O2O-w-diff-ckpts/cube-triple-play-singletask-task1-v0/cgql/20260325_174636/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
0.19562006,9.554044,-86.32441,-224.36754,-268.94098,0.50893897,-0.55329305,38.95229,405000
0.1851914,9.10905,-139.11562,-223.39844,-262.4037,0.790658,-0.6364833,45.401367,410000
0.2299172,8.478297,-95.47627,-220.26427,-258.76437,0.3341473,-0.44158643,36.412952,415000
0.16986556,7.7263484,-142.96106,-225.27625,-273.22046,0.6676563,-0.42287615,46.55578,420000
0.21046722,8.705988,-96.105125,-221.66295,-260.3634,0.53993124,-0.5135146,42.954712,425000
0.21101967,5.6397276,1.4254997,-218.54097,-264.43286,0.76039666,-0.7698584,40.115925,430000
0.17133701,7.4622407,-98.14849,-217.72684,-253.97679,0.487705,-0.3869359,33.291958,435000
0.20546202,8.502616,-74.66043,-215.3052,-264.22708,0.4299056,-0.6124099,41.957573,440000
0.20593856,7.2988315,-79.95084,-212.6951,-277.64578,0.5192374,-0.5922802,35.938377,445000
0.18039533,10.804018,-77.40353,-210.78271,-256.97797,0.5128953,-0.58142257,46.86564,450000
0.17917497,6.1743846,-65.90853,-210.67302,-252.615,0.6200152,-0.5811304,38.91163,455000
0.21092568,9.288061,-70.97661,-207.61055,-260.14514,0.35038298,-0.50060743,36.684006,460000
0.19379692,9.49824,-56.786663,-205.41759,-251.44702,0.44514298,-0.4450177,36.14976,465000
0.20380452,9.489539,-48.87471,-200.38197,-250.83746,0.59938776,-0.655882,47.05015,470000
0.19843176,13.733698,-30.032743,-194.26848,-245.4631,0.948238,-0.91635907,52.570812,475000
0.20442462,10.343336,-54.680317,-196.19182,-243.74757,0.6986343,-0.9094624,43.696697,480000
0.16963755,10.61779,-24.254942,-196.38872,-257.90134,0.7540697,-0.8665681,41.19345,485000
0.19732785,10.961362,-49.542297,-196.79568,-248.01953,0.6281394,-0.981156,43.600513,490000
0.20057741,11.624827,-54.413063,-195.4504,-252.6352,0.4234767,-0.5214193,37.14166,495000
0.18780676,9.849956,-31.01898,-194.34239,-248.031,1.0610198,-1.086867,42.12627,500000
0.22545178,12.319467,-33.461792,-192.98322,-251.34012,0.8140854,-0.91621065,46.327034,505000
0.22594771,11.445393,-13.429546,-192.35449,-237.91296,0.8742208,-0.82113016,56.536438,510000
0.21722633,10.164598,-26.589321,-187.38152,-240.99318,1.0479661,-0.95461607,46.950485,515000
0.192285,8.727744,-48.659897,-189.70609,-246.98755,0.5453192,-0.5183489,35.523716,520000
0.18143643,9.545379,-25.570948,-191.04439,-267.948,0.43451923,-0.3640577,38.32494,525000
0.20526534,13.143442,-14.121636,-187.33342,-258.63004,1.7681508,-1.8244812,92.2843,530000
0.22772703,10.05526,-22.875992,-186.46835,-236.42068,0.6503561,-0.53638446,51.950806,535000
0.18577276,12.044411,-23.442394,-184.54507,-237.51117,0.92868507,-0.7980976,46.705658,540000
0.21642984,11.49601,-12.680045,-182.02623,-241.17462,0.9871323,-0.7048248,47.88166,545000
0.1831302,10.658091,-39.106228,-186.93329,-244.76369,0.44281283,-0.5152392,38.31396,550000
0.22370774,11.273409,-13.778983,-188.75331,-240.61731,0.4357282,-0.6352315,48.577656,555000
0.21938881,9.476863,-28.745445,-182.3733,-247.09836,0.45680633,-0.50549203,40.346073,560000
