Upload folder using huggingface_hub

.gitattributes

@@ -952,3 +952,13 @@ O2O-w-diff-ckpts/qam/20260317_114429/visited_states_1300000.png filter=lfs diff=
 O2O-w-diff-ckpts/qam/20260317_114429/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260317_114429/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/qam/20260317_114429/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1000000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1050000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1100000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1150000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1200000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1250000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1300000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1350000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_1400000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/qam/20260317_150042/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text

O2O-w-diff-ckpts/qam/20260317_150042/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
+0.0,0.0,35.16324525291759,4.7586662717611565,0.09322176541547268,4.7656907465004315,0.05530130385928262,0.46,24741.06,-0.54,-962.94,963.4,1.4165321588516235,950000
+0.0,0.0,29.897973781910665,4.060314369690019,0.031438355404940846,4.065835372383346,0.07107964057112211,0.3,74987.86,-0.7,-969.72,970.02,1.5227079963684083,1000000
+0.0,0.0,30.378005447812548,4.128373651289865,0.026895138769600722,4.130724817271218,-0.001677457749302414,0.26,125494.22,-0.74,-974.6,974.86,1.4884014081954957,1050000
+0.0,0.0,27.479892594184417,3.754810834887395,0.030443494336157978,3.7550499006895866,-0.034843120234658874,0.24,175841.98,-0.76,-972.22,972.46,1.4893057584762572,1100000
+0.0,0.0,26.96216740942334,3.6879442844143777,0.12304048579662727,3.699230082524789,0.07917853090612334,0.28,226577.68,-0.72,-974.46,974.74,1.4093933629989623,1150000
+0.0,0.0,26.591954043493775,3.6128310138938255,0.06823860208008292,3.62517142644303,0.12918735624981587,0.24,277145.54,-0.76,-965.58,965.82,1.4132313871383666,1200000
+0.0,0.0,27.470638430384177,3.7466574456977226,0.10426066925967785,3.757358218055747,0.08072394070186249,0.3,327223.0,-0.7,-959.42,959.72,1.4063479089736939,1250000
+0.0,0.0,20.524482683547326,2.8194788220946383,0.0813199761217888,2.8292027412593805,0.10140661758821681,0.1,377909.34,-0.9,-989.42,989.52,1.4162150955200195,1300000
+0.0,0.0,26.749914008228632,3.6455780265115516,0.06060191561282149,3.6509729736117436,0.03754730227442347,0.34,428371.98,-0.66,-948.94,949.28,1.3700331926345826,1350000
+0.0,0.0,21.759364043758232,2.956646978511338,0.05464544866207214,2.9634475200395123,0.10565740465943617,0.2,478668.88,-0.8,-972.78,972.98,1.3897840547561646,1400000

O2O-w-diff-ckpts/qam/20260317_150042/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
+0.0,0.0,35.16324525291759,4.7586662717611565,0.09322176541547268,4.7656907465004315,0.05530130385928262,0.46,24741.06,-0.54,-962.94,963.4,1.4165321588516235,950000
+0.0,0.0,29.897973781910665,4.060314369690019,0.031438355404940846,4.065835372383346,0.07107964057112211,0.3,74987.86,-0.7,-969.72,970.02,1.5227079963684083,1000000
+0.0,0.0,30.378005447812548,4.128373651289865,0.026895138769600722,4.130724817271218,-0.001677457749302414,0.26,125494.22,-0.74,-974.6,974.86,1.4884014081954957,1050000
+0.0,0.0,27.479892594184417,3.754810834887395,0.030443494336157978,3.7550499006895866,-0.034843120234658874,0.24,175841.98,-0.76,-972.22,972.46,1.4893057584762572,1100000
+0.0,0.0,26.96216740942334,3.6879442844143777,0.12304048579662727,3.699230082524789,0.07917853090612334,0.28,226577.68,-0.72,-974.46,974.74,1.4093933629989623,1150000
+0.0,0.0,26.591954043493775,3.6128310138938255,0.06823860208008292,3.62517142644303,0.12918735624981587,0.24,277145.54,-0.76,-965.58,965.82,1.4132313871383666,1200000
+0.0,0.0,27.470638430384177,3.7466574456977226,0.10426066925967785,3.757358218055747,0.08072394070186249,0.3,327223.0,-0.7,-959.42,959.72,1.4063479089736939,1250000
+0.0,0.0,20.524482683547326,2.8194788220946383,0.0813199761217888,2.8292027412593805,0.10140661758821681,0.1,377909.34,-0.9,-989.42,989.52,1.4162150955200195,1300000
+0.0,0.0,26.749914008228632,3.6455780265115516,0.06060191561282149,3.6509729736117436,0.03754730227442347,0.34,428371.98,-0.66,-948.94,949.28,1.3700331926345826,1350000
