534805,374.92493,1305000
+16.500254,16.064434,0.35075933,0.78769666,16.500254,0.31148714,0.30509114,-10.596845,-184.24345,-231.66977,56.571,-89.0344,440.55075,1310000
+12.961564,6.834469,0.3455436,0.6469207,12.961564,0.3012461,0.3207117,-0.32388768,-180.33562,-212.5089,67.972336,-92.526566,424.4366,1315000
+8.965698,5.271091,0.28808725,0.4890862,8.965698,0.28257692,0.2663258,0.7959095,-185.1201,-274.62256,92.77969,-46.83674,331.42584,1320000
+24.095608,13.32702,0.3457129,0.6974402,24.095608,0.3176008,0.4859995,0.16702196,-178.52864,-215.96033,149.65103,-118.73236,586.8214,1325000
+15.871125,6.08875,0.34353518,0.61463857,15.871125,0.31310284,0.39967662,-25.32607,-185.15694,-244.72813,109.03165,-72.97385,411.1921,1330000
+16.823128,7.5045137,0.36077455,0.6522576,16.823128,0.35240456,0.37580264,-24.993847,-182.10971,-218.98695,97.440125,-66.45556,465.06128,1335000
+22.851728,43.880413,0.32453394,1.155684,22.851728,0.3294841,0.42739925,-11.473211,-184.13615,-215.68626,95.66434,-258.64774,755.7969,1340000
+10.080801,6.7111917,0.28291905,0.535488,10.080801,0.3040926,0.34353822,-27.95331,-185.64417,-245.34868,54.19702,-95.93216,384.56903,1345000
+16.371601,8.410902,0.34109885,0.63564926,16.371601,0.31491426,0.42920086,0.82310665,-185.79074,-225.43294,97.5558,-59.81056,396.4607,1350000
+19.351223,9.389974,0.36263043,0.7080989,19.351223,0.33602694,0.40838432,0.885629,-183.7391,-221.77365,78.46221,-69.15567,400.85736,1355000
+16.668121,8.793621,0.32111704,0.5957519,16.668121,0.27178317,0.31172475,-24.28721,-185.481,-214.64224,53.717876,-40.119194,356.79373,1360000
+14.631353,8.138956,0.36528558,0.65638584,14.631353,0.30749407,0.4081585,1.4637227,-179.77817,-216.26852,69.42976,-44.415916,365.1496,1365000
+17.753136,25.50483,0.38290226,1.1089957,17.753136,0.29913732,1.6822453,0.7821441,-182.94757,-217.75584,80.311935,-100.13672,528.80225,1370000
+10.19923,4.724362,0.29477477,0.4524356,10.19923,0.3309749,0.39409003,0.28957722,-181.28192,-226.25562,58.95849,-58.589897,337.80643,1375000
+12.857175,7.5080013,0.31354743,0.5434168,12.857175,0.3012358,0.3695154,-7.8200817,-183.11282,-236.87427,72.146355,-69.784,421.61945,1380000
+23.79715,24.971804,0.38708946,1.0944945,23.79715,0.32170635,0.38107795,-7.221701,-181.80566,-218.63954,82.63348,-91.10463,601.66534,1385000
+13.706912,7.700267,0.32051283,0.6125247,13.706912,0.25108173,0.694212,-0.4431312,-184.5172,-228.5061,64.3212,-54.59188,420.13486,1390000
+25.673824,12.718926,0.33845776,0.66234505,25.673824,0.27294818,0.64538187,-17.780073,-184.67374,-242.83098,57.306545,-88.49217,381.99823,1395000
+14.029976,7.915642,0.34161282,0.6300532,14.029976,0.29799256,0.4787541,0.38192198,-181.99962,-226.17705,44.59868,-43.59864,287.23877,1400000
+12.06969,8.801892,0.35506853,0.6704184,12.06969,0.30689874,0.45735082,-8.086192,-182.29723,-227.08282,62.45709,-57.56552,392.56396,1405000
+14.314215,13.965368,0.3457878,0.6757126,14.314215,0.3042498,0.6153693,-4.764558,-180.39693,-218.32909,93.827255,-62.827538,446.45224,1410000
+10.587704,8.19772,0.28439802,0.5361592,10.587704,0.33092391,0.34435984,2.228195,-185.34598,-237.12956,39.841736,-55.016953,328.31763,1415000
