Upload folder using huggingface_hub

.gitattributes

@@ -872,3 +872,13 @@ O2O-w-diff-ckpts/fql/20260317_193804/visited_states_1500000.png filter=lfs diff=
 O2O-w-diff-ckpts/qam/20260316_083915/visited_states_1050000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260316_083915/visited_states_1100000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260316_083915/visited_states_1150000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_150000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_200000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_250000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_300000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_350000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_400000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_450000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_500000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_550000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_123356/visited_states_600000.png filter=lfs diff=lfs merge=lfs -text

O2O-w-diff-ckpts/qam/20260316_123356/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
+0.0,0.0,20.113730695613263,2.745292490138188,0.05286387262060979,2.748981960962076,0.0421332460781873,0.0,25500.0,-1.0,-1000.0,1000.0,1.4133140230178833,150000
+0.0,0.0,26.683932757055608,3.6227778246514135,0.05138404780173528,3.6256433068058906,0.041244084982956675,0.04,77435.52,-0.96,-996.94,996.98,1.4292691850662231,200000
+0.0,0.0,29.937402923038704,4.063252658559712,0.05124313617476463,4.070474442996648,0.10416112163265366,0.24,129094.34,-0.76,-987.14,987.38,1.515173454284668,250000
+0.0,0.0,30.513741230203678,4.121325477909432,0.12020216605356121,4.127648285020174,0.001991828121530424,0.26,180190.34,-0.74,-978.84,979.1,1.4050209283828736,300000
+0.0,0.0,24.862073629448073,3.3733386746447365,0.02378336194296134,3.375475489421592,0.01415888173066486,0.08,231482.28,-0.92,-990.06,990.14,1.4135451936721801,350000
+0.0,0.0,23.537486692628427,3.184275125353863,0.08207189849082414,3.1897057934013358,0.027786670001547956,0.16,282832.16,-0.84,-986.76,986.92,1.5210441446304321,400000
+0.0,0.0,21.903766872749443,2.9841463868919624,0.03403031219271159,2.990856758332178,0.08258379175346917,0.14,334066.24,-0.86,-984.32,984.46,1.403982219696045,450000
+0.0,0.0,26.523056199150947,3.580397234049921,0.010494928508245882,3.58009453718492,-0.004733710352528475,0.26,384969.66,-0.74,-972.02,972.28,1.4342591762542725,500000
+0.0,0.0,28.480825002530054,3.844237153984541,0.04497346752318206,3.849080990228886,0.06876527908085099,0.3,435094.06,-0.7,-962.74,963.04,1.5537309837341309,550000
+0.0,0.0,29.15805891569038,3.9573801787841516,0.06986915200680593,3.96550789987168,0.07697085718511813,0.24,485419.94,-0.76,-968.12,968.36,1.4476770877838134,600000

O2O-w-diff-ckpts/qam/20260316_123356/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
+0.0,0.0,20.113730695613263,2.745292490138188,0.05286387262060979,2.748981960962076,0.0421332460781873,0.0,25500.0,-1.0,-1000.0,1000.0,1.4133140230178833,150000
+0.0,0.0,26.683932757055608,3.6227778246514135,0.05138404780173528,3.6256433068058906,0.041244084982956675,0.04,77435.52,-0.96,-996.94,996.98,1.4292691850662231,200000
+0.0,0.0,29.937402923038704,4.063252658559712,0.05124313617476463,4.070474442996648,0.10416112163265366,0.24,129094.34,-0.76,-987.14,987.38,1.515173454284668,250000
+0.0,0.0,30.513741230203678,4.121325477909432,0.12020216605356121,4.127648285020174,0.001991828121530424,0.26,180190.34,-0.74,-978.84,979.1,1.4050209283828736,300000
+0.0,0.0,24.862073629448073,3.3733386746447365,0.02378336194296134,3.375475489421592,0.01415888173066486,0.08,231482.28,-0.92,-990.06,990.14,1.4135451936721801,350000
+0.0,0.0,23.537486692628427,3.184275125353863,0.08207189849082414,3.1897057934013358,0.027786670001547956,0.16,282832.16,-0.84,-986.76,986.92,1.5210441446304321,400000
+0.0,0.0,21.903766872749443,2.9841463868919624,0.03403031219271159,2.990856758332178,0.08258379175346917,0.14,334066.24,-0.86,-984.32,984.46,1.403982219696045,450000
+0.0,0.0,26.523056199150947,3.580397234049921,0.010494928508245882,3.58009453718492,-0.004733710352528475,0.26,384969.66,-0.74,-972.02,972.28,1.4342591762542725,500000
+0.0,0.0,28.480825002530054,3.844237153984541,0.04497346752318206,3.849080990228886,0.06876527908085099,0.3,435094.06,-0.7,-962.74,963.04,1.5537309837341309,550000