+0.0,0.0,21.759364043758232,2.956646978511338,0.05464544866207214,2.9634475200395123,0.10565740465943617,0.2,478668.88,-0.8,-972.78,972.98,1.3897840547561646,1400000

O2O-w-diff-ckpts/qam/20260317_150042/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
+22.835407,8.511239,0.39365506,0.6550111,22.835407,0.34972313,0.6316496,-6.0765314,-177.08235,-218.64362,56.264633,-49.415604,420.18262,905000
+21.356115,8.32028,0.43633848,0.6594407,21.356115,0.3004384,0.48495445,-8.77516,-174.09897,-217.68672,81.54497,-69.26502,451.771,910000
+17.918793,6.8630924,0.38984013,0.58654094,17.918793,0.37087047,0.275096,-11.250025,-180.15326,-218.82784,70.320786,-74.356285,403.90073,915000
+76.093025,6.8189487,0.4058724,0.6534967,76.093025,0.27867323,0.46033946,-20.337324,-178.87329,-212.88301,95.22159,-119.152466,545.9765,920000
+36.573784,10.187702,0.43530124,0.68605477,36.573784,0.33265457,0.47510216,-0.20183563,-176.7075,-217.28275,108.13359,-36.102444,476.93823,925000
+23.739586,12.092998,0.38881013,0.6701087,23.739586,0.28032026,0.38848463,0.29345983,-176.55502,-219.6122,87.06654,-102.79474,521.54333,930000
+29.604918,12.90099,0.42391646,0.7840348,29.604918,0.33536404,0.5071199,0.5663998,-175.98009,-218.86507,62.24495,-108.067856,508.48636,935000
+16.965748,8.471491,0.3697011,0.60423625,16.965748,0.35419714,0.439607,-7.551371,-176.0836,-218.56293,39.378418,-49.246895,336.40793,940000
+24.515003,6.1301785,0.3952521,0.64249414,24.515003,0.3281726,0.4234766,-9.65856,-178.76822,-234.4408,45.296986,-101.2582,472.6004,945000
+18.199127,6.692951,0.36965913,0.54849625,18.199127,0.35148585,0.29168043,0.2539107,-178.73459,-214.66176,41.756058,-32.270874,316.86453,950000
+19.048138,7.9595346,0.39431697,0.617569,19.048138,0.31676024,0.8811783,0.7826824,-176.79915,-236.0529,42.107605,-68.77712,448.8509,955000
+13.871018,6.703974,0.369658,0.60086113,13.871018,0.28553432,0.5465457,-41.103703,-180.39151,-222.74693,88.64378,-89.72753,472.55038,960000
+14.428338,7.603917,0.36709195,0.5632191,14.428338,0.3692674,0.22136155,-17.919914,-182.78627,-218.49414,31.36073,-41.211372,294.1651,965000
+32.997547,6.057873,0.3983819,0.6542174,32.997547,0.30224642,0.46152145,-19.258276,-180.02843,-214.00238,87.88392,-83.52063,467.17725,970000
+14.222685,8.15564,0.35046405,0.62947637,14.222685,0.28236896,0.4654418,0.18943918,-183.16815,-216.33769,71.61654,-69.44144,381.7097,975000
+31.434656,11.75277,0.42529303,0.85312474,31.434656,0.34064728,0.5013778,-8.487129,-180.47072,-217.47873,160.99577,-517.8726,940.2193,980000
+17.172024,7.0743704,0.3290744,0.50630563,17.172024,0.28992444,0.4469764,-11.262733,-183.67796,-217.46143,51.076096,-48.34163,397.65088,985000
+22.612955,4.472224,0.35179937,0.5260064,22.612955,0.34766054,0.53232574,-20.762653,-180.70712,-225.60464,53.913757,-69.83993,371.35162,990000
+19.28028,17.788847,0.4287244,0.9093447,19.28028,0.32097888,0.50197995,1.7032609,-177.40363,-216.83905,152.20927,-238.99962,649.96936,995000
+18.945301,7.2800655,0.37206978,0.5958906,18.945301,0.2679817,0.677381,-4.1866226,-179.61003,-221.82353,93.03513,-66.1432,424.9807,1000000
+19.608763,6.531781,0.38849574,0.63783,19.608763,0.28570125,0.38984933,-19.983541,-183.61801,-234.69554,115.00366,-59.843975,410.9016,1005000
+21.656372,11.225064,0.38803375,0.72674716,21.656372,0.26186568,0.38160044,-15.8937435,-179.90686,-220.39714,391.554,-162.49884,810.2436,1010000
+17.9413,6.527192,0.3330717,0.5234036,17.9413,0.32056275,0.3069757,-16.775856,-186.03035,-216.85452,57.69681,-90.63091,470.03833,1015000
+13.837907,6.757672,0.32589474,0.56626135,13.837907,0.3098085,0.48414356,-22.565886,-184.64786,-226.55962,45.5774,-46.380104,345.2802,1020000
+15.204688,6.7713146,0.37600017,0.6473243,15.204688,0.3233288,0.46718636,-19.147837,-182.42151,-235.89117,92.38836,-99.806305,431.89102,1025000
+15.408054,5.4021983,0.36845663,0.5875465,15.408054,0.30759513,1.373556,-1.7774721,-182.21777,-237.67819,77.64124,-77.24196,630.9007,1030000
+18.580633,7.7278776,0.36045632,0.628892,18.580633,0.3153962,0.51387215,-4.964365,-183.28542,-226.98586,129.42165,-98.449005,461.25253,1035000
+35.3056,9.226419,0.32849455,0.5877052,35.3056,0.26657575,0.5569667,-11.634139,-185.33968,-239.56093,90.01409,-57.5781,542.866,1040000
+17.039957,17.362936,0.36571217,0.7221856,17.039957,0.30902523,0.376863,-19.59161,-179.42804,-211.76846,123.88394,-121.191475,478.72498,1045000
+39.058918,6.0346684,0.2953408,0.4750311,39.058918,0.32520103,0.21926318,-22.444546,-185.6895,-235.324,51.409767,-78.483765,377.49738,1050000
