Upload folder using huggingface_hub

.gitattributes

@@ -902,3 +902,13 @@ O2O-w-diff-ckpts/qam/20260316_191952/visited_states_650000.png filter=lfs diff=l
 O2O-w-diff-ckpts/qam/20260316_191952/visited_states_700000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260316_191952/visited_states_750000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260316_191952/visited_states_800000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_450000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_500000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_550000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_600000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_650000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_700000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_750000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_800000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260316_223947/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text

O2O-w-diff-ckpts/qam/20260316_223947/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
+0.0,0.0,32.94092307744082,4.462159362776147,0.04188647914935631,4.464432941023022,0.053278032344982386,0.22,25099.98,-0.78,-983.7,983.92,1.4509189414978028,450000
+0.0,0.0,25.729441933319617,3.4869347300819316,0.0034002930185051306,3.4891609681214577,0.03375300218264471,0.2,76350.2,-0.8,-981.58,981.78,1.4173968029022217,500000
+0.0,0.0,32.887590825075435,4.466653455079171,0.07937689963387266,4.473223096843006,0.05482985009926502,0.32,127118.06,-0.68,-973.48,973.8,1.4862169694900513,550000
+0.0,0.0,29.510224865805814,4.012556175406187,0.037654065305928054,4.01965690302125,0.1163838001849619,0.32,177793.18,-0.68,-968.6,968.92,1.416569366455078,600000
+0.0,0.0,26.414415839914117,3.592695937021315,0.10326294805592633,3.6029215373141934,0.03242022289411811,0.22,228497.5,-0.78,-983.36,983.58,1.4225374126434327,650000
+0.0,0.0,27.69380085409916,3.757488359852883,0.0745016112979637,3.764923033629378,0.03331718934195799,0.18,279772.24,-0.82,-982.58,982.76,1.5351657247543335,700000
+0.0,0.0,27.871278884517764,3.79525665957927,0.07064461299774911,3.800392339105017,0.10361640132579453,0.34,330182.36,-0.66,-957.2,957.54,1.39207950592041,750000
+0.0,0.0,25.92887263531465,3.5296563960996803,0.011351086139473493,3.5314248418927856,-0.004793806520982738,0.2,380468.08,-0.8,-977.58,977.78,1.4052427673339845,800000
+0.0,0.0,19.2366424144044,2.6167059983405996,0.04807798061034131,2.6183799088547413,-0.04676402274055053,0.18,431265.02,-0.82,-975.76,975.94,1.479915246963501,850000
+0.0,0.0,26.375631074099633,3.568303197460129,0.04934508655505313,3.5735115452304225,0.06654554610067934,0.3,481802.42,-0.7,-965.46,965.76,1.3927733659744264,900000

O2O-w-diff-ckpts/qam/20260316_223947/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
+0.0,0.0,32.94092307744082,4.462159362776147,0.04188647914935631,4.464432941023022,0.053278032344982386,0.22,25099.98,-0.78,-983.7,983.92,1.4509189414978028,450000
+0.0,0.0,25.729441933319617,3.4869347300819316,0.0034002930185051306,3.4891609681214577,0.03375300218264471,0.2,76350.2,-0.8,-981.58,981.78,1.4173968029022217,500000
+0.0,0.0,32.887590825075435,4.466653455079171,0.07937689963387266,4.473223096843006,0.05482985009926502,0.32,127118.06,-0.68,-973.48,973.8,1.4862169694900513,550000
+0.0,0.0,29.510224865805814,4.012556175406187,0.037654065305928054,4.01965690302125,0.1163838001849619,0.32,177793.18,-0.68,-968.6,968.92,1.416569366455078,600000
+0.0,0.0,26.414415839914117,3.592695937021315,0.10326294805592633,3.6029215373141934,0.03242022289411811,0.22,228497.5,-0.78,-983.36,983.58,1.4225374126434327,650000
+0.0,0.0,27.69380085409916,3.757488359852883,0.0745016112979637,3.764923033629378,0.03331718934195799,0.18,279772.24,-0.82,-982.58,982.76,1.5351657247543335,700000
+0.0,0.0,27.871278884517764,3.79525665957927,0.07064461299774911,3.800392339105017,0.10361640132579453,0.34,330182.36,-0.66,-957.2,957.54,1.39207950592041,750000
+0.0,0.0,25.92887263531465,3.5296563960996803,0.011351086139473493,3.5314248418927856,-0.004793806520982738,0.2,380468.08,-0.8,-977.58,977.78,1.4052427673339845,800000
+0.0,0.0,19.2366424144044,2.6167059983405996,0.04807798061034131,2.6183799088547413,-0.04676402274055053,0.18,431265.02,-0.82,-975.76,975.94,1.479915246963501,850000