+0.0,0.0,29.15805891569038,3.9573801787841516,0.06986915200680593,3.96550789987168,0.07697085718511813,0.24,485419.94,-0.76,-968.12,968.36,1.4476770877838134,600000

O2O-w-diff-ckpts/qam/20260316_123356/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
+8.721852,3.7065663,0.41195866,0.49369547,8.721852,0.37627435,0.4672044,-6.251737,-164.29727,-218.62973,17.103642,-34.654152,258.69928,105000
+10.859697,6.6287355,0.43090522,0.5317836,10.859697,0.369251,0.707261,-4.876668,-162.31897,-212.78453,20.089016,-26.985823,284.94363,110000
+12.796208,7.318019,0.4034996,0.59223086,12.796208,0.35705358,0.4828795,-9.177037,-169.01668,-235.17258,37.18309,-64.67706,428.5945,115000
+13.20039,6.9647183,0.39442047,0.5430058,13.20039,0.3699987,0.6196193,-18.271807,-169.33493,-224.39491,40.68647,-20.789303,294.2883,120000
+34.486572,25.385239,0.46421587,0.9706769,34.486572,0.33813077,0.9011599,-0.038489282,-167.01213,-242.23505,49.515213,-50.688652,435.66953,125000
+36.825043,5.171736,0.42629898,0.52878577,36.825043,0.31714022,0.4875022,0.41919374,-170.08195,-253.33595,37.7096,-49.614677,339.0302,130000
+10.225029,6.0321207,0.39028865,0.5220037,10.225029,0.36526665,0.9347704,0.28438926,-169.77515,-230.78886,37.30433,-19.418024,312.6125,135000
+10.794497,22.19598,0.41386902,0.7586047,10.794497,0.30900937,0.83027536,-1.5728161,-170.11458,-232.9648,25.272993,-32.121716,329.78113,140000
+15.721862,9.01546,0.4047358,0.61680895,15.721862,0.34004986,0.7078666,-7.5331774,-173.4449,-258.96616,56.377327,-34.4254,386.73187,145000
+11.592751,15.234331,0.4446805,0.71375746,11.592751,0.35024267,0.8304855,-0.82910585,-172.52214,-236.33998,39.00201,-36.286976,431.6787,150000
+16.385052,11.399836,0.45011896,0.7075772,16.385052,0.3264464,0.7774905,0.19011018,-171.30377,-253.90297,53.59887,-35.059902,391.83365,155000
+9.320791,5.7459307,0.40980196,0.59173614,9.320791,0.36219043,0.79996383,-39.85278,-175.72276,-267.7404,31.876783,-29.347313,320.3923,160000
+17.02856,4.021686,0.37727055,0.48647264,17.02856,0.34841818,0.42923957,-7.2431674,-178.31084,-261.48346,38.202156,-55.398384,359.179,165000
+9.408144,5.724895,0.3933427,0.5556626,9.408144,0.32960185,0.77912366,-13.274607,-176.14641,-248.15318,29.506042,-33.589836,300.45435,170000
+12.101633,7.8956637,0.3785809,0.55806774,12.101633,0.36587834,0.50416833,-1.1597629,-178.87175,-252.21837,33.59904,-37.048462,323.3019,175000
+13.460493,7.2389097,0.420902,0.5849251,13.460493,0.33890814,0.64796895,-5.523455,-175.92128,-234.86218,39.56271,-27.3833,300.65982,180000
+10.818464,5.545231,0.3783217,0.5066806,10.818464,0.33240643,0.5122549,-3.6594107,-176.878,-251.09853,31.613514,-27.664352,293.17694,185000
+10.959671,6.185258,0.40119815,0.5619984,10.959671,0.33918953,0.6565978,-17.476578,-176.3137,-276.6353,22.461208,-32.603115,271.90436,190000
+10.9354105,10.066529,0.38975787,0.5914294,10.9354105,0.3238529,0.6116682,-0.28381762,-173.62202,-260.85608,44.601532,-44.66716,374.6266,195000
+16.18872,5.300413,0.4106971,0.52907485,16.18872,0.33597997,0.5955171,-4.1223335,-176.01736,-258.83563,48.88482,-60.681778,366.94638,200000
+22.940022,5.535411,0.41287783,0.5836551,22.940022,0.3429097,1.028489,-10.335651,-179.38084,-263.9651,34.155052,-50.903767,378.95462,205000
+14.985503,10.834057,0.394572,0.59998447,14.985503,0.33553326,0.4784429,-6.141741,-176.17137,-277.88345,56.62349,-25.0682,376.9944,210000
+8.899124,10.616174,0.38420373,0.62537396,8.899124,0.3470419,0.64608425,-6.8793125,-180.42398,-232.78224,30.99442,-40.072903,305.9704,215000
+13.155247,6.594822,0.3741784,0.53429306,13.155247,0.29287243,0.4183952,-31.726318,-180.38188,-294.11832,37.91264,-37.728462,330.33405,220000
+12.384404,8.761534,0.4119433,0.61351967,12.384404,0.34504998,0.5109644,-32.558544,-180.63127,-282.4425,38.86423,-44.897675,332.08685,225000
+11.932867,5.0269585,0.3742659,0.49888948,11.932867,0.36926952,0.42966864,-13.336003,-179.3145,-301.67007,78.99196,-56.92872,436.24005,230000
+16.571201,5.404269,0.37364152,0.5135894,16.571201,0.33856905,0.31505352,-11.377425,-179.9641,-258.63852,34.410828,-41.530357,299.58133,235000
+13.165558,5.2167954,0.37986743,0.5261388,13.165558,0.3644194,0.4475124,-0.33554265,-180.93452,-268.75208,28.896692,-30.860165,297.70392,240000
+13.493194,5.1985974,0.4068725,0.56813985,13.493194,0.3453343,0.8107479,-15.801795,-175.20988,-234.24603,70.92763,-41.31378,386.75537,245000
