Upload folder using huggingface_hub

.gitattributes

@@ -922,3 +922,13 @@ O2O-w-diff-ckpts/qam/20260317_015426/visited_states_800000.png filter=lfs diff=l
 O2O-w-diff-ckpts/qam/20260317_015426/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260317_015426/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260317_015426/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_1000000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_1050000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_1100000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_650000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_700000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_750000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_800000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_051145/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text

O2O-w-diff-ckpts/qam/20260317_051145/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
+0.0,0.0,32.63524873050408,4.425771247711575,0.0241884694400132,4.430689489860235,0.08511878998102516,0.3,24683.76,-0.7,-968.98,969.28,1.4203732347488403,650000
+0.0,0.0,33.18660503005687,4.494332246717154,0.06865781773546979,4.498907080114602,-0.003990720247575763,0.4,75032.12,-0.6,-962.58,962.98,1.394748215675354,700000
+0.0,0.0,33.95781386310043,4.601566786847365,0.06361162538731095,4.603946340989235,0.0021144701019091424,0.38,125442.46,-0.62,-973.64,974.02,1.4868253469467163,750000
+0.0,0.0,30.140671011530106,4.10211142745139,0.09171327357098777,4.1083111270411115,0.07475348934805388,0.28,175591.52,-0.72,-967.84,968.12,1.3858654165267945,800000
+0.0,0.0,30.835746970758755,4.174028098311697,0.04426390885671134,4.178978962303167,0.06884066012503666,0.3,225780.66,-0.7,-959.58,959.88,1.3960252714157104,850000
+0.0,0.0,26.1176362704742,3.5591012396497645,-0.020267490234147794,3.5590628701929816,0.025512798644716332,0.2,276751.16,-0.8,-986.0,986.2,1.4730163526535034,900000
+0.0,0.0,23.19401634311399,3.160805828944241,0.08389809086684526,3.1680538746070575,0.07248143390758317,0.22,327693.74,-0.78,-970.0,970.22,1.355952672958374,950000
+0.0,0.0,31.096840566583943,4.2102000916714095,0.06619055399380108,4.219373697745334,0.12454923935392906,0.34,378088.08,-0.66,-970.92,971.26,1.3458438920974731,1000000
+0.0,0.0,30.340658297877404,4.1250748865742,0.024962697914877208,4.130517284429351,0.0717418237981948,0.24,428712.64,-0.76,-973.2,973.44,1.442502360343933,1050000
+0.0,0.0,29.700954943667174,4.03293835121304,0.04552954154295867,4.041074227778083,0.10312756432980544,0.3,478683.4,-0.7,-951.58,951.88,1.3134329509735108,1100000

O2O-w-diff-ckpts/qam/20260317_051145/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
+0.0,0.0,32.63524873050408,4.425771247711575,0.0241884694400132,4.430689489860235,0.08511878998102516,0.3,24683.76,-0.7,-968.98,969.28,1.4203732347488403,650000
+0.0,0.0,33.18660503005687,4.494332246717154,0.06865781773546979,4.498907080114602,-0.003990720247575763,0.4,75032.12,-0.6,-962.58,962.98,1.394748215675354,700000
+0.0,0.0,33.95781386310043,4.601566786847365,0.06361162538731095,4.603946340989235,0.0021144701019091424,0.38,125442.46,-0.62,-973.64,974.02,1.4868253469467163,750000
+0.0,0.0,30.140671011530106,4.10211142745139,0.09171327357098777,4.1083111270411115,0.07475348934805388,0.28,175591.52,-0.72,-967.84,968.12,1.3858654165267945,800000
+0.0,0.0,30.835746970758755,4.174028098311697,0.04426390885671134,4.178978962303167,0.06884066012503666,0.3,225780.66,-0.7,-959.58,959.88,1.3960252714157104,850000
+0.0,0.0,26.1176362704742,3.5591012396497645,-0.020267490234147794,3.5590628701929816,0.025512798644716332,0.2,276751.16,-0.8,-986.0,986.2,1.4730163526535034,900000
+0.0,0.0,23.19401634311399,3.160805828944241,0.08389809086684526,3.1680538746070575,0.07248143390758317,0.22,327693.74,-0.78,-970.0,970.22,1.355952672958374,950000
+0.0,0.0,31.096840566583943,4.2102000916714095,0.06619055399380108,4.219373697745334,0.12454923935392906,0.34,378088.08,-0.66,-970.92,971.26,1.3458438920974731,1000000
+0.0,0.0,30.340658297877404,4.1250748865742,0.024962697914877208,4.130517284429351,0.0717418237981948,0.24,428712.64,-0.76,-973.2,973.44,1.442502360343933,1050000
+0.0,0.0,29.700954943667174,4.03293835121304,0.04552954154295867,4.041074227778083,0.10312756432980544,0.3,478683.4,-0.7,-951.58,951.88,1.3134329509735108,1100000

