O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/cgql/20260324_162305/online_agent.csv

actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
0.20371293,11.802498,-64.22159,-215.33138,-255.28448,0.6681028,-0.69547915,52.916603,205000
0.20463958,9.775073,-120.91399,-212.10301,-249.71063,1.6124135,-0.97495115,59.339424,210000
0.19038452,9.444701,-89.72525,-210.10356,-250.12029,0.7298001,-0.7957616,46.736816,215000
0.20514402,12.371544,-125.01078,-215.52258,-245.85217,0.6464044,-0.54736793,48.628513,220000
0.2284896,11.11306,-83.7838,-212.94385,-258.27548,0.74666417,-0.71252346,64.34476,225000
0.19639859,8.131555,1.5015382,-214.81978,-260.39822,0.55324554,-0.4342831,43.833996,230000
0.20285927,9.770413,-98.802605,-213.78516,-247.75903,0.73467726,-0.8696715,51.373913,235000
0.22598821,10.550569,-77.18579,-210.85997,-247.09697,0.7367881,-1.0308578,69.49618,240000
0.19492152,13.2529545,-87.536736,-209.40495,-253.84805,0.4292197,-0.68355495,61.270046,245000
0.21097778,8.022339,-70.328224,-203.58527,-250.84494,0.4599523,-0.55376834,50.668404,250000
0.1772263,7.909221,-64.595085,-198.81956,-233.80284,0.8444898,-0.5635702,39.475758,255000
0.22095348,9.833327,-46.11379,-197.82465,-241.50581,0.58653456,-0.7982017,43.790226,260000
0.21254957,7.2617464,-69.67823,-198.16486,-246.5553,0.38907856,-0.49551842,35.690933,265000
0.18551329,9.793708,-59.906948,-190.61635,-249.23242,0.55990356,-0.601412,48.74922,270000
0.22027636,11.478298,-24.06489,-190.90314,-243.14023,1.2536036,-1.2415195,53.835148,275000
0.21184325,9.570814,-27.70974,-187.98611,-236.25438,0.49885705,-0.38663015,39.40906,280000
0.21167718,11.344054,-24.706377,-191.9805,-237.3328,0.48023555,-0.62856185,48.102757,285000
0.19237292,9.977429,-53.993534,-192.92822,-236.90262,1.222924,-1.1973251,65.824295,290000
0.2124281,11.130531,-44.033154,-192.1617,-245.60771,0.8833944,-0.9292266,53.384575,295000
0.21738884,16.679876,-45.80271,-187.04166,-249.25386,1.3180664,-1.4065912,73.394775,300000
0.17927262,10.120048,-32.065826,-186.61624,-240.76907,0.71126574,-0.6769341,44.634377,305000
0.2155982,14.801663,-48.09173,-186.42989,-231.78085,1.5215039,-1.0295833,70.33073,310000
0.18271565,10.527132,-26.497437,-184.30302,-235.99515,0.88888985,-0.862662,60.839928,315000
0.1937371,9.058487,-28.782116,-185.32018,-236.3338,1.0403742,-1.0205668,55.289364,320000
0.19871801,13.319892,-19.593851,-193.49364,-245.65211,0.6942824,-0.9615432,56.59749,325000
0.22977208,8.461592,-41.512165,-188.13623,-246.44908,1.0201232,-1.0848036,66.88655,330000
0.20089999,12.748689,-29.142128,-190.92586,-239.12048,1.0462768,-1.0860581,51.424427,335000
0.199556,9.340202,-34.647842,-190.02074,-240.5903,0.73857564,-0.73485667,53.91601,340000
0.24133798,11.989216,-23.101904,-186.11623,-240.85966,0.6914821,-0.68690085,52.84263,345000
0.20883252,9.546336,-29.096146,-191.82211,-240.43616,0.51240146,-0.52528673,49.304432,350000
0.21229039,13.4431,-20.855103,-191.3392,-251.46674,0.5733199,-0.69570124,55.50834,355000
0.258219,9.594097,-16.87881,-190.05229,-249.1745,0.6146684,-0.6332931,45.019783,360000