+9.103591,5.436701,0.32814476,0.48303872,9.103591,0.32384068,0.40375376,-19.570404,-182.73772,-292.01328,36.675774,-26.818226,293.44785,250000
+17.419996,6.260297,0.33779466,0.54776925,17.419996,0.32236823,1.1479254,-7.3281803,-184.04012,-288.38144,91.703926,-38.58193,456.53595,255000
+20.050404,12.503208,0.40009338,0.7762729,20.050404,0.33274198,0.91780704,0.34996134,-177.89267,-259.958,71.23863,-35.19197,397.20792,260000
+12.64006,7.430521,0.33426154,0.47958204,12.64006,0.34713316,0.5782693,-45.33753,-184.25632,-299.91782,25.605627,-89.95529,385.6812,265000
+13.980164,10.953421,0.39170018,0.6748567,13.980164,0.34525934,0.7930216,-0.2889686,-179.86931,-279.0925,44.16638,-58.49161,378.68192,270000
+10.768852,7.1695876,0.35019562,0.53293175,10.768852,0.3203035,0.5983389,-44.3857,-180.96057,-322.75287,38.333363,-22.803808,352.96313,275000
+32.447887,46.860527,0.45860815,1.7727075,32.447887,0.36377776,3.5177624,0.45834506,-176.13539,-220.77411,92.569756,-150.23425,1162.931,280000
+11.269994,11.8033905,0.3583299,0.63854843,11.269994,0.32198626,0.6801433,-7.9868336,-184.52487,-284.96844,45.870293,-76.88561,416.10995,285000
+19.597569,15.371466,0.42135656,0.7697019,19.597569,0.31239843,0.9491229,-40.450897,-179.33702,-235.38087,45.94073,-99.6433,441.167,290000
+15.025234,7.4914074,0.3803581,0.59797627,15.025234,0.28364593,0.37771943,-0.6260812,-184.69585,-288.04727,39.73742,-40.395454,357.67514,295000
+16.65918,9.549272,0.37781405,0.61640316,16.65918,0.3380545,0.70765823,-6.7967453,-180.17357,-245.21829,47.221413,-40.503433,446.24915,300000
+10.387797,5.6263094,0.33448416,0.5024124,10.387797,0.28572422,0.75688183,-16.876429,-179.20654,-251.09444,30.320744,-40.197037,378.4394,305000
+11.485249,11.173054,0.35330945,0.5687517,11.485249,0.3068889,0.5676839,-33.137787,-183.20824,-291.8529,28.983551,-43.621063,309.9278,310000
+9.521746,9.596047,0.33724236,0.5791416,9.521746,0.322922,3.188253,0.4941521,-184.70213,-289.55835,44.43636,-48.59857,656.2173,315000
+8.97221,6.4102526,0.31459618,0.43647686,8.97221,0.32050347,0.48936167,-0.5512041,-185.78716,-449.1281,39.66952,-47.23916,309.77606,320000
+23.86668,6.446784,0.32479873,0.51711076,23.86668,0.31973806,0.33538923,1.5138831,-183.64195,-254.41548,58.53029,-39.68419,366.53934,325000
+14.108091,4.5416384,0.36391538,0.5179423,14.108091,0.32770956,0.4543829,-14.516898,-184.17879,-469.92642,48.410538,-41.736584,334.5067,330000
+11.351719,10.550566,0.34498394,0.61121935,11.351719,0.31368902,0.4771574,0.2259343,-184.02672,-483.512,48.00283,-87.05249,442.0116,335000
+13.943152,8.422209,0.3417023,0.60804445,13.943152,0.2841527,0.75149554,-39.131737,-185.96077,-273.90128,48.650112,-38.102406,366.44543,340000
+9.653437,5.775957,0.33374667,0.50841236,9.653437,0.32691562,0.52107257,-20.529259,-184.57115,-288.25824,32.056065,-42.06298,284.66882,345000
+11.01357,8.854577,0.33639044,0.5717389,11.01357,0.33017763,0.5367466,-2.1207645,-183.6398,-288.19827,35.409164,-54.771805,311.13776,350000
+13.699198,6.221943,0.35381073,0.5313368,13.699198,0.3431034,0.6751599,-8.407439,-181.05304,-290.2012,49.60989,-40.7844,361.1683,355000
+10.392461,5.4129124,0.34513417,0.5506128,10.392461,0.3462488,0.48088866,-1.5229629,-183.39523,-514.8129,36.307617,-21.644947,277.65085,360000
+10.401701,4.990123,0.31640548,0.4848605,10.401701,0.3261302,0.35490584,-10.220821,-187.64006,-447.50073,38.820423,-60.74597,341.04074,365000
+14.758768,20.094135,0.38182774,0.75111216,14.758768,0.37175936,0.8550606,-0.79513526,-183.2337,-289.9761,42.980446,-85.31723,466.35065,370000
+11.681238,6.906822,0.3209976,0.5659908,11.681238,0.3386949,0.41759726,-23.104519,-184.25179,-253.14406,66.898224,-42.961,378.61826,375000
+14.963855,10.297775,0.33409223,0.58112884,14.963855,0.31125668,0.3688829,0.32783225,-183.65181,-283.02713,76.75091,-65.873695,416.5452,380000
+9.7529545,6.3559446,0.35168225,0.540175,9.7529545,0.32177082,0.77861726,-0.4325851,-183.30879,-353.65237,53.84762,-39.06389,321.65125,385000
+12.436081,7.02504,0.33661526,0.53945976,12.436081,0.3303112,0.27620292,-8.649446,-187.6399,-355.5598,40.35751,-34.453293,347.14227,390000
+12.475937,25.594282,0.37005198,0.9136971,12.475937,0.35009822,0.59805995,-0.6556288,-182.20677,-238.03777,44.77928,-37.628723,378.05307,395000
+43.07315,6.793909,0.32147014,0.53569037,43.07315,0.28029376,0.46908155,-54.438854,-186.27103,-258.01166,91.0452,-85.07645,720.3955,400000