O2O-w-diff-ckpts/qam/20260317_051145/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
+14.38155,14.036884,0.39870784,0.68917394,14.38155,0.34522057,0.4639542,-5.7697577,-177.19115,-249.82442,108.804886,-84.68452,493.83994,605000
+28.360964,7.4051266,0.4759215,0.738732,28.360964,0.31676888,0.65764993,-8.94748,-173.99516,-223.60175,59.709465,-96.19886,499.83752,610000
+22.264961,8.416692,0.39800167,0.6329795,22.264961,0.3315193,0.44596893,-13.716183,-180.13419,-241.45782,105.24792,-80.12675,478.09012,615000
+14.347237,4.3046775,0.3934421,0.5733898,14.347237,0.3155614,0.43795148,-19.998693,-178.43762,-218.1973,42.983124,-75.193146,352.26276,620000
+28.78484,6.4850054,0.41672757,0.58693767,28.78484,0.3108055,0.5362216,-2.9130514,-176.22435,-225.20384,158.44383,-66.35121,644.53613,625000
+12.177072,5.035273,0.3788002,0.5365017,12.177072,0.29849505,0.41531006,0.61837316,-176.71397,-238.7659,57.995914,-29.039942,310.83124,630000
+15.594732,8.096076,0.4146175,0.6744894,15.594732,0.32957822,0.46851322,0.6019582,-175.85008,-230.39444,57.78106,-46.74706,421.27756,635000
+16.355904,17.924818,0.4096306,0.7802102,16.355904,0.29769382,0.5734767,-7.902758,-176.46419,-226.56886,92.26164,-166.5521,513.9231,640000
+15.513168,4.6928234,0.38392437,0.555257,15.513168,0.2986431,0.42278004,-11.481418,-180.36789,-228.59712,30.914179,-27.416664,276.28912,645000
+44.53952,9.6680355,0.3828635,0.56645864,44.53952,0.31446028,0.47542667,-0.54784876,-178.58394,-228.12993,75.493164,-84.15192,467.43512,650000
+14.342833,5.250194,0.3987741,0.5891162,14.342833,0.34403813,0.48804626,0.61480916,-175.41801,-227.51852,37.369442,-70.34659,321.6805,655000
+13.703683,8.589487,0.39731544,0.6553332,13.703683,0.33366483,0.54413384,-1.5710894,-179.81712,-241.32788,40.319023,-50.843674,365.55563,660000
+13.23276,7.5347548,0.361448,0.53680754,13.23276,0.3083874,0.30899355,-15.543957,-181.69847,-221.65778,45.00119,-42.558098,319.80054,665000
+21.095947,9.063304,0.40360942,0.6877203,21.095947,0.30325523,0.3494444,-14.036461,-180.44969,-239.94049,108.36942,-89.13731,441.08466,670000
+17.851202,5.38998,0.34309018,0.5426291,17.851202,0.32400882,0.42236397,0.046910822,-182.62158,-225.84332,34.667637,-38.72397,316.11743,675000
+17.982689,5.3971686,0.3460419,0.533688,17.982689,0.33910835,0.8951773,-7.4696245,-180.05779,-222.14897,50.292282,-55.61013,434.4018,680000
+10.469865,4.280608,0.32715023,0.4429734,10.469865,0.32212433,0.6414843,0.26511452,-180.55362,-237.95958,56.407303,-52.560223,414.85938,685000
+27.62166,6.508282,0.3793608,0.60586506,27.62166,0.3532975,0.617709,-21.909464,-179.30835,-237.1252,52.450207,-174.28584,567.2635,690000
+14.762928,9.056204,0.39640713,0.7310676,14.762928,0.3500256,0.4455842,0.23925638,-177.76472,-233.75052,88.859985,-108.63589,542.4906,695000
+15.61324,6.6619806,0.38944134,0.59251213,15.61324,0.3537902,0.9738183,-4.848066,-179.56844,-233.7204,55.49369,-59.68978,390.22675,700000
+16.499527,4.5620146,0.40277612,0.6116677,16.499527,0.30431753,0.6801428,-16.026031,-182.6239,-251.08742,34.323547,-48.841724,315.89117,705000
+49.372185,9.305565,0.38346893,0.65730816,49.372185,0.29545137,0.58274126,-21.091097,-178.50304,-228.11574,85.8138,-246.64664,841.9394,710000
+12.007858,6.2823963,0.35854334,0.5518885,12.007858,0.33444628,0.58017206,-12.5225,-184.56187,-223.50493,49.362488,-53.166683,341.61044,715000
+16.428383,5.864354,0.35060298,0.58394253,16.428383,0.31170577,0.4499941,-23.838934,-182.58914,-222.67331,48.02945,-56.3198,410.85162,720000
+14.12484,7.854949,0.38314897,0.646326,14.12484,0.28209072,0.55355716,-16.833057,-182.40904,-220.86449,68.304,-81.456116,431.45367,725000
+13.32299,4.8092604,0.36160702,0.5632468,13.32299,0.31522122,0.47723314,-14.594212,-182.23174,-223.86581,108.7987,-49.550022,370.35532,730000
+16.60635,10.15933,0.36976537,0.62574553,16.60635,0.31899303,1.5593792,0.25252476,-182.97655,-243.15314,54.345554,-75.4877,665.87823,735000
+14.207708,16.345749,0.33664614,0.6599141,14.207708,0.24906889,0.49909002,-9.386688,-185.6604,-224.85081,101.21326,-52.402298,430.0536,740000
+34.17217,33.20231,0.4461083,1.6103698,34.17217,0.28017822,0.4711216,-19.563847,-180.49474,-233.67137,61.38646,-132.2009,656.70074,745000
+18.30884,7.3269596,0.3478576,0.56752986,18.30884,0.28945816,0.44727117,-0.6156059,-182.55424,-232.88478,80.26041,-67.18294,401.34076,750000