+0.0,0.0,26.375631074099633,3.568303197460129,0.04934508655505313,3.5735115452304225,0.06654554610067934,0.3,481802.42,-0.7,-965.46,965.76,1.3927733659744264,900000

O2O-w-diff-ckpts/qam/20260316_223947/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
+15.027469,7.294092,0.40720493,0.58424723,15.027469,0.3628245,0.4402874,-7.2382092,-176.47794,-279.49887,38.793,-38.22844,332.6899,405000
+26.698284,6.1675987,0.45515707,0.637683,26.698284,0.33179283,0.77972895,-9.976385,-173.82124,-227.66006,41.30638,-39.328003,454.7655,410000
+11.648981,5.4197054,0.39603004,0.56974196,11.648981,0.34141523,0.8159386,-10.273772,-179.82228,-234.33237,102.07121,-60.100624,442.29315,415000
+26.408728,11.7589655,0.40294468,0.65345323,26.408728,0.2819583,0.52081525,-21.006996,-178.45879,-230.83443,28.165195,-56.808945,349.55432,420000
+30.582764,5.360916,0.42344046,0.57732487,30.582764,0.3310975,0.5751948,-0.30270112,-177.13432,-237.1833,55.782936,-53.170353,395.62814,425000
+13.548999,11.086451,0.4186048,0.6806131,13.548999,0.28821415,0.43345433,0.22529238,-176.24834,-310.2898,54.69014,-70.56999,417.84607,430000
+11.794697,6.1615663,0.39593613,0.5647456,11.794697,0.3257249,0.58553374,0.41005436,-175.78947,-228.28696,44.740246,-38.554462,347.69244,435000
+21.113216,7.008642,0.42676958,0.6627074,21.113216,0.34069848,0.97762805,-5.3322344,-174.09624,-230.56532,124.4403,-189.12347,727.52783,440000
+13.151348,4.6332655,0.4055702,0.55848753,13.151348,0.3027984,0.6054372,-16.53466,-177.82053,-235.63412,50.5117,-37.893997,354.87408,445000
+28.424223,6.818184,0.39308238,0.54160947,28.424223,0.32608414,0.48793507,-0.25460204,-177.2711,-227.85994,69.357506,-50.86331,419.14203,450000
+14.735737,6.4038467,0.39934847,0.58958095,14.735737,0.29473194,0.5276411,0.4537409,-175.73216,-240.26779,84.331635,-253.5436,643.0849,455000
+19.000645,25.154572,0.4613126,0.98177356,19.000645,0.34592518,1.8070077,-3.6461935,-178.90596,-227.77231,66.0198,-73.2481,452.0973,460000
+14.610064,5.8035097,0.3708993,0.55938,14.610064,0.33073473,0.4008091,-16.811537,-182.7529,-244.573,37.31866,-31.100092,329.06934,465000
+17.136692,7.1125355,0.36907715,0.5822372,17.136692,0.3239242,0.37395865,-16.54531,-180.82225,-231.76558,63.721573,-68.037605,417.43155,470000
+13.448225,5.7282295,0.36217758,0.5327221,13.448225,0.3242702,0.35011867,-0.98080826,-183.40118,-228.19907,49.44696,-80.15603,401.84116,475000
+11.938435,7.0320425,0.3657844,0.58448803,11.938435,0.35924083,1.2297592,-11.283518,-181.31747,-231.82288,53.745453,-77.87648,341.62802,480000
+14.653442,21.905853,0.40686902,0.9070208,14.653442,0.28459886,0.69711083,-11.537811,-181.67432,-266.52658,131.14766,-27.858032,535.3636,485000
+16.852737,5.539156,0.354527,0.5146691,16.852737,0.33376235,0.51307315,-18.377066,-179.27283,-272.6478,70.638504,-50.88656,397.47095,490000
+15.9351635,15.533083,0.40593517,0.8671342,15.9351635,0.30557972,0.7242713,-0.14348054,-176.21379,-237.16661,37.148624,-108.06239,431.26645,495000
+15.271311,10.728797,0.41778794,0.7118476,15.271311,0.35154974,1.1966041,-2.4840312,-179.78117,-237.36298,47.708458,-50.42132,462.29797,500000
+15.824137,6.740711,0.3991556,0.62636125,15.824137,0.3690992,0.5225784,-1.8225745,-180.15746,-229.53455,53.48983,-77.98024,413.62665,505000
+16.8114,6.6212926,0.3766098,0.58029586,16.8114,0.3958212,0.59766906,-12.8559885,-178.14001,-218.0338,56.4402,-56.534683,431.3178,510000
+9.717542,6.735326,0.38645956,0.6195033,9.717542,0.36925936,0.540205,-12.573461,-184.50914,-243.22525,24.107681,-33.47837,278.47162,515000
+10.516964,5.2218804,0.34056938,0.511997,10.516964,0.3167857,0.43700323,-22.194506,-183.78351,-226.14261,56.200584,-82.33896,366.03308,520000
+24.672447,5.117663,0.38766068,0.5924815,24.672447,0.2933985,0.6680312,-33.268013,-182.75854,-222.11766,60.423344,-58.746983,450.06473,525000
+12.594006,5.911641,0.37127393,0.54407644,12.594006,0.32633558,0.37609425,-16.589304,-182.87834,-222.10213,52.20526,-38.063133,300.54486,530000
+15.078058,16.647007,0.37426972,0.70913756,15.078058,0.37413853,1.1317682,-36.33488,-183.51584,-290.8601,74.70323,-37.668633,423.72406,535000
+12.238157,10.095685,0.33937982,0.5877563,12.238157,0.27637416,0.6240096,-9.527532,-184.25084,-254.70184,65.91733,-88.41255,426.73688,540000
+13.7114525,16.487247,0.36704564,0.7074164,13.7114525,0.31379265,0.52373236,-9.003307,-180.1101,-236.44962,73.32733,-47.40587,392.92914,545000
+12.119519,7.5029716,0.32069114,0.5075616,12.119519,0.30858523,0.34075877,-20.039389,-183.71281,-226.0306,37.947357,-35.98247,293.8518,550000