+14.237013,9.838537,0.34424365,0.63194466,14.237013,0.358244,0.43458953,-10.17229,-186.75473,-244.1703,72.04919,-37.13489,371.7621,405000
+13.479151,22.858955,0.33488807,0.8142728,13.479151,0.30735022,0.59713835,-29.52927,-188.07799,-330.35303,40.61195,-71.45874,343.99606,410000
+24.24765,58.835236,0.42720425,1.7678511,24.24765,0.3571779,5.701198,0.4619052,-180.1861,-246.7687,77.69824,-93.827354,896.59796,415000
+13.721904,8.27533,0.33872807,0.5755304,13.721904,0.26301992,0.47589198,0.44179899,-184.5906,-322.5273,44.81011,-81.394226,434.0802,420000
+12.760977,7.9896793,0.35514998,0.6578316,12.760977,0.30690297,0.9749519,0.16628826,-179.87572,-235.48091,45.36374,-42.826923,442.62152,425000
+21.122473,4.6339145,0.3239866,0.5339363,21.122473,0.30678868,0.49284458,-23.47106,-183.69438,-224.311,61.20468,-61.166412,392.67056,430000
+16.911966,20.005623,0.38099408,0.9581043,16.911966,0.31144807,0.7948336,-0.09859234,-183.75749,-308.49033,48.269665,-30.04486,395.11908,435000
+8.901811,8.123434,0.29973823,0.5221553,8.901811,0.3347196,0.5781515,-1.6327862,-187.96991,-267.18005,49.216484,-38.230045,378.16693,440000
+16.472073,7.378746,0.3544148,0.61430156,16.472073,0.31859845,0.3519304,-30.039495,-184.25237,-238.3563,31.266333,-51.50106,306.4162,445000
+9.68656,6.1229897,0.32253385,0.53357947,9.68656,0.32205415,0.29490778,0.2689731,-186.80699,-227.43254,37.766914,-38.799812,297.17673,450000
+14.400349,6.8569527,0.37697944,0.62112516,14.400349,0.31731975,0.4196112,-0.20551673,-184.14595,-304.56265,49.0822,-56.560623,413.60397,455000
+11.222731,6.0033884,0.32964215,0.5497317,11.222731,0.3304062,0.396611,-22.814583,-186.99187,-283.8119,52.31068,-59.25184,333.43552,460000
+8.326868,5.099764,0.31097186,0.480797,8.326868,0.34967083,0.33272186,0.96738964,-183.90637,-221.02068,27.616621,-31.612427,267.45844,465000
+12.309048,16.235588,0.34351942,0.70529413,12.309048,0.3044935,4.884276,1.1147816,-186.43758,-300.35983,43.964874,-49.290245,477.03778,470000
+19.582417,7.5703907,0.2912531,0.495613,19.582417,0.29500076,0.5211114,0.54572064,-185.17085,-239.90608,32.43923,-40.864532,325.79514,475000
+19.0989,6.586252,0.3343078,0.55896723,19.0989,0.35980463,0.47861958,-0.66399366,-183.50128,-241.8726,54.96793,-85.32483,407.55804,480000
+29.998951,7.1387367,0.35225448,0.57756025,29.998951,0.30033916,0.8083393,-12.179616,-182.21204,-400.3162,134.32608,-413.4386,1020.16785,485000
+42.087906,7.1379757,0.3684116,0.6149333,42.087906,0.30789012,0.61251974,0.6923871,-181.80423,-228.0902,77.0565,-229.02765,691.38824,490000
+13.279331,4.683917,0.30701464,0.48923516,13.279331,0.31319252,0.5026781,-49.861843,-187.82771,-245.60744,43.123283,-29.046024,290.14258,495000
+15.064287,7.1327286,0.34223765,0.52921855,15.064287,0.35139865,0.4460329,-0.18034577,-183.30948,-222.77132,73.694954,-91.170235,447.481,500000
+15.967598,6.440544,0.35956752,0.59705967,15.967598,0.34090132,0.53303415,-4.680501,-181.36978,-247.376,49.239807,-77.11794,413.9789,505000
+10.54105,10.624697,0.35759312,0.65138054,10.54105,0.37754846,0.9182501,-1.6213908,-184.23584,-225.96013,35.62948,-47.147335,335.4375,510000
+30.08417,5.9538565,0.28537184,0.4961887,30.08417,0.3525365,0.48983344,0.047448218,-188.07451,-247.07942,37.083282,-37.92768,378.84702,515000
+9.855529,8.612024,0.33539352,0.597137,9.855529,0.28709716,0.40969345,-61.738216,-187.19333,-242.35893,31.64741,-60.811485,357.7352,520000
+8.824729,4.846725,0.29100358,0.450446,8.824729,0.2812434,0.32175502,-24.799126,-185.79953,-261.71283,23.263186,-46.674927,288.64783,525000
+11.245197,6.1910505,0.3032022,0.47684264,11.245197,0.31865305,0.46447107,-18.934965,-186.09218,-229.55382,17.797077,-31.068707,256.3449,530000
+11.781323,6.3007665,0.32500273,0.52983356,11.781323,0.34934175,0.6515666,-40.286495,-185.33682,-229.63646,61.14576,-48.382908,361.39606,535000
+11.600106,7.2417774,0.2869951,0.45142844,11.600106,0.30468667,0.35637498,-0.2493046,-187.5317,-239.18225,37.300404,-43.376427,300.81805,540000
+11.798876,7.364393,0.3319865,0.5107066,11.798876,0.2906639,0.43808928,-15.163009,-185.67935,-274.46576,32.05006,-56.221714,385.98898,545000
+15.871521,8.829124,0.33342868,0.54917157,15.871521,0.3010859,0.5422277,-0.334751,-180.54932,-247.3921,259.9951,-34.517662,566.3177,550000
+16.634443,16.174519,0.35018006,0.8119975,16.634443,0.30682662,0.6254641,0.25613704,-182.97896,-252.55602,94.76177,-108.993645,490.86453,555000