+56.3731,6.9820595,0.30077755,0.5212482,56.3731,0.32154736,0.2714706,-19.816704,-186.3096,-224.91403,68.07994,-47.61128,399.0514,755000
+14.085119,8.756351,0.34526688,0.58737195,14.085119,0.32672152,0.44084302,-0.7599521,-179.81557,-215.24919,68.107124,-52.310726,353.37506,760000
+12.517292,6.4945064,0.34458673,0.5893355,12.517292,0.3365025,0.52195406,1.6957682,-184.50246,-225.63483,40.7402,-56.118587,407.66528,765000
+17.998083,10.499813,0.33584023,0.61148226,17.998083,0.33514172,0.42199692,-19.674494,-184.25475,-224.27083,50.240944,-49.98313,399.7709,770000
+11.100914,7.138129,0.3472189,0.6278437,11.100914,0.29871148,0.5038051,-41.75064,-183.87675,-234.13484,60.572098,-51.632675,381.84625,775000
+13.798231,7.8292227,0.40319717,0.644665,13.798231,0.3448892,1.2084156,-0.34056863,-176.0161,-286.91583,71.86637,-175.31268,538.6527,780000
+25.572416,13.888935,0.35484016,0.6596404,25.572416,0.35053515,0.5385307,-11.299213,-183.38063,-216.20322,84.82497,-147.51424,489.2271,785000
+16.303074,6.657656,0.38322735,0.6489242,16.303074,0.31413168,0.43643245,-41.673717,-181.43852,-212.62215,65.36533,-64.910286,465.62933,790000
+13.222588,11.348453,0.38210058,0.67355657,13.222588,0.28912157,0.51230305,0.92168856,-183.34676,-225.68846,55.40501,-53.988297,389.9223,795000
+18.665783,11.899092,0.36240983,0.7836558,18.665783,0.31301352,1.3521614,-0.9732803,-183.00732,-226.00246,44.72982,-40.91853,498.52203,800000
+16.110888,4.8968534,0.32569474,0.5165092,16.110888,0.32840616,0.25693533,0.38168684,-181.16539,-221.96176,35.73049,-51.46067,365.6704,805000
+13.724642,13.867113,0.38735604,0.7337945,13.724642,0.32600498,0.44333267,-13.693759,-183.27437,-222.64043,67.29011,-77.51868,466.13278,810000
+10.601127,7.4766035,0.33171955,0.5814587,10.601127,0.36593324,0.33172494,-0.22988176,-184.3296,-235.33536,76.262695,-44.71649,339.45023,815000
+12.452414,6.1739345,0.30763772,0.4983416,12.452414,0.32669887,0.25296906,-0.33556947,-185.36858,-237.48628,50.953278,-45.723972,360.3046,820000
+13.01704,9.419937,0.32081392,0.62373906,13.01704,0.29448026,0.6290628,1.2561971,-180.59184,-219.21391,36.98681,-85.14612,413.30365,825000
+12.2344055,4.057358,0.33710068,0.5285968,12.2344055,0.33102703,0.48839194,-19.094452,-182.35147,-234.09297,60.118443,-45.453983,351.13123,830000
+10.487125,6.029434,0.2919048,0.48332638,10.487125,0.29220808,0.3723468,0.77915096,-184.5314,-221.55089,34.794044,-60.01529,332.80377,835000
+27.063303,5.475378,0.31345403,0.5423536,27.063303,0.34482715,0.50596863,-3.5949097,-184.3002,-223.42116,48.669006,-111.444176,449.11298,840000
+14.62297,4.441828,0.30152175,0.5134486,14.62297,0.32827184,0.48149267,-17.32963,-183.44003,-221.11708,28.993885,-54.15293,350.99265,845000
+33.648712,5.723567,0.33169824,0.58267426,33.648712,0.29228666,0.43903312,-7.678013,-182.96239,-216.07158,105.791794,-61.123505,454.99185,850000
+21.949898,8.999446,0.35000113,0.64969987,21.949898,0.29617533,0.6159773,-8.578474,-181.48975,-216.52892,345.3244,-52.43105,743.6221,855000
+21.828518,10.128595,0.34239274,0.68283635,21.828518,0.34840918,0.5707995,-2.2148056,-182.42949,-223.22433,152.54468,-64.208885,641.284,860000
+13.318972,7.0470505,0.3405708,0.5780146,13.318972,0.29739112,0.6174825,-62.205067,-185.37169,-228.40604,49.826744,-67.01761,360.99088,865000
+22.529072,29.03868,0.4142109,1.2921503,22.529072,0.30525073,0.78384364,-6.387648,-182.65062,-235.15588,111.39092,-104.00626,509.11548,870000
+36.310352,5.1646695,0.32951927,0.57669246,36.310352,0.2698726,0.3276188,-3.579577,-183.28249,-296.44656,71.21756,-83.76176,458.18448,875000
+12.885318,6.120446,0.32061204,0.53201383,12.885318,0.30423853,0.41770503,-0.30675563,-183.24576,-242.88899,39.436794,-192.03162,489.27472,880000
+12.435785,5.761635,0.34721327,0.56697565,12.435785,0.27979106,0.57710934,-1.2997046,-183.4149,-225.25375,51.101566,-66.07576,384.10284,885000
+12.088207,5.5740814,0.30992293,0.51537937,12.088207,0.3158779,0.8064518,-3.003371,-184.48332,-214.17067,50.046116,-82.85382,440.1984,890000
+12.786763,9.778581,0.34692636,0.65211076,12.786763,0.2906598,1.050167,1.0753433,-181.51656,-213.27652,70.98483,-69.10815,466.31934,895000
+11.782911,9.616444,0.3330661,0.56990856,11.782911,0.3105369,0.42567053,-37.86254,-183.44334,-252.67242,38.021027,-45.474792,334.76852,900000
+11.883229,9.952657,0.31900242,0.557067,11.883229,0.35980478,0.679928,-4.840981,-184.83171,-220.9324,49.58143,-80.15853,441.6936,905000
