Upload folder using huggingface_hub

.gitattributes

@@ -500,3 +500,9 @@ O2O-w-diff-ckpts/cgql/20260317_071429/visited_states_800000.png filter=lfs diff=
 O2O-w-diff-ckpts/cgql/20260317_071429/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/cgql/20260317_071429/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/cgql/20260317_071429/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260316_192847/visited_states_350000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260316_192847/visited_states_450000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260316_192847/visited_states_500000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260316_192847/visited_states_550000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260316_192847/visited_states_600000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260316_192847/visited_states_700000.png filter=lfs diff=lfs merge=lfs -text

O2O-w-diff-ckpts/dsrl/20260316_192847/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
+0.0,0.0,16.582969481717498,2.321768345904391,0.020387713843345017,2.3232441527593712,0.03251214780361523,0.0,25500.0,-1.0,-1000.0,1000.0,1.5797999811172485,350000
+0.0,0.0,12.874535916563962,1.792273195579855,-0.009233619718511681,1.7919610227313219,0.022667204915508096,0.0,77500.0,-1.0,-1000.0,1000.0,1.6763226509094238,400000
+0.0,0.0,11.208417572332182,1.5062350170046896,0.056845911463976974,1.50791847765252,-0.036764389762595176,0.0,129500.0,-1.0,-1000.0,1000.0,1.5680742120742799,450000
+0.0,0.0,9.589520950516158,1.2891827912804092,-0.01790928958859416,1.2926624170613068,0.07798060066445464,0.0,181500.0,-1.0,-1000.0,1000.0,1.5721551179885864,500000
+0.0,0.0,10.119087149283503,1.3800304071149416,-0.06509285446805388,1.3758302103996471,-0.009005273254545459,0.0,233500.0,-1.0,-1000.0,1000.0,1.650519471168518,550000
+0.0,0.0,9.982853856504784,1.3431695415229108,-0.012753157963639598,1.342596396645704,-0.004692087449528048,0.0,285500.0,-1.0,-1000.0,1000.0,1.5906791877746582,600000
+0.0,0.0,10.501388848633578,1.440872305364616,0.011661271952171532,1.44196981464758,0.041191229254227926,0.0,337500.0,-1.0,-1000.0,1000.0,1.5716626024246216,650000
+0.0,0.0,8.218453614055946,1.1008875561424454,0.04521989923020701,1.1024362385198638,-0.01949951218995585,0.0,389500.0,-1.0,-1000.0,1000.0,1.5673666572570801,700000
+0.0,0.0,9.347504229612603,1.2819998674203184,0.03714144561072738,1.284710468302016,0.02938987171254286,0.0,441500.0,-1.0,-1000.0,1000.0,1.5830374956130981,750000
+0.0,0.0,8.312570042088637,1.1304527797154926,-0.0472585937254376,1.1290187846857263,0.0312225772418081,0.0,493500.0,-1.0,-1000.0,1000.0,1.5578750944137574,800000

O2O-w-diff-ckpts/dsrl/20260316_192847/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
+0.0,0.0,16.582969481717498,2.321768345904391,0.020387713843345017,2.3232441527593712,0.03251214780361523,0.0,25500.0,-1.0,-1000.0,1000.0,1.5797999811172485,350000
+0.0,0.0,12.874535916563962,1.792273195579855,-0.009233619718511681,1.7919610227313219,0.022667204915508096,0.0,77500.0,-1.0,-1000.0,1000.0,1.6763226509094238,400000
+0.0,0.0,11.208417572332182,1.5062350170046896,0.056845911463976974,1.50791847765252,-0.036764389762595176,0.0,129500.0,-1.0,-1000.0,1000.0,1.5680742120742799,450000
+0.0,0.0,9.589520950516158,1.2891827912804092,-0.01790928958859416,1.2926624170613068,0.07798060066445464,0.0,181500.0,-1.0,-1000.0,1000.0,1.5721551179885864,500000
+0.0,0.0,10.119087149283503,1.3800304071149416,-0.06509285446805388,1.3758302103996471,-0.009005273254545459,0.0,233500.0,-1.0,-1000.0,1000.0,1.650519471168518,550000
+0.0,0.0,9.982853856504784,1.3431695415229108,-0.012753157963639598,1.342596396645704,-0.004692087449528048,0.0,285500.0,-1.0,-1000.0,1000.0,1.5906791877746582,600000
+0.0,0.0,10.501388848633578,1.440872305364616,0.011661271952171532,1.44196981464758,0.041191229254227926,0.0,337500.0,-1.0,-1000.0,1000.0,1.5716626024246216,650000
+0.0,0.0,8.218453614055946,1.1008875561424454,0.04521989923020701,1.1024362385198638,-0.01949951218995585,0.0,389500.0,-1.0,-1000.0,1000.0,1.5673666572570801,700000
+0.0,0.0,9.347504229612603,1.2819998674203184,0.03714144561072738,1.284710468302016,0.02938987171254286,0.0,441500.0,-1.0,-1000.0,1000.0,1.5830374956130981,750000
+0.0,0.0,8.312570042088637,1.1304527797154926,-0.0472585937254376,1.1290187846857263,0.0312225772418081,0.0,493500.0,-1.0,-1000.0,1000.0,1.5578750944137574,800000

O2O-w-diff-ckpts/dsrl/20260316_192847/online_agent.csv

@@ -0,0 +1,101 @@
+actor/action_std,actor/actor_loss,actor/alpha,actor/alpha_loss,actor/entropy,actor/flow_loss,actor/q,actor/total_loss,critic/critic_loss,critic/distill_loss,critic/q_max,critic/q_mean,critic/q_min,critic/total_loss,grad/max,grad/min,grad/norm,step
+0.65190405,165.8779,0.005302432,0.0017743882,-3.6653633,0.28544554,-165.85846,166.16512,0.7866831,1.1567634,-3.4438224,-165.79944,-322.15024,1.9434465,6.1900234,-5.412445,86.13,305000
+0.6378956,163.31241,0.0054098475,-0.0018684831,-4.3453856,0.3041193,-163.28891,163.61467,1.8849125,2.3143818,-3.319524,-163.61133,-365.69174,4.199294,73.73241,-21.313492,253.08263,310000
+0.63433164,170.46149,0.0055153426,-0.0049109105,-4.890409,0.3122282,-170.43451,170.7688,0.6778327,1.6790257,-1.889926,-170.57523,-318.66837,2.3568583,37.362934,-49.788803,212.75179,315000
+0.64605355,169.47502,0.0052787564,0.0035873775,-3.3204124,0.31294182,-169.45749,169.79155,0.80688334,0.99739724,-19.813538,-169.7721,-279.91458,1.8042805,4.1256504,-4.661874,80.2821,320000
+0.64738476,171.67744,0.005163804,0.0013074558,-3.7468038,0.30775702,-171.65811,171.98651,1.6609195,1.902367,2.778079,-171.80374,-651.5815,3.5632865,7.888319,-7.868909,151.31097,325000