+16.492477,5.9209394,0.3279875,0.6084957,16.492477,0.27986023,0.76014656,0.79780936,-185.61761,-217.36736,39.19066,-56.056023,352.2361,1420000
+10.902336,5.0136857,0.29517603,0.50904214,10.902336,0.29972816,0.2981623,-28.579748,-182.53606,-216.83621,85.68612,-102.22559,437.58826,1425000
+16.765528,12.524319,0.3733774,0.75606346,16.765528,0.2609436,0.4068284,-0.4458801,-181.43889,-234.40793,158.76286,-459.0487,870.0361,1430000
+14.355965,7.7412767,0.3338471,0.5975931,14.355965,0.30440176,0.35253718,-22.481287,-183.13493,-219.526,28.096523,-50.366486,283.8803,1435000
+12.064701,10.868216,0.32782626,0.6757479,12.064701,0.30015194,0.35357633,0.13315332,-184.42558,-219.85263,192.04099,-87.17892,499.31754,1440000
+12.316614,7.485974,0.33989674,0.60744196,12.316614,0.2869926,0.6976442,-7.049477,-183.92044,-216.57265,63.64096,-46.351902,430.37543,1445000
+22.249626,9.643875,0.35980138,0.6715873,22.249626,0.31905568,0.38242203,-0.39706874,-178.7617,-232.94572,76.82332,-57.732468,399.2274,1450000
+13.05963,8.456002,0.3299387,0.62436366,13.05963,0.2982712,0.48530886,0.474428,-181.51547,-233.22879,59.920235,-62.783363,369.56445,1455000
+24.051691,8.513937,0.39521104,0.7707828,24.051691,0.29813942,0.46048188,-20.356913,-180.38974,-228.53563,63.39169,-60.087196,431.9406,1460000
+21.548035,8.715666,0.35846525,0.67165226,21.548035,0.2983875,0.3024089,-19.646507,-181.62778,-213.57693,67.322136,-49.00968,366.64294,1465000
+11.551889,10.445959,0.3482654,0.6268342,11.551889,0.2575293,1.0688862,-15.685765,-183.15355,-226.10338,64.03623,-67.44023,483.94196,1470000
+10.4344635,8.859465,0.35161296,0.6451994,10.4344635,0.3120435,0.67542356,-13.795599,-181.05052,-231.02246,26.599085,-37.4368,302.76834,1475000
+14.51753,17.337467,0.3691283,0.8788551,14.51753,0.29121965,0.37254748,-0.52418035,-182.75809,-219.12503,55.60482,-41.87712,366.96136,1480000
+34.43631,5.798568,0.3061396,0.5222459,34.43631,0.2926647,0.2901287,-1.1819196,-183.77495,-224.60945,58.986748,-108.3544,455.08344,1485000
+38.42366,11.120152,0.35165322,0.73644286,38.42366,0.27765116,0.9207983,0.88978994,-180.48763,-226.62065,145.37129,-141.60782,920.2883,1490000
+11.053539,7.6355333,0.33913738,0.6199029,11.053539,0.2632475,0.38973698,-2.0751126,-185.0194,-227.90474,94.86211,-79.04294,424.30106,1495000
+17.279861,13.307606,0.30892318,0.7384506,17.279861,0.34924912,0.57668096,-5.2596297,-186.28288,-219.09668,161.76225,-125.89636,592.19855,1500000

O2O-w-diff-ckpts/qam/20260317_181920/online_agent_sv.csv

@@ -0,0 +1,101 @@
+actor/adj_loss,actor/adj_max,actor/adj_mean,actor/adj_std,actor/fast_loss,actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
+24.053583,11.416684,0.4137994,0.74002093,24.053583,0.2683622,0.49191594,-5.9619665,-177.29106,-219.35425,63.97785,-68.54767,459.96042,1005000
+25.655807,6.7525406,0.44540626,0.6574334,25.655807,0.2757206,0.36778307,-10.46353,-174.7085,-214.2866,128.15623,-96.48595,489.03748,1010000
+17.491636,7.9249125,0.3651009,0.6130472,17.491636,0.3299815,0.3253989,-10.0960865,-181.08417,-217.23824,33.108246,-58.461838,329.55743,1015000
+12.976393,6.2365847,0.39547804,0.6325385,12.976393,0.29245433,0.29446617,-19.68103,-179.18309,-211.62968,45.378937,-63.785324,296.0389,1020000