+13.657482,23.716158,0.3320868,0.829405,13.657482,0.29982102,0.5727965,-25.750431,-183.8004,-229.72314,69.86309,-88.74044,477.1764,1055000
+21.416359,8.353473,0.34846574,0.62861985,21.416359,0.2970963,1.5916814,-0.31690782,-179.28369,-241.21725,138.30057,-107.56312,613.65784,1060000
+29.769287,10.541379,0.35934842,0.6658361,29.769287,0.330449,0.5405171,-5.581058,-182.85971,-242.58641,152.22015,-81.910286,529.5362,1065000
+14.63911,9.89299,0.33380452,0.595136,14.63911,0.34842813,0.6408578,-0.029596537,-183.65349,-215.91214,101.06556,-245.21979,586.06934,1070000
+12.340368,10.035977,0.3735487,0.7486441,12.340368,0.31791633,0.56739646,-2.7626498,-181.38518,-243.17813,60.839134,-31.379873,346.2285,1075000
+29.882633,13.353261,0.41260138,0.85640496,29.882633,0.3271941,0.52986705,-3.6815717,-175.76323,-210.29358,70.15005,-68.626114,459.96823,1080000
+25.84067,11.738569,0.3286868,0.66391444,25.84067,0.3241409,0.5823158,-13.842867,-186.44041,-217.53653,135.52625,-101.37656,681.5165,1085000
+30.472893,7.412045,0.36646515,0.6480667,30.472893,0.29729736,0.57122034,-42.229767,-183.13927,-214.77426,43.325333,-72.6287,455.38538,1090000
+15.897087,6.3140616,0.35554844,0.616488,15.897087,0.3063251,0.5276074,1.2722588,-182.82104,-216.59981,155.62808,-355.94086,746.6685,1095000
+14.028766,17.65521,0.34596288,0.7612587,14.028766,0.3213874,0.4857788,0.50748515,-182.57156,-217.6493,52.514763,-56.155983,465.3156,1100000
+16.291506,6.0247154,0.32666558,0.5558027,16.291506,0.33129942,0.4496606,0.6241641,-180.57852,-218.6231,47.056576,-68.312805,345.5179,1105000
+20.290005,36.43933,0.40376484,1.3337495,20.290005,0.2801852,0.46784058,-31.905931,-184.85036,-247.73967,40.02464,-55.245506,400.8574,1110000
+16.596333,7.155184,0.34728014,0.6782782,16.596333,0.29963773,0.65491396,0.04477179,-184.88615,-227.36504,79.7715,-92.997574,468.56595,1115000
+12.535835,9.832299,0.3229167,0.5760439,12.535835,0.30520743,0.30024067,-0.21333939,-184.0074,-235.88007,131.68265,-53.168385,421.17908,1120000
+15.379259,9.305651,0.31364056,0.6300923,15.379259,0.33606043,0.37696406,0.43032393,-184.18413,-216.20503,75.226425,-30.31501,343.60626,1125000
+13.481331,6.0918145,0.35206762,0.57484186,13.481331,0.31078857,0.28067526,-13.808331,-183.0722,-213.67708,70.16901,-56.642357,403.0075,1130000
+14.922014,8.274178,0.28190285,0.5163147,14.922014,0.32283276,0.4263737,0.9136236,-185.41467,-228.39368,55.737946,-82.610565,403.80878,1135000
+12.16106,7.1964984,0.30565405,0.6225388,12.16106,0.30780596,0.3451464,-21.301641,-188.126,-216.10445,70.48531,-47.8823,319.8745,1140000
+25.471931,6.1386094,0.30614167,0.5343747,25.471931,0.33366808,0.6308348,-19.081953,-186.6132,-215.82909,68.08215,-73.287735,464.3027,1145000
+18.954712,8.462196,0.34091425,0.63383764,18.954712,0.28429505,0.5329025,-8.995345,-182.13493,-215.11855,312.53094,-98.32494,674.5254,1150000
+18.140375,4.919292,0.3524487,0.57930684,18.140375,0.35780293,0.6353864,-1.1995256,-181.17143,-212.94284,93.65059,-87.97777,432.443,1155000
+15.966945,7.8517284,0.32145253,0.59186524,15.966945,0.32066122,0.42372915,-1.0478891,-181.90688,-221.0673,59.99327,-67.633896,427.71747,1160000
+12.923611,8.518557,0.31458658,0.5490157,12.923611,0.3201511,0.42256624,-62.668854,-187.38966,-219.89618,89.17146,-74.894936,487.02573,1165000
+29.555801,34.936035,0.37514448,1.3123826,29.555801,0.3144738,0.43218938,-14.916834,-184.65134,-220.23103,73.0833,-260.21255,635.71204,1170000
+30.32085,5.969478,0.3285113,0.58654666,30.32085,0.2537669,0.43260136,-30.356998,-184.52982,-229.27657,161.89915,-40.958138,461.45715,1175000
+10.118337,6.320225,0.2874899,0.4989346,10.118337,0.33768386,0.36697298,0.3398274,-186.2933,-221.62694,109.95787,-112.94728,428.4461,1180000
+17.083458,5.02156,0.3507874,0.5686232,17.083458,0.30489558,0.5013861,-0.28114885,-181.3412,-213.98462,56.857845,-88.99782,445.01025,1185000
+168.97968,15.306919,0.3615598,0.8083539,168.97968,0.28808025,0.4639538,-3.8093126,-182.14647,-227.8758,388.2574,-169.77766,1220.493,1190000
+10.806854,5.2022505,0.3411954,0.5833473,10.806854,0.31253248,0.4853674,0.14356866,-182.4954,-213.80043,75.95372,-65.23794,355.8175,1195000
+22.141043,10.516785,0.32176378,0.60784346,22.141043,0.30945054,0.43209845,-20.795673,-182.90334,-222.3326,70.28011,-68.69677,445.1262,1200000