+0.64587367,168.75636,0.0050593386,-0.00013580336,-4.026842,0.2956421,-168.736,169.05186,1.0101393,1.8425789,0.23597738,-168.91528,-316.3651,2.8527184,15.016986,-15.851705,141.45242,330000
+0.65176797,169.6677,0.004962684,0.0007392349,-3.8510413,0.3125143,-169.64859,169.98094,1.9716122,4.065412,0.71186745,-169.93071,-320.58405,6.0370245,11.848728,-22.302162,264.85007,335000
+0.6442949,168.97388,0.0050886525,-0.0028927317,-4.568467,0.28675508,-168.95062,169.25774,3.0748549,5.618911,0.58771896,-169.40147,-304.63766,8.693766,18.85864,-22.966904,354.73035,340000
+0.63992715,171.41608,0.004953705,-0.00045854942,-4.092567,0.337938,-171.39581,171.75356,0.7760425,1.3038918,-5.2465277,-171.63255,-288.2562,2.0799344,2.874102,-2.4000344,81.60121,345000
+0.6403782,176.4986,0.0051468667,-0.0001342506,-4.026084,0.34986028,-176.4779,176.84831,2.7719343,21.10802,-1.6105424,-177.00224,-769.00555,23.879955,246.3798,-285.17355,1978.1866,350000
+0.62867856,174.9358,0.0053532342,-0.004113845,-4.7684784,0.31304416,-174.91028,175.24474,0.82374495,1.9332955,1.2968588,-175.25064,-786.87854,2.7570405,14.721909,-18.107378,165.85896,355000
+0.6457268,176.78474,0.005494249,0.0011605216,-3.7887752,0.37760848,-176.76392,177.16351,1.1304549,2.2559013,-37.45145,-176.83305,-813.0693,3.3863564,13.776581,-7.081804,143.85248,360000
+0.645025,174.46274,0.004972166,0.001095311,-3.7797115,0.29927447,-174.44394,174.7631,1.3120044,1.2846364,-7.155112,-174.4691,-240.24321,2.5966408,6.852143,-10.2877445,132.24713,365000
+0.65178084,180.5452,0.005203607,0.00017423376,-3.9665167,0.33193058,-180.52455,180.87729,0.61688274,2.1168735,-9.416031,-180.71063,-840.5523,2.7337563,16.301863,-9.559705,150.37427,370000
+0.64879537,180.2057,0.005286353,-0.0023922278,-4.452529,0.34860232,-180.18216,180.55191,1.1693782,2.700391,1.0994608,-180.59352,-669.6207,3.869769,8.279745,-9.526651,133.10092,375000
+0.6495932,177.26672,0.0053756344,0.0009267645,-3.827599,0.32942683,-177.24615,177.59708,9.3274555,7.4802895,-0.9111727,-177.08897,-655.4023,16.807745,438.56195,-285.98892,1987.0864,380000
+0.63780284,186.99294,0.0051468764,-0.004947272,-4.9612184,0.3427367,-186.9674,187.33073,1.6237414,2.0167031,-0.55932796,-187.15385,-932.8465,3.6404445,6.279961,-11.198244,141.71144,385000
+0.64054155,177.08572,0.0049123457,-0.0020270143,-4.4126368,0.3343872,-177.06404,177.41808,1.430576,2.2725015,-17.703533,-177.13933,-307.47885,3.7030773,11.804242,-3.9012566,123.61615,390000
+0.64635074,178.09996,0.0054569277,-0.0041559287,-4.7615876,0.34797826,-178.07397,178.44379,2.1158044,3.81694,4.977904,-178.12962,-998.8338,5.9327445,34.01505,-21.431986,269.0889,395000
+0.63640136,177.5755,0.005041929,-0.0012072441,-4.239441,0.293699,-177.55411,177.868,1.2450598,1.7738285,-2.3227887,-177.68172,-311.23343,3.0188885,5.7544103,-4.639542,98.16675,400000
+0.63562787,181.96344,0.0049036886,-0.0012038958,-4.245508,0.34957653,-181.94261,182.31181,1.5112237,2.3369863,-5.0396757,-182.29256,-697.7353,3.8482099,6.8428884,-9.088067,127.45903,405000
+0.6292087,181.9704,0.0048866533,-0.0014900509,-4.3049226,0.32482052,-181.94934,182.29372,0.9736924,1.3162382,-6.185815,-182.11197,-1050.4877,2.2899306,9.106683,-12.61252,154.59804,410000
+0.6535957,184.828,0.004834411,0.003963552,-3.1801376,0.32328567,-184.81262,185.15526,0.9190155,1.4203008,-1.6724339,-184.87962,-305.55872,2.3393164,2.1117744,-3.0158558,77.681625,415000
+0.6411215,183.063,0.004925809,-0.0012017586,-4.243972,0.28162596,-183.04211,183.34343,0.8403303,1.3052429,-13.97532,-183.42091,-540.75946,2.1455731,7.1845493,-13.106476,110.78599,420000
+0.6435565,180.78558,0.0047628433,-0.00083702325,-4.1757402,0.3046242,-180.76569,181.08937,1.7104224,1.329995,-34.374718,-181.27576,-335.86386,3.0404174,5.5545864,-3.7106087,86.39929,425000
+0.6444941,180.95488,0.0046603167,-0.00021491013,-4.046115,0.31659165,-180.93602,181.27126,32.935593,36.163853,-9.417093,-181.4055,-583.28143,69.09944,348.05338,-404.55872,2331.506,430000
+0.65019476,187.31876,0.004874008,0.002689136,-3.44827,0.29710224,-187.30196,187.61855,0.8735499,1.981348,-75.35665,-187.39883,-1128.6993,2.854898,6.526506,-6.255607,105.256226,435000
+0.6439402,184.1926,0.0045220884,-0.0011690336,-4.2585163,0.29848394,-184.17334,184.4899,1.1092217,1.9407688,-7.455441,-184.46265,-437.99326,3.0499907,5.0093594,-7.120329,123.33768,440000
+0.6400594,177.54588,0.0045237946,-0.0005259862,-4.116271,0.32032496,-177.52727,177.86569,0.8080805,1.053423,-2.3266203,-177.99896,-626.55133,1.8615036,3.7874908,-3.112287,72.17585,445000
+0.64976835,182.66797,0.0044793366,0.0027541812,-3.3851364,0.31622052,-182.6528,182.98694,0.7899103,0.8913302,-13.10727,-182.76973,-254.09056,1.6812406,2.417381,-1.7537684,53.46707,450000
+0.6517472,185.31776,0.0044912836,0.0017715641,-3.605555,0.30971137,-185.30156,185.62924,2.306048,6.6643686,-4.8946505,-185.33716,-643.0832,8.970417,38.67115,-22.184374,356.81088,455000
+0.6437141,176.71893,0.004214192,0.0007679291,-3.8177755,0.30903578,-176.70284,177.02873,1.8595362,2.4169526,-0.5466883,-177.05545,-313.76663,4.276489,24.851908,-12.66319,209.495,460000
+0.65486944,191.11435,0.0041868775,0.003729888,-3.109148,0.3064775,-191.10132,191.42455,0.76095265,1.2447213,-41.266422,-191.56325,-1185.1459,2.005674,3.130833,-2.1435974,85.250305,465000
+0.6416023,186.42433,0.0044340966,0.0013370095,-3.6984708,0.29272777,-186.40793,186.7184,1.2862681,1.5518125,-0.33411595,-186.72392,-1229.379,2.8380806,8.300149,-19.548836,143.96228,470000