+56.67389,9.181837,0.4318375,0.65023726,56.67389,0.31896207,0.4979473,0.43735224,-176.78978,-218.5623,60.281544,-88.258354,568.83905,1025000
+13.649202,7.3755636,0.37932807,0.586568,13.649202,0.2918892,0.41033497,0.3824906,-176.6591,-214.85904,56.503963,-58.47045,355.3679,1030000
+22.614159,11.025528,0.39412123,0.71844923,22.614159,0.33817303,0.3680289,0.96891207,-176.91528,-216.20015,71.09589,-67.76231,375.36847,1035000
+14.802422,10.177118,0.40101564,0.721759,14.802422,0.26246276,0.32778308,-10.037554,-176.22134,-215.53569,84.82708,-53.263115,360.30252,1040000
+25.343029,15.9279585,0.4154485,0.809764,25.343029,0.3126763,0.41046104,-18.774488,-180.0783,-237.55899,42.1129,-66.3568,377.21054,1045000
+13.90407,4.4865003,0.37714148,0.5478736,13.90407,0.32330456,0.5843158,0.6388816,-178.8322,-213.77165,57.374813,-55.775352,388.29523,1050000
+16.938072,9.977825,0.40378517,0.6958985,16.938072,0.29595512,0.38194656,0.8812933,-176.08778,-236.08698,72.30664,-67.4977,433.77356,1055000
+22.233307,7.2894354,0.4051507,0.67468596,22.233307,0.30641663,0.5100822,-43.432877,-180.57976,-218.82051,94.221664,-66.806656,469.67838,1060000
+10.308928,6.2228136,0.3373704,0.5214709,10.308928,0.3049242,0.21890989,-24.484362,-184.1034,-215.84082,40.688225,-62.27069,306.12128,1065000
+21.399437,10.734043,0.38680965,0.6973657,21.399437,0.35412738,0.48768583,-18.132734,-180.43039,-211.00247,83.23067,-120.83323,433.2458,1070000
+18.342852,6.9879427,0.36207888,0.6172443,18.342852,0.31676257,0.30169162,-0.22732607,-183.38292,-212.94144,76.90894,-49.114666,350.8566,1075000
+16.524727,16.660717,0.399638,0.89535326,16.524727,0.30096555,0.3807828,-15.828323,-181.7397,-215.47241,36.781555,-60.681656,373.49927,1080000
+13.440106,6.137291,0.33441374,0.52428347,13.440106,0.3277539,0.34690508,-9.332224,-183.19263,-216.98216,72.86182,-63.810646,368.4379,1085000
+24.124094,6.263713,0.37394816,0.61331016,24.124094,0.31898817,0.45926744,-23.621746,-180.55046,-210.385,99.98787,-90.8852,503.21918,1090000
+20.6125,8.51436,0.38337898,0.6621284,20.6125,0.32579458,0.48078987,1.2199218,-178.20024,-212.12556,81.20235,-49.432335,430.56842,1095000
+21.493513,7.090083,0.39960685,0.6859983,21.493513,0.30451325,0.62393343,-7.563723,-181.63225,-217.29233,104.08113,-95.369446,468.3804,1100000
+21.888512,9.320791,0.39173472,0.64291584,21.888512,0.35664195,0.4891337,-21.811665,-182.52272,-228.51239,69.947334,-120.76936,536.7847,1105000
+31.55491,7.427208,0.39681756,0.6696737,31.55491,0.26664644,0.5343031,-17.806759,-179.55319,-217.68242,188.90503,-120.37823,598.9484,1110000
+29.190165,5.479189,0.34140527,0.5699353,29.190165,0.27275467,0.4098969,-15.169944,-184.19351,-217.38115,101.510445,-115.47577,541.6714,1115000
+16.872005,7.0805984,0.3420713,0.589407,16.872005,0.31487,0.69547933,-0.5326252,-181.4555,-223.16551,62.92398,-62.601616,391.7257,1120000
+13.541498,5.18156,0.33990398,0.55171824,13.541498,0.34523284,0.41076085,-21.44351,-183.89622,-217.3108,57.66825,-55.238297,353.84808,1125000
+14.516006,5.9874835,0.35198882,0.566091,14.516006,0.3125421,0.46484986,-19.2453,-183.57458,-215.52649,44.58857,-56.773773,345.2204,1130000