+18.736076,12.239338,0.34907842,0.71974844,18.736076,0.31633714,0.5911954,-16.78134,-185.58488,-245.86841,99.13945,-48.929832,408.10632,555000
+14.990069,13.050312,0.35523847,0.7512118,14.990069,0.31796712,1.879949,1.1209207,-180.60887,-254.74094,108.41823,-61.209656,579.6157,560000
+15.201576,21.959507,0.35739344,0.8579131,15.201576,0.33597368,0.58915347,-0.1839746,-184.19951,-232.346,38.836853,-69.18338,430.49387,565000
+19.472973,5.2009544,0.3343655,0.5029733,19.472973,0.3177964,0.6299974,0.06293404,-182.23323,-220.79335,40.681965,-90.12255,449.13553,570000
+10.169889,6.588725,0.3455394,0.57002324,10.169889,0.32194942,0.5979004,-40.036263,-182.65585,-245.667,54.138176,-36.16597,331.94205,575000
+21.12332,22.015577,0.41237414,0.90034044,21.12332,0.3175956,0.48973742,-1.5376424,-178.29738,-295.11328,74.88415,-166.09805,550.1758,580000
+15.142287,13.333027,0.3512416,0.7129704,15.142287,0.3209942,0.382194,-9.687547,-183.91048,-222.9092,167.53041,-48.627327,504.7838,585000
+19.676659,7.7323456,0.37527305,0.6149842,19.676659,0.299938,0.3960776,-40.287193,-181.51608,-253.5834,51.854458,-40.303154,378.37085,590000
+24.955204,26.993282,0.42975754,1.3526111,24.955204,0.3105396,0.60023254,-0.45974132,-184.94073,-226.65437,82.57321,-62.086193,435.67453,595000
+17.48238,11.268765,0.3989465,0.80939984,17.48238,0.32194483,0.8159364,-2.6578338,-180.93677,-252.6262,58.795475,-66.349884,479.7383,600000
+28.386961,5.2272644,0.34292027,0.4912811,28.386961,0.34459227,0.89547366,-8.464895,-178.66164,-235.20999,51.687958,-44.1699,440.40842,605000
+11.505533,6.624603,0.33947605,0.53742987,11.505533,0.32044268,0.42419073,-33.574764,-183.30846,-248.92361,37.507122,-48.507355,326.82837,610000
+13.247313,19.645596,0.37361878,0.876007,13.247313,0.32706994,0.553026,0.4400645,-185.30264,-222.92535,55.489464,-43.93725,365.47018,615000
+17.035332,6.604333,0.3258096,0.48988953,17.035332,0.32737708,0.3423038,-0.7127548,-183.55411,-226.87694,167.83144,-56.804436,464.8041,620000
+19.547255,6.8544197,0.31453907,0.5589486,19.547255,0.31301785,0.70280063,0.9185498,-180.46751,-237.54129,43.611908,-65.127625,464.6525,625000
+10.331743,6.0444374,0.32598615,0.5007087,10.331743,0.29788643,0.41199723,-30.52438,-184.0471,-248.5216,23.318958,-29.507292,259.07236,630000
+16.659885,5.4429893,0.2887454,0.47595274,16.659885,0.31409293,0.5462556,0.67197526,-183.75652,-255.42815,109.89832,-62.828373,517.67706,635000
+30.622608,9.664227,0.36249542,0.7107028,30.622608,0.29212362,0.49021998,-43.98957,-185.8243,-224.15979,62.276382,-151.58928,548.72504,640000
+13.09459,5.3558326,0.34854314,0.55607384,13.09459,0.2915908,0.5479844,-3.8980818,-181.85022,-227.6215,48.233856,-29.353064,377.34692,645000
+22.932364,5.1951036,0.35055345,0.5897869,22.932364,0.30089104,0.39450458,-5.8307357,-182.85228,-215.18169,282.45105,-95.81617,648.38635,650000
+13.924633,8.162586,0.3769716,0.62992746,13.924633,0.35551536,0.55432624,-2.0787947,-181.60458,-230.09949,297.24066,-123.71611,688.06885,655000
+12.184023,5.722903,0.34250423,0.57072127,12.184023,0.32182747,0.48093987,-1.973354,-182.87822,-226.6209,58.76732,-50.400658,415.92575,660000
+12.253184,7.4122105,0.3046509,0.5091146,12.253184,0.3173328,0.40352494,-11.528533,-186.23405,-230.46545,36.29702,-116.75842,440.09128,665000
+12.823023,15.971715,0.34429532,0.72078234,12.823023,0.31813914,0.4858925,-6.3120956,-183.8315,-221.97626,95.74641,-59.165707,412.59952,670000
+23.116982,10.302712,0.36192715,0.6291504,23.116982,0.3087364,0.44566652,-11.059996,-180.82806,-229.12071,64.66504,-55.384914,427.65753,675000
+7.501254,6.6102047,0.2989691,0.4745075,7.501254,0.33147323,0.35041,0.18820605,-184.95934,-270.1285,28.867529,-61.200127,290.612,680000
+34.415585,6.4666543,0.35642695,0.5672233,34.415585,0.32621455,0.52855676,-0.67235196,-181.579,-269.15128,40.8901,-85.00676,353.15894,685000
+13.116684,6.2425737,0.3157325,0.52668345,13.116684,0.34092072,0.38000822,0.7054551,-184.92998,-219.16737,35.98504,-42.57453,318.61224,690000
+20.065132,22.005157,0.38758832,0.92304933,20.065132,0.36250198,1.2317531,-0.30702385,-181.10112,-236.71956,53.5387,-149.59612,648.13824,695000
+15.463575,10.791939,0.3324653,0.63305295,15.463575,0.3360973,0.4369094,-55.338306,-184.18454,-226.14551,48.634354,-40.66808,391.3914,700000