+0.6464348,181.34073,0.00429143,0.0003798019,-3.9114976,0.27626824,-181.32394,181.61739,0.84046745,1.0018212,-30.859097,-181.60962,-276.80057,1.8422886,3.6386416,-3.2182314,69.16331,475000
+0.6424699,179.88107,0.004367166,-0.00056909816,-4.130313,0.32520664,-179.86304,180.20572,1.0176531,1.3734155,-0.50975794,-180.22966,-566.0318,2.3910685,4.2157536,-3.5694993,80.56244,480000
+0.6480551,189.50952,0.004139514,0.0006171604,-3.85091,0.26887426,-189.49359,189.779,3.7049406,4.2353153,-2.2075944,-189.80411,-1320.0867,7.940256,38.343468,-22.935806,432.45898,485000
+0.632545,181.39323,0.0044296044,-0.0018557451,-4.4189415,0.29798794,-181.37366,181.68936,1.628032,2.760862,-50.7757,-181.49918,-307.6623,4.388894,13.216695,-10.386584,144.47832,490000
+0.6548782,190.01686,0.004339003,1.0762927e-05,-3.9975195,0.30356777,-189.99953,190.32045,0.86504126,1.4188043,1.1775779,-190.05687,-1371.9624,2.2838454,5.550036,-4.268482,84.06813,495000
+0.6457781,183.29158,0.0040230495,-0.0011207476,-4.2785816,0.33542937,-183.27435,183.6259,6.9177375,5.793308,-4.2033544,-183.4843,-476.90042,12.711045,37.424232,-27.99992,453.91956,500000
+0.660113,181.6053,0.0038327645,0.0015722342,-3.589791,0.3086442,-181.59154,181.91551,1.2573636,1.5222147,-10.956393,-182.05327,-279.25854,2.7795782,4.328054,-7.065139,112.211334,505000
+0.65217614,189.87854,0.004202002,0.00044569754,-3.893932,0.37770143,-189.86218,190.25668,1.2367169,3.310581,-18.48759,-190.23018,-1410.5178,4.547298,13.1996565,-9.794511,178.33856,510000
+0.64521426,192.34045,0.0037770784,0.0010298322,-3.727347,0.33933562,-192.32639,192.68082,1.7747644,4.7924685,1.8004932,-192.61992,-1413.079,6.567233,15.302065,-16.199629,268.81216,515000
+0.64964664,186.64722,0.0036353818,0.0017017155,-3.5319018,0.28561327,-186.63437,186.93454,0.9314068,2.1815288,0.46407175,-186.87508,-271.48404,3.1129355,2.8637853,-2.3254035,72.54268,520000
+0.65691423,184.41966,0.004363863,0.0029121127,-3.3326755,0.2909251,-184.40512,184.7135,1.8471321,7.060384,1.3489902,-184.69829,-301.88882,8.907516,163.2008,-177.7622,1201.9633,525000
+0.6509633,186.50832,0.0037911525,-0.00023325377,-4.061526,0.28946954,-186.49292,186.79756,1.0904472,1.520554,-21.938704,-186.79654,-280.34976,2.611001,9.742095,-13.662375,105.82088,530000
+0.6438937,187.5875,0.003574225,0.00091789995,-3.743189,0.3428866,-187.57411,187.93129,1.4394144,3.4129474,0.26322204,-187.60703,-506.3811,4.8523617,33.966053,-34.143658,261.3481,535000
+0.64842236,190.99023,0.0034260813,2.3379635e-05,-3.993176,0.29431534,-190.97656,191.28458,1.0978837,1.2959658,-58.29827,-190.97977,-509.57028,2.3938494,4.4059916,-7.95204,87.65306,540000
+0.6577076,189.17096,0.003609679,0.0018112132,-3.4982343,0.2793792,-189.15833,189.45215,1.362821,1.1720608,-17.80289,-189.3636,-296.92337,2.5348818,2.4909146,-3.2963781,84.59417,545000
+0.65105665,192.16699,0.0034911798,-0.0027711615,-4.793761,0.25122726,-192.15025,192.41544,1.7248325,2.4630864,-2.780936,-192.46504,-1617.122,4.1879187,19.257635,-15.439744,311.49066,550000
+0.63023126,182.44716,0.0034982206,-0.0030136446,-4.8614793,0.30871812,-182.43015,182.75285,25.421715,782.5892,0.24487239,-181.61267,-407.6082,808.01086,7005.0566,-4595.2905,51620.7,555000
+0.6582415,192.36484,0.003495826,0.0012220544,-3.6504247,0.28470722,-192.35208,192.65077,2.340625,4.2599216,-0.9979039,-192.6598,-1698.9668,6.600547,21.897478,-14.899897,250.6076,560000
+0.6546152,191.90678,0.0035075154,0.0025468797,-3.2738793,0.31793854,-191.8953,192.22726,5.236383,4.4120784,-65.95695,-191.95076,-326.60873,9.648461,24.950369,-26.871056,409.9339,565000
+0.6485504,188.20462,0.00372281,-7.370878e-05,-4.019799,0.3391655,-188.18967,188.54372,1.3807893,2.0719383,-7.517023,-188.497,-330.966,3.4527276,8.031169,-2.983958,99.07129,570000
+0.661369,184.5469,0.0033249704,0.00082670816,-3.7513638,0.31135648,-184.53442,184.85909,2.031268,2.5274198,-6.2461314,-184.85103,-480.34653,4.5586877,12.844814,-57.543404,221.1081,575000
+0.6411834,193.67046,0.0034028639,-0.00030595483,-4.089911,0.26114008,-193.65656,193.93129,0.76446384,1.1186546,1.6800886,-193.87459,-1788.8029,1.8831184,4.7293468,-5.782282,86.36388,580000
+0.6479727,187.77432,0.0034364676,-0.0016901001,-4.491813,0.27195036,-187.75888,188.04459,1.6617367,1.9608284,0.35817856,-187.97348,-458.0653,3.6225653,9.179996,-11.458566,248.50722,585000
+0.6678066,197.9457,0.0036092056,0.0011021082,-3.6946397,0.281213,-197.93237,198.22801,0.93242115,1.1728034,-9.738867,-198.2606,-1799.693,2.1052246,3.6732676,-3.4313138,95.84508,590000
+0.65079564,191.28326,0.0033616528,-0.0022677763,-4.6746016,0.28304377,-191.26755,191.56404,1.0438347,1.4041494,0.9755785,-191.60057,-1808.6534,2.4479842,2.5349026,-2.1078985,83.76131,595000
+0.6539549,195.26208,0.0034004278,0.0010179813,-3.7006314,0.27814427,-195.2495,195.54124,1.0576239,1.4318639,-54.68244,-195.60428,-1793.7008,2.4894876,4.198876,-2.4169495,87.564156,600000
+0.6502267,191.73459,0.0033220495,-0.0002314035,-4.069657,0.31918606,-191.72107,192.05354,0.60123324,1.0468934,-4.9120517,-191.81258,-329.53085,1.6481266,3.2013788,-2.0363579,55.70854,605000
+0.6736288,192.05219,0.003754301,0.0013415077,-3.6426744,0.26806656,-192.03851,192.3216,1.7998549,2.8255672,-39.423496,-192.49776,-331.49548,4.625422,7.1491594,-19.076696,181.7806,610000
+0.65037197,187.64885,0.0031815488,0.00015340948,-3.9517815,0.2560464,-187.63629,187.90504,1.5827538,2.0369983,1.6196127,-187.87804,-305.5382,3.619752,18.774149,-18.972872,231.6386,615000
+0.6566,191.28777,0.0032190334,-0.0002579829,-4.080143,0.26541775,-191.27463,191.55292,1.3454593,1.5037394,0.24037069,-191.52284,-345.91937,2.8491988,4.5672317,-4.714498,101.11265,620000