+14.802598,5.301402,0.34682098,0.583379,14.802598,0.3437723,0.36835513,-59.38504,-184.09471,-214.55447,23.998405,-42.59326,315.40305,1135000
+24.922337,12.521458,0.33511567,0.6627384,24.922337,0.290289,0.67729324,-2.0271668,-183.35,-216.25768,301.48224,-166.24982,849.1623,1140000
+19.11364,7.593748,0.3593455,0.611358,19.11364,0.34383762,0.34029746,-24.493994,-178.47879,-209.34708,93.77597,-100.04336,432.7758,1145000
+17.839388,8.728241,0.34008718,0.6082963,17.839388,0.32201993,0.35550252,-3.3090708,-182.50595,-232.39047,109.74577,-32.087322,354.70953,1150000
+15.421583,9.460504,0.3330061,0.59802353,15.421583,0.3285662,0.36493516,-24.63506,-185.70406,-224.74852,65.23112,-53.36161,420.79578,1155000
+13.9464855,12.674206,0.36453438,0.7710948,13.9464855,0.3231025,0.544296,-0.09403837,-179.84683,-230.45032,45.835926,-76.1012,353.14874,1160000
+20.333067,5.76051,0.32718235,0.5513508,20.333067,0.30301744,0.42544833,-11.7021885,-183.66641,-215.48317,68.45408,-81.74828,452.5905,1165000
+15.704923,10.382608,0.33455148,0.6323106,15.704923,0.2961579,0.35042503,0.88313675,-182.2292,-215.53516,66.45413,-184.30771,519.6419,1170000
+11.166485,9.996065,0.3396886,0.65164375,11.166485,0.2776364,0.7567703,-12.209002,-181.43803,-212.84845,38.071606,-76.11424,390.2139,1175000
+22.920717,6.9746284,0.37124726,0.62419194,22.920717,0.33702847,0.64210266,-1.2297196,-178.83023,-217.41197,253.2004,-84.24035,646.158,1180000
+13.022151,8.643882,0.35051537,0.6508596,13.022151,0.32112765,0.40961733,-14.86686,-184.16808,-216.539,73.6053,-72.520676,457.5015,1185000
+14.253891,6.9553146,0.3649599,0.6140741,14.253891,0.30040237,0.40278408,-40.28539,-182.47472,-215.2205,69.92546,-42.30809,366.93985,1190000
+41.979904,8.596763,0.31921512,0.6039357,41.979904,0.32890683,0.5685987,0.5492133,-186.95792,-240.91133,332.28992,-690.48694,1326.9727,1195000
+25.088814,12.504887,0.38948357,0.8405885,25.088814,0.3197922,0.5451253,0.71870166,-180.28532,-241.74915,55.974564,-92.95025,505.58466,1200000
+150.53491,5.2242,0.34095305,0.54197156,150.53491,0.28663272,0.37301388,-24.929222,-179.41795,-242.54681,112.53007,-143.87312,845.6875,1205000
+20.876621,28.530052,0.40243813,1.1679446,20.876621,0.3009073,0.34019846,-36.682846,-185.65874,-213.02553,47.46687,-62.649563,449.00296,1210000
+11.78117,7.829261,0.3190478,0.58384377,11.78117,0.37477756,0.2412391,-0.17563623,-186.11412,-218.16173,76.026855,-61.845737,346.2193,1215000
+15.109015,9.04556,0.33632356,0.6011679,15.109015,0.33361727,0.26521298,0.16144481,-183.36034,-233.79454,81.15796,-71.1878,436.46262,1220000
+21.149422,9.612463,0.33475226,0.6438035,21.149422,0.34450403,0.38017014,0.67517525,-180.87627,-215.02739,183.95477,-385.55853,799.9033,1225000
+13.593729,5.1992435,0.33771157,0.5711954,13.593729,0.30750066,0.4756975,-2.6612444,-184.14554,-222.381,87.037285,-45.317467,377.52667,1230000
+10.351461,5.4282484,0.30705985,0.52706,10.351461,0.30402803,0.6066308,0.8881378,-182.341,-214.03087,51.781075,-58.416412,464.60986,1235000
+12.949773,14.869415,0.32163066,0.6876027,12.949773,0.37572956,0.26055768,-7.3144045,-187.031,-259.1927,68.777145,-41.521698,371.10742,1240000
