O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/cgql/20260323_231318/online_agent_sv.csv

actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
0.20278193,9.020888,-69.29223,-204.61613,-244.8014,0.7597409,-0.9747023,60.57042,105000
0.19677977,10.419122,-114.7377,-204.01172,-253.5573,0.5758852,-0.58879393,71.72533,110000
0.20958102,8.304919,-94.48439,-205.45792,-243.3522,0.8711691,-0.49031666,43.90927,115000
0.21415262,9.718261,-140.86128,-209.60301,-248.28981,0.7167376,-0.665435,55.62179,120000
0.18877125,11.295578,-65.49997,-205.89049,-247.31932,0.62997025,-0.55463684,51.420795,125000
0.20980306,7.1617074,0.90822136,-202.41664,-245.14635,0.5251723,-0.4659771,51.585358,130000
0.18867612,8.460653,-92.91773,-205.00378,-241.02873,0.6033751,-0.5084465,47.406525,135000
0.19025767,8.820968,-72.909615,-200.20006,-239.36365,0.77617055,-0.5324077,46.14516,140000
0.193324,10.827983,-79.82131,-197.89003,-237.00117,0.57498974,-0.44151267,49.93411,145000
0.20539303,7.035141,-61.348644,-198.07799,-239.77989,0.513875,-0.4447837,43.418423,150000
0.19177033,8.589063,-70.724045,-192.76775,-230.67938,0.5420707,-0.607551,52.067856,155000
0.23010573,9.739177,-40.053192,-192.68077,-231.79355,0.6219107,-0.7741456,71.60482,160000
0.20121637,10.18423,-59.218227,-190.33003,-237.98611,0.7484101,-0.70231223,58.082745,165000
0.21065748,8.273341,-55.67223,-188.73778,-244.58093,0.52847356,-0.5388629,48.390503,170000
0.21944919,11.179502,-29.621456,-186.5203,-228.94731,0.6689159,-0.7850703,75.8286,175000
0.18537474,9.282326,-69.81886,-187.1616,-230.28864,0.42038587,-0.37184379,46.30365,180000
0.18684226,12.201419,-23.754557,-186.37685,-235.34904,0.6720755,-0.6505196,56.68166,185000
0.2065152,12.2349,-28.452469,-188.89943,-236.97185,0.527252,-0.7969895,54.048424,190000
0.1814244,11.256672,-45.25682,-186.87,-240.879,0.6380391,-1.0178984,74.37224,195000
0.19658166,15.913681,-49.78718,-182.81018,-239.02174,0.779315,-0.7204983,64.8628,200000
0.22109234,11.664107,-25.83727,-187.81633,-238.54353,0.43742752,-0.46561766,54.71624,205000
0.2191867,10.419608,-27.510286,-182.88065,-243.84769,0.592541,-0.5475873,50.47235,210000
0.1963293,11.165191,-37.944035,-181.82407,-233.81778,0.82151425,-0.85982996,71.08221,215000
0.20497052,13.977524,-48.782417,-181.692,-243.11732,0.8969333,-0.99033743,55.868484,220000
0.22079468,20.732504,-22.024803,-185.72044,-239.60515,0.8148024,-0.85377425,65.905174,225000
0.20680377,10.817062,-43.452084,-184.27425,-240.40259,1.0982165,-1.0901787,53.851013,230000
0.20995495,10.216932,-30.03991,-187.04764,-236.72717,0.46850377,-0.456591,48.5045,235000
0.25769547,12.371939,-43.13999,-186.1516,-242.1056,0.5473617,-0.50286174,50.104332,240000
0.2515966,11.194498,-9.199809,-181.60858,-230.44186,0.7423211,-0.7273388,58.520924,245000
0.21745187,12.056947,-31.416533,-185.6515,-235.83817,0.86750364,-0.92978007,62.43194,250000
0.20288768,9.375833,-11.359747,-185.9138,-237.21793,0.7026347,-0.6222869,48.712982,255000
0.24250452,11.077544,-16.673536,-184.72241,-236.23909,0.74351156,-0.757651,58.118156,260000