+0.6498436,184.92728,0.0032177826,-0.0008366043,-4.259994,0.25556964,-184.91357,185.182,1.8170464,2.3014324,1.2719009,-185.07617,-330.25006,4.118479,8.174308,-7.9607635,161.82072,625000
+0.6559906,189.9192,0.0031538948,0.0012067924,-3.6173644,0.24604532,-189.90778,190.16646,0.9132385,1.1928023,-19.340273,-190.11864,-311.86722,2.106041,2.1954153,-2.5871172,76.556526,630000
+0.6418952,189.07918,0.0031135858,-0.0021473619,-4.689675,0.2796114,-189.06458,189.35664,22.028753,92.519806,-44.338173,-189.27255,-382.46146,114.54856,1149.3005,-1440.8569,9487.892,635000
+0.6569283,199.26074,0.0031457723,-5.3598753e-05,-4.0170383,0.2731874,-199.24812,199.53387,1.7405556,3.8453515,-5.5309725,-199.70036,-1987.6846,5.585907,17.885475,-16.88912,229.53177,640000
+0.6583229,190.5654,0.0033105437,0.00070694956,-3.7864552,0.27363554,-190.55287,190.83974,1.3593864,2.3936684,-25.883787,-190.83696,-335.78,3.7530549,33.004833,-10.494973,195.35474,645000
+0.6648632,194.48817,0.003444053,0.0044060927,-2.7206664,0.27504748,-194.47882,194.76764,6.056115,9.878381,1.000144,-194.34386,-292.0043,15.934496,25.856075,-39.92903,573.04175,650000
+0.6521802,196.68568,0.0030790858,-0.0006415883,-4.2083697,0.32666183,-196.67273,197.0117,2.1675167,2.1951492,0.53713757,-197.14012,-1900.635,4.362666,7.199414,-4.683694,146.42224,655000
+0.6606333,200.0885,0.003589131,0.0014762658,-3.5886843,0.27103323,-200.07562,200.36101,1.8039582,5.3696322,-19.773914,-200.4497,-1990.8748,7.1735907,80.89676,-20.890095,572.9492,660000
+0.6722541,192.03708,0.003161734,0.002984358,-3.0561008,0.2893701,-192.02744,192.32944,1.2735704,2.058748,0.5986207,-192.04286,-293.81982,3.3323183,8.953724,-8.53545,146.0895,665000
+0.63567364,190.21526,0.0031675692,-0.0041497964,-5.3100886,0.2792707,-190.19844,190.49037,1.0005058,3.3433099,1.3833745,-190.76128,-298.51282,4.343816,12.444227,-13.076882,203.07169,670000
+0.6689377,191.48096,0.0029001406,0.0035141748,-2.7882743,0.28516513,-191.47287,191.76964,1.0127704,1.5087874,-0.27742958,-191.46756,-260.72507,2.5215578,3.6443238,-6.324162,98.930214,675000
+0.645731,189.8778,0.002962827,-0.00023776059,-4.080248,0.32818633,-189.86572,190.20575,1.067025,1.7104939,28.384842,-190.12097,-284.13272,2.7775187,5.726515,-6.729068,128.63768,680000
+0.65904856,188.18219,0.0031343421,0.0002977738,-3.9049964,0.2867741,-188.16994,188.46927,1.3914452,2.9671938,9.461855,-188.31657,-281.04385,4.358639,12.213637,-7.584697,166.1417,685000
+0.6735049,189.82013,0.0031102647,0.0020923489,-3.3272762,0.28705707,-189.80978,190.10928,1.2676836,1.6696266,2.5938175,-190.17314,-364.68277,2.9373102,12.797435,-10.289824,144.70451,690000
+0.6623415,195.1351,0.002995013,-0.00017941926,-4.059906,0.30851558,-195.12294,195.44344,1.5389264,2.4017737,-52.08781,-195.3319,-376.92593,3.9407,9.017529,-6.9404135,160.51115,695000
+0.65147245,191.58655,0.0030928191,-0.002424832,-4.78402,0.31120533,-191.57175,191.89532,1.1691302,1.4724667,0.6675213,-191.95937,-279.9017,2.6415968,2.4888618,-3.4526377,85.12153,700000
+0.6553565,190.02303,0.0032476208,-0.0014028148,-4.4319515,0.2765453,-190.00864,190.29817,1.1592344,3.6711571,-0.55111563,-190.31378,-280.5886,4.8303914,26.9601,-11.064292,193.47166,705000
+0.6583419,193.63873,0.0031302585,0.00052825443,-3.8312426,0.26576555,-193.62674,193.90503,1.0164169,1.5784544,-0.10950118,-194.05803,-417.845,2.5948713,7.246735,-6.6677823,138.2306,710000
+0.6676092,193.48117,0.0031261132,0.0036780566,-2.823441,0.24602002,-193.47232,193.73087,1.465,2.298867,-0.73324376,-193.574,-244.59412,3.763867,6.2867875,-8.432671,119.313614,715000
+0.66789436,192.8758,0.003264158,0.0007545246,-3.7688456,0.25795496,-192.8635,193.13449,2.41322,2.716434,-29.775888,-193.0935,-242.84076,5.129654,22.513485,-35.00277,229.1524,720000
+0.6749618,205.6136,0.0031313573,0.002402687,-3.232701,0.2359066,-205.60349,205.8519,1.0166484,1.4866769,-23.945263,-205.8391,-1868.9614,2.5033255,9.925005,-4.5430813,128.52281,725000
+0.6727841,195.8379,0.0029828956,-0.00024357553,-4.0816574,0.2585144,-195.82573,196.09618,2.6421497,4.624632,47.58543,-195.95322,-354.98944,7.266782,21.172075,-42.98654,316.57462,730000
+0.667981,190.89297,0.0030912564,0.0011371962,-3.632125,0.25883386,-190.88174,191.15295,1.5603999,2.2134073,-40.20613,-190.98264,-255.67435,3.773807,8.859969,-12.280368,134.81525,735000
+0.6564244,201.57231,0.002898769,-0.00023114798,-4.07974,0.19564447,-201.56049,201.76773,1.4332607,2.3448932,0.07168281,-201.6709,-1758.0842,3.778154,4.329458,-4.1147485,123.18854,740000
+0.6552061,190.64145,0.0027755718,-0.00086237525,-4.310702,0.2184229,-190.62947,190.85901,1.2511551,2.529841,-10.057115,-190.8279,-293.4225,3.780996,2.7145414,-8.007617,94.56508,745000
+0.6547136,185.16072,0.0029279026,-0.0014922481,-4.5096645,0.24829033,-185.14752,185.40752,1.2079304,2.641082,68.38677,-185.47266,-271.4753,3.8490124,7.852045,-10.3601265,156.6205,750000
+0.65426964,188.01614,0.002810583,0.0018392766,-3.345589,0.25192195,-188.00674,188.26991,0.9957585,2.1799257,1.595343,-188.08922,-262.40826,3.1756842,4.5416317,-5.433778,112.44729,755000
+0.66659784,195.27339,0.0030604093,0.00025341404,-3.917196,0.27547657,-195.26141,195.54913,1.4249035,2.6117008,10.716497,-195.72406,-1565.0979,4.0366044,23.286325,-16.206848,175.91393,760000
+0.66369665,193.05142,0.002760518,-0.00087593304,-4.3173075,0.2906729,-193.0395,193.34123,1.058608,1.4145138,23.55786,-193.34056,-469.42508,2.473122,2.7937005,-4.4824157,91.53653,765000
+0.64915395,189.3901,0.0028950598,-0.0030297579,-5.046527,0.27110735,-189.37549,189.65817,0.8943238,1.4338536,-7.4920726,-189.75339,-322.4225,2.3281775,3.4755654,-5.014498,85.12587,770000