0.22374827,11.915567,-16.40769,-193.39168,-255.88306,0.5827794,-0.5474609,46.664124,365000
0.21012913,10.820579,-32.274654,-189.2822,-262.43024,0.6473294,-0.54540586,57.62053,370000
0.23717237,10.592802,-25.213873,-193.19626,-246.3953,0.72667295,-0.7669495,48.682953,375000
0.22348496,8.991376,-6.428416,-191.48363,-249.7562,0.730684,-0.69193774,43.239456,380000
0.2219713,9.994584,-26.548487,-189.00049,-249.80554,0.6271815,-0.6663075,52.391167,385000
0.21291095,11.254478,-9.794211,-189.53336,-248.31183,0.6498231,-0.7340814,50.928024,390000
0.21341842,9.330836,-17.691904,-195.69452,-249.73607,0.70933276,-0.34149504,51.13226,395000
0.2148567,8.770765,-25.739134,-191.60802,-263.92725,0.5666426,-0.62305355,50.163055,400000
0.22650303,13.418937,-15.402519,-191.84746,-254.10191,1.1980333,-0.6544223,64.03183,405000
0.21042871,9.1953745,-23.430876,-195.19133,-276.21823,0.9933948,-1.5948532,57.22103,410000
0.2650179,8.073653,-29.726017,-192.979,-267.2044,0.79512143,-0.87267524,57.24877,415000
0.19873762,7.402126,-31.88447,-197.26602,-273.7108,0.94479376,-0.84286314,46.355637,420000
0.24025643,12.262536,-2.7177696,-200.01924,-259.23013,1.5289984,-1.6485958,73.51213,425000
0.24421272,9.996517,-18.246012,-198.88246,-267.13147,0.66386837,-0.47184375,49.260036,430000
0.20646998,8.550426,-22.437077,-198.66907,-261.46124,0.6900809,-0.4944959,49.180374,435000
0.2454092,7.446112,-21.616985,-197.42818,-255.84676,0.8738832,-0.88941044,49.565727,440000
0.27621448,12.174987,2.7350416,-197.08864,-271.5802,0.6339866,-0.95723534,48.677246,445000
0.21559954,8.065538,-15.8945465,-201.82913,-265.88278,0.6451289,-0.6813554,42.795425,450000
0.21893513,9.359648,-2.5377555,-198.14616,-257.2933,0.7609156,-0.51871437,42.868824,455000
0.25894666,7.095833,-23.555916,-198.58957,-262.77786,0.5468687,-0.8068996,49.531193,460000
0.21530823,9.039078,-18.756279,-197.27632,-263.50943,0.6682463,-0.68618023,43.975113,465000
0.23839758,9.298197,-20.666456,-201.59517,-259.77097,0.84878683,-0.5027435,49.161133,470000
0.23834386,11.58203,-14.551603,-194.94205,-272.50864,1.3750314,-1.3469507,62.132133,475000
0.24370846,7.4119544,-17.199375,-195.06413,-259.30798,0.59584635,-0.5769553,46.438957,480000
0.1863831,8.539557,-18.177433,-197.05188,-273.3276,0.6631301,-0.47613826,47.84548,485000
0.24399525,10.339454,-15.179802,-194.89555,-271.64627,0.44240904,-0.4824661,43.743134,490000
0.22100028,7.3946023,-18.404724,-201.02766,-265.50314,0.660938,-0.85621744,54.386894,495000
0.25665605,10.026736,-18.211237,-196.01555,-266.50903,0.73105985,-0.5142173,59.699314,500000
0.26913753,7.822206,-16.256622,-196.88348,-266.89493,0.4429361,-0.4823245,36.869015,505000
0.27593026,11.93397,-19.628277,-195.40105,-277.52725,0.8291196,-0.81962895,65.3634,510000
0.25762057,8.797063,-10.5051985,-193.35924,-276.91315,0.7529334,-0.7199995,48.78499,515000
0.26933184,11.507493,-8.554894,-189.65056,-262.10843,0.9205479,-0.68486524,56.883953,520000
0.22623673,9.590076,-1.4682685,-199.13028,-272.43088,0.86571383,-0.63617706,48.462578,525000
0.25004268,9.428004,-14.160945,-196.40205,-284.10684,0.9209338,-0.88900846,50.580856,530000