+13.647072,7.5877376,0.30893993,0.5851014,13.647072,0.30247316,0.26782718,-11.162057,-188.54237,-216.52267,66.43909,-31.074429,341.09445,1205000
+37.542717,39.24818,0.36101007,1.4705321,37.542717,0.30185318,0.38262254,-44.67371,-187.37608,-219.87102,125.43291,-128.91862,670.2919,1210000
+20.584332,5.0214167,0.31887084,0.55071986,20.584332,0.32591122,0.2729952,-0.07246941,-182.51007,-213.92584,139.48172,-354.00806,718.0958,1215000
+66.777,7.142926,0.30580643,0.55286163,66.777,0.32701597,0.54702467,0.23991957,-184.03279,-218.26944,154.66942,-60.58427,576.0208,1220000
+18.085506,15.918454,0.32842448,0.70566976,18.085506,0.32219893,0.2869564,-22.700066,-182.8308,-213.17133,150.9607,-75.04132,462.45255,1225000
+17.593887,7.376939,0.34105557,0.63345003,17.593887,0.31266233,0.38191614,-11.220416,-184.13736,-217.74976,41.46572,-48.687378,373.81918,1230000
+19.836088,5.3651547,0.31242713,0.5317687,19.836088,0.3081095,0.2624081,-0.75170267,-182.4605,-213.63768,87.0441,-88.22236,437.94925,1235000
+14.6916065,19.090355,0.3315824,0.7675895,14.6916065,0.34110832,0.78481,-13.548358,-184.54044,-215.27446,74.79843,-48.081123,453.32336,1240000
+11.209528,5.471487,0.30930525,0.5633294,11.209528,0.2829033,0.26608625,-31.222692,-184.98907,-209.43152,56.973,-50.65328,330.03085,1245000
+31.261059,7.4897795,0.33592826,0.6514533,31.261059,0.32126933,0.70769805,0.37612018,-185.07817,-222.44456,121.47479,-111.38093,531.4182,1250000
+36.666336,9.076302,0.37225357,0.7251306,36.666336,0.32738066,0.30703816,0.20506671,-183.48882,-223.8218,85.80101,-40.42286,447.8244,1255000
+14.498391,8.684569,0.3255802,0.6556363,14.498391,0.32690144,0.3674905,-7.887602,-184.65245,-215.43968,40.91001,-44.553154,324.81842,1260000
+12.259519,9.206425,0.31041676,0.6293573,12.259519,0.3135695,0.25271884,0.96566975,-186.14854,-215.9873,57.599556,-51.56013,366.48264,1265000
+14.821642,7.2624273,0.32846597,0.6401922,14.821642,0.26859954,0.6235196,-0.087198615,-182.65471,-228.94173,123.053406,-128.6114,502.86066,1270000
+45.37641,5.228051,0.27363032,0.5291713,45.37641,0.34201604,0.27901164,0.4522846,-184.56932,-216.52185,607.016,-329.84216,1295.4716,1275000
+13.830396,7.5753546,0.33087286,0.6036207,13.830396,0.35055554,0.3239258,-7.787829,-183.0777,-232.62637,98.534805,-41.95128,435.9839,1280000
+10.512142,7.9324594,0.32713467,0.655118,10.512142,0.30432773,0.48994216,-13.409731,-182.65547,-215.95248,35.502228,-46.605743,330.7043,1285000
+13.107204,8.150488,0.3107118,0.6365322,13.107204,0.33530167,0.55652946,-1.2724557,-183.52931,-210.11703,68.37543,-75.14431,378.16812,1290000
+12.711788,6.0925784,0.32330817,0.57618165,12.711788,0.32121193,0.5569554,-0.092135966,-184.77875,-214.51068,64.610344,-59.027622,343.88586,1295000
+12.227438,6.529626,0.32862312,0.64211434,12.227438,0.30459228,0.43441388,0.4453172,-183.91982,-211.2322,53.33441,-50.202557,365.70615,1300000
+11.601817,8.976908,0.3281695,0.65074986,11.601817,0.27480704,0.60349923,-11.620761,-181.26237,-215.82117,115.028824,-45.40245,428.47757,1305000
+52.859436,12.607095,0.34281632,0.70169234,52.859436,0.32563856,0.41367432,-8.9594555,-181.86327,-218.85913,56.807884,-228.45091,652.47174,1310000
+11.841673,6.643626,0.26354337,0.4736531,11.841673,0.30915594,0.35432076,1.9066998,-185.1726,-215.87059,56.24797,-32.087276,335.14978,1315000
+10.149202,5.766963,0.30197108,0.5200353,10.149202,0.29105428,0.51526576,-67.72894,-186.41441,-217.7873,54.00697,-36.473976,320.1126,1320000
+10.785681,5.2475586,0.2700932,0.48343682,10.785681,0.2898029,0.36574623,-16.264412,-186.07072,-218.74672,32.852238,-53.31714,277.38824,1325000
+16.924854,9.218929,0.3271064,0.69046307,16.924854,0.3282594,0.40838337,-3.9991322,-185.99258,-225.5655,120.93822,-80.69233,525.23254,1330000
+13.451216,6.7471495,0.33830327,0.61722165,13.451216,0.33226615,0.6335129,-13.887289,-182.64702,-240.83119,85.40263,-96.415016,411.25684,1335000
+11.365493,8.008421,0.28518766,0.53874254,11.365493,0.3436424,0.40826783,0.38426855,-185.07738,-220.54907,39.77639,-38.38089,334.9564,1340000
+10.857212,7.1819725,0.34297913,0.63187885,10.857212,0.30612934,0.47490785,-13.192123,-183.85364,-216.7325,102.815575,-43.395084,420.82532,1345000
+22.841549,11.299458,0.38576236,0.7667217,22.841549,0.32530922,0.5727677,-0.6534583,-181.52094,-243.98523,94.32877,-50.067505,528.83655,1350000
+33.639015,29.4949,0.39957485,1.2377666,33.639015,0.33006865,0.67750466,-0.24865934,-182.90112,-248.31511,259.4879,-55.521263,750.9992,1355000