+50.615936,69.4972,0.45801836,2.161593,50.615936,0.27975446,0.5737662,-13.413954,-183.5214,-221.89406,135.79175,-217.88087,887.3159,910000
+12.274824,6.5237856,0.33984149,0.56448334,12.274824,0.3598134,0.50315493,-1.1290195,-181.3522,-217.49925,29.140749,-28.483027,316.62567,915000
+53.599358,9.319954,0.32753003,0.6370526,53.599358,0.3082889,0.43418312,-6.2644615,-185.81094,-221.72467,60.972862,-79.62885,541.7032,920000
+17.772789,14.64827,0.3613076,0.78392905,17.772789,0.28534698,0.5497284,-28.878729,-181.2473,-247.16411,70.25604,-146.23538,506.21597,925000
+20.773993,9.897046,0.32327694,0.62226737,20.773993,0.2982288,0.36081025,-24.790829,-185.4596,-277.46075,25.311012,-139.9688,434.43634,930000
+10.942235,6.008633,0.3124551,0.5437685,10.942235,0.29508084,0.38573942,-7.91828,-181.96056,-222.50885,82.43139,-83.656136,496.28314,935000
+16.399809,23.807014,0.3623128,0.8476521,16.399809,0.35014445,0.4995608,-3.4482508,-181.85657,-215.30353,57.82969,-182.09995,469.01263,940000
+12.702381,5.8004637,0.29593796,0.5135429,12.702381,0.30941156,0.21462913,-31.17999,-185.88426,-229.33577,60.4031,-34.811813,291.4651,945000
+11.337051,7.677994,0.31991684,0.5708986,11.337051,0.38459873,0.25590175,0.8692649,-186.33244,-236.95255,40.935616,-55.205406,315.36725,950000
+13.424581,11.189848,0.34583294,0.65640336,13.424581,0.320297,0.4893662,-0.3032287,-182.81772,-226.79648,55.191208,-40.997086,387.56256,955000
+10.841392,5.806847,0.30155087,0.5302544,10.841392,0.27652207,0.28753057,-23.711798,-187.00296,-237.3997,41.385887,-64.08905,315.59528,960000
+11.461292,5.8569884,0.316725,0.5341365,11.461292,0.34181684,0.19923475,1.1456044,-184.03194,-220.32146,75.5246,-62.789665,399.76773,965000
+12.391882,12.0959015,0.3662246,0.747571,12.391882,0.27797332,0.58854216,0.77114666,-181.83293,-211.5073,44.80457,-39.366905,323.4969,970000
+10.903098,10.402897,0.2727066,0.52473086,10.903098,0.2832339,0.36620447,0.2352159,-184.32469,-235.46245,41.56537,-67.21007,371.97772,975000
+12.081623,6.2736416,0.32090676,0.5233292,12.081623,0.32520074,0.5187986,-29.159117,-183.43108,-229.60458,31.048018,-51.46474,311.12595,980000
+14.133579,6.538183,0.35296595,0.636553,14.133579,0.29143775,0.53493327,-1.568514,-182.26419,-279.2062,60.307343,-111.31208,474.2936,985000
+17.383703,9.428503,0.35795063,0.70363444,17.383703,0.33400106,0.58981293,-0.10084334,-180.83081,-231.89246,52.30616,-45.964348,412.38736,990000
+17.652977,7.67968,0.34154063,0.6176613,17.652977,0.29969063,0.34789294,-49.100407,-185.27492,-224.20676,85.943886,-38.277412,377.28546,995000
+14.191984,7.0858974,0.32703394,0.5909566,14.191984,0.2550008,0.34523234,0.15177631,-183.6801,-233.49559,198.60413,-57.837772,472.0875,1000000
+38.602898,8.50338,0.32709223,0.6062651,38.602898,0.28131095,0.36969897,-7.1873507,-183.55849,-223.91138,72.15231,-214.099,638.38983,1005000
+19.923832,9.169821,0.3171972,0.5721644,19.923832,0.25649127,0.82760715,-3.0314996,-183.87596,-232.48555,140.06993,-31.749153,458.82715,1010000
+11.878871,7.6454954,0.32937634,0.604287,11.878871,0.33298504,0.3807796,-5.4219112,-182.71207,-214.98242,73.71637,-52.097733,379.53156,1015000
+9.513542,5.79609,0.31206375,0.5311385,9.513542,0.28556478,0.55255985,0.0122562945,-183.94939,-222.90611,36.31158,-42.311996,339.85962,1020000
+11.839717,7.848265,0.32235497,0.58831155,11.839717,0.2884143,0.36348948,-4.7635927,-183.38986,-232.08333,96.97271,-80.01604,460.05948,1025000
+18.77418,13.402386,0.33620873,0.74062324,18.77418,0.31053668,0.60503906,-18.998407,-183.14369,-218.34467,45.16419,-208.50272,647.72736,1030000
+16.150658,5.8256817,0.3206067,0.5381273,16.150658,0.29575324,0.54474497,-0.8833045,-180.92451,-217.0988,101.18925,-54.096413,420.67712,1035000
+17.964386,19.445936,0.34829432,0.85319555,17.964386,0.25982085,0.36971888,0.8099465,-183.26637,-235.99078,61.210785,-50.521027,365.5335,1040000
+15.370259,6.483623,0.34373146,0.5464403,15.370259,0.2834326,0.3276855,-3.7542572,-181.82117,-236.07852,50.146355,-57.351635,345.6417,1045000
+15.933102,8.0180855,0.32486057,0.6011399,15.933102,0.30808568,0.5153993,-0.3731357,-181.23189,-221.21802,56.737865,-56.1852,368.9058,1050000
+27.795074,39.669056,0.39276367,1.612353,27.795074,0.2899719,1.6062653,-0.15946102,-181.84422,-226.34825,62.790802,-177.25627,584.5188,1055000
+15.491474,7.880821,0.34189975,0.6343181,15.491474,0.3114971,0.4574604,-24.422956,-181.55168,-221.47542,44.54454,-38.93785,320.00452,1060000