+15.422861,7.4707346,0.35149854,0.58865976,15.422861,0.33747074,0.5256632,-13.437379,-186.89842,-229.86981,27.84194,-28.451042,292.67084,705000
+32.719315,48.142536,0.3624244,1.3974997,32.719315,0.28543597,0.46857047,-43.395325,-185.16122,-229.86293,36.866974,-84.7517,358.7671,710000
+18.958206,4.2069297,0.3550622,0.5379955,18.958206,0.27271587,0.62631655,-1.5560348,-179.91125,-252.44122,61.81072,-37.490067,388.18115,715000
+11.661972,8.882111,0.30675578,0.6079849,11.661972,0.29150736,0.43950874,0.7880099,-185.59583,-249.33414,37.052353,-42.73018,328.58237,720000
+13.193626,10.355741,0.35464904,0.63637733,13.193626,0.27738798,0.44276476,0.64190555,-178.80986,-228.8385,71.39994,-38.208958,351.66254,725000
+16.042904,11.04138,0.34105074,0.7128465,16.042904,0.2918908,0.39262554,-24.968527,-186.65623,-215.88892,47.326385,-48.122288,336.43616,730000
+10.909526,5.4253216,0.320872,0.5108684,10.909526,0.328564,0.34229493,-9.583217,-183.01591,-223.90862,41.791237,-67.477554,382.0663,735000
+11.8661,4.9535418,0.30821446,0.5137561,11.8661,0.2828809,0.43248472,-17.470678,-186.7949,-222.59058,84.6763,-50.22825,480.25574,740000
+11.746171,9.29507,0.31334972,0.5872332,11.746171,0.282758,0.37754872,-30.031569,-185.37831,-268.37262,41.191734,-47.3246,332.81296,745000
+17.706448,5.6270876,0.31456107,0.5082026,17.706448,0.29637334,0.35548007,0.30209905,-186.65166,-236.39427,65.80141,-56.633533,323.3061,750000
+13.406273,7.9601154,0.37335378,0.6380929,13.406273,0.3194671,0.7299287,-0.42739797,-182.78581,-273.33188,44.758312,-37.177933,339.5904,755000
+15.015011,12.454419,0.33131027,0.68843657,15.015011,0.33693573,0.42466068,-23.111004,-186.69144,-225.28447,50.15332,-60.94848,367.33813,760000
+40.279015,9.183409,0.35084662,0.64116496,40.279015,0.31799155,0.43527976,1.1645758,-183.50938,-229.38525,63.08308,-51.71009,510.70752,765000
+30.685148,4.6498103,0.29749823,0.49080393,30.685148,0.32302743,0.49085483,0.74316084,-183.9143,-220.73898,65.53143,-59.989983,402.18842,770000
+15.502748,5.169983,0.27490243,0.46873653,15.502748,0.31640312,0.77038383,0.702615,-183.1588,-224.37231,172.4123,-484.68958,957.88904,775000
+11.621369,5.7708845,0.31415674,0.500422,11.621369,0.32040656,0.5240438,-8.841658,-184.71353,-222.90817,36.548378,-144.86458,390.0473,780000
+12.733702,11.69017,0.35029787,0.6760215,12.733702,0.33523285,0.37041965,-15.743196,-182.87717,-224.52696,50.22171,-49.55852,342.48297,785000
+18.971205,16.023952,0.33590096,0.7786017,18.971205,0.3460358,0.63645965,-0.28844124,-183.85234,-239.86534,82.254684,-71.26662,502.8117,790000
+16.491127,21.130333,0.3415859,0.88957816,16.491127,0.30487698,2.5366898,-17.004955,-185.40726,-216.94069,47.562675,-52.2462,449.9249,795000
+17.44038,6.3642387,0.3607246,0.6119124,17.44038,0.3240857,1.6628081,0.3547739,-180.05403,-241.91315,27.385433,-133.67935,591.97675,800000
+12.796009,8.287292,0.3263388,0.62596595,12.796009,0.31528014,0.46240616,-6.37382,-182.18115,-222.23582,47.241497,-68.01625,392.3526,805000
+12.425904,10.792187,0.3442121,0.6723028,12.425904,0.34521812,0.47153878,-7.216181,-183.19423,-222.40237,42.044518,-45.700466,314.6463,810000
+11.229788,5.191076,0.2938775,0.52620226,11.229788,0.3496831,0.36586186,1.4957281,-187.14915,-220.27008,39.993553,-133.28976,346.53265,815000
+12.931757,7.9454203,0.31401324,0.53656775,12.931757,0.28116763,0.37524888,-15.584457,-186.80586,-232.69069,27.616608,-141.35872,481.19733,820000
+10.209385,8.33383,0.31109172,0.5387243,10.209385,0.27360693,0.37972212,-6.5112433,-183.0194,-234.01369,66.79898,-33.997154,334.00067,825000
+11.012672,12.1773,0.36569917,0.69828343,11.012672,0.30536988,0.4295844,-9.808426,-184.43547,-221.91054,39.815308,-36.05207,266.1567,830000
+11.517827,10.85397,0.34905598,0.66319907,11.517827,0.29927146,0.53656954,-40.162262,-183.01636,-222.54724,70.15306,-34.255234,347.7569,835000
+12.69837,7.5620313,0.27525026,0.49980834,12.69837,0.29693726,0.30836827,0.051751524,-185.38393,-268.50128,66.205376,-100.00527,411.9016,840000
+15.518274,9.236994,0.33785748,0.6147923,15.518274,0.29914412,0.46243382,-15.208879,-184.8296,-225.31479,60.258553,-35.658115,369.96973,845000
+12.406264,6.2605295,0.3769244,0.64435047,12.406264,0.28402352,0.4301629,-0.63282204,-178.51689,-225.24545,31.394176,-43.765408,306.1309,850000
+24.568275,16.342216,0.3371418,0.7632523,24.568275,0.29016456,0.5111618,-0.9826772,-183.94975,-259.66943,61.538128,-81.38012,541.43176,855000