+10.157741,8.825706,0.30466777,0.5353522,10.157741,0.34206352,0.32440522,-24.78978,-187.38097,-215.6499,50.306953,-46.854317,288.73502,1245000
+12.754471,6.500566,0.32818234,0.61222357,12.754471,0.32342595,0.46449095,-13.4869375,-185.45381,-263.37924,54.984924,-31.870201,322.67606,1250000
+26.729515,6.7954516,0.36825478,0.64621466,26.729515,0.3196206,0.5095401,-13.273157,-180.53346,-266.52087,304.12238,-86.47249,734.1753,1255000
+14.78716,8.935659,0.3176572,0.53863895,14.78716,0.31579572,0.3362088,-1.4323549,-182.93668,-263.069,57.674347,-110.26239,382.1859,1260000
+15.244109,4.8048034,0.30967227,0.5258454,15.244109,0.3287324,0.33510032,-18.380392,-187.57886,-262.35855,35.82089,-54.05519,360.40198,1265000
+21.508526,15.757578,0.35060623,0.7987446,21.508526,0.28954858,0.47451258,-16.434013,-182.64241,-259.84717,54.801277,-74.39519,432.48813,1270000
+45.217823,8.080565,0.35824153,0.65227026,45.217823,0.34000418,0.44573504,-17.620178,-180.59387,-234.19595,69.423485,-249.97586,730.4998,1275000
+11.624324,6.434434,0.3103066,0.59528273,11.624324,0.31897897,0.49483132,1.1902401,-184.81244,-223.43396,63.878113,-71.13687,315.2352,1280000
+13.48103,4.1116266,0.3359308,0.53184277,13.48103,0.30770218,0.4590459,-2.2935102,-182.59431,-214.16666,48.162487,-46.111465,352.45663,1285000
+11.784887,8.150109,0.29869708,0.5497626,11.784887,0.35183877,0.32627583,-14.85692,-187.3567,-216.4617,58.14784,-75.423996,419.2025,1290000
+13.102032,13.021348,0.34765583,0.68480664,13.102032,0.35734332,0.54197234,0.15911075,-182.18831,-256.43378,89.69271,-67.66,420.46793,1295000
+13.274937,10.316909,0.30804464,0.60139817,13.274937,0.3134747,0.28508782,-56.957417,-185.38316,-213.37946,46.489178,-44.734745,309.69028,1300000
+14.8218,7.964216,0.30419642,0.5657333,14.8218,0.30925995,0.40576106,-18.058186,-187.17314,-224.1631,97.23839,-61.534805,374.92493,1305000
+16.500254,16.064434,0.35075933,0.78769666,16.500254,0.31148714,0.30509114,-10.596845,-184.24345,-231.66977,56.571,-89.0344,440.55075,1310000
+12.961564,6.834469,0.3455436,0.6469207,12.961564,0.3012461,0.3207117,-0.32388768,-180.33562,-212.5089,67.972336,-92.526566,424.4366,1315000
+8.965698,5.271091,0.28808725,0.4890862,8.965698,0.28257692,0.2663258,0.7959095,-185.1201,-274.62256,92.77969,-46.83674,331.42584,1320000
+24.095608,13.32702,0.3457129,0.6974402,24.095608,0.3176008,0.4859995,0.16702196,-178.52864,-215.96033,149.65103,-118.73236,586.8214,1325000
+15.871125,6.08875,0.34353518,0.61463857,15.871125,0.31310284,0.39967662,-25.32607,-185.15694,-244.72813,109.03165,-72.97385,411.1921,1330000
+16.823128,7.5045137,0.36077455,0.6522576,16.823128,0.35240456,0.37580264,-24.993847,-182.10971,-218.98695,97.440125,-66.45556,465.06128,1335000
+22.851728,43.880413,0.32453394,1.155684,22.851728,0.3294841,0.42739925,-11.473211,-184.13615,-215.68626,95.66434,-258.64774,755.7969,1340000
+10.080801,6.7111917,0.28291905,0.535488,10.080801,0.3040926,0.34353822,-27.95331,-185.64417,-245.34868,54.19702,-95.93216,384.56903,1345000
+16.371601,8.410902,0.34109885,0.63564926,16.371601,0.31491426,0.42920086,0.82310665,-185.79074,-225.43294,97.5558,-59.81056,396.4607,1350000