+15.524554,8.690095,0.3429551,0.6152261,15.524554,0.31364748,0.34241858,-9.858243,-184.09142,-249.79651,43.539734,-51.79756,313.69382,1065000
+14.180585,8.063939,0.36205244,0.5672867,14.180585,0.36017162,0.41664812,-15.149908,-182.876,-222.87607,44.281002,-34.05455,363.95306,1070000
+13.120348,5.348059,0.31984502,0.5876369,13.120348,0.313614,0.3994462,-1.383338,-184.86641,-228.46866,65.465454,-68.51074,360.61752,1075000
+13.196564,8.324635,0.34474838,0.5993287,13.196564,0.31429744,0.4034283,0.3068117,-179.95763,-217.59406,60.349457,-104.86755,445.34268,1080000
+12.054886,9.633214,0.30549082,0.6037158,12.054886,0.3169094,0.44946787,-16.75601,-185.11131,-214.71124,68.496086,-47.341343,399.12308,1085000
+19.8656,11.44415,0.34151226,0.6971026,19.8656,0.31707385,0.57937664,-0.046315283,-181.10411,-225.38342,106.247574,-60.810463,531.4316,1090000
+13.615146,6.112976,0.32163653,0.55047643,13.615146,0.27858824,0.39163893,-12.485995,-187.20909,-243.99588,52.80668,-36.54915,375.1705,1095000
+8.052207,3.9908414,0.25952283,0.44959378,8.052207,0.30168766,0.684668,-21.525455,-188.61076,-231.80165,45.44039,-57.739975,306.72812,1100000

O2O-w-diff-ckpts/qam/20260317_051145/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
+14.38155,14.036884,0.39870784,0.68917394,14.38155,0.34522057,0.4639542,-5.7697577,-177.19115,-249.82442,108.804886,-84.68452,493.83994,605000
+28.360964,7.4051266,0.4759215,0.738732,28.360964,0.31676888,0.65764993,-8.94748,-173.99516,-223.60175,59.709465,-96.19886,499.83752,610000
+22.264961,8.416692,0.39800167,0.6329795,22.264961,0.3315193,0.44596893,-13.716183,-180.13419,-241.45782,105.24792,-80.12675,478.09012,615000
+14.347237,4.3046775,0.3934421,0.5733898,14.347237,0.3155614,0.43795148,-19.998693,-178.43762,-218.1973,42.983124,-75.193146,352.26276,620000
+28.78484,6.4850054,0.41672757,0.58693767,28.78484,0.3108055,0.5362216,-2.9130514,-176.22435,-225.20384,158.44383,-66.35121,644.53613,625000
+12.177072,5.035273,0.3788002,0.5365017,12.177072,0.29849505,0.41531006,0.61837316,-176.71397,-238.7659,57.995914,-29.039942,310.83124,630000
+15.594732,8.096076,0.4146175,0.6744894,15.594732,0.32957822,0.46851322,0.6019582,-175.85008,-230.39444,57.78106,-46.74706,421.27756,635000
+16.355904,17.924818,0.4096306,0.7802102,16.355904,0.29769382,0.5734767,-7.902758,-176.46419,-226.56886,92.26164,-166.5521,513.9231,640000
+15.513168,4.6928234,0.38392437,0.555257,15.513168,0.2986431,0.42278004,-11.481418,-180.36789,-228.59712,30.914179,-27.416664,276.28912,645000
+44.53952,9.6680355,0.3828635,0.56645864,44.53952,0.31446028,0.47542667,-0.54784876,-178.58394,-228.12993,75.493164,-84.15192,467.43512,650000
+14.342833,5.250194,0.3987741,0.5891162,14.342833,0.34403813,0.48804626,0.61480916,-175.41801,-227.51852,37.369442,-70.34659,321.6805,655000
+13.703683,8.589487,0.39731544,0.6553332,13.703683,0.33366483,0.54413384,-1.5710894,-179.81712,-241.32788,40.319023,-50.843674,365.55563,660000
+13.23276,7.5347548,0.361448,0.53680754,13.23276,0.3083874,0.30899355,-15.543957,-181.69847,-221.65778,45.00119,-42.558098,319.80054,665000
+21.095947,9.063304,0.40360942,0.6877203,21.095947,0.30325523,0.3494444,-14.036461,-180.44969,-239.94049,108.36942,-89.13731,441.08466,670000
+17.851202,5.38998,0.34309018,0.5426291,17.851202,0.32400882,0.42236397,0.046910822,-182.62158,-225.84332,34.667637,-38.72397,316.11743,675000
+17.982689,5.3971686,0.3460419,0.533688,17.982689,0.33910835,0.8951773,-7.4696245,-180.05779,-222.14897,50.292282,-55.61013,434.4018,680000
+10.469865,4.280608,0.32715023,0.4429734,10.469865,0.32212433,0.6414843,0.26511452,-180.55362,-237.95958,56.407303,-52.560223,414.85938,685000
+27.62166,6.508282,0.3793608,0.60586506,27.62166,0.3532975,0.617709,-21.909464,-179.30835,-237.1252,52.450207,-174.28584,567.2635,690000
+14.762928,9.056204,0.39640713,0.7310676,14.762928,0.3500256,0.4455842,0.23925638,-177.76472,-233.75052,88.859985,-108.63589,542.4906,695000
+15.61324,6.6619806,0.38944134,0.59251213,15.61324,0.3537902,0.9738183,-4.848066,-179.56844,-233.7204,55.49369,-59.68978,390.22675,700000
+16.499527,4.5620146,0.40277612,0.6116677,16.499527,0.30431753,0.6801428,-16.026031,-182.6239,-251.08742,34.323547,-48.841724,315.89117,705000
+49.372185,9.305565,0.38346893,0.65730816,49.372185,0.29545137,0.58274126,-21.091097,-178.50304,-228.11574,85.8138,-246.64664,841.9394,710000