+11.291677,11.65169,0.3451267,0.68082833,11.291677,0.28812307,0.45463702,-1.8651593,-181.45479,-233.99593,45.91986,-67.39162,359.46863,860000
+16.044605,8.259094,0.36117542,0.63328695,16.044605,0.28733522,0.39042845,-19.495852,-179.75908,-229.5908,73.89434,-120.678825,443.39703,865000
+11.316336,10.748129,0.36178643,0.6666638,11.316336,0.27556005,0.46931824,-14.11096,-180.82022,-218.12486,84.990845,-40.734383,398.94385,870000
+13.684128,6.0719223,0.32878512,0.5856388,13.684128,0.2568056,0.5936511,-13.869679,-182.69127,-233.6503,66.688065,-46.825775,364.14883,875000
+15.396511,17.7348,0.3521108,0.8111804,15.396511,0.2953678,0.44073746,-0.23646462,-182.72334,-219.18683,56.93643,-44.46659,408.43115,880000
+14.871503,9.688551,0.3033327,0.5680168,14.871503,0.25401643,0.47574112,-0.9585936,-185.87415,-219.22067,64.66655,-35.258568,316.37277,885000
+18.188023,14.262907,0.3114729,0.69685876,18.188023,0.32645705,0.431073,-1.4059807,-185.46098,-219.0571,78.28937,-141.91635,508.0724,890000
+10.884359,6.3595805,0.30032766,0.5371074,10.884359,0.2677973,0.26829904,-34.616608,-188.59906,-226.28458,33.58674,-58.151115,290.99905,895000
+26.698935,4.863863,0.27112377,0.4351311,26.698935,0.3318774,0.7315359,-24.145197,-189.20105,-225.78969,51.714947,-35.17035,377.88037,900000

O2O-w-diff-ckpts/qam/20260316_223947/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
+15.027469,7.294092,0.40720493,0.58424723,15.027469,0.3628245,0.4402874,-7.2382092,-176.47794,-279.49887,38.793,-38.22844,332.6899,405000
+26.698284,6.1675987,0.45515707,0.637683,26.698284,0.33179283,0.77972895,-9.976385,-173.82124,-227.66006,41.30638,-39.328003,454.7655,410000
+11.648981,5.4197054,0.39603004,0.56974196,11.648981,0.34141523,0.8159386,-10.273772,-179.82228,-234.33237,102.07121,-60.100624,442.29315,415000
+26.408728,11.7589655,0.40294468,0.65345323,26.408728,0.2819583,0.52081525,-21.006996,-178.45879,-230.83443,28.165195,-56.808945,349.55432,420000
+30.582764,5.360916,0.42344046,0.57732487,30.582764,0.3310975,0.5751948,-0.30270112,-177.13432,-237.1833,55.782936,-53.170353,395.62814,425000
+13.548999,11.086451,0.4186048,0.6806131,13.548999,0.28821415,0.43345433,0.22529238,-176.24834,-310.2898,54.69014,-70.56999,417.84607,430000
+11.794697,6.1615663,0.39593613,0.5647456,11.794697,0.3257249,0.58553374,0.41005436,-175.78947,-228.28696,44.740246,-38.554462,347.69244,435000
+21.113216,7.008642,0.42676958,0.6627074,21.113216,0.34069848,0.97762805,-5.3322344,-174.09624,-230.56532,124.4403,-189.12347,727.52783,440000
+13.151348,4.6332655,0.4055702,0.55848753,13.151348,0.3027984,0.6054372,-16.53466,-177.82053,-235.63412,50.5117,-37.893997,354.87408,445000
+28.424223,6.818184,0.39308238,0.54160947,28.424223,0.32608414,0.48793507,-0.25460204,-177.2711,-227.85994,69.357506,-50.86331,419.14203,450000
+14.735737,6.4038467,0.39934847,0.58958095,14.735737,0.29473194,0.5276411,0.4537409,-175.73216,-240.26779,84.331635,-253.5436,643.0849,455000
+19.000645,25.154572,0.4613126,0.98177356,19.000645,0.34592518,1.8070077,-3.6461935,-178.90596,-227.77231,66.0198,-73.2481,452.0973,460000
+14.610064,5.8035097,0.3708993,0.55938,14.610064,0.33073473,0.4008091,-16.811537,-182.7529,-244.573,37.31866,-31.100092,329.06934,465000
+17.136692,7.1125355,0.36907715,0.5822372,17.136692,0.3239242,0.37395865,-16.54531,-180.82225,-231.76558,63.721573,-68.037605,417.43155,470000
+13.448225,5.7282295,0.36217758,0.5327221,13.448225,0.3242702,0.35011867,-0.98080826,-183.40118,-228.19907,49.44696,-80.15603,401.84116,475000
+11.938435,7.0320425,0.3657844,0.58448803,11.938435,0.35924083,1.2297592,-11.283518,-181.31747,-231.82288,53.745453,-77.87648,341.62802,480000
+14.653442,21.905853,0.40686902,0.9070208,14.653442,0.28459886,0.69711083,-11.537811,-181.67432,-266.52658,131.14766,-27.858032,535.3636,485000
+16.852737,5.539156,0.354527,0.5146691,16.852737,0.33376235,0.51307315,-18.377066,-179.27283,-272.6478,70.638504,-50.88656,397.47095,490000
+15.9351635,15.533083,0.40593517,0.8671342,15.9351635,0.30557972,0.7242713,-0.14348054,-176.21379,-237.16661,37.148624,-108.06239,431.26645,495000
+15.271311,10.728797,0.41778794,0.7118476,15.271311,0.35154974,1.1966041,-2.4840312,-179.78117,-237.36298,47.708458,-50.42132,462.29797,500000
+15.824137,6.740711,0.3991556,0.62636125,15.824137,0.3690992,0.5225784,-1.8225745,-180.15746,-229.53455,53.48983,-77.98024,413.62665,505000
+16.8114,6.6212926,0.3766098,0.58029586,16.8114,0.3958212,0.59766906,-12.8559885,-178.14001,-218.0338,56.4402,-56.534683,431.3178,510000