0.21258572,11.383765,-6.653318,-180.99438,-248.72807,0.3855201,-0.41070217,37.639954,565000
0.22085434,11.384688,-21.42697,-179.04439,-251.43256,0.6670679,-0.72098565,47.120743,570000
0.216618,10.08018,-17.407103,-180.62547,-245.30609,0.5482706,-0.33552217,36.499878,575000
0.20512754,10.491332,-17.654036,-178.78398,-243.48521,0.7320169,-0.69411254,47.095024,580000
0.22002764,8.45148,-10.37965,-178.36824,-248.87872,0.69175184,-0.53551483,44.93841,585000
0.20957366,11.841002,-22.20695,-180.19789,-248.18362,0.68429303,-1.4515274,46.56013,590000
0.2018819,10.178737,-22.678291,-184.96638,-255.07817,0.633496,-0.69797426,44.28791,595000
0.24076718,7.810558,-5.642222,-182.17815,-253.22127,0.5832201,-0.71257997,44.262978,600000
0.2249797,8.810167,-13.215175,-181.29922,-268.05136,0.6900253,-0.32351744,45.346897,605000
0.20893729,12.380845,-15.513974,-182.89055,-261.7908,0.5537318,-0.5550942,44.810402,610000
0.23294488,9.018149,-9.27043,-181.95488,-288.50577,0.47213066,-0.61134374,43.105717,615000
0.20004982,12.052798,-12.567976,-181.58562,-243.71747,1.2152412,-0.8607624,67.33627,620000
0.19154607,10.780095,-19.103928,-187.95403,-250.00548,0.56644356,-0.52853125,43.224144,625000
0.19109112,12.057284,-15.772055,-186.54807,-265.9596,0.57511276,-0.5240979,39.380882,630000
0.19816771,9.888753,-20.741335,-185.8477,-275.77435,0.3382732,-0.4815695,35.8619,635000
0.20939912,11.218482,-15.580793,-188.60558,-264.33038,0.7973213,-1.0456287,70.161255,640000
0.24605569,12.68213,-8.574083,-183.64413,-265.21017,0.52720475,-0.895316,61.809376,645000
0.22187287,9.409436,-16.075333,-191.33362,-252.13184,1.2313094,-1.7818931,50.677277,650000
0.24104242,8.825445,-7.838924,-191.7064,-262.26697,0.39978266,-0.3785981,38.457638,655000
0.24400082,8.966102,-12.311522,-187.42833,-262.0443,0.43255824,-0.661192,44.228027,660000
0.2262883,13.659709,-6.27194,-187.64732,-273.11493,0.76659596,-0.814653,48.480114,665000
0.21656913,11.79,-19.795425,-191.64157,-256.43884,0.67121166,-0.4435366,44.452126,670000
0.2413789,11.927368,-6.7917376,-187.91719,-274.18192,0.9050312,-0.89177895,51.496017,675000
0.23411052,9.800276,-13.046568,-187.20769,-273.31558,0.61386126,-0.636104,45.01487,680000
0.20766594,10.7110405,-10.963879,-190.99748,-254.23515,0.7919618,-0.8298565,44.046875,685000
0.22422102,11.71976,-12.534754,-185.8792,-268.98758,1.4612746,-0.9227478,82.12457,690000
0.24435034,8.587059,-12.867555,-193.17612,-262.27527,0.71122557,-0.68679404,34.700943,695000
0.2419846,9.072243,-14.631435,-191.50972,-272.43152,0.673023,-0.45841634,44.908157,700000
0.25159723,13.252136,-9.565932,-189.37842,-263.3019,0.8864763,-0.96694034,52.47181,705000
0.2226329,12.013997,-9.137914,-189.11224,-292.27298,0.66870147,-0.66964614,51.21828,710000
0.24940673,9.256627,-10.000895,-183.43964,-263.50186,0.4764436,-0.42772135,41.29634,715000
0.24465835,9.748871,-9.81461,-184.32216,-256.67358,0.39391434,-0.46547365,40.18787,720000
0.21013287,9.992006,-6.552832,-188.79109,-253.44708,0.588408,-0.5079908,42.085106,725000
0.23970231,10.356696,-13.04039,-187.27852,-261.97977,0.7289174,-0.7502068,45.10511,730000