+12.007858,6.2823963,0.35854334,0.5518885,12.007858,0.33444628,0.58017206,-12.5225,-184.56187,-223.50493,49.362488,-53.166683,341.61044,715000
+16.428383,5.864354,0.35060298,0.58394253,16.428383,0.31170577,0.4499941,-23.838934,-182.58914,-222.67331,48.02945,-56.3198,410.85162,720000
+14.12484,7.854949,0.38314897,0.646326,14.12484,0.28209072,0.55355716,-16.833057,-182.40904,-220.86449,68.304,-81.456116,431.45367,725000
+13.32299,4.8092604,0.36160702,0.5632468,13.32299,0.31522122,0.47723314,-14.594212,-182.23174,-223.86581,108.7987,-49.550022,370.35532,730000
+16.60635,10.15933,0.36976537,0.62574553,16.60635,0.31899303,1.5593792,0.25252476,-182.97655,-243.15314,54.345554,-75.4877,665.87823,735000
+14.207708,16.345749,0.33664614,0.6599141,14.207708,0.24906889,0.49909002,-9.386688,-185.6604,-224.85081,101.21326,-52.402298,430.0536,740000
+34.17217,33.20231,0.4461083,1.6103698,34.17217,0.28017822,0.4711216,-19.563847,-180.49474,-233.67137,61.38646,-132.2009,656.70074,745000
+18.30884,7.3269596,0.3478576,0.56752986,18.30884,0.28945816,0.44727117,-0.6156059,-182.55424,-232.88478,80.26041,-67.18294,401.34076,750000
+56.3731,6.9820595,0.30077755,0.5212482,56.3731,0.32154736,0.2714706,-19.816704,-186.3096,-224.91403,68.07994,-47.61128,399.0514,755000
+14.085119,8.756351,0.34526688,0.58737195,14.085119,0.32672152,0.44084302,-0.7599521,-179.81557,-215.24919,68.107124,-52.310726,353.37506,760000
+12.517292,6.4945064,0.34458673,0.5893355,12.517292,0.3365025,0.52195406,1.6957682,-184.50246,-225.63483,40.7402,-56.118587,407.66528,765000
+17.998083,10.499813,0.33584023,0.61148226,17.998083,0.33514172,0.42199692,-19.674494,-184.25475,-224.27083,50.240944,-49.98313,399.7709,770000
+11.100914,7.138129,0.3472189,0.6278437,11.100914,0.29871148,0.5038051,-41.75064,-183.87675,-234.13484,60.572098,-51.632675,381.84625,775000
+13.798231,7.8292227,0.40319717,0.644665,13.798231,0.3448892,1.2084156,-0.34056863,-176.0161,-286.91583,71.86637,-175.31268,538.6527,780000
+25.572416,13.888935,0.35484016,0.6596404,25.572416,0.35053515,0.5385307,-11.299213,-183.38063,-216.20322,84.82497,-147.51424,489.2271,785000
+16.303074,6.657656,0.38322735,0.6489242,16.303074,0.31413168,0.43643245,-41.673717,-181.43852,-212.62215,65.36533,-64.910286,465.62933,790000
+13.222588,11.348453,0.38210058,0.67355657,13.222588,0.28912157,0.51230305,0.92168856,-183.34676,-225.68846,55.40501,-53.988297,389.9223,795000
+18.665783,11.899092,0.36240983,0.7836558,18.665783,0.31301352,1.3521614,-0.9732803,-183.00732,-226.00246,44.72982,-40.91853,498.52203,800000
+16.110888,4.8968534,0.32569474,0.5165092,16.110888,0.32840616,0.25693533,0.38168684,-181.16539,-221.96176,35.73049,-51.46067,365.6704,805000
+13.724642,13.867113,0.38735604,0.7337945,13.724642,0.32600498,0.44333267,-13.693759,-183.27437,-222.64043,67.29011,-77.51868,466.13278,810000
+10.601127,7.4766035,0.33171955,0.5814587,10.601127,0.36593324,0.33172494,-0.22988176,-184.3296,-235.33536,76.262695,-44.71649,339.45023,815000
+12.452414,6.1739345,0.30763772,0.4983416,12.452414,0.32669887,0.25296906,-0.33556947,-185.36858,-237.48628,50.953278,-45.723972,360.3046,820000
+13.01704,9.419937,0.32081392,0.62373906,13.01704,0.29448026,0.6290628,1.2561971,-180.59184,-219.21391,36.98681,-85.14612,413.30365,825000
+12.2344055,4.057358,0.33710068,0.5285968,12.2344055,0.33102703,0.48839194,-19.094452,-182.35147,-234.09297,60.118443,-45.453983,351.13123,830000
+10.487125,6.029434,0.2919048,0.48332638,10.487125,0.29220808,0.3723468,0.77915096,-184.5314,-221.55089,34.794044,-60.01529,332.80377,835000
+27.063303,5.475378,0.31345403,0.5423536,27.063303,0.34482715,0.50596863,-3.5949097,-184.3002,-223.42116,48.669006,-111.444176,449.11298,840000
+14.62297,4.441828,0.30152175,0.5134486,14.62297,0.32827184,0.48149267,-17.32963,-183.44003,-221.11708,28.993885,-54.15293,350.99265,845000
+33.648712,5.723567,0.33169824,0.58267426,33.648712,0.29228666,0.43903312,-7.678013,-182.96239,-216.07158,105.791794,-61.123505,454.99185,850000
+21.949898,8.999446,0.35000113,0.64969987,21.949898,0.29617533,0.6159773,-8.578474,-181.48975,-216.52892,345.3244,-52.43105,743.6221,855000
+21.828518,10.128595,0.34239274,0.68283635,21.828518,0.34840918,0.5707995,-2.2148056,-182.42949,-223.22433,152.54468,-64.208885,641.284,860000
+13.318972,7.0470505,0.3405708,0.5780146,13.318972,0.29739112,0.6174825,-62.205067,-185.37169,-228.40604,49.826744,-67.01761,360.99088,865000