+9.717542,6.735326,0.38645956,0.6195033,9.717542,0.36925936,0.540205,-12.573461,-184.50914,-243.22525,24.107681,-33.47837,278.47162,515000
+10.516964,5.2218804,0.34056938,0.511997,10.516964,0.3167857,0.43700323,-22.194506,-183.78351,-226.14261,56.200584,-82.33896,366.03308,520000
+24.672447,5.117663,0.38766068,0.5924815,24.672447,0.2933985,0.6680312,-33.268013,-182.75854,-222.11766,60.423344,-58.746983,450.06473,525000
+12.594006,5.911641,0.37127393,0.54407644,12.594006,0.32633558,0.37609425,-16.589304,-182.87834,-222.10213,52.20526,-38.063133,300.54486,530000
+15.078058,16.647007,0.37426972,0.70913756,15.078058,0.37413853,1.1317682,-36.33488,-183.51584,-290.8601,74.70323,-37.668633,423.72406,535000
+12.238157,10.095685,0.33937982,0.5877563,12.238157,0.27637416,0.6240096,-9.527532,-184.25084,-254.70184,65.91733,-88.41255,426.73688,540000
+13.7114525,16.487247,0.36704564,0.7074164,13.7114525,0.31379265,0.52373236,-9.003307,-180.1101,-236.44962,73.32733,-47.40587,392.92914,545000
+12.119519,7.5029716,0.32069114,0.5075616,12.119519,0.30858523,0.34075877,-20.039389,-183.71281,-226.0306,37.947357,-35.98247,293.8518,550000
+18.736076,12.239338,0.34907842,0.71974844,18.736076,0.31633714,0.5911954,-16.78134,-185.58488,-245.86841,99.13945,-48.929832,408.10632,555000
+14.990069,13.050312,0.35523847,0.7512118,14.990069,0.31796712,1.879949,1.1209207,-180.60887,-254.74094,108.41823,-61.209656,579.6157,560000
+15.201576,21.959507,0.35739344,0.8579131,15.201576,0.33597368,0.58915347,-0.1839746,-184.19951,-232.346,38.836853,-69.18338,430.49387,565000
+19.472973,5.2009544,0.3343655,0.5029733,19.472973,0.3177964,0.6299974,0.06293404,-182.23323,-220.79335,40.681965,-90.12255,449.13553,570000
+10.169889,6.588725,0.3455394,0.57002324,10.169889,0.32194942,0.5979004,-40.036263,-182.65585,-245.667,54.138176,-36.16597,331.94205,575000
+21.12332,22.015577,0.41237414,0.90034044,21.12332,0.3175956,0.48973742,-1.5376424,-178.29738,-295.11328,74.88415,-166.09805,550.1758,580000
+15.142287,13.333027,0.3512416,0.7129704,15.142287,0.3209942,0.382194,-9.687547,-183.91048,-222.9092,167.53041,-48.627327,504.7838,585000
+19.676659,7.7323456,0.37527305,0.6149842,19.676659,0.299938,0.3960776,-40.287193,-181.51608,-253.5834,51.854458,-40.303154,378.37085,590000
+24.955204,26.993282,0.42975754,1.3526111,24.955204,0.3105396,0.60023254,-0.45974132,-184.94073,-226.65437,82.57321,-62.086193,435.67453,595000
+17.48238,11.268765,0.3989465,0.80939984,17.48238,0.32194483,0.8159364,-2.6578338,-180.93677,-252.6262,58.795475,-66.349884,479.7383,600000
+28.386961,5.2272644,0.34292027,0.4912811,28.386961,0.34459227,0.89547366,-8.464895,-178.66164,-235.20999,51.687958,-44.1699,440.40842,605000
+11.505533,6.624603,0.33947605,0.53742987,11.505533,0.32044268,0.42419073,-33.574764,-183.30846,-248.92361,37.507122,-48.507355,326.82837,610000
+13.247313,19.645596,0.37361878,0.876007,13.247313,0.32706994,0.553026,0.4400645,-185.30264,-222.92535,55.489464,-43.93725,365.47018,615000
+17.035332,6.604333,0.3258096,0.48988953,17.035332,0.32737708,0.3423038,-0.7127548,-183.55411,-226.87694,167.83144,-56.804436,464.8041,620000
+19.547255,6.8544197,0.31453907,0.5589486,19.547255,0.31301785,0.70280063,0.9185498,-180.46751,-237.54129,43.611908,-65.127625,464.6525,625000
+10.331743,6.0444374,0.32598615,0.5007087,10.331743,0.29788643,0.41199723,-30.52438,-184.0471,-248.5216,23.318958,-29.507292,259.07236,630000
+16.659885,5.4429893,0.2887454,0.47595274,16.659885,0.31409293,0.5462556,0.67197526,-183.75652,-255.42815,109.89832,-62.828373,517.67706,635000
+30.622608,9.664227,0.36249542,0.7107028,30.622608,0.29212362,0.49021998,-43.98957,-185.8243,-224.15979,62.276382,-151.58928,548.72504,640000
+13.09459,5.3558326,0.34854314,0.55607384,13.09459,0.2915908,0.5479844,-3.8980818,-181.85022,-227.6215,48.233856,-29.353064,377.34692,645000
+22.932364,5.1951036,0.35055345,0.5897869,22.932364,0.30089104,0.39450458,-5.8307357,-182.85228,-215.18169,282.45105,-95.81617,648.38635,650000
+13.924633,8.162586,0.3769716,0.62992746,13.924633,0.35551536,0.55432624,-2.0787947,-181.60458,-230.09949,297.24066,-123.71611,688.06885,655000
+12.184023,5.722903,0.34250423,0.57072127,12.184023,0.32182747,0.48093987,-1.973354,-182.87822,-226.6209,58.76732,-50.400658,415.92575,660000