+17.56464,7.8442936,0.35064635,0.62748444,17.56464,0.3173445,0.61194307,-27.774918,-181.03186,-249.46432,42.756447,-41.614643,375.88858,1360000
+13.137317,7.3573766,0.34668982,0.63728666,13.137317,0.3081681,0.32015732,-19.342752,-179.90704,-211.1674,52.994354,-179.55304,549.25964,1365000
+80.6644,13.075582,0.3132329,0.58987564,80.6644,0.30882567,0.3253904,-23.250753,-186.12741,-210.00487,190.2192,-46.46761,514.46704,1370000
+11.6653595,7.849996,0.34314725,0.63337564,11.6653595,0.32924524,0.41308022,-20.694633,-182.22055,-231.86967,37.116524,-48.813225,306.91907,1375000
+17.81585,30.598305,0.34846592,1.0720116,17.81585,0.28155443,0.6079333,0.09382215,-184.10023,-217.11693,41.487553,-64.44055,386.8072,1380000
+21.293724,8.471132,0.2656474,0.5431505,21.293724,0.30403382,0.2860702,-36.802944,-189.39241,-253.78905,67.019424,-97.1989,438.64532,1385000
+16.581455,6.206217,0.28355008,0.5233412,16.581455,0.26010418,0.42486987,-2.481328,-185.73575,-256.5416,54.618473,-165.46957,486.35855,1390000
+57.704185,8.513565,0.31737068,0.57750255,57.704185,0.29792583,0.34011966,-3.59307,-187.57578,-219.49759,101.563,-87.14716,583.1011,1395000
+14.913715,8.174233,0.2740499,0.5085121,14.913715,0.2924654,0.47413608,-26.628668,-189.26021,-262.4284,49.08449,-160.84073,460.10638,1400000

O2O-w-diff-ckpts/qam/20260317_150042/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
+22.835407,8.511239,0.39365506,0.6550111,22.835407,0.34972313,0.6316496,-6.0765314,-177.08235,-218.64362,56.264633,-49.415604,420.18262,905000
+21.356115,8.32028,0.43633848,0.6594407,21.356115,0.3004384,0.48495445,-8.77516,-174.09897,-217.68672,81.54497,-69.26502,451.771,910000
+17.918793,6.8630924,0.38984013,0.58654094,17.918793,0.37087047,0.275096,-11.250025,-180.15326,-218.82784,70.320786,-74.356285,403.90073,915000
+76.093025,6.8189487,0.4058724,0.6534967,76.093025,0.27867323,0.46033946,-20.337324,-178.87329,-212.88301,95.22159,-119.152466,545.9765,920000
+36.573784,10.187702,0.43530124,0.68605477,36.573784,0.33265457,0.47510216,-0.20183563,-176.7075,-217.28275,108.13359,-36.102444,476.93823,925000
+23.739586,12.092998,0.38881013,0.6701087,23.739586,0.28032026,0.38848463,0.29345983,-176.55502,-219.6122,87.06654,-102.79474,521.54333,930000
+29.604918,12.90099,0.42391646,0.7840348,29.604918,0.33536404,0.5071199,0.5663998,-175.98009,-218.86507,62.24495,-108.067856,508.48636,935000
+16.965748,8.471491,0.3697011,0.60423625,16.965748,0.35419714,0.439607,-7.551371,-176.0836,-218.56293,39.378418,-49.246895,336.40793,940000
+24.515003,6.1301785,0.3952521,0.64249414,24.515003,0.3281726,0.4234766,-9.65856,-178.76822,-234.4408,45.296986,-101.2582,472.6004,945000
+18.199127,6.692951,0.36965913,0.54849625,18.199127,0.35148585,0.29168043,0.2539107,-178.73459,-214.66176,41.756058,-32.270874,316.86453,950000
+19.048138,7.9595346,0.39431697,0.617569,19.048138,0.31676024,0.8811783,0.7826824,-176.79915,-236.0529,42.107605,-68.77712,448.8509,955000
+13.871018,6.703974,0.369658,0.60086113,13.871018,0.28553432,0.5465457,-41.103703,-180.39151,-222.74693,88.64378,-89.72753,472.55038,960000
+14.428338,7.603917,0.36709195,0.5632191,14.428338,0.3692674,0.22136155,-17.919914,-182.78627,-218.49414,31.36073,-41.211372,294.1651,965000
+32.997547,6.057873,0.3983819,0.6542174,32.997547,0.30224642,0.46152145,-19.258276,-180.02843,-214.00238,87.88392,-83.52063,467.17725,970000
+14.222685,8.15564,0.35046405,0.62947637,14.222685,0.28236896,0.4654418,0.18943918,-183.16815,-216.33769,71.61654,-69.44144,381.7097,975000
+31.434656,11.75277,0.42529303,0.85312474,31.434656,0.34064728,0.5013778,-8.487129,-180.47072,-217.47873,160.99577,-517.8726,940.2193,980000
+17.172024,7.0743704,0.3290744,0.50630563,17.172024,0.28992444,0.4469764,-11.262733,-183.67796,-217.46143,51.076096,-48.34163,397.65088,985000
+22.612955,4.472224,0.35179937,0.5260064,22.612955,0.34766054,0.53232574,-20.762653,-180.70712,-225.60464,53.913757,-69.83993,371.35162,990000
+19.28028,17.788847,0.4287244,0.9093447,19.28028,0.32097888,0.50197995,1.7032609,-177.40363,-216.83905,152.20927,-238.99962,649.96936,995000
+18.945301,7.2800655,0.37206978,0.5958906,18.945301,0.2679817,0.677381,-4.1866226,-179.61003,-221.82353,93.03513,-66.1432,424.9807,1000000
+19.608763,6.531781,0.38849574,0.63783,19.608763,0.28570125,0.38984933,-19.983541,-183.61801,-234.69554,115.00366,-59.843975,410.9016,1005000
+21.656372,11.225064,0.38803375,0.72674716,21.656372,0.26186568,0.38160044,-15.8937435,-179.90686,-220.39714,391.554,-162.49884,810.2436,1010000
