O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_162754/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
0.18149361,10.770656,-69.63544,-178.48453,-203.45818,6.4619594,-5.2552533,88.74516,605000
0.18900698,9.030531,-55.09287,-176.65636,-202.55371,0.8122563,-0.7591868,39.263794,610000
0.16334763,14.62717,-63.787476,-173.77612,-203.13094,2.834384,-3.284259,89.98244,615000
0.17279549,8.796367,-45.594185,-171.53198,-203.23277,0.45103335,-0.35438013,35.860962,620000
0.17033543,14.035697,-63.363377,-170.49251,-203.6196,0.3611988,-0.24920782,30.50163,625000
0.1487838,13.171274,-52.99109,-168.62581,-203.3114,1.005476,-1.0268499,45.768658,630000
0.17093715,15.755618,-47.424934,-168.58818,-203.91971,0.56876236,-0.58015066,34.035267,635000
0.17306837,11.381632,-54.647984,-170.88017,-203.89455,0.25964648,-0.5181953,38.609604,640000
0.1726426,10.893585,-44.17311,-168.91743,-203.70294,1.8795323,-1.9288293,62.78119,645000
0.21124563,13.121109,-60.983456,-169.74138,-203.73184,2.8368087,-3.0079257,59.852863,650000
0.21604124,26.283895,-12.683628,-165.62279,-204.04395,1.1842676,-1.1546617,66.51207,655000
0.20794272,18.274607,-41.52997,-166.73763,-204.76328,1.0678836,-0.9047382,54.87703,660000
0.1841031,16.085785,-39.787453,-165.54208,-203.8896,0.4704731,-0.61251336,41.94644,665000
0.18265773,23.670889,-22.864594,-160.62877,-204.11401,0.68244535,-0.35235846,41.50007,670000
0.19592988,15.562625,-21.773092,-162.31816,-204.12729,1.2277611,-1.2209828,61.914665,675000
0.16973722,21.572844,-33.639614,-163.91907,-204.49228,4.5487204,-4.805919,107.964615,680000
0.17540517,24.482077,-11.219797,-158.24005,-204.03676,0.6222923,-0.4292074,50.49976,685000
0.18125317,21.67726,-13.872416,-155.19437,-204.58739,1.1825339,-1.1678051,59.061134,690000
0.19741122,25.183416,-27.536001,-156.66551,-204.33415,0.56458366,-0.5456915,47.523453,695000
0.21261409,14.777178,-24.02796,-152.87163,-205.41525,5.04823,-4.7617717,132.8537,700000
0.19905838,13.097626,-13.172584,-155.4646,-205.22931,0.37480423,-0.5980596,45.712456,705000
0.1810158,19.986425,-25.9632,-151.36205,-204.17108,0.7025285,-0.8701248,61.775562,710000
0.17825834,13.437314,-0.75335264,-150.42773,-203.78476,0.55345047,-0.37657487,43.33674,715000
0.1779558,18.367231,-9.718344,-151.21602,-204.5409,0.8900057,-1.3547488,56.748783,720000
0.15429404,18.564363,-12.166916,-152.86409,-203.36554,1.1626246,-0.98378754,56.16232,725000
0.18404125,17.591085,-9.588404,-151.6967,-203.0908,0.3552453,-0.66885453,48.197323,730000
0.18255621,20.340698,1.9639667,-151.83037,-203.23766,0.67076576,-0.4687282,56.49893,735000
0.14115596,14.015037,-13.592476,-147.35966,-201.14473,1.3861026,-1.365747,58.921494,740000
0.14994368,15.834683,-29.714256,-148.344,-201.23045,0.59826255,-0.61780745,44.301987,745000
0.15747133,15.860873,-9.775315,-149.5426,-203.44705,0.76527613,-0.7569389,52.886185,750000
0.17194635,12.824081,-35.980583,-147.76494,-204.042,1.0158801,-0.48425606,44.457592,755000
0.20447919,16.634949,-14.464982,-146.55916,-203.99866,2.2651043,-2.2789505,72.43519,760000