+11.154624,7.82197,0.32891852,0.5711468,11.154624,0.32512128,0.4151643,-4.212316,-182.90086,-265.76828,30.6804,-30.997381,288.27808,560000
+16.810242,7.8078103,0.35466027,0.64376825,16.810242,0.33086425,0.7328374,-3.9469752,-181.80864,-233.70964,201.48557,-79.07982,556.3075,565000
+12.040159,4.203062,0.31388873,0.48232222,12.040159,0.3265325,0.42983285,-23.356325,-183.81708,-219.2103,34.45124,-52.454323,337.69815,570000
+11.968643,5.2251344,0.3235885,0.52670074,11.968643,0.33778143,0.46207818,-21.022226,-185.68689,-258.85275,36.101364,-37.452972,295.3571,575000
+11.812862,5.5146966,0.32461312,0.5235407,11.812862,0.297767,0.5596999,-0.4748238,-182.92772,-231.37314,45.49321,-52.10289,358.97318,580000
+12.380479,5.051265,0.29782522,0.5083557,12.380479,0.29364544,0.34645993,-33.524033,-188.41545,-219.27104,61.580986,-53.455463,386.93375,585000
+9.94115,6.61616,0.29900128,0.52891016,9.94115,0.31957382,0.39399102,-0.44896165,-184.52551,-242.31375,48.496925,-50.304413,347.87128,590000
+7.9741764,5.0060277,0.29022592,0.47126597,7.9741764,0.30803716,0.31420946,-73.79655,-190.50145,-241.62115,50.503613,-60.2798,312.33038,595000
+10.981232,5.2146425,0.27986443,0.47147316,10.981232,0.31648406,0.43589908,-9.352852,-188.27396,-237.80133,103.22863,-195.92583,497.30756,600000

O2O-w-diff-ckpts/qam/20260316_123356/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
+8.721852,3.7065663,0.41195866,0.49369547,8.721852,0.37627435,0.4672044,-6.251737,-164.29727,-218.62973,17.103642,-34.654152,258.69928,105000
+10.859697,6.6287355,0.43090522,0.5317836,10.859697,0.369251,0.707261,-4.876668,-162.31897,-212.78453,20.089016,-26.985823,284.94363,110000
+12.796208,7.318019,0.4034996,0.59223086,12.796208,0.35705358,0.4828795,-9.177037,-169.01668,-235.17258,37.18309,-64.67706,428.5945,115000
+13.20039,6.9647183,0.39442047,0.5430058,13.20039,0.3699987,0.6196193,-18.271807,-169.33493,-224.39491,40.68647,-20.789303,294.2883,120000
+34.486572,25.385239,0.46421587,0.9706769,34.486572,0.33813077,0.9011599,-0.038489282,-167.01213,-242.23505,49.515213,-50.688652,435.66953,125000
+36.825043,5.171736,0.42629898,0.52878577,36.825043,0.31714022,0.4875022,0.41919374,-170.08195,-253.33595,37.7096,-49.614677,339.0302,130000
+10.225029,6.0321207,0.39028865,0.5220037,10.225029,0.36526665,0.9347704,0.28438926,-169.77515,-230.78886,37.30433,-19.418024,312.6125,135000
+10.794497,22.19598,0.41386902,0.7586047,10.794497,0.30900937,0.83027536,-1.5728161,-170.11458,-232.9648,25.272993,-32.121716,329.78113,140000
+15.721862,9.01546,0.4047358,0.61680895,15.721862,0.34004986,0.7078666,-7.5331774,-173.4449,-258.96616,56.377327,-34.4254,386.73187,145000
+11.592751,15.234331,0.4446805,0.71375746,11.592751,0.35024267,0.8304855,-0.82910585,-172.52214,-236.33998,39.00201,-36.286976,431.6787,150000
+16.385052,11.399836,0.45011896,0.7075772,16.385052,0.3264464,0.7774905,0.19011018,-171.30377,-253.90297,53.59887,-35.059902,391.83365,155000
+9.320791,5.7459307,0.40980196,0.59173614,9.320791,0.36219043,0.79996383,-39.85278,-175.72276,-267.7404,31.876783,-29.347313,320.3923,160000
+17.02856,4.021686,0.37727055,0.48647264,17.02856,0.34841818,0.42923957,-7.2431674,-178.31084,-261.48346,38.202156,-55.398384,359.179,165000
+9.408144,5.724895,0.3933427,0.5556626,9.408144,0.32960185,0.77912366,-13.274607,-176.14641,-248.15318,29.506042,-33.589836,300.45435,170000
+12.101633,7.8956637,0.3785809,0.55806774,12.101633,0.36587834,0.50416833,-1.1597629,-178.87175,-252.21837,33.59904,-37.048462,323.3019,175000
+13.460493,7.2389097,0.420902,0.5849251,13.460493,0.33890814,0.64796895,-5.523455,-175.92128,-234.86218,39.56271,-27.3833,300.65982,180000
+10.818464,5.545231,0.3783217,0.5066806,10.818464,0.33240643,0.5122549,-3.6594107,-176.878,-251.09853,31.613514,-27.664352,293.17694,185000
+10.959671,6.185258,0.40119815,0.5619984,10.959671,0.33918953,0.6565978,-17.476578,-176.3137,-276.6353,22.461208,-32.603115,271.90436,190000
+10.9354105,10.066529,0.38975787,0.5914294,10.9354105,0.3238529,0.6116682,-0.28381762,-173.62202,-260.85608,44.601532,-44.66716,374.6266,195000
+16.18872,5.300413,0.4106971,0.52907485,16.18872,0.33597997,0.5955171,-4.1223335,-176.01736,-258.83563,48.88482,-60.681778,366.94638,200000
+22.940022,5.535411,0.41287783,0.5836551,22.940022,0.3429097,1.028489,-10.335651,-179.38084,-263.9651,34.155052,-50.903767,378.95462,205000