+22.529072,29.03868,0.4142109,1.2921503,22.529072,0.30525073,0.78384364,-6.387648,-182.65062,-235.15588,111.39092,-104.00626,509.11548,870000
+36.310352,5.1646695,0.32951927,0.57669246,36.310352,0.2698726,0.3276188,-3.579577,-183.28249,-296.44656,71.21756,-83.76176,458.18448,875000
+12.885318,6.120446,0.32061204,0.53201383,12.885318,0.30423853,0.41770503,-0.30675563,-183.24576,-242.88899,39.436794,-192.03162,489.27472,880000
+12.435785,5.761635,0.34721327,0.56697565,12.435785,0.27979106,0.57710934,-1.2997046,-183.4149,-225.25375,51.101566,-66.07576,384.10284,885000
+12.088207,5.5740814,0.30992293,0.51537937,12.088207,0.3158779,0.8064518,-3.003371,-184.48332,-214.17067,50.046116,-82.85382,440.1984,890000
+12.786763,9.778581,0.34692636,0.65211076,12.786763,0.2906598,1.050167,1.0753433,-181.51656,-213.27652,70.98483,-69.10815,466.31934,895000
+11.782911,9.616444,0.3330661,0.56990856,11.782911,0.3105369,0.42567053,-37.86254,-183.44334,-252.67242,38.021027,-45.474792,334.76852,900000
+11.883229,9.952657,0.31900242,0.557067,11.883229,0.35980478,0.679928,-4.840981,-184.83171,-220.9324,49.58143,-80.15853,441.6936,905000
+50.615936,69.4972,0.45801836,2.161593,50.615936,0.27975446,0.5737662,-13.413954,-183.5214,-221.89406,135.79175,-217.88087,887.3159,910000
+12.274824,6.5237856,0.33984149,0.56448334,12.274824,0.3598134,0.50315493,-1.1290195,-181.3522,-217.49925,29.140749,-28.483027,316.62567,915000
+53.599358,9.319954,0.32753003,0.6370526,53.599358,0.3082889,0.43418312,-6.2644615,-185.81094,-221.72467,60.972862,-79.62885,541.7032,920000
+17.772789,14.64827,0.3613076,0.78392905,17.772789,0.28534698,0.5497284,-28.878729,-181.2473,-247.16411,70.25604,-146.23538,506.21597,925000
+20.773993,9.897046,0.32327694,0.62226737,20.773993,0.2982288,0.36081025,-24.790829,-185.4596,-277.46075,25.311012,-139.9688,434.43634,930000
+10.942235,6.008633,0.3124551,0.5437685,10.942235,0.29508084,0.38573942,-7.91828,-181.96056,-222.50885,82.43139,-83.656136,496.28314,935000
+16.399809,23.807014,0.3623128,0.8476521,16.399809,0.35014445,0.4995608,-3.4482508,-181.85657,-215.30353,57.82969,-182.09995,469.01263,940000
+12.702381,5.8004637,0.29593796,0.5135429,12.702381,0.30941156,0.21462913,-31.17999,-185.88426,-229.33577,60.4031,-34.811813,291.4651,945000
+11.337051,7.677994,0.31991684,0.5708986,11.337051,0.38459873,0.25590175,0.8692649,-186.33244,-236.95255,40.935616,-55.205406,315.36725,950000
+13.424581,11.189848,0.34583294,0.65640336,13.424581,0.320297,0.4893662,-0.3032287,-182.81772,-226.79648,55.191208,-40.997086,387.56256,955000
+10.841392,5.806847,0.30155087,0.5302544,10.841392,0.27652207,0.28753057,-23.711798,-187.00296,-237.3997,41.385887,-64.08905,315.59528,960000
+11.461292,5.8569884,0.316725,0.5341365,11.461292,0.34181684,0.19923475,1.1456044,-184.03194,-220.32146,75.5246,-62.789665,399.76773,965000
+12.391882,12.0959015,0.3662246,0.747571,12.391882,0.27797332,0.58854216,0.77114666,-181.83293,-211.5073,44.80457,-39.366905,323.4969,970000
+10.903098,10.402897,0.2727066,0.52473086,10.903098,0.2832339,0.36620447,0.2352159,-184.32469,-235.46245,41.56537,-67.21007,371.97772,975000
+12.081623,6.2736416,0.32090676,0.5233292,12.081623,0.32520074,0.5187986,-29.159117,-183.43108,-229.60458,31.048018,-51.46474,311.12595,980000
+14.133579,6.538183,0.35296595,0.636553,14.133579,0.29143775,0.53493327,-1.568514,-182.26419,-279.2062,60.307343,-111.31208,474.2936,985000
+17.383703,9.428503,0.35795063,0.70363444,17.383703,0.33400106,0.58981293,-0.10084334,-180.83081,-231.89246,52.30616,-45.964348,412.38736,990000
+17.652977,7.67968,0.34154063,0.6176613,17.652977,0.29969063,0.34789294,-49.100407,-185.27492,-224.20676,85.943886,-38.277412,377.28546,995000
+14.191984,7.0858974,0.32703394,0.5909566,14.191984,0.2550008,0.34523234,0.15177631,-183.6801,-233.49559,198.60413,-57.837772,472.0875,1000000
+38.602898,8.50338,0.32709223,0.6062651,38.602898,0.28131095,0.36969897,-7.1873507,-183.55849,-223.91138,72.15231,-214.099,638.38983,1005000
+19.923832,9.169821,0.3171972,0.5721644,19.923832,0.25649127,0.82760715,-3.0314996,-183.87596,-232.48555,140.06993,-31.749153,458.82715,1010000
+11.878871,7.6454954,0.32937634,0.604287,11.878871,0.33298504,0.3807796,-5.4219112,-182.71207,-214.98242,73.71637,-52.097733,379.53156,1015000
+9.513542,5.79609,0.31206375,0.5311385,9.513542,0.28556478,0.55255985,0.0122562945,-183.94939,-222.90611,36.31158,-42.311996,339.85962,1020000