+17.9413,6.527192,0.3330717,0.5234036,17.9413,0.32056275,0.3069757,-16.775856,-186.03035,-216.85452,57.69681,-90.63091,470.03833,1015000
+13.837907,6.757672,0.32589474,0.56626135,13.837907,0.3098085,0.48414356,-22.565886,-184.64786,-226.55962,45.5774,-46.380104,345.2802,1020000
+15.204688,6.7713146,0.37600017,0.6473243,15.204688,0.3233288,0.46718636,-19.147837,-182.42151,-235.89117,92.38836,-99.806305,431.89102,1025000
+15.408054,5.4021983,0.36845663,0.5875465,15.408054,0.30759513,1.373556,-1.7774721,-182.21777,-237.67819,77.64124,-77.24196,630.9007,1030000
+18.580633,7.7278776,0.36045632,0.628892,18.580633,0.3153962,0.51387215,-4.964365,-183.28542,-226.98586,129.42165,-98.449005,461.25253,1035000
+35.3056,9.226419,0.32849455,0.5877052,35.3056,0.26657575,0.5569667,-11.634139,-185.33968,-239.56093,90.01409,-57.5781,542.866,1040000
+17.039957,17.362936,0.36571217,0.7221856,17.039957,0.30902523,0.376863,-19.59161,-179.42804,-211.76846,123.88394,-121.191475,478.72498,1045000
+39.058918,6.0346684,0.2953408,0.4750311,39.058918,0.32520103,0.21926318,-22.444546,-185.6895,-235.324,51.409767,-78.483765,377.49738,1050000
+13.657482,23.716158,0.3320868,0.829405,13.657482,0.29982102,0.5727965,-25.750431,-183.8004,-229.72314,69.86309,-88.74044,477.1764,1055000
+21.416359,8.353473,0.34846574,0.62861985,21.416359,0.2970963,1.5916814,-0.31690782,-179.28369,-241.21725,138.30057,-107.56312,613.65784,1060000
+29.769287,10.541379,0.35934842,0.6658361,29.769287,0.330449,0.5405171,-5.581058,-182.85971,-242.58641,152.22015,-81.910286,529.5362,1065000
+14.63911,9.89299,0.33380452,0.595136,14.63911,0.34842813,0.6408578,-0.029596537,-183.65349,-215.91214,101.06556,-245.21979,586.06934,1070000
+12.340368,10.035977,0.3735487,0.7486441,12.340368,0.31791633,0.56739646,-2.7626498,-181.38518,-243.17813,60.839134,-31.379873,346.2285,1075000
+29.882633,13.353261,0.41260138,0.85640496,29.882633,0.3271941,0.52986705,-3.6815717,-175.76323,-210.29358,70.15005,-68.626114,459.96823,1080000
+25.84067,11.738569,0.3286868,0.66391444,25.84067,0.3241409,0.5823158,-13.842867,-186.44041,-217.53653,135.52625,-101.37656,681.5165,1085000
+30.472893,7.412045,0.36646515,0.6480667,30.472893,0.29729736,0.57122034,-42.229767,-183.13927,-214.77426,43.325333,-72.6287,455.38538,1090000
+15.897087,6.3140616,0.35554844,0.616488,15.897087,0.3063251,0.5276074,1.2722588,-182.82104,-216.59981,155.62808,-355.94086,746.6685,1095000
+14.028766,17.65521,0.34596288,0.7612587,14.028766,0.3213874,0.4857788,0.50748515,-182.57156,-217.6493,52.514763,-56.155983,465.3156,1100000
+16.291506,6.0247154,0.32666558,0.5558027,16.291506,0.33129942,0.4496606,0.6241641,-180.57852,-218.6231,47.056576,-68.312805,345.5179,1105000
+20.290005,36.43933,0.40376484,1.3337495,20.290005,0.2801852,0.46784058,-31.905931,-184.85036,-247.73967,40.02464,-55.245506,400.8574,1110000
+16.596333,7.155184,0.34728014,0.6782782,16.596333,0.29963773,0.65491396,0.04477179,-184.88615,-227.36504,79.7715,-92.997574,468.56595,1115000
+12.535835,9.832299,0.3229167,0.5760439,12.535835,0.30520743,0.30024067,-0.21333939,-184.0074,-235.88007,131.68265,-53.168385,421.17908,1120000
+15.379259,9.305651,0.31364056,0.6300923,15.379259,0.33606043,0.37696406,0.43032393,-184.18413,-216.20503,75.226425,-30.31501,343.60626,1125000
+13.481331,6.0918145,0.35206762,0.57484186,13.481331,0.31078857,0.28067526,-13.808331,-183.0722,-213.67708,70.16901,-56.642357,403.0075,1130000
+14.922014,8.274178,0.28190285,0.5163147,14.922014,0.32283276,0.4263737,0.9136236,-185.41467,-228.39368,55.737946,-82.610565,403.80878,1135000
+12.16106,7.1964984,0.30565405,0.6225388,12.16106,0.30780596,0.3451464,-21.301641,-188.126,-216.10445,70.48531,-47.8823,319.8745,1140000
+25.471931,6.1386094,0.30614167,0.5343747,25.471931,0.33366808,0.6308348,-19.081953,-186.6132,-215.82909,68.08215,-73.287735,464.3027,1145000
+18.954712,8.462196,0.34091425,0.63383764,18.954712,0.28429505,0.5329025,-8.995345,-182.13493,-215.11855,312.53094,-98.32494,674.5254,1150000
+18.140375,4.919292,0.3524487,0.57930684,18.140375,0.35780293,0.6353864,-1.1995256,-181.17143,-212.94284,93.65059,-87.97777,432.443,1155000
+15.966945,7.8517284,0.32145253,0.59186524,15.966945,0.32066122,0.42372915,-1.0478891,-181.90688,-221.0673,59.99327,-67.633896,427.71747,1160000
+12.923611,8.518557,0.31458658,0.5490157,12.923611,0.3201511,0.42256624,-62.668854,-187.38966,-219.89618,89.17146,-74.894936,487.02573,1165000