+0.6633673,192.3747,0.0025482944,7.80594e-05,-3.969368,0.29624495,-192.36458,192.67102,1.0432965,2.5760112,-78.417496,-192.39119,-326.85913,3.6193075,26.171326,-37.958748,244.64157,775000
+0.6556161,187.84073,0.0026494719,-0.002062307,-4.778384,0.2692387,-187.82806,188.10791,12.86442,9.047754,0.46814126,-188.14026,-338.17853,21.912174,33.64795,-40.373672,696.6522,780000
+0.6705277,192.15363,0.002733136,0.0023297046,-3.1476076,0.25165084,-192.14502,192.40761,2.2732162,2.0789247,1.357026,-192.14932,-238.56227,4.352141,5.1128616,-16.160028,163.88525,785000
+0.67633635,193.67609,0.0027337875,0.0016783691,-3.3860645,0.27777594,-193.66684,193.95554,1.0853139,8.678,-0.61047965,-193.7078,-1096.1384,9.763314,69.58699,-70.65977,428.85028,790000
+0.66677344,192.55045,0.0027489853,-0.0013348063,-4.4855633,0.23077339,-192.53812,192.77989,0.88745785,1.7137196,37.52061,-192.71689,-278.08005,2.6011775,5.6016445,-6.698583,88.865685,795000
+0.6738764,194.17578,0.002517782,0.0022644643,-3.1006114,0.29052967,-194.16797,194.46857,0.4739155,0.7615647,-18.074146,-194.26361,-272.7415,1.2354802,2.2441792,-1.6756281,49.614582,800000

O2O-w-diff-ckpts/dsrl/20260316_192847/online_agent_sv.csv

@@ -0,0 +1,101 @@
+actor/action_std,actor/actor_loss,actor/alpha,actor/alpha_loss,actor/entropy,actor/flow_loss,actor/q,actor/total_loss,critic/critic_loss,critic/distill_loss,critic/q_max,critic/q_mean,critic/q_min,critic/total_loss,grad/max,grad/min,grad/norm,step
+0.65190405,165.8779,0.005302432,0.0017743882,-3.6653633,0.28544554,-165.85846,166.16512,0.7866831,1.1567634,-3.4438224,-165.79944,-322.15024,1.9434465,6.1900234,-5.412445,86.13,305000
+0.6378956,163.31241,0.0054098475,-0.0018684831,-4.3453856,0.3041193,-163.28891,163.61467,1.8849125,2.3143818,-3.319524,-163.61133,-365.69174,4.199294,73.73241,-21.313492,253.08263,310000
+0.63433164,170.46149,0.0055153426,-0.0049109105,-4.890409,0.3122282,-170.43451,170.7688,0.6778327,1.6790257,-1.889926,-170.57523,-318.66837,2.3568583,37.362934,-49.788803,212.75179,315000
+0.64605355,169.47502,0.0052787564,0.0035873775,-3.3204124,0.31294182,-169.45749,169.79155,0.80688334,0.99739724,-19.813538,-169.7721,-279.91458,1.8042805,4.1256504,-4.661874,80.2821,320000
+0.64738476,171.67744,0.005163804,0.0013074558,-3.7468038,0.30775702,-171.65811,171.98651,1.6609195,1.902367,2.778079,-171.80374,-651.5815,3.5632865,7.888319,-7.868909,151.31097,325000
+0.64587367,168.75636,0.0050593386,-0.00013580336,-4.026842,0.2956421,-168.736,169.05186,1.0101393,1.8425789,0.23597738,-168.91528,-316.3651,2.8527184,15.016986,-15.851705,141.45242,330000
+0.65176797,169.6677,0.004962684,0.0007392349,-3.8510413,0.3125143,-169.64859,169.98094,1.9716122,4.065412,0.71186745,-169.93071,-320.58405,6.0370245,11.848728,-22.302162,264.85007,335000
+0.6442949,168.97388,0.0050886525,-0.0028927317,-4.568467,0.28675508,-168.95062,169.25774,3.0748549,5.618911,0.58771896,-169.40147,-304.63766,8.693766,18.85864,-22.966904,354.73035,340000
+0.63992715,171.41608,0.004953705,-0.00045854942,-4.092567,0.337938,-171.39581,171.75356,0.7760425,1.3038918,-5.2465277,-171.63255,-288.2562,2.0799344,2.874102,-2.4000344,81.60121,345000
+0.6403782,176.4986,0.0051468667,-0.0001342506,-4.026084,0.34986028,-176.4779,176.84831,2.7719343,21.10802,-1.6105424,-177.00224,-769.00555,23.879955,246.3798,-285.17355,1978.1866,350000
+0.62867856,174.9358,0.0053532342,-0.004113845,-4.7684784,0.31304416,-174.91028,175.24474,0.82374495,1.9332955,1.2968588,-175.25064,-786.87854,2.7570405,14.721909,-18.107378,165.85896,355000
+0.6457268,176.78474,0.005494249,0.0011605216,-3.7887752,0.37760848,-176.76392,177.16351,1.1304549,2.2559013,-37.45145,-176.83305,-813.0693,3.3863564,13.776581,-7.081804,143.85248,360000
+0.645025,174.46274,0.004972166,0.001095311,-3.7797115,0.29927447,-174.44394,174.7631,1.3120044,1.2846364,-7.155112,-174.4691,-240.24321,2.5966408,6.852143,-10.2877445,132.24713,365000
+0.65178084,180.5452,0.005203607,0.00017423376,-3.9665167,0.33193058,-180.52455,180.87729,0.61688274,2.1168735,-9.416031,-180.71063,-840.5523,2.7337563,16.301863,-9.559705,150.37427,370000
+0.64879537,180.2057,0.005286353,-0.0023922278,-4.452529,0.34860232,-180.18216,180.55191,1.1693782,2.700391,1.0994608,-180.59352,-669.6207,3.869769,8.279745,-9.526651,133.10092,375000
+0.6495932,177.26672,0.0053756344,0.0009267645,-3.827599,0.32942683,-177.24615,177.59708,9.3274555,7.4802895,-0.9111727,-177.08897,-655.4023,16.807745,438.56195,-285.98892,1987.0864,380000
+0.63780284,186.99294,0.0051468764,-0.004947272,-4.9612184,0.3427367,-186.9674,187.33073,1.6237414,2.0167031,-0.55932796,-187.15385,-932.8465,3.6404445,6.279961,-11.198244,141.71144,385000
+0.64054155,177.08572,0.0049123457,-0.0020270143,-4.4126368,0.3343872,-177.06404,177.41808,1.430576,2.2725015,-17.703533,-177.13933,-307.47885,3.7030773,11.804242,-3.9012566,123.61615,390000
+0.64635074,178.09996,0.0054569277,-0.0041559287,-4.7615876,0.34797826,-178.07397,178.44379,2.1158044,3.81694,4.977904,-178.12962,-998.8338,5.9327445,34.01505,-21.431986,269.0889,395000
+0.63640136,177.5755,0.005041929,-0.0012072441,-4.239441,0.293699,-177.55411,177.868,1.2450598,1.7738285,-2.3227887,-177.68172,-311.23343,3.0188885,5.7544103,-4.639542,98.16675,400000
+0.63562787,181.96344,0.0049036886,-0.0012038958,-4.245508,0.34957653,-181.94261,182.31181,1.5112237,2.3369863,-5.0396757,-182.29256,-697.7353,3.8482099,6.8428884,-9.088067,127.45903,405000
+0.6292087,181.9704,0.0048866533,-0.0014900509,-4.3049226,0.32482052,-181.94934,182.29372,0.9736924,1.3162382,-6.185815,-182.11197,-1050.4877,2.2899306,9.106683,-12.61252,154.59804,410000