0.18404788,16.2477,3.0666661,-145.51329,-202.8693,1.4037758,-1.3667523,60.612892,765000
0.16979067,11.468221,-11.106342,-147.57051,-203.75787,0.39207378,-0.3917803,40.71564,770000
0.18300147,14.4105625,-24.573938,-151.09464,-202.91934,1.8821434,-1.5137308,52.374973,775000
0.18308401,21.382505,3.1143563,-145.21288,-202.72258,1.427079,-0.99529105,55.900784,780000
0.19801475,25.656311,-8.765387,-146.02332,-201.9457,6.0669737,-6.1205997,204.88818,785000
0.17999713,13.105371,-5.7999477,-142.64757,-202.45996,0.9060383,-0.895956,56.321045,790000
0.16619655,18.40803,-8.369674,-143.63939,-200.4639,0.45288143,-0.6642518,54.196983,795000
0.18101014,12.085637,-19.21122,-142.60388,-202.54877,0.38912752,-0.57242143,41.781048,800000
0.18757764,13.012662,-16.082989,-143.08609,-202.22423,0.4336656,-0.4560138,38.787373,805000
0.1770925,13.365439,-16.953074,-145.3564,-201.32529,0.6506002,-0.87504566,45.257603,810000
0.19132775,18.881903,-5.7923217,-142.41399,-205.0406,0.66165257,-0.6892584,49.838562,815000
0.17855182,14.265958,-9.707783,-141.94695,-198.73077,0.49123088,-0.4596376,42.28885,820000
0.18094277,18.282297,-17.7906,-138.96121,-199.92915,1.00289,-0.56299627,50.38916,825000
0.18825278,12.598001,-6.487669,-144.46309,-203.50366,0.67002875,-0.7109991,45.78469,830000
0.18515775,11.257098,-6.624858,-139.3612,-202.07173,0.9670785,-0.8552146,45.89318,835000
0.18476292,12.829785,1.6014817,-138.68854,-201.86208,0.73478943,-0.66708416,42.4556,840000
0.1660653,19.21007,-4.2469635,-140.90894,-203.35114,3.9505358,-3.5292032,128.81294,845000
0.156286,16.808012,-11.013762,-131.12463,-203.94562,0.6234627,-0.527684,44.51595,850000
0.16782859,13.886775,-1.9724091,-143.13174,-202.10703,0.5908528,-0.62315196,41.194847,855000
0.17823313,16.733658,0.084092766,-135.88925,-198.49994,0.5902613,-0.5594628,46.16589,860000
0.17253369,17.291811,-5.840454,-142.06227,-201.5159,0.6328767,-0.32974514,44.771667,865000
0.1449359,27.87469,0.6390357,-136.07233,-200.85098,1.88658,-2.1388693,94.56812,870000
0.15939578,18.917086,-0.406325,-135.6627,-204.69627,0.66237634,-0.6241346,47.821606,875000
0.17388284,15.784098,-13.692907,-138.851,-202.00154,0.70405364,-0.7911723,49.062603,880000
0.13275586,9.910104,-7.338972,-134.36339,-200.87196,0.50628763,-0.50515604,35.134144,885000
0.16266197,17.128855,-21.31716,-134.27068,-199.0033,1.0950606,-1.1320697,57.231415,890000
0.15334944,38.0532,-0.055494234,-133.09985,-202.90755,2.1598606,-2.0990908,130.15782,895000
0.18995085,21.228659,-2.2442575,-137.18782,-199.39703,0.8044864,-0.80173755,67.6462,900000
0.17172381,15.022082,-15.041162,-141.39742,-204.00298,1.4322855,-1.5151681,68.95676,905000
0.14906499,31.001326,-2.6715136,-134.62273,-202.1332,1.0137703,-1.0227699,65.02101,910000
0.19885328,19.156954,-3.7604945,-134.16624,-202.60478,0.76261604,-0.75871783,56.55289,915000
0.17051378,20.697302,5.0488563,-136.58003,-198.41803,1.0632218,-0.5431143,57.616707,920000
0.15836528,17.627895,-2.505874,-132.57362,-203.43884,0.7949646,-0.6911663,58.18158,925000
0.16860104,17.901625,2.7006292,-129.52713,-205.00339,1.3660346,-0.92344683,70.29282,930000