+19.351223,9.389974,0.36263043,0.7080989,19.351223,0.33602694,0.40838432,0.885629,-183.7391,-221.77365,78.46221,-69.15567,400.85736,1355000
+16.668121,8.793621,0.32111704,0.5957519,16.668121,0.27178317,0.31172475,-24.28721,-185.481,-214.64224,53.717876,-40.119194,356.79373,1360000
+14.631353,8.138956,0.36528558,0.65638584,14.631353,0.30749407,0.4081585,1.4637227,-179.77817,-216.26852,69.42976,-44.415916,365.1496,1365000
+17.753136,25.50483,0.38290226,1.1089957,17.753136,0.29913732,1.6822453,0.7821441,-182.94757,-217.75584,80.311935,-100.13672,528.80225,1370000
+10.19923,4.724362,0.29477477,0.4524356,10.19923,0.3309749,0.39409003,0.28957722,-181.28192,-226.25562,58.95849,-58.589897,337.80643,1375000
+12.857175,7.5080013,0.31354743,0.5434168,12.857175,0.3012358,0.3695154,-7.8200817,-183.11282,-236.87427,72.146355,-69.784,421.61945,1380000
+23.79715,24.971804,0.38708946,1.0944945,23.79715,0.32170635,0.38107795,-7.221701,-181.80566,-218.63954,82.63348,-91.10463,601.66534,1385000
+13.706912,7.700267,0.32051283,0.6125247,13.706912,0.25108173,0.694212,-0.4431312,-184.5172,-228.5061,64.3212,-54.59188,420.13486,1390000
+25.673824,12.718926,0.33845776,0.66234505,25.673824,0.27294818,0.64538187,-17.780073,-184.67374,-242.83098,57.306545,-88.49217,381.99823,1395000
+14.029976,7.915642,0.34161282,0.6300532,14.029976,0.29799256,0.4787541,0.38192198,-181.99962,-226.17705,44.59868,-43.59864,287.23877,1400000
+12.06969,8.801892,0.35506853,0.6704184,12.06969,0.30689874,0.45735082,-8.086192,-182.29723,-227.08282,62.45709,-57.56552,392.56396,1405000
+14.314215,13.965368,0.3457878,0.6757126,14.314215,0.3042498,0.6153693,-4.764558,-180.39693,-218.32909,93.827255,-62.827538,446.45224,1410000
+10.587704,8.19772,0.28439802,0.5361592,10.587704,0.33092391,0.34435984,2.228195,-185.34598,-237.12956,39.841736,-55.016953,328.31763,1415000
+16.492477,5.9209394,0.3279875,0.6084957,16.492477,0.27986023,0.76014656,0.79780936,-185.61761,-217.36736,39.19066,-56.056023,352.2361,1420000
+10.902336,5.0136857,0.29517603,0.50904214,10.902336,0.29972816,0.2981623,-28.579748,-182.53606,-216.83621,85.68612,-102.22559,437.58826,1425000
+16.765528,12.524319,0.3733774,0.75606346,16.765528,0.2609436,0.4068284,-0.4458801,-181.43889,-234.40793,158.76286,-459.0487,870.0361,1430000
+14.355965,7.7412767,0.3338471,0.5975931,14.355965,0.30440176,0.35253718,-22.481287,-183.13493,-219.526,28.096523,-50.366486,283.8803,1435000
+12.064701,10.868216,0.32782626,0.6757479,12.064701,0.30015194,0.35357633,0.13315332,-184.42558,-219.85263,192.04099,-87.17892,499.31754,1440000
+12.316614,7.485974,0.33989674,0.60744196,12.316614,0.2869926,0.6976442,-7.049477,-183.92044,-216.57265,63.64096,-46.351902,430.37543,1445000
+22.249626,9.643875,0.35980138,0.6715873,22.249626,0.31905568,0.38242203,-0.39706874,-178.7617,-232.94572,76.82332,-57.732468,399.2274,1450000
+13.05963,8.456002,0.3299387,0.62436366,13.05963,0.2982712,0.48530886,0.474428,-181.51547,-233.22879,59.920235,-62.783363,369.56445,1455000
+24.051691,8.513937,0.39521104,0.7707828,24.051691,0.29813942,0.46048188,-20.356913,-180.38974,-228.53563,63.39169,-60.087196,431.9406,1460000