+12.253184,7.4122105,0.3046509,0.5091146,12.253184,0.3173328,0.40352494,-11.528533,-186.23405,-230.46545,36.29702,-116.75842,440.09128,665000
+12.823023,15.971715,0.34429532,0.72078234,12.823023,0.31813914,0.4858925,-6.3120956,-183.8315,-221.97626,95.74641,-59.165707,412.59952,670000
+23.116982,10.302712,0.36192715,0.6291504,23.116982,0.3087364,0.44566652,-11.059996,-180.82806,-229.12071,64.66504,-55.384914,427.65753,675000
+7.501254,6.6102047,0.2989691,0.4745075,7.501254,0.33147323,0.35041,0.18820605,-184.95934,-270.1285,28.867529,-61.200127,290.612,680000
+34.415585,6.4666543,0.35642695,0.5672233,34.415585,0.32621455,0.52855676,-0.67235196,-181.579,-269.15128,40.8901,-85.00676,353.15894,685000
+13.116684,6.2425737,0.3157325,0.52668345,13.116684,0.34092072,0.38000822,0.7054551,-184.92998,-219.16737,35.98504,-42.57453,318.61224,690000
+20.065132,22.005157,0.38758832,0.92304933,20.065132,0.36250198,1.2317531,-0.30702385,-181.10112,-236.71956,53.5387,-149.59612,648.13824,695000
+15.463575,10.791939,0.3324653,0.63305295,15.463575,0.3360973,0.4369094,-55.338306,-184.18454,-226.14551,48.634354,-40.66808,391.3914,700000
+15.422861,7.4707346,0.35149854,0.58865976,15.422861,0.33747074,0.5256632,-13.437379,-186.89842,-229.86981,27.84194,-28.451042,292.67084,705000
+32.719315,48.142536,0.3624244,1.3974997,32.719315,0.28543597,0.46857047,-43.395325,-185.16122,-229.86293,36.866974,-84.7517,358.7671,710000
+18.958206,4.2069297,0.3550622,0.5379955,18.958206,0.27271587,0.62631655,-1.5560348,-179.91125,-252.44122,61.81072,-37.490067,388.18115,715000
+11.661972,8.882111,0.30675578,0.6079849,11.661972,0.29150736,0.43950874,0.7880099,-185.59583,-249.33414,37.052353,-42.73018,328.58237,720000
+13.193626,10.355741,0.35464904,0.63637733,13.193626,0.27738798,0.44276476,0.64190555,-178.80986,-228.8385,71.39994,-38.208958,351.66254,725000
+16.042904,11.04138,0.34105074,0.7128465,16.042904,0.2918908,0.39262554,-24.968527,-186.65623,-215.88892,47.326385,-48.122288,336.43616,730000
+10.909526,5.4253216,0.320872,0.5108684,10.909526,0.328564,0.34229493,-9.583217,-183.01591,-223.90862,41.791237,-67.477554,382.0663,735000
+11.8661,4.9535418,0.30821446,0.5137561,11.8661,0.2828809,0.43248472,-17.470678,-186.7949,-222.59058,84.6763,-50.22825,480.25574,740000
+11.746171,9.29507,0.31334972,0.5872332,11.746171,0.282758,0.37754872,-30.031569,-185.37831,-268.37262,41.191734,-47.3246,332.81296,745000
+17.706448,5.6270876,0.31456107,0.5082026,17.706448,0.29637334,0.35548007,0.30209905,-186.65166,-236.39427,65.80141,-56.633533,323.3061,750000
+13.406273,7.9601154,0.37335378,0.6380929,13.406273,0.3194671,0.7299287,-0.42739797,-182.78581,-273.33188,44.758312,-37.177933,339.5904,755000
+15.015011,12.454419,0.33131027,0.68843657,15.015011,0.33693573,0.42466068,-23.111004,-186.69144,-225.28447,50.15332,-60.94848,367.33813,760000
+40.279015,9.183409,0.35084662,0.64116496,40.279015,0.31799155,0.43527976,1.1645758,-183.50938,-229.38525,63.08308,-51.71009,510.70752,765000
+30.685148,4.6498103,0.29749823,0.49080393,30.685148,0.32302743,0.49085483,0.74316084,-183.9143,-220.73898,65.53143,-59.989983,402.18842,770000
+15.502748,5.169983,0.27490243,0.46873653,15.502748,0.31640312,0.77038383,0.702615,-183.1588,-224.37231,172.4123,-484.68958,957.88904,775000
+11.621369,5.7708845,0.31415674,0.500422,11.621369,0.32040656,0.5240438,-8.841658,-184.71353,-222.90817,36.548378,-144.86458,390.0473,780000
+12.733702,11.69017,0.35029787,0.6760215,12.733702,0.33523285,0.37041965,-15.743196,-182.87717,-224.52696,50.22171,-49.55852,342.48297,785000
+18.971205,16.023952,0.33590096,0.7786017,18.971205,0.3460358,0.63645965,-0.28844124,-183.85234,-239.86534,82.254684,-71.26662,502.8117,790000
+16.491127,21.130333,0.3415859,0.88957816,16.491127,0.30487698,2.5366898,-17.004955,-185.40726,-216.94069,47.562675,-52.2462,449.9249,795000
+17.44038,6.3642387,0.3607246,0.6119124,17.44038,0.3240857,1.6628081,0.3547739,-180.05403,-241.91315,27.385433,-133.67935,591.97675,800000
+12.796009,8.287292,0.3263388,0.62596595,12.796009,0.31528014,0.46240616,-6.37382,-182.18115,-222.23582,47.241497,-68.01625,392.3526,805000
+12.425904,10.792187,0.3442121,0.6723028,12.425904,0.34521812,0.47153878,-7.216181,-183.19423,-222.40237,42.044518,-45.700466,314.6463,810000
+11.229788,5.191076,0.2938775,0.52620226,11.229788,0.3496831,0.36586186,1.4957281,-187.14915,-220.27008,39.993553,-133.28976,346.53265,815000