+14.985503,10.834057,0.394572,0.59998447,14.985503,0.33553326,0.4784429,-6.141741,-176.17137,-277.88345,56.62349,-25.0682,376.9944,210000
+8.899124,10.616174,0.38420373,0.62537396,8.899124,0.3470419,0.64608425,-6.8793125,-180.42398,-232.78224,30.99442,-40.072903,305.9704,215000
+13.155247,6.594822,0.3741784,0.53429306,13.155247,0.29287243,0.4183952,-31.726318,-180.38188,-294.11832,37.91264,-37.728462,330.33405,220000
+12.384404,8.761534,0.4119433,0.61351967,12.384404,0.34504998,0.5109644,-32.558544,-180.63127,-282.4425,38.86423,-44.897675,332.08685,225000
+11.932867,5.0269585,0.3742659,0.49888948,11.932867,0.36926952,0.42966864,-13.336003,-179.3145,-301.67007,78.99196,-56.92872,436.24005,230000
+16.571201,5.404269,0.37364152,0.5135894,16.571201,0.33856905,0.31505352,-11.377425,-179.9641,-258.63852,34.410828,-41.530357,299.58133,235000
+13.165558,5.2167954,0.37986743,0.5261388,13.165558,0.3644194,0.4475124,-0.33554265,-180.93452,-268.75208,28.896692,-30.860165,297.70392,240000
+13.493194,5.1985974,0.4068725,0.56813985,13.493194,0.3453343,0.8107479,-15.801795,-175.20988,-234.24603,70.92763,-41.31378,386.75537,245000
+9.103591,5.436701,0.32814476,0.48303872,9.103591,0.32384068,0.40375376,-19.570404,-182.73772,-292.01328,36.675774,-26.818226,293.44785,250000
+17.419996,6.260297,0.33779466,0.54776925,17.419996,0.32236823,1.1479254,-7.3281803,-184.04012,-288.38144,91.703926,-38.58193,456.53595,255000
+20.050404,12.503208,0.40009338,0.7762729,20.050404,0.33274198,0.91780704,0.34996134,-177.89267,-259.958,71.23863,-35.19197,397.20792,260000
+12.64006,7.430521,0.33426154,0.47958204,12.64006,0.34713316,0.5782693,-45.33753,-184.25632,-299.91782,25.605627,-89.95529,385.6812,265000
+13.980164,10.953421,0.39170018,0.6748567,13.980164,0.34525934,0.7930216,-0.2889686,-179.86931,-279.0925,44.16638,-58.49161,378.68192,270000
+10.768852,7.1695876,0.35019562,0.53293175,10.768852,0.3203035,0.5983389,-44.3857,-180.96057,-322.75287,38.333363,-22.803808,352.96313,275000
+32.447887,46.860527,0.45860815,1.7727075,32.447887,0.36377776,3.5177624,0.45834506,-176.13539,-220.77411,92.569756,-150.23425,1162.931,280000
+11.269994,11.8033905,0.3583299,0.63854843,11.269994,0.32198626,0.6801433,-7.9868336,-184.52487,-284.96844,45.870293,-76.88561,416.10995,285000
+19.597569,15.371466,0.42135656,0.7697019,19.597569,0.31239843,0.9491229,-40.450897,-179.33702,-235.38087,45.94073,-99.6433,441.167,290000
+15.025234,7.4914074,0.3803581,0.59797627,15.025234,0.28364593,0.37771943,-0.6260812,-184.69585,-288.04727,39.73742,-40.395454,357.67514,295000
+16.65918,9.549272,0.37781405,0.61640316,16.65918,0.3380545,0.70765823,-6.7967453,-180.17357,-245.21829,47.221413,-40.503433,446.24915,300000
+10.387797,5.6263094,0.33448416,0.5024124,10.387797,0.28572422,0.75688183,-16.876429,-179.20654,-251.09444,30.320744,-40.197037,378.4394,305000
+11.485249,11.173054,0.35330945,0.5687517,11.485249,0.3068889,0.5676839,-33.137787,-183.20824,-291.8529,28.983551,-43.621063,309.9278,310000
+9.521746,9.596047,0.33724236,0.5791416,9.521746,0.322922,3.188253,0.4941521,-184.70213,-289.55835,44.43636,-48.59857,656.2173,315000
+8.97221,6.4102526,0.31459618,0.43647686,8.97221,0.32050347,0.48936167,-0.5512041,-185.78716,-449.1281,39.66952,-47.23916,309.77606,320000
+23.86668,6.446784,0.32479873,0.51711076,23.86668,0.31973806,0.33538923,1.5138831,-183.64195,-254.41548,58.53029,-39.68419,366.53934,325000
+14.108091,4.5416384,0.36391538,0.5179423,14.108091,0.32770956,0.4543829,-14.516898,-184.17879,-469.92642,48.410538,-41.736584,334.5067,330000
+11.351719,10.550566,0.34498394,0.61121935,11.351719,0.31368902,0.4771574,0.2259343,-184.02672,-483.512,48.00283,-87.05249,442.0116,335000
+13.943152,8.422209,0.3417023,0.60804445,13.943152,0.2841527,0.75149554,-39.131737,-185.96077,-273.90128,48.650112,-38.102406,366.44543,340000
+9.653437,5.775957,0.33374667,0.50841236,9.653437,0.32691562,0.52107257,-20.529259,-184.57115,-288.25824,32.056065,-42.06298,284.66882,345000
+11.01357,8.854577,0.33639044,0.5717389,11.01357,0.33017763,0.5367466,-2.1207645,-183.6398,-288.19827,35.409164,-54.771805,311.13776,350000
+13.699198,6.221943,0.35381073,0.5313368,13.699198,0.3431034,0.6751599,-8.407439,-181.05304,-290.2012,49.60989,-40.7844,361.1683,355000
+10.392461,5.4129124,0.34513417,0.5506128,10.392461,0.3462488,0.48088866,-1.5229629,-183.39523,-514.8129,36.307617,-21.644947,277.65085,360000