+0.6535957,184.828,0.004834411,0.003963552,-3.1801376,0.32328567,-184.81262,185.15526,0.9190155,1.4203008,-1.6724339,-184.87962,-305.55872,2.3393164,2.1117744,-3.0158558,77.681625,415000
+0.6411215,183.063,0.004925809,-0.0012017586,-4.243972,0.28162596,-183.04211,183.34343,0.8403303,1.3052429,-13.97532,-183.42091,-540.75946,2.1455731,7.1845493,-13.106476,110.78599,420000
+0.6435565,180.78558,0.0047628433,-0.00083702325,-4.1757402,0.3046242,-180.76569,181.08937,1.7104224,1.329995,-34.374718,-181.27576,-335.86386,3.0404174,5.5545864,-3.7106087,86.39929,425000
+0.6444941,180.95488,0.0046603167,-0.00021491013,-4.046115,0.31659165,-180.93602,181.27126,32.935593,36.163853,-9.417093,-181.4055,-583.28143,69.09944,348.05338,-404.55872,2331.506,430000
+0.65019476,187.31876,0.004874008,0.002689136,-3.44827,0.29710224,-187.30196,187.61855,0.8735499,1.981348,-75.35665,-187.39883,-1128.6993,2.854898,6.526506,-6.255607,105.256226,435000
+0.6439402,184.1926,0.0045220884,-0.0011690336,-4.2585163,0.29848394,-184.17334,184.4899,1.1092217,1.9407688,-7.455441,-184.46265,-437.99326,3.0499907,5.0093594,-7.120329,123.33768,440000
+0.6400594,177.54588,0.0045237946,-0.0005259862,-4.116271,0.32032496,-177.52727,177.86569,0.8080805,1.053423,-2.3266203,-177.99896,-626.55133,1.8615036,3.7874908,-3.112287,72.17585,445000
+0.64976835,182.66797,0.0044793366,0.0027541812,-3.3851364,0.31622052,-182.6528,182.98694,0.7899103,0.8913302,-13.10727,-182.76973,-254.09056,1.6812406,2.417381,-1.7537684,53.46707,450000
+0.6517472,185.31776,0.0044912836,0.0017715641,-3.605555,0.30971137,-185.30156,185.62924,2.306048,6.6643686,-4.8946505,-185.33716,-643.0832,8.970417,38.67115,-22.184374,356.81088,455000
+0.6437141,176.71893,0.004214192,0.0007679291,-3.8177755,0.30903578,-176.70284,177.02873,1.8595362,2.4169526,-0.5466883,-177.05545,-313.76663,4.276489,24.851908,-12.66319,209.495,460000
+0.65486944,191.11435,0.0041868775,0.003729888,-3.109148,0.3064775,-191.10132,191.42455,0.76095265,1.2447213,-41.266422,-191.56325,-1185.1459,2.005674,3.130833,-2.1435974,85.250305,465000
+0.6416023,186.42433,0.0044340966,0.0013370095,-3.6984708,0.29272777,-186.40793,186.7184,1.2862681,1.5518125,-0.33411595,-186.72392,-1229.379,2.8380806,8.300149,-19.548836,143.96228,470000
+0.6464348,181.34073,0.00429143,0.0003798019,-3.9114976,0.27626824,-181.32394,181.61739,0.84046745,1.0018212,-30.859097,-181.60962,-276.80057,1.8422886,3.6386416,-3.2182314,69.16331,475000
+0.6424699,179.88107,0.004367166,-0.00056909816,-4.130313,0.32520664,-179.86304,180.20572,1.0176531,1.3734155,-0.50975794,-180.22966,-566.0318,2.3910685,4.2157536,-3.5694993,80.56244,480000
+0.6480551,189.50952,0.004139514,0.0006171604,-3.85091,0.26887426,-189.49359,189.779,3.7049406,4.2353153,-2.2075944,-189.80411,-1320.0867,7.940256,38.343468,-22.935806,432.45898,485000
+0.632545,181.39323,0.0044296044,-0.0018557451,-4.4189415,0.29798794,-181.37366,181.68936,1.628032,2.760862,-50.7757,-181.49918,-307.6623,4.388894,13.216695,-10.386584,144.47832,490000
+0.6548782,190.01686,0.004339003,1.0762927e-05,-3.9975195,0.30356777,-189.99953,190.32045,0.86504126,1.4188043,1.1775779,-190.05687,-1371.9624,2.2838454,5.550036,-4.268482,84.06813,495000
+0.6457781,183.29158,0.0040230495,-0.0011207476,-4.2785816,0.33542937,-183.27435,183.6259,6.9177375,5.793308,-4.2033544,-183.4843,-476.90042,12.711045,37.424232,-27.99992,453.91956,500000
+0.660113,181.6053,0.0038327645,0.0015722342,-3.589791,0.3086442,-181.59154,181.91551,1.2573636,1.5222147,-10.956393,-182.05327,-279.25854,2.7795782,4.328054,-7.065139,112.211334,505000
+0.65217614,189.87854,0.004202002,0.00044569754,-3.893932,0.37770143,-189.86218,190.25668,1.2367169,3.310581,-18.48759,-190.23018,-1410.5178,4.547298,13.1996565,-9.794511,178.33856,510000
+0.64521426,192.34045,0.0037770784,0.0010298322,-3.727347,0.33933562,-192.32639,192.68082,1.7747644,4.7924685,1.8004932,-192.61992,-1413.079,6.567233,15.302065,-16.199629,268.81216,515000
+0.64964664,186.64722,0.0036353818,0.0017017155,-3.5319018,0.28561327,-186.63437,186.93454,0.9314068,2.1815288,0.46407175,-186.87508,-271.48404,3.1129355,2.8637853,-2.3254035,72.54268,520000
+0.65691423,184.41966,0.004363863,0.0029121127,-3.3326755,0.2909251,-184.40512,184.7135,1.8471321,7.060384,1.3489902,-184.69829,-301.88882,8.907516,163.2008,-177.7622,1201.9633,525000
+0.6509633,186.50832,0.0037911525,-0.00023325377,-4.061526,0.28946954,-186.49292,186.79756,1.0904472,1.520554,-21.938704,-186.79654,-280.34976,2.611001,9.742095,-13.662375,105.82088,530000
+0.6438937,187.5875,0.003574225,0.00091789995,-3.743189,0.3428866,-187.57411,187.93129,1.4394144,3.4129474,0.26322204,-187.60703,-506.3811,4.8523617,33.966053,-34.143658,261.3481,535000
+0.64842236,190.99023,0.0034260813,2.3379635e-05,-3.993176,0.29431534,-190.97656,191.28458,1.0978837,1.2959658,-58.29827,-190.97977,-509.57028,2.3938494,4.4059916,-7.95204,87.65306,540000
+0.6577076,189.17096,0.003609679,0.0018112132,-3.4982343,0.2793792,-189.15833,189.45215,1.362821,1.1720608,-17.80289,-189.3636,-296.92337,2.5348818,2.4909146,-3.2963781,84.59417,545000
+0.65105665,192.16699,0.0034911798,-0.0027711615,-4.793761,0.25122726,-192.15025,192.41544,1.7248325,2.4630864,-2.780936,-192.46504,-1617.122,4.1879187,19.257635,-15.439744,311.49066,550000
+0.63023126,182.44716,0.0034982206,-0.0030136446,-4.8614793,0.30871812,-182.43015,182.75285,25.421715,782.5892,0.24487239,-181.61267,-407.6082,808.01086,7005.0566,-4595.2905,51620.7,555000