0.2425454,9.086841,-6.7299128,-185.69807,-257.14835,1.1195251,-1.2823013,53.763924,735000
0.20951822,11.024099,-16.53551,-191.99442,-286.17148,0.50612694,-0.517765,41.35126,740000
0.20213893,12.458567,-15.168885,-189.22935,-262.7821,0.9962595,-0.5447884,73.14408,745000
0.2156651,8.758434,-13.083808,-184.37459,-271.05646,0.53936887,-0.5567176,37.37456,750000
0.21562108,8.224021,-14.096779,-189.79651,-265.31607,0.30590564,-0.80282164,54.164993,755000
0.25986952,10.399869,-1.8225815,-188.15208,-268.22562,0.81316036,-1.0550393,56.52672,760000
0.21590212,7.2893,-15.803901,-194.62396,-284.0777,0.6852522,-0.31501022,42.48816,765000
0.25148878,8.680788,-8.964836,-183.73592,-266.92267,0.47232252,-0.503766,46.8135,770000
0.2394802,24.34908,-16.34218,-188.15097,-269.45145,3.1987634,-3.1039848,159.0206,775000
0.23382601,10.303396,-13.802018,-185.8541,-265.31537,0.73268783,-0.39326182,51.238827,780000
0.24542938,9.879602,-9.930203,-187.95964,-269.0917,0.5581979,-0.5862975,50.602135,785000
0.25416434,10.615561,-1.4138453,-183.27153,-261.59958,0.33771476,-0.6215292,43.04502,790000
0.24595934,7.7055736,-22.940989,-190.90645,-278.95425,0.6838521,-0.60574114,30.69441,795000
0.24275026,9.400208,0.67969596,-184.63992,-266.6244,0.62601554,-0.6184629,49.093147,800000
0.24433239,9.146388,-4.708815,-186.2694,-271.26498,0.53726745,-0.6209871,48.25056,805000
0.2770847,9.3440695,-4.948033,-190.41167,-296.70062,0.38503352,-0.5934127,38.719044,810000
0.24692073,11.304949,-12.979296,-184.98654,-275.10373,1.1476035,-1.1697073,57.971718,815000
0.22700754,9.634883,-2.1773481,-189.2267,-277.31613,0.6892246,-0.3753589,50.826683,820000
0.22692081,9.008121,-0.06176269,-192.152,-273.68555,0.3218089,-0.77439916,46.77824,825000
0.23702931,11.356674,-12.928366,-186.02208,-273.66962,0.6190051,-0.5323248,43.308327,830000
0.2582488,8.826428,-12.849865,-185.16614,-275.3753,1.1591119,-1.1582236,59.693497,835000
0.27928078,8.894149,0.6106151,-184.04529,-266.70197,0.5763279,-0.64099437,41.817715,840000
0.2767543,10.4271,-17.783957,-179.71756,-271.73694,0.9091723,-1.0996472,55.033813,845000
0.26880848,11.64818,-14.40091,-182.82631,-260.18396,1.1260583,-0.68090546,57.349,850000
0.26888865,9.575446,-3.8430107,-186.69052,-283.10788,0.50595903,-0.5235768,43.418716,855000
0.26473194,11.558637,-13.909842,-176.42836,-279.38434,1.1084832,-2.5745986,58.21077,860000
0.2552324,9.235015,-3.8205843,-181.98796,-282.79376,0.43025792,-0.80665314,52.062172,865000
0.22550029,9.379435,-13.015729,-183.61458,-272.90543,0.51871,-0.50361466,37.679024,870000
0.26111656,11.365982,-9.587444,-182.49408,-278.45358,0.64944,-0.48726133,48.02449,875000
0.26719302,9.007533,-13.311237,-187.7758,-274.10074,0.4899825,-0.71873057,49.30631,880000
0.2199546,10.875536,-9.92644,-187.1427,-269.315,0.63485897,-0.6386268,44.250214,885000
0.27091402,9.531296,-4.191404,-182.5394,-275.02283,0.55287224,-0.4710744,42.018272,890000
0.25370044,8.900024,-15.294019,-184.3127,-257.16464,1.4857036,-1.5085212,57.042324,895000
0.24989942,11.092531,-6.3018584,-188.52332,-278.89313,1.163205,-1.1788636,52.940987,900000