+10.401701,4.990123,0.31640548,0.4848605,10.401701,0.3261302,0.35490584,-10.220821,-187.64006,-447.50073,38.820423,-60.74597,341.04074,365000
+14.758768,20.094135,0.38182774,0.75111216,14.758768,0.37175936,0.8550606,-0.79513526,-183.2337,-289.9761,42.980446,-85.31723,466.35065,370000
+11.681238,6.906822,0.3209976,0.5659908,11.681238,0.3386949,0.41759726,-23.104519,-184.25179,-253.14406,66.898224,-42.961,378.61826,375000
+14.963855,10.297775,0.33409223,0.58112884,14.963855,0.31125668,0.3688829,0.32783225,-183.65181,-283.02713,76.75091,-65.873695,416.5452,380000
+9.7529545,6.3559446,0.35168225,0.540175,9.7529545,0.32177082,0.77861726,-0.4325851,-183.30879,-353.65237,53.84762,-39.06389,321.65125,385000
+12.436081,7.02504,0.33661526,0.53945976,12.436081,0.3303112,0.27620292,-8.649446,-187.6399,-355.5598,40.35751,-34.453293,347.14227,390000
+12.475937,25.594282,0.37005198,0.9136971,12.475937,0.35009822,0.59805995,-0.6556288,-182.20677,-238.03777,44.77928,-37.628723,378.05307,395000
+43.07315,6.793909,0.32147014,0.53569037,43.07315,0.28029376,0.46908155,-54.438854,-186.27103,-258.01166,91.0452,-85.07645,720.3955,400000
+14.237013,9.838537,0.34424365,0.63194466,14.237013,0.358244,0.43458953,-10.17229,-186.75473,-244.1703,72.04919,-37.13489,371.7621,405000
+13.479151,22.858955,0.33488807,0.8142728,13.479151,0.30735022,0.59713835,-29.52927,-188.07799,-330.35303,40.61195,-71.45874,343.99606,410000
+24.24765,58.835236,0.42720425,1.7678511,24.24765,0.3571779,5.701198,0.4619052,-180.1861,-246.7687,77.69824,-93.827354,896.59796,415000
+13.721904,8.27533,0.33872807,0.5755304,13.721904,0.26301992,0.47589198,0.44179899,-184.5906,-322.5273,44.81011,-81.394226,434.0802,420000
+12.760977,7.9896793,0.35514998,0.6578316,12.760977,0.30690297,0.9749519,0.16628826,-179.87572,-235.48091,45.36374,-42.826923,442.62152,425000
+21.122473,4.6339145,0.3239866,0.5339363,21.122473,0.30678868,0.49284458,-23.47106,-183.69438,-224.311,61.20468,-61.166412,392.67056,430000
+16.911966,20.005623,0.38099408,0.9581043,16.911966,0.31144807,0.7948336,-0.09859234,-183.75749,-308.49033,48.269665,-30.04486,395.11908,435000
+8.901811,8.123434,0.29973823,0.5221553,8.901811,0.3347196,0.5781515,-1.6327862,-187.96991,-267.18005,49.216484,-38.230045,378.16693,440000
+16.472073,7.378746,0.3544148,0.61430156,16.472073,0.31859845,0.3519304,-30.039495,-184.25237,-238.3563,31.266333,-51.50106,306.4162,445000
+9.68656,6.1229897,0.32253385,0.53357947,9.68656,0.32205415,0.29490778,0.2689731,-186.80699,-227.43254,37.766914,-38.799812,297.17673,450000
+14.400349,6.8569527,0.37697944,0.62112516,14.400349,0.31731975,0.4196112,-0.20551673,-184.14595,-304.56265,49.0822,-56.560623,413.60397,455000
+11.222731,6.0033884,0.32964215,0.5497317,11.222731,0.3304062,0.396611,-22.814583,-186.99187,-283.8119,52.31068,-59.25184,333.43552,460000
+8.326868,5.099764,0.31097186,0.480797,8.326868,0.34967083,0.33272186,0.96738964,-183.90637,-221.02068,27.616621,-31.612427,267.45844,465000
+12.309048,16.235588,0.34351942,0.70529413,12.309048,0.3044935,4.884276,1.1147816,-186.43758,-300.35983,43.964874,-49.290245,477.03778,470000
+19.582417,7.5703907,0.2912531,0.495613,19.582417,0.29500076,0.5211114,0.54572064,-185.17085,-239.90608,32.43923,-40.864532,325.79514,475000
+19.0989,6.586252,0.3343078,0.55896723,19.0989,0.35980463,0.47861958,-0.66399366,-183.50128,-241.8726,54.96793,-85.32483,407.55804,480000
+29.998951,7.1387367,0.35225448,0.57756025,29.998951,0.30033916,0.8083393,-12.179616,-182.21204,-400.3162,134.32608,-413.4386,1020.16785,485000
+42.087906,7.1379757,0.3684116,0.6149333,42.087906,0.30789012,0.61251974,0.6923871,-181.80423,-228.0902,77.0565,-229.02765,691.38824,490000
+13.279331,4.683917,0.30701464,0.48923516,13.279331,0.31319252,0.5026781,-49.861843,-187.82771,-245.60744,43.123283,-29.046024,290.14258,495000
+15.064287,7.1327286,0.34223765,0.52921855,15.064287,0.35139865,0.4460329,-0.18034577,-183.30948,-222.77132,73.694954,-91.170235,447.481,500000
+15.967598,6.440544,0.35956752,0.59705967,15.967598,0.34090132,0.53303415,-4.680501,-181.36978,-247.376,49.239807,-77.11794,413.9789,505000
+10.54105,10.624697,0.35759312,0.65138054,10.54105,0.37754846,0.9182501,-1.6213908,-184.23584,-225.96013,35.62948,-47.147335,335.4375,510000
+30.08417,5.9538565,0.28537184,0.4961887,30.08417,0.3525365,0.48983344,0.047448218,-188.07451,-247.07942,37.083282,-37.92768,378.84702,515000