+21.548035,8.715666,0.35846525,0.67165226,21.548035,0.2983875,0.3024089,-19.646507,-181.62778,-213.57693,67.322136,-49.00968,366.64294,1465000
+11.551889,10.445959,0.3482654,0.6268342,11.551889,0.2575293,1.0688862,-15.685765,-183.15355,-226.10338,64.03623,-67.44023,483.94196,1470000
+10.4344635,8.859465,0.35161296,0.6451994,10.4344635,0.3120435,0.67542356,-13.795599,-181.05052,-231.02246,26.599085,-37.4368,302.76834,1475000
+14.51753,17.337467,0.3691283,0.8788551,14.51753,0.29121965,0.37254748,-0.52418035,-182.75809,-219.12503,55.60482,-41.87712,366.96136,1480000
+34.43631,5.798568,0.3061396,0.5222459,34.43631,0.2926647,0.2901287,-1.1819196,-183.77495,-224.60945,58.986748,-108.3544,455.08344,1485000
+38.42366,11.120152,0.35165322,0.73644286,38.42366,0.27765116,0.9207983,0.88978994,-180.48763,-226.62065,145.37129,-141.60782,920.2883,1490000
+11.053539,7.6355333,0.33913738,0.6199029,11.053539,0.2632475,0.38973698,-2.0751126,-185.0194,-227.90474,94.86211,-79.04294,424.30106,1495000
+17.279861,13.307606,0.30892318,0.7384506,17.279861,0.34924912,0.57668096,-5.2596297,-186.28288,-219.09668,161.76225,-125.89636,592.19855,1500000

O2O-w-diff-ckpts/qam/20260317_181920/params_1050000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384e0014c064a2489dc72933b5c5e1f42a329b285bc156801bb98ce8b474823c
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1100000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aecf82c4ad8d7f774ed9f0b291bc74082c085653b4938f964087b6e85394ded
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1150000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2540d335bf5879cf777eec328ec4120726734768a4cc1b0df71f55fe57baa71f
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1200000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a87041cda8a3d2b03c956864e2523a67a33ba8f994171e9cb9d72a18262ae2
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1250000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab5b77758710a3abd6d21d037e32e17c90204543c8c1a07fbad1b75e8ec13cf
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1300000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91fc665cfec1f91a0405f8b929c5dee02df8326ff03809ae43db483e1a5858fe
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1350000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f37f5fe9d92ac15b23e22fb26fb06ecfe24b851a91859e1c255a2c7b9456e07
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1400000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8d7fdf9fdedc8398af9d65928d83275892a9bf9842f73ea50ecda41e524446
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1450000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df69f5928103d8ce0b6d8029bd5cd3ac00319684c06b3a664b7b2a4cb68a866
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/params_1500000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b66489293c299aa4861640ef0894cb13fc3434d80ed907f2ddc657ece32bb2e
+size 233879450

O2O-w-diff-ckpts/qam/20260317_181920/progress.tk

@@ -0,0 +1 @@
+online,500000

O2O-w-diff-ckpts/qam/20260317_181920/token.tk

@@ -0,0 +1 @@
+https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/5fr04pag