0.17989422,19.712727,-5.3049684,-130.45177,-202.73831,1.1848552,-0.9127667,77.76312,935000
0.2083143,24.790087,-3.0665379,-133.42505,-203.2743,1.3501201,-0.5533944,68.558334,940000
0.17328711,12.712865,-14.282575,-139.88158,-205.02493,0.296056,-0.44145182,30.17837,945000
0.18855762,32.596294,-5.7611322,-126.23006,-205.37166,0.7221476,-0.811638,66.977,950000
0.17027602,16.765284,-6.2760053,-136.6451,-202.1583,0.38034424,-0.40593058,38.59187,955000
0.15565985,20.369253,-0.6106086,-131.86089,-205.15436,0.6241219,-0.51773167,49.36305,960000
0.18814728,19.599277,-5.806262,-135.80257,-204.41669,2.106326,-2.048653,74.87982,965000
0.1791274,12.601131,-6.101187,-133.97095,-203.38925,0.87454295,-0.9783568,42.47452,970000
0.14682646,29.804932,2.0463717,-127.94216,-202.81204,0.6977848,-0.8988836,53.115845,975000
0.1622604,8.678998,-1.2907234,-130.09666,-205.72029,0.7998382,-0.6241276,36.126625,980000
0.1688441,23.659391,-4.34774,-132.48186,-203.23013,2.448882,-4.482315,116.989265,985000
0.16841732,12.765657,-3.766621,-132.70854,-197.94496,0.6145212,-0.62520176,46.51712,990000
0.17758667,14.05445,-7.932486,-133.77808,-202.74873,1.2619591,-1.0724149,60.382027,995000
0.13436377,19.969915,-9.864133,-133.26384,-200.12088,1.6320388,-1.6419907,57.88228,1000000
0.16641426,26.04758,-4.8172855,-132.57426,-202.89139,1.1307167,-1.4723741,71.29947,1005000
0.16146922,16.164785,-6.4092164,-138.23802,-197.72655,1.9359865,-2.059835,78.082535,1010000
0.16518447,16.15905,-0.27416843,-130.496,-201.4345,0.65617365,-0.7345609,52.201912,1015000
0.17268868,14.060981,-6.111781,-130.97081,-202.5192,1.142187,-1.1695116,59.323368,1020000
0.18335587,23.88639,-1.521777,-126.03356,-205.29593,0.60109717,-0.868268,54.996216,1025000
0.15765032,14.405054,-5.8119016,-127.2386,-203.32326,2.3038058,-3.287555,91.19762,1030000
0.17614523,18.675734,-6.113062,-130.54117,-203.41266,1.2814215,-1.3087206,79.51066,1035000
0.13339551,23.827509,-4.697192,-126.83091,-203.43567,0.8060874,-0.77415985,52.63987,1040000
0.16661187,21.924225,-2.549275,-134.09045,-202.10777,2.293522,-2.1966822,71.86399,1045000
0.16406903,14.454041,-0.87668055,-125.67122,-202.05528,5.3701177,-12.457293,85.578156,1050000
0.16261041,13.648926,-4.7572064,-129.65196,-201.83522,0.8868658,-0.35485572,45.365086,1055000
0.15964392,15.846898,6.4013276,-129.63217,-202.984,0.45694458,-0.71686697,44.347977,1060000
0.1601392,18.525248,4.044255,-128.9945,-201.067,0.8667977,-0.8954989,53.79528,1065000
0.18033966,11.139968,3.2880507,-128.09006,-197.92975,1.2166821,-1.3088068,50.64286,1070000
0.164108,16.196558,4.7928996,-126.654015,-203.01369,1.4573547,-1.6620568,73.20533,1075000
0.17255673,17.724543,1.5594741,-127.26284,-202.50389,0.76407105,-0.7381286,45.10688,1080000
0.17001326,28.536707,-0.44273394,-125.34552,-203.4257,1.6181571,-1.0990368,70.1046,1085000
0.1418097,17.100986,-0.10629429,-124.172585,-201.88438,1.6445886,-1.835743,58.54152,1090000
0.14041077,18.833567,-3.085478,-125.10967,-202.95346,0.67836666,-0.8969635,60.178577,1095000
0.15928507,11.11501,-3.1772742,-120.58144,-204.42258,0.84261864,-0.8591411,49.169456,1100000