+12.931757,7.9454203,0.31401324,0.53656775,12.931757,0.28116763,0.37524888,-15.584457,-186.80586,-232.69069,27.616608,-141.35872,481.19733,820000
+10.209385,8.33383,0.31109172,0.5387243,10.209385,0.27360693,0.37972212,-6.5112433,-183.0194,-234.01369,66.79898,-33.997154,334.00067,825000
+11.012672,12.1773,0.36569917,0.69828343,11.012672,0.30536988,0.4295844,-9.808426,-184.43547,-221.91054,39.815308,-36.05207,266.1567,830000
+11.517827,10.85397,0.34905598,0.66319907,11.517827,0.29927146,0.53656954,-40.162262,-183.01636,-222.54724,70.15306,-34.255234,347.7569,835000
+12.69837,7.5620313,0.27525026,0.49980834,12.69837,0.29693726,0.30836827,0.051751524,-185.38393,-268.50128,66.205376,-100.00527,411.9016,840000
+15.518274,9.236994,0.33785748,0.6147923,15.518274,0.29914412,0.46243382,-15.208879,-184.8296,-225.31479,60.258553,-35.658115,369.96973,845000
+12.406264,6.2605295,0.3769244,0.64435047,12.406264,0.28402352,0.4301629,-0.63282204,-178.51689,-225.24545,31.394176,-43.765408,306.1309,850000
+24.568275,16.342216,0.3371418,0.7632523,24.568275,0.29016456,0.5111618,-0.9826772,-183.94975,-259.66943,61.538128,-81.38012,541.43176,855000
+11.291677,11.65169,0.3451267,0.68082833,11.291677,0.28812307,0.45463702,-1.8651593,-181.45479,-233.99593,45.91986,-67.39162,359.46863,860000
+16.044605,8.259094,0.36117542,0.63328695,16.044605,0.28733522,0.39042845,-19.495852,-179.75908,-229.5908,73.89434,-120.678825,443.39703,865000
+11.316336,10.748129,0.36178643,0.6666638,11.316336,0.27556005,0.46931824,-14.11096,-180.82022,-218.12486,84.990845,-40.734383,398.94385,870000
+13.684128,6.0719223,0.32878512,0.5856388,13.684128,0.2568056,0.5936511,-13.869679,-182.69127,-233.6503,66.688065,-46.825775,364.14883,875000
+15.396511,17.7348,0.3521108,0.8111804,15.396511,0.2953678,0.44073746,-0.23646462,-182.72334,-219.18683,56.93643,-44.46659,408.43115,880000
+14.871503,9.688551,0.3033327,0.5680168,14.871503,0.25401643,0.47574112,-0.9585936,-185.87415,-219.22067,64.66655,-35.258568,316.37277,885000
+18.188023,14.262907,0.3114729,0.69685876,18.188023,0.32645705,0.431073,-1.4059807,-185.46098,-219.0571,78.28937,-141.91635,508.0724,890000
+10.884359,6.3595805,0.30032766,0.5371074,10.884359,0.2677973,0.26829904,-34.616608,-188.59906,-226.28458,33.58674,-58.151115,290.99905,895000
+26.698935,4.863863,0.27112377,0.4351311,26.698935,0.3318774,0.7315359,-24.145197,-189.20105,-225.78969,51.714947,-35.17035,377.88037,900000

O2O-w-diff-ckpts/qam/20260316_223947/params_450000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86875b311a69f2f40350cfdfd780e40a5e14437f5aa03bb4f1887057f191b3ac
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_500000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e908792754a6858982a5bc6a5a27e532a697229e02d73304cfcfd77ed849b4
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_550000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2f90b499eaf116242908c2e38fef34c9f5b96b31dbaef7b3fb74b69892857b
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_600000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42535f9a6c6973a29cefa2b59d0a6d6afb7472dd7801e62b3c6782f2490e035c
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_650000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11d5bcaee836b5fd0bff4eb63a7fecf9bd768de0d07124ff67dfad79c41209f
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_700000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b649f033ce82fc6c9e728b2b3946e20367ad4faa562a55fcc5ab40322905e3
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_750000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ece556e0657302281e65753a6472ee1bb565305558e17bfff78f21e4837b93b
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_800000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd2a0f9f1a9488f08b5762f4ed5bdad4b0b7bbbd14b08e6cd23bc446c6d8f65
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_850000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e53d6f5fcf171d84e70d7cecb99ead240c50ae8a4a28dbb61fb89dc053cc994
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/params_900000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4df96f4b602ecb554c5dbf2cbb596d4f9ff46516084174f573c7352bc7a25c
+size 233879450

O2O-w-diff-ckpts/qam/20260316_223947/progress.tk

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

O2O-w-diff-ckpts/qam/20260316_223947/token.tk

@@ -0,0 +1 @@
+https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/vbuyjcx0