0.23293547,13.095916,-14.5005045,-184.85936,-239.41678,0.5274003,-0.7919475,60.369152,265000
0.23616946,10.665067,-5.2572503,-183.45052,-245.21277,0.8436808,-0.96125066,54.802383,270000
0.23700276,12.479296,-7.5061693,-187.96259,-253.19563,0.67316854,-0.6888136,54.413185,275000
0.23832616,9.322211,-28.08931,-183.88065,-240.0983,0.8622448,-0.8884227,55.429073,280000
0.2352085,11.121478,-9.144472,-187.43547,-244.17882,0.8111202,-0.9266114,76.99991,285000
0.2340525,11.504962,-4.1746936,-185.03355,-247.90617,1.0157542,-0.8980155,71.41188,290000
0.21709365,9.635287,-27.750538,-187.99821,-258.29062,0.6694262,-0.75733143,48.914925,295000
0.27270558,8.857162,-30.943298,-184.62732,-255.45953,0.46851507,-0.49437216,46.1483,300000
0.19014625,9.449229,-9.910983,-182.34943,-248.25218,0.5097664,-0.6777716,56.17635,305000
0.22012109,9.553384,-22.821772,-185.32124,-251.83293,0.80718845,-0.8334968,59.943214,310000
0.23351145,11.32056,-13.737731,-184.03392,-246.66948,1.2260737,-1.2298218,64.293915,315000
0.21752834,9.996968,-29.126793,-184.84593,-251.82462,0.74989945,-0.73753756,54.097305,320000
0.23714036,9.068104,-12.922159,-191.95953,-252.07117,0.6283213,-0.5799188,52.574177,325000
0.2226916,10.118474,-13.833104,-189.74825,-253.91978,0.9817351,-0.8129889,58.938988,330000
0.22621024,8.0921135,-15.998319,-191.5253,-257.23795,0.54256874,-0.5681233,50.452663,335000
0.18886478,9.2201185,-24.171612,-187.9042,-238.71867,0.56304306,-0.5663563,41.29402,340000
0.28012186,12.6502905,-11.7654705,-182.56688,-255.37762,0.51995635,-0.49292806,50.785072,345000
0.23620105,9.247436,-5.8294983,-193.41158,-247.10933,0.5497414,-0.78243095,48.760757,350000
0.21435063,12.85258,-14.972801,-187.17711,-245.06558,1.0392632,-1.3492777,80.98763,355000
0.2512111,9.865904,-14.560915,-188.62486,-251.59468,0.9309238,-0.89012253,58.29041,360000
0.19644736,10.907866,-22.813526,-185.70317,-248.37788,0.7481969,-0.86364496,54.49718,365000
0.23539871,9.238828,-19.648504,-188.98352,-254.66817,0.7607218,-1.1853617,46.342056,370000
0.23368421,9.398261,-14.537296,-185.53667,-256.63077,0.626831,-0.887493,54.763725,375000
0.2180931,8.901842,-10.19008,-186.23018,-245.973,0.46755505,-0.49545157,50.219006,380000
0.22697516,9.361336,-18.595922,-190.87956,-258.27597,0.7993123,-1.0194055,56.75827,385000
0.23436175,12.721748,-13.865439,-186.88957,-263.28934,1.3241432,-0.5309201,47.228302,390000
0.21823841,7.2363076,-18.86972,-194.66959,-251.63992,0.5232587,-0.4727902,39.620293,395000
0.23406643,10.201799,-17.756092,-190.15045,-254.68433,0.79913247,-0.90040505,52.767776,400000
0.25452137,12.074523,-16.661507,-190.28453,-264.55438,0.66477466,-0.5541732,44.1827,405000
0.25074863,11.447145,-5.1804433,-190.6168,-254.4426,0.74180937,-0.49121004,53.257935,410000
0.2802819,9.92839,-9.254949,-184.32668,-258.7719,0.57925755,-0.46463495,47.169735,415000
0.22807972,10.385582,-14.19397,-182.60461,-252.21797,0.94144845,-0.91767484,52.335827,420000
0.24525568,11.440805,-4.0283947,-190.12164,-252.74602,0.482726,-0.44033384,46.037437,425000
0.27506715,10.2214985,-11.358953,-188.01277,-274.0549,0.90756327,-0.9242424,60.50921,430000