+0.6582415,192.36484,0.003495826,0.0012220544,-3.6504247,0.28470722,-192.35208,192.65077,2.340625,4.2599216,-0.9979039,-192.6598,-1698.9668,6.600547,21.897478,-14.899897,250.6076,560000
+0.6546152,191.90678,0.0035075154,0.0025468797,-3.2738793,0.31793854,-191.8953,192.22726,5.236383,4.4120784,-65.95695,-191.95076,-326.60873,9.648461,24.950369,-26.871056,409.9339,565000
+0.6485504,188.20462,0.00372281,-7.370878e-05,-4.019799,0.3391655,-188.18967,188.54372,1.3807893,2.0719383,-7.517023,-188.497,-330.966,3.4527276,8.031169,-2.983958,99.07129,570000
+0.661369,184.5469,0.0033249704,0.00082670816,-3.7513638,0.31135648,-184.53442,184.85909,2.031268,2.5274198,-6.2461314,-184.85103,-480.34653,4.5586877,12.844814,-57.543404,221.1081,575000
+0.6411834,193.67046,0.0034028639,-0.00030595483,-4.089911,0.26114008,-193.65656,193.93129,0.76446384,1.1186546,1.6800886,-193.87459,-1788.8029,1.8831184,4.7293468,-5.782282,86.36388,580000
+0.6479727,187.77432,0.0034364676,-0.0016901001,-4.491813,0.27195036,-187.75888,188.04459,1.6617367,1.9608284,0.35817856,-187.97348,-458.0653,3.6225653,9.179996,-11.458566,248.50722,585000
+0.6678066,197.9457,0.0036092056,0.0011021082,-3.6946397,0.281213,-197.93237,198.22801,0.93242115,1.1728034,-9.738867,-198.2606,-1799.693,2.1052246,3.6732676,-3.4313138,95.84508,590000
+0.65079564,191.28326,0.0033616528,-0.0022677763,-4.6746016,0.28304377,-191.26755,191.56404,1.0438347,1.4041494,0.9755785,-191.60057,-1808.6534,2.4479842,2.5349026,-2.1078985,83.76131,595000
+0.6539549,195.26208,0.0034004278,0.0010179813,-3.7006314,0.27814427,-195.2495,195.54124,1.0576239,1.4318639,-54.68244,-195.60428,-1793.7008,2.4894876,4.198876,-2.4169495,87.564156,600000
+0.6502267,191.73459,0.0033220495,-0.0002314035,-4.069657,0.31918606,-191.72107,192.05354,0.60123324,1.0468934,-4.9120517,-191.81258,-329.53085,1.6481266,3.2013788,-2.0363579,55.70854,605000
+0.6736288,192.05219,0.003754301,0.0013415077,-3.6426744,0.26806656,-192.03851,192.3216,1.7998549,2.8255672,-39.423496,-192.49776,-331.49548,4.625422,7.1491594,-19.076696,181.7806,610000
+0.65037197,187.64885,0.0031815488,0.00015340948,-3.9517815,0.2560464,-187.63629,187.90504,1.5827538,2.0369983,1.6196127,-187.87804,-305.5382,3.619752,18.774149,-18.972872,231.6386,615000
+0.6566,191.28777,0.0032190334,-0.0002579829,-4.080143,0.26541775,-191.27463,191.55292,1.3454593,1.5037394,0.24037069,-191.52284,-345.91937,2.8491988,4.5672317,-4.714498,101.11265,620000
+0.6498436,184.92728,0.0032177826,-0.0008366043,-4.259994,0.25556964,-184.91357,185.182,1.8170464,2.3014324,1.2719009,-185.07617,-330.25006,4.118479,8.174308,-7.9607635,161.82072,625000
+0.6559906,189.9192,0.0031538948,0.0012067924,-3.6173644,0.24604532,-189.90778,190.16646,0.9132385,1.1928023,-19.340273,-190.11864,-311.86722,2.106041,2.1954153,-2.5871172,76.556526,630000
+0.6418952,189.07918,0.0031135858,-0.0021473619,-4.689675,0.2796114,-189.06458,189.35664,22.028753,92.519806,-44.338173,-189.27255,-382.46146,114.54856,1149.3005,-1440.8569,9487.892,635000
+0.6569283,199.26074,0.0031457723,-5.3598753e-05,-4.0170383,0.2731874,-199.24812,199.53387,1.7405556,3.8453515,-5.5309725,-199.70036,-1987.6846,5.585907,17.885475,-16.88912,229.53177,640000
+0.6583229,190.5654,0.0033105437,0.00070694956,-3.7864552,0.27363554,-190.55287,190.83974,1.3593864,2.3936684,-25.883787,-190.83696,-335.78,3.7530549,33.004833,-10.494973,195.35474,645000
+0.6648632,194.48817,0.003444053,0.0044060927,-2.7206664,0.27504748,-194.47882,194.76764,6.056115,9.878381,1.000144,-194.34386,-292.0043,15.934496,25.856075,-39.92903,573.04175,650000
+0.6521802,196.68568,0.0030790858,-0.0006415883,-4.2083697,0.32666183,-196.67273,197.0117,2.1675167,2.1951492,0.53713757,-197.14012,-1900.635,4.362666,7.199414,-4.683694,146.42224,655000
+0.6606333,200.0885,0.003589131,0.0014762658,-3.5886843,0.27103323,-200.07562,200.36101,1.8039582,5.3696322,-19.773914,-200.4497,-1990.8748,7.1735907,80.89676,-20.890095,572.9492,660000
+0.6722541,192.03708,0.003161734,0.002984358,-3.0561008,0.2893701,-192.02744,192.32944,1.2735704,2.058748,0.5986207,-192.04286,-293.81982,3.3323183,8.953724,-8.53545,146.0895,665000
+0.63567364,190.21526,0.0031675692,-0.0041497964,-5.3100886,0.2792707,-190.19844,190.49037,1.0005058,3.3433099,1.3833745,-190.76128,-298.51282,4.343816,12.444227,-13.076882,203.07169,670000
+0.6689377,191.48096,0.0029001406,0.0035141748,-2.7882743,0.28516513,-191.47287,191.76964,1.0127704,1.5087874,-0.27742958,-191.46756,-260.72507,2.5215578,3.6443238,-6.324162,98.930214,675000
+0.645731,189.8778,0.002962827,-0.00023776059,-4.080248,0.32818633,-189.86572,190.20575,1.067025,1.7104939,28.384842,-190.12097,-284.13272,2.7775187,5.726515,-6.729068,128.63768,680000
+0.65904856,188.18219,0.0031343421,0.0002977738,-3.9049964,0.2867741,-188.16994,188.46927,1.3914452,2.9671938,9.461855,-188.31657,-281.04385,4.358639,12.213637,-7.584697,166.1417,685000
+0.6735049,189.82013,0.0031102647,0.0020923489,-3.3272762,0.28705707,-189.80978,190.10928,1.2676836,1.6696266,2.5938175,-190.17314,-364.68277,2.9373102,12.797435,-10.289824,144.70451,690000
+0.6623415,195.1351,0.002995013,-0.00017941926,-4.059906,0.30851558,-195.12294,195.44344,1.5389264,2.4017737,-52.08781,-195.3319,-376.92593,3.9407,9.017529,-6.9404135,160.51115,695000
+0.65147245,191.58655,0.0030928191,-0.002424832,-4.78402,0.31120533,-191.57175,191.89532,1.1691302,1.4724667,0.6675213,-191.95937,-279.9017,2.6415968,2.4888618,-3.4526377,85.12153,700000
+0.6553565,190.02303,0.0032476208,-0.0014028148,-4.4319515,0.2765453,-190.00864,190.29817,1.1592344,3.6711571,-0.55111563,-190.31378,-280.5886,4.8303914,26.9601,-11.064292,193.47166,705000