+9.855529,8.612024,0.33539352,0.597137,9.855529,0.28709716,0.40969345,-61.738216,-187.19333,-242.35893,31.64741,-60.811485,357.7352,520000
+8.824729,4.846725,0.29100358,0.450446,8.824729,0.2812434,0.32175502,-24.799126,-185.79953,-261.71283,23.263186,-46.674927,288.64783,525000
+11.245197,6.1910505,0.3032022,0.47684264,11.245197,0.31865305,0.46447107,-18.934965,-186.09218,-229.55382,17.797077,-31.068707,256.3449,530000
+11.781323,6.3007665,0.32500273,0.52983356,11.781323,0.34934175,0.6515666,-40.286495,-185.33682,-229.63646,61.14576,-48.382908,361.39606,535000
+11.600106,7.2417774,0.2869951,0.45142844,11.600106,0.30468667,0.35637498,-0.2493046,-187.5317,-239.18225,37.300404,-43.376427,300.81805,540000
+11.798876,7.364393,0.3319865,0.5107066,11.798876,0.2906639,0.43808928,-15.163009,-185.67935,-274.46576,32.05006,-56.221714,385.98898,545000
+15.871521,8.829124,0.33342868,0.54917157,15.871521,0.3010859,0.5422277,-0.334751,-180.54932,-247.3921,259.9951,-34.517662,566.3177,550000
+16.634443,16.174519,0.35018006,0.8119975,16.634443,0.30682662,0.6254641,0.25613704,-182.97896,-252.55602,94.76177,-108.993645,490.86453,555000
+11.154624,7.82197,0.32891852,0.5711468,11.154624,0.32512128,0.4151643,-4.212316,-182.90086,-265.76828,30.6804,-30.997381,288.27808,560000
+16.810242,7.8078103,0.35466027,0.64376825,16.810242,0.33086425,0.7328374,-3.9469752,-181.80864,-233.70964,201.48557,-79.07982,556.3075,565000
+12.040159,4.203062,0.31388873,0.48232222,12.040159,0.3265325,0.42983285,-23.356325,-183.81708,-219.2103,34.45124,-52.454323,337.69815,570000
+11.968643,5.2251344,0.3235885,0.52670074,11.968643,0.33778143,0.46207818,-21.022226,-185.68689,-258.85275,36.101364,-37.452972,295.3571,575000
+11.812862,5.5146966,0.32461312,0.5235407,11.812862,0.297767,0.5596999,-0.4748238,-182.92772,-231.37314,45.49321,-52.10289,358.97318,580000
+12.380479,5.051265,0.29782522,0.5083557,12.380479,0.29364544,0.34645993,-33.524033,-188.41545,-219.27104,61.580986,-53.455463,386.93375,585000
+9.94115,6.61616,0.29900128,0.52891016,9.94115,0.31957382,0.39399102,-0.44896165,-184.52551,-242.31375,48.496925,-50.304413,347.87128,590000
+7.9741764,5.0060277,0.29022592,0.47126597,7.9741764,0.30803716,0.31420946,-73.79655,-190.50145,-241.62115,50.503613,-60.2798,312.33038,595000
+10.981232,5.2146425,0.27986443,0.47147316,10.981232,0.31648406,0.43589908,-9.352852,-188.27396,-237.80133,103.22863,-195.92583,497.30756,600000

O2O-w-diff-ckpts/qam/20260316_123356/params_150000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661a00033d32e9b807c26231a8caf4d765e19293161ef557a531a6b4a549d381
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_200000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a963d613c4e93b49702cdda9b2fed0a74a568b58407f675c45227cde0e0a750
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_250000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9183ed66390dee904138a694b813c5a1b7f78e282d62e4e1649e6768a44c5de
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_300000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97452b2d8ceaf8231275f6e15e0d22c80d5a04f75330a34460823ae59d5de86
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_350000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc05f9fbba75a7cdb4c42188847f7ba1db24eef2515745b446d333f54b4c166
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_400000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad80b5d48996cf6f19cd8f9c42d835c3cfe17bc1e389931473d1fd0eeb80ebd
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_450000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8ab5c58f0eed2ca4d1b0e06bd5b3eeffb30424ab829dc0da90bb5830a09881
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_500000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cff4945a0a192f8491dd1a0444fe752048d449240ec27d7d75ab4921b27e789
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_550000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74de7ea72727043c2eef62beb2d963647e5c8766d2747c29cd36c173c791bf98
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/params_600000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be8a2abe65c0d3334fa04e4522462c13e63558aee5a29c0aecc41bcb95af671
+size 233879450

O2O-w-diff-ckpts/qam/20260316_123356/progress.tk

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

O2O-w-diff-ckpts/qam/20260316_123356/token.tk

@@ -0,0 +1 @@
+https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/nuj4x02n