0.26980743,10.607382,-18.901466,-187.48495,-263.0153,0.6842109,-0.6644366,56.632706,435000
0.25306138,8.635003,-13.760778,-192.15637,-265.5492,0.62307453,-0.36366025,43.70398,440000
0.23318934,9.295308,-22.982365,-191.42601,-253.72511,0.82057166,-0.78001225,61.89215,445000
0.23490019,10.180344,-10.355659,-186.75545,-260.66525,0.5418245,-0.52431875,47.591972,450000
0.23214053,9.525148,-14.198555,-189.45709,-256.93918,0.58903915,-0.30862734,45.1967,455000
0.25931105,10.422446,-13.161998,-187.79437,-264.65924,0.7103919,-0.6752369,52.55693,460000
0.23922503,7.5033007,-17.616512,-192.31856,-271.49686,0.53609276,-0.55562323,41.989433,465000
0.2517023,9.704528,-5.589724,-180.37654,-259.70102,0.5824288,-0.8836925,65.91198,470000
0.23650424,8.747965,-11.784016,-189.38132,-253.63773,0.90369326,-0.8528719,47.94922,475000
0.25560558,9.576868,-8.801677,-187.21964,-263.77963,0.47539437,-0.63179094,48.15255,480000
0.23504019,14.92401,-15.211294,-189.92244,-271.52362,2.1125479,-2.1683245,79.31961,485000
0.25651693,11.477056,-12.918302,-181.69412,-258.24283,0.47201142,-0.44505882,49.671562,490000
0.2486566,10.989722,-16.433823,-189.06006,-274.03012,0.28797033,-0.33376247,37.701385,495000
0.24861619,7.915413,-9.551641,-187.82,-272.3377,0.55030507,-0.54880667,39.5586,500000
0.28654733,9.161628,-17.700705,-187.26619,-257.2795,0.6696472,-0.73392296,46.367588,505000
0.26950073,9.304248,-6.432826,-189.91911,-259.6881,1.1087409,-1.0682299,47.793587,510000
0.27893645,8.026453,-12.605689,-185.10277,-266.4377,0.9250439,-0.9291733,42.05373,515000
0.24705103,10.908963,-13.918901,-189.35277,-265.55292,0.8502538,-0.42012787,56.42876,520000
0.21998434,10.585095,-9.391996,-190.71056,-270.44437,0.50892377,-0.433458,49.57994,525000
0.25299525,8.519218,-15.492084,-187.4918,-260.30746,1.0216632,-1.0583401,49.39599,530000
0.29862192,9.674991,-17.640055,-184.8505,-282.2139,0.93830526,-0.9463634,43.707973,535000
0.22195677,10.69603,-3.4259367,-184.23538,-255.80257,0.60089356,-0.63429093,56.99113,540000
0.2872513,10.32936,-11.035748,-180.69115,-269.55426,0.55338717,-0.6914362,44.01593,545000
0.25713724,8.616122,-11.759751,-183.16278,-260.45477,0.6291447,-0.6374226,40.169052,550000
0.26683578,7.257725,-8.940119,-190.36092,-269.36597,0.36934558,-0.4851183,38.712894,555000
0.27480227,9.620099,-8.728056,-180.89624,-271.65622,0.6724979,-0.77895725,53.924812,560000
0.25987327,8.957971,-1.4806036,-184.32132,-259.85175,0.5275012,-1.076823,67.45964,565000
0.2322219,9.896286,-13.714369,-185.02005,-266.66504,2.1918905,-2.4634945,84.57757,570000
0.29301408,8.858714,-0.55298984,-184.17131,-274.04666,0.33724135,-0.31538254,38.13984,575000
0.2497949,8.399773,-10.530357,-192.44975,-277.54147,0.60568607,-0.42954972,45.121487,580000
0.25661305,9.772571,-13.192622,-192.84795,-260.65198,0.54123986,-0.54146403,43.445827,585000
0.2758891,11.750505,-10.651894,-182.40373,-266.98828,0.6941514,-0.7565148,46.28627,590000
0.25870836,9.296644,-11.612806,-182.15448,-264.5152,0.6826399,-0.47096792,39.135136,595000
0.26083255,8.04483,-8.111745,-189.2277,-254.11472,0.91651535,-0.7728515,42.290726,600000