+11.839717,7.848265,0.32235497,0.58831155,11.839717,0.2884143,0.36348948,-4.7635927,-183.38986,-232.08333,96.97271,-80.01604,460.05948,1025000
+18.77418,13.402386,0.33620873,0.74062324,18.77418,0.31053668,0.60503906,-18.998407,-183.14369,-218.34467,45.16419,-208.50272,647.72736,1030000
+16.150658,5.8256817,0.3206067,0.5381273,16.150658,0.29575324,0.54474497,-0.8833045,-180.92451,-217.0988,101.18925,-54.096413,420.67712,1035000
+17.964386,19.445936,0.34829432,0.85319555,17.964386,0.25982085,0.36971888,0.8099465,-183.26637,-235.99078,61.210785,-50.521027,365.5335,1040000
+15.370259,6.483623,0.34373146,0.5464403,15.370259,0.2834326,0.3276855,-3.7542572,-181.82117,-236.07852,50.146355,-57.351635,345.6417,1045000
+15.933102,8.0180855,0.32486057,0.6011399,15.933102,0.30808568,0.5153993,-0.3731357,-181.23189,-221.21802,56.737865,-56.1852,368.9058,1050000
+27.795074,39.669056,0.39276367,1.612353,27.795074,0.2899719,1.6062653,-0.15946102,-181.84422,-226.34825,62.790802,-177.25627,584.5188,1055000
+15.491474,7.880821,0.34189975,0.6343181,15.491474,0.3114971,0.4574604,-24.422956,-181.55168,-221.47542,44.54454,-38.93785,320.00452,1060000
+15.524554,8.690095,0.3429551,0.6152261,15.524554,0.31364748,0.34241858,-9.858243,-184.09142,-249.79651,43.539734,-51.79756,313.69382,1065000
+14.180585,8.063939,0.36205244,0.5672867,14.180585,0.36017162,0.41664812,-15.149908,-182.876,-222.87607,44.281002,-34.05455,363.95306,1070000
+13.120348,5.348059,0.31984502,0.5876369,13.120348,0.313614,0.3994462,-1.383338,-184.86641,-228.46866,65.465454,-68.51074,360.61752,1075000
+13.196564,8.324635,0.34474838,0.5993287,13.196564,0.31429744,0.4034283,0.3068117,-179.95763,-217.59406,60.349457,-104.86755,445.34268,1080000
+12.054886,9.633214,0.30549082,0.6037158,12.054886,0.3169094,0.44946787,-16.75601,-185.11131,-214.71124,68.496086,-47.341343,399.12308,1085000
+19.8656,11.44415,0.34151226,0.6971026,19.8656,0.31707385,0.57937664,-0.046315283,-181.10411,-225.38342,106.247574,-60.810463,531.4316,1090000
+13.615146,6.112976,0.32163653,0.55047643,13.615146,0.27858824,0.39163893,-12.485995,-187.20909,-243.99588,52.80668,-36.54915,375.1705,1095000
+8.052207,3.9908414,0.25952283,0.44959378,8.052207,0.30168766,0.684668,-21.525455,-188.61076,-231.80165,45.44039,-57.739975,306.72812,1100000

O2O-w-diff-ckpts/qam/20260317_051145/params_1000000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a150311a91354d85016e3012bb793040ec70c342521170d666f048f6887917
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_1050000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e4f4212291911b41d053474ec70fcd2de199451cfc034e0853c7ec8d2a7d3a
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_1100000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca4f7ef965229061ae20aa42ede56d690bf39ba2a15c39476dffd5c8161c150c
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_650000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ee5c394305917bfa304b6383e74bfda24558d4fb834730eea989771c0c559a
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_700000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e80b9741fccf5f0871424e266fca528508e3c6df62bec190a76a6cee52e6f40
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_750000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2faf9dff379da59126a35cbfe842ec0872a1d1037ecd0c0311d2eddad196acb
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_800000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60e9813a33f7a20c35b2b9e623f5d9aaafaa9e50913d26625e1fb9e9723b3ad
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_850000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe7eb2f44a3e2b3d8b714d92f8656736b975c4878e68f37c77a51606da76998
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_900000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e38d5d0b68e5183a0fb605ab5a20f97ef5f5bb2e438f5a3b4ba1825aca2e53
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/params_950000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a44f1db00fdbf4d46e4f5a710ad1e10e6a1bad910cdb6f7a5f9f01ee2c7900e
+size 233879450

O2O-w-diff-ckpts/qam/20260317_051145/progress.tk

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

O2O-w-diff-ckpts/qam/20260317_051145/token.tk

@@ -0,0 +1 @@
+https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/4y6qnfk0