+29.555801,34.936035,0.37514448,1.3123826,29.555801,0.3144738,0.43218938,-14.916834,-184.65134,-220.23103,73.0833,-260.21255,635.71204,1170000
+30.32085,5.969478,0.3285113,0.58654666,30.32085,0.2537669,0.43260136,-30.356998,-184.52982,-229.27657,161.89915,-40.958138,461.45715,1175000
+10.118337,6.320225,0.2874899,0.4989346,10.118337,0.33768386,0.36697298,0.3398274,-186.2933,-221.62694,109.95787,-112.94728,428.4461,1180000
+17.083458,5.02156,0.3507874,0.5686232,17.083458,0.30489558,0.5013861,-0.28114885,-181.3412,-213.98462,56.857845,-88.99782,445.01025,1185000
+168.97968,15.306919,0.3615598,0.8083539,168.97968,0.28808025,0.4639538,-3.8093126,-182.14647,-227.8758,388.2574,-169.77766,1220.493,1190000
+10.806854,5.2022505,0.3411954,0.5833473,10.806854,0.31253248,0.4853674,0.14356866,-182.4954,-213.80043,75.95372,-65.23794,355.8175,1195000
+22.141043,10.516785,0.32176378,0.60784346,22.141043,0.30945054,0.43209845,-20.795673,-182.90334,-222.3326,70.28011,-68.69677,445.1262,1200000
+13.647072,7.5877376,0.30893993,0.5851014,13.647072,0.30247316,0.26782718,-11.162057,-188.54237,-216.52267,66.43909,-31.074429,341.09445,1205000
+37.542717,39.24818,0.36101007,1.4705321,37.542717,0.30185318,0.38262254,-44.67371,-187.37608,-219.87102,125.43291,-128.91862,670.2919,1210000
+20.584332,5.0214167,0.31887084,0.55071986,20.584332,0.32591122,0.2729952,-0.07246941,-182.51007,-213.92584,139.48172,-354.00806,718.0958,1215000
+66.777,7.142926,0.30580643,0.55286163,66.777,0.32701597,0.54702467,0.23991957,-184.03279,-218.26944,154.66942,-60.58427,576.0208,1220000
+18.085506,15.918454,0.32842448,0.70566976,18.085506,0.32219893,0.2869564,-22.700066,-182.8308,-213.17133,150.9607,-75.04132,462.45255,1225000
+17.593887,7.376939,0.34105557,0.63345003,17.593887,0.31266233,0.38191614,-11.220416,-184.13736,-217.74976,41.46572,-48.687378,373.81918,1230000
+19.836088,5.3651547,0.31242713,0.5317687,19.836088,0.3081095,0.2624081,-0.75170267,-182.4605,-213.63768,87.0441,-88.22236,437.94925,1235000
+14.6916065,19.090355,0.3315824,0.7675895,14.6916065,0.34110832,0.78481,-13.548358,-184.54044,-215.27446,74.79843,-48.081123,453.32336,1240000
+11.209528,5.471487,0.30930525,0.5633294,11.209528,0.2829033,0.26608625,-31.222692,-184.98907,-209.43152,56.973,-50.65328,330.03085,1245000
+31.261059,7.4897795,0.33592826,0.6514533,31.261059,0.32126933,0.70769805,0.37612018,-185.07817,-222.44456,121.47479,-111.38093,531.4182,1250000
+36.666336,9.076302,0.37225357,0.7251306,36.666336,0.32738066,0.30703816,0.20506671,-183.48882,-223.8218,85.80101,-40.42286,447.8244,1255000
+14.498391,8.684569,0.3255802,0.6556363,14.498391,0.32690144,0.3674905,-7.887602,-184.65245,-215.43968,40.91001,-44.553154,324.81842,1260000
+12.259519,9.206425,0.31041676,0.6293573,12.259519,0.3135695,0.25271884,0.96566975,-186.14854,-215.9873,57.599556,-51.56013,366.48264,1265000
+14.821642,7.2624273,0.32846597,0.6401922,14.821642,0.26859954,0.6235196,-0.087198615,-182.65471,-228.94173,123.053406,-128.6114,502.86066,1270000
+45.37641,5.228051,0.27363032,0.5291713,45.37641,0.34201604,0.27901164,0.4522846,-184.56932,-216.52185,607.016,-329.84216,1295.4716,1275000
+13.830396,7.5753546,0.33087286,0.6036207,13.830396,0.35055554,0.3239258,-7.787829,-183.0777,-232.62637,98.534805,-41.95128,435.9839,1280000
+10.512142,7.9324594,0.32713467,0.655118,10.512142,0.30432773,0.48994216,-13.409731,-182.65547,-215.95248,35.502228,-46.605743,330.7043,1285000
+13.107204,8.150488,0.3107118,0.6365322,13.107204,0.33530167,0.55652946,-1.2724557,-183.52931,-210.11703,68.37543,-75.14431,378.16812,1290000
+12.711788,6.0925784,0.32330817,0.57618165,12.711788,0.32121193,0.5569554,-0.092135966,-184.77875,-214.51068,64.610344,-59.027622,343.88586,1295000
+12.227438,6.529626,0.32862312,0.64211434,12.227438,0.30459228,0.43441388,0.4453172,-183.91982,-211.2322,53.33441,-50.202557,365.70615,1300000
+11.601817,8.976908,0.3281695,0.65074986,11.601817,0.27480704,0.60349923,-11.620761,-181.26237,-215.82117,115.028824,-45.40245,428.47757,1305000
+52.859436,12.607095,0.34281632,0.70169234,52.859436,0.32563856,0.41367432,-8.9594555,-181.86327,-218.85913,56.807884,-228.45091,652.47174,1310000
+11.841673,6.643626,0.26354337,0.4736531,11.841673,0.30915594,0.35432076,1.9066998,-185.1726,-215.87059,56.24797,-32.087276,335.14978,1315000