+0.6583419,193.63873,0.0031302585,0.00052825443,-3.8312426,0.26576555,-193.62674,193.90503,1.0164169,1.5784544,-0.10950118,-194.05803,-417.845,2.5948713,7.246735,-6.6677823,138.2306,710000
+0.6676092,193.48117,0.0031261132,0.0036780566,-2.823441,0.24602002,-193.47232,193.73087,1.465,2.298867,-0.73324376,-193.574,-244.59412,3.763867,6.2867875,-8.432671,119.313614,715000
+0.66789436,192.8758,0.003264158,0.0007545246,-3.7688456,0.25795496,-192.8635,193.13449,2.41322,2.716434,-29.775888,-193.0935,-242.84076,5.129654,22.513485,-35.00277,229.1524,720000
+0.6749618,205.6136,0.0031313573,0.002402687,-3.232701,0.2359066,-205.60349,205.8519,1.0166484,1.4866769,-23.945263,-205.8391,-1868.9614,2.5033255,9.925005,-4.5430813,128.52281,725000
+0.6727841,195.8379,0.0029828956,-0.00024357553,-4.0816574,0.2585144,-195.82573,196.09618,2.6421497,4.624632,47.58543,-195.95322,-354.98944,7.266782,21.172075,-42.98654,316.57462,730000
+0.667981,190.89297,0.0030912564,0.0011371962,-3.632125,0.25883386,-190.88174,191.15295,1.5603999,2.2134073,-40.20613,-190.98264,-255.67435,3.773807,8.859969,-12.280368,134.81525,735000
+0.6564244,201.57231,0.002898769,-0.00023114798,-4.07974,0.19564447,-201.56049,201.76773,1.4332607,2.3448932,0.07168281,-201.6709,-1758.0842,3.778154,4.329458,-4.1147485,123.18854,740000
+0.6552061,190.64145,0.0027755718,-0.00086237525,-4.310702,0.2184229,-190.62947,190.85901,1.2511551,2.529841,-10.057115,-190.8279,-293.4225,3.780996,2.7145414,-8.007617,94.56508,745000
+0.6547136,185.16072,0.0029279026,-0.0014922481,-4.5096645,0.24829033,-185.14752,185.40752,1.2079304,2.641082,68.38677,-185.47266,-271.4753,3.8490124,7.852045,-10.3601265,156.6205,750000
+0.65426964,188.01614,0.002810583,0.0018392766,-3.345589,0.25192195,-188.00674,188.26991,0.9957585,2.1799257,1.595343,-188.08922,-262.40826,3.1756842,4.5416317,-5.433778,112.44729,755000
+0.66659784,195.27339,0.0030604093,0.00025341404,-3.917196,0.27547657,-195.26141,195.54913,1.4249035,2.6117008,10.716497,-195.72406,-1565.0979,4.0366044,23.286325,-16.206848,175.91393,760000
+0.66369665,193.05142,0.002760518,-0.00087593304,-4.3173075,0.2906729,-193.0395,193.34123,1.058608,1.4145138,23.55786,-193.34056,-469.42508,2.473122,2.7937005,-4.4824157,91.53653,765000
+0.64915395,189.3901,0.0028950598,-0.0030297579,-5.046527,0.27110735,-189.37549,189.65817,0.8943238,1.4338536,-7.4920726,-189.75339,-322.4225,2.3281775,3.4755654,-5.014498,85.12587,770000
+0.6633673,192.3747,0.0025482944,7.80594e-05,-3.969368,0.29624495,-192.36458,192.67102,1.0432965,2.5760112,-78.417496,-192.39119,-326.85913,3.6193075,26.171326,-37.958748,244.64157,775000
+0.6556161,187.84073,0.0026494719,-0.002062307,-4.778384,0.2692387,-187.82806,188.10791,12.86442,9.047754,0.46814126,-188.14026,-338.17853,21.912174,33.64795,-40.373672,696.6522,780000
+0.6705277,192.15363,0.002733136,0.0023297046,-3.1476076,0.25165084,-192.14502,192.40761,2.2732162,2.0789247,1.357026,-192.14932,-238.56227,4.352141,5.1128616,-16.160028,163.88525,785000
+0.67633635,193.67609,0.0027337875,0.0016783691,-3.3860645,0.27777594,-193.66684,193.95554,1.0853139,8.678,-0.61047965,-193.7078,-1096.1384,9.763314,69.58699,-70.65977,428.85028,790000
+0.66677344,192.55045,0.0027489853,-0.0013348063,-4.4855633,0.23077339,-192.53812,192.77989,0.88745785,1.7137196,37.52061,-192.71689,-278.08005,2.6011775,5.6016445,-6.698583,88.865685,795000
+0.6738764,194.17578,0.002517782,0.0022644643,-3.1006114,0.29052967,-194.16797,194.46857,0.4739155,0.7615647,-18.074146,-194.26361,-272.7415,1.2354802,2.2441792,-1.6756281,49.614582,800000

O2O-w-diff-ckpts/dsrl/20260316_192847/params_350000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c496271b28b2ca1ecc91caeca640dc0d0c9ea90ea8b9209b1103b2afa64b724
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_400000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d5cd66879c49a11ac073632c3f8983257d124b371d0531120ff8a184378cb2
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_450000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47522a454108b42bd56b93dd4927bf90df43b11748206149395e6fc393152fa3
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_500000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4324d88cd702833e2985d1e45c0d5d03360133b5732532a14075c342129aa2
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_550000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2fa438a4a548207b18ad40953bd3e3baf8b68f20caee7f19e7db9cea8ed5f36
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_600000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1afeaca0dd6dff055899769ff2cb1bdf3c02778627216424de764e6ffb7360c3
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_650000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e3d471c62d061720c273ab1aca6be19a432ec1d0ed2af3725d3f75a8edc7ed
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_700000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4ef52ff55a55561e4a20ee33c5c3369997fae81903032264b889ade658912c
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_750000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bab4a82263e92f00f7b9f2a556698208cf2ec5d9ee7f29c2d0067058dd90dce
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/params_800000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f698f227dac095a4451c14bbe84b2cb39a6da3eb9eadef17b60e57340b317fe
+size 321574838

O2O-w-diff-ckpts/dsrl/20260316_192847/progress.tk

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

O2O-w-diff-ckpts/dsrl/20260316_192847/token.tk

@@ -0,0 +1 @@
+https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/udadk19o