0.27190298,11.057424,-11.692807,-193.67068,-266.61157,0.44243965,-0.7263421,48.22996,535000
0.21567552,7.74616,-2.7607589,-199.56064,-270.79437,0.5258605,-0.69962454,37.278435,540000
0.24240142,14.609027,-21.196203,-198.82756,-268.86047,0.9515805,-0.70470464,55.23231,545000
0.23556536,10.459376,-17.189993,-195.44995,-277.02234,0.6555184,-0.61809886,46.630936,550000
0.2344407,8.530951,-13.229037,-199.02086,-285.2502,0.46397954,-0.95871073,63.728935,555000
0.24842815,9.422953,-16.04262,-194.4125,-264.73993,1.3241745,-1.2639968,62.38665,560000
0.24854824,12.096639,-26.123793,-197.29558,-285.70016,1.2364442,-1.3170295,101.640236,565000
0.2472743,10.172271,-6.243801,-187.97072,-272.9332,0.55151325,-0.85395133,56.51509,570000
0.24556664,11.553341,-14.196299,-195.39484,-265.76782,0.8067334,-0.5538272,57.33505,575000
0.21762848,9.320983,-7.580908,-193.64981,-272.9369,0.53867316,-0.715485,52.755775,580000
0.23305486,7.955461,-16.526484,-194.84804,-269.65924,0.5627722,-0.60594916,45.08783,585000
0.23818873,9.237349,-10.761425,-190.27808,-270.6337,0.53852326,-0.9978196,48.64238,590000
0.25729427,11.062579,-15.77628,-195.4536,-298.48285,0.395015,-0.7286392,46.785965,595000
0.25165227,7.970506,-10.23993,-190.76553,-269.39102,0.6640635,-0.45944113,40.937145,600000
0.27799058,7.207251,-11.872495,-198.71495,-266.0887,0.58069754,-0.4572058,41.541077,605000
0.27416575,9.663206,-1.903784,-197.42004,-274.92712,3.1626756,-3.6144958,95.85866,610000
0.2873939,9.027907,-11.364601,-192.40953,-277.31024,0.8545231,-1.0536832,58.12655,615000
0.23771754,7.4524827,-11.590958,-193.78238,-266.17487,0.6170709,-0.6190426,37.260185,620000
0.21912158,6.981346,-15.240249,-198.29272,-279.87045,0.9873453,-1.1741878,47.954647,625000
0.24793603,6.985181,-4.544094,-195.61694,-270.80185,0.39519054,-0.4802824,38.355965,630000
0.25969964,9.391535,-12.697726,-193.99692,-288.25656,0.46036208,-0.542031,43.454967,635000
0.28523564,11.465241,-12.265231,-189.30121,-272.59647,0.38361877,-0.7007493,44.318317,640000
0.2923115,10.389416,-5.364705,-186.74307,-276.262,0.80874974,-1.2233877,57.12085,645000
0.27160853,9.37946,-7.2355394,-190.481,-273.23416,0.8009324,-0.6859633,55.201557,650000
0.28979066,7.4072375,-9.539728,-195.63298,-286.25366,0.34420612,-0.5231329,41.294693,655000
0.27987027,7.813029,-7.285699,-188.14067,-276.547,0.4713252,-0.48997635,40.402138,660000
0.2753346,8.662714,-9.340708,-191.92332,-269.39285,0.79115325,-0.76007503,44.461983,665000
0.2557491,8.926847,-3.2685933,-192.57722,-271.76266,0.5868467,-0.62500066,44.82112,670000
0.3012075,8.848456,-23.139402,-193.15555,-278.49542,0.32407397,-0.5205706,41.734924,675000
0.2591666,10.381126,-19.694105,-201.73242,-276.9153,0.48269343,-0.5305508,50.21386,680000
0.25294736,8.014714,-7.776815,-198.03972,-278.0432,0.72264636,-0.89873385,49.25196,685000
0.281227,9.014419,-10.288513,-191.33475,-282.5162,0.87202716,-0.7196968,45.72914,690000
0.3082193,10.648782,-5.433712,-189.02332,-281.22552,0.6211634,-0.6662702,45.23021,695000
0.27382022,5.642219,-8.250152,-197.92345,-280.3989,0.61452585,-0.6313513,44.021088,700000