+10.149202,5.766963,0.30197108,0.5200353,10.149202,0.29105428,0.51526576,-67.72894,-186.41441,-217.7873,54.00697,-36.473976,320.1126,1320000
+10.785681,5.2475586,0.2700932,0.48343682,10.785681,0.2898029,0.36574623,-16.264412,-186.07072,-218.74672,32.852238,-53.31714,277.38824,1325000
+16.924854,9.218929,0.3271064,0.69046307,16.924854,0.3282594,0.40838337,-3.9991322,-185.99258,-225.5655,120.93822,-80.69233,525.23254,1330000
+13.451216,6.7471495,0.33830327,0.61722165,13.451216,0.33226615,0.6335129,-13.887289,-182.64702,-240.83119,85.40263,-96.415016,411.25684,1335000
+11.365493,8.008421,0.28518766,0.53874254,11.365493,0.3436424,0.40826783,0.38426855,-185.07738,-220.54907,39.77639,-38.38089,334.9564,1340000
+10.857212,7.1819725,0.34297913,0.63187885,10.857212,0.30612934,0.47490785,-13.192123,-183.85364,-216.7325,102.815575,-43.395084,420.82532,1345000
+22.841549,11.299458,0.38576236,0.7667217,22.841549,0.32530922,0.5727677,-0.6534583,-181.52094,-243.98523,94.32877,-50.067505,528.83655,1350000
+33.639015,29.4949,0.39957485,1.2377666,33.639015,0.33006865,0.67750466,-0.24865934,-182.90112,-248.31511,259.4879,-55.521263,750.9992,1355000
+17.56464,7.8442936,0.35064635,0.62748444,17.56464,0.3173445,0.61194307,-27.774918,-181.03186,-249.46432,42.756447,-41.614643,375.88858,1360000
+13.137317,7.3573766,0.34668982,0.63728666,13.137317,0.3081681,0.32015732,-19.342752,-179.90704,-211.1674,52.994354,-179.55304,549.25964,1365000
+80.6644,13.075582,0.3132329,0.58987564,80.6644,0.30882567,0.3253904,-23.250753,-186.12741,-210.00487,190.2192,-46.46761,514.46704,1370000
+11.6653595,7.849996,0.34314725,0.63337564,11.6653595,0.32924524,0.41308022,-20.694633,-182.22055,-231.86967,37.116524,-48.813225,306.91907,1375000
+17.81585,30.598305,0.34846592,1.0720116,17.81585,0.28155443,0.6079333,0.09382215,-184.10023,-217.11693,41.487553,-64.44055,386.8072,1380000
+21.293724,8.471132,0.2656474,0.5431505,21.293724,0.30403382,0.2860702,-36.802944,-189.39241,-253.78905,67.019424,-97.1989,438.64532,1385000
+16.581455,6.206217,0.28355008,0.5233412,16.581455,0.26010418,0.42486987,-2.481328,-185.73575,-256.5416,54.618473,-165.46957,486.35855,1390000
+57.704185,8.513565,0.31737068,0.57750255,57.704185,0.29792583,0.34011966,-3.59307,-187.57578,-219.49759,101.563,-87.14716,583.1011,1395000
+14.913715,8.174233,0.2740499,0.5085121,14.913715,0.2924654,0.47413608,-26.628668,-189.26021,-262.4284,49.08449,-160.84073,460.10638,1400000

O2O-w-diff-ckpts/qam/20260317_150042/params_1000000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f702fec3c9edf4bf0fcdae727ac40917b10808212faf9ac18e783cdf7f5fdbe
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_1050000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6742a649584466b57328e70420cc2fbae5e2c2903fdd7914115b8cf248ebba04
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_1100000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63be1ee38b21fc3a05f923706085e48660b78ebe9251e248ac066d92b61fe278
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_1150000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1361678a2e3981f33a167ea0f3330af0baf1e9c2097de98b7ce715ddb867eeb0
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_1200000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c905f099ab80402a2a608b23a378a22d216f8d9bb2d7ed9b7c073a0c9265a0d1
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_1250000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afef911cac3f62962610d9a56649878e4f1f0e23effc7ce0875a78b77d67d189
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_1300000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ec789a7530ae31987e964a6b6f5d4092b1bf0c8a96efc13d56accc6b739f16
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_1350000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf636cfb5f68597a6b0d2debd935c4655d586111e9db6b15c2c51c901f7770f
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_1400000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c40cc0a2148e9593798cc549f5caebd676d6b8bb4fa4528ed4eb76da6f712d
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/params_950000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebcec184186ff899f1b365e91754af419d26101e5bc2ec1582e6132dc351152
+size 233879450

O2O-w-diff-ckpts/qam/20260317_150042/progress.tk

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

O2O-w-diff-ckpts/qam/20260317_150042/token.tk

@@ -0,0 +1 @@
+https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/62xfu3lq