O2O / O2O-w-diff-ckpts /cube-triple-play-singletask-task1-v0 /rebrac /20260327_034037 /online_agent.csv
| actor/action_std,actor/actor_loss,actor/bc_loss,actor/mse,actor/total_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step | |
| 1.0,0.99999994,0.006939605,0.6939605,1.0069395,7.797007,-134.97946,-280.41998,-306.45642,3.9834557,-3.3307495,154.8898,605000 | |
| 1.0,0.9999999,0.0077142483,0.7714249,1.0077142,1.8326676,-144.52847,-276.63974,-308.5027,0.3064831,-0.33289278,29.362553,610000 | |
| 1.0,1.0,0.007433554,0.7433554,1.0074335,2.0132256,-120.188416,-272.5721,-306.7316,0.24487253,-0.34298506,29.664452,615000 | |
| 1.0,1.0,0.0073700855,0.7370086,1.0073701,1.8885307,-173.07855,-279.14053,-307.58524,0.41491157,-0.6019633,29.35925,620000 | |
| 1.0,1.0,0.0073542306,0.7354231,1.0073543,1.8292147,-111.2861,-278.0288,-306.54782,0.31986657,-0.27723855,26.90563,625000 | |
| 1.0,1.0,0.006740022,0.6740022,1.00674,2.4996078,2.4726987,-277.097,-306.94455,2.0158558,-4.4552474,65.61555,630000 | |
| 1.0,1.0,0.0075617633,0.75617635,1.0075618,1.9482502,-113.69652,-280.9823,-307.73972,0.83327454,-0.49475735,31.18629,635000 | |
| 1.0,0.9999999,0.007267262,0.7267262,1.0072671,2.1461656,-103.22004,-277.5314,-306.9229,0.3365489,-0.6656267,29.983747,640000 | |
| 1.0,1.0,0.0067867553,0.67867553,1.0067867,1.8810635,-102.30688,-278.94293,-307.17307,0.45123234,-0.3816021,27.163006,645000 | |
| 1.0,1.0,0.007111867,0.71118665,1.0071119,2.1037748,-102.26555,-276.3899,-307.34637,0.56493247,-0.7616645,36.30103,650000 | |
| 1.0,0.99999994,0.0070430506,0.70430505,1.007043,2.0737102,-102.08785,-275.1542,-306.36108,0.65067977,-0.6546958,33.032177,655000 | |
| 1.0,0.9999999,0.007712546,0.77125466,1.0077125,1.9781955,-101.41021,-276.28375,-307.36566,0.52501225,-0.3227281,29.774837,660000 | |
| 1.0,1.0,0.007825183,0.78251827,1.0078251,2.2229383,-101.79869,-277.15704,-307.3723,0.9425175,-0.3934868,32.7376,665000 | |
| 1.0,1.0,0.008147096,0.81470966,1.0081471,1.7931617,-101.67364,-270.94846,-308.0327,0.6501871,-1.543381,31.917164,670000 | |
| 1.0,0.99999994,0.008001206,0.8001206,1.0080011,2.0211465,-34.05183,-267.7389,-306.83646,0.37485683,-0.37751603,27.369257,675000 | |
| 1.0,1.0,0.008252682,0.82526827,1.0082527,2.3602288,-100.48712,-270.42563,-307.7106,0.58588904,-0.32803887,35.233997,680000 | |
| 1.0,1.0,0.008181267,0.81812674,1.0081812,2.0421827,-20.180458,-271.41144,-307.45444,0.27173543,-0.3992725,29.47791,685000 | |
| 1.0,1.0,0.007241321,0.7241321,1.0072414,1.6468823,-100.58062,-272.9526,-306.33746,0.33321065,-0.5395086,23.115873,690000 | |
| 1.0,1.0,0.008407846,0.84078455,1.0084078,1.7661949,-100.16265,-273.5586,-308.0477,0.46515065,-0.2932447,26.947212,695000 | |
| 1.0,1.0000001,0.007302054,0.7302054,1.0073022,2.3410087,-100.3398,-269.83292,-307.2339,0.6339575,-1.5654252,37.513657,700000 | |
| 1.0,0.9999999,0.0070607006,0.70607007,1.0070605,1.598365,-101.08811,-274.70584,-306.37067,0.17903283,-0.2712995,22.567175,705000 | |
| 1.0,0.99999994,0.007769492,0.77694917,1.0077695,1.8223114,-100.56481,-275.46262,-306.93985,0.6194258,-0.3105813,26.520035,710000 | |
| 1.0,0.99999994,0.007250596,0.7250596,1.0072505,2.67721,-101.00929,-268.46384,-306.87695,1.0837766,-0.95969963,41.871124,715000 | |
| 1.0,0.99999994,0.007310167,0.73101664,1.0073102,1.5091741,-100.85992,-268.58582,-306.4635,0.3917191,-0.5754552,28.287594,720000 | |
| 1.0,1.0,0.007289632,0.72896326,1.0072896,1.3900832,-100.573,-274.72092,-306.81174,0.3152185,-0.43788457,24.316462,725000 | |
| 1.0,0.9999999,0.0074863834,0.74863833,1.0074862,1.6177777,-100.90267,-272.0381,-306.98334,0.65391624,-0.5442856,25.926695,730000 | |
| 1.0,0.9999999,0.006948308,0.69483083,1.0069482,1.8033183,-100.37633,-272.45142,-307.50842,0.5210306,-0.5617948,24.131603,735000 | |
| 1.0,1.0000001,0.0075228023,0.75228024,1.007523,1.671339,-100.939705,-268.8918,-306.73566,0.7415279,-0.431942,30.38176,740000 | |
| 1.0,0.99999994,0.007896613,0.78966135,1.0078965,1.7153414,-101.281136,-268.4189,-307.2442,0.64195544,-0.7940818,36.13011,745000 | |
| 1.0,1.0,0.0070126755,0.70126754,1.0070127,1.7816113,-100.423096,-270.55795,-307.1738,0.4887466,-0.91492873,27.865925,750000 | |
| 1.0,1.0,0.007220027,0.72200274,1.00722,1.5914986,-100.042885,-271.0649,-306.27792,0.63290596,-0.4050324,29.543451,755000 | |
| 1.0,1.0,0.0067068404,0.6706841,1.0067068,2.2727795,-100.919,-265.1237,-307.66818,1.1888747,-0.61451894,45.08323,760000 | |
| 1.0,1.0,0.007868402,0.78684014,1.0078684,3.0524297,-101.12042,-268.18924,-306.9014,1.1294479,-0.72484773,49.426086,765000 | |
| 1.0,1.0000002,0.007886597,0.78865975,1.0078869,10.757331,-100.85931,-267.37015,-306.63242,5.553249,-6.5597763,214.39484,770000 | |
| 1.0,0.9999999,0.0074304435,0.7430444,1.0074303,1.4329948,-100.477684,-267.8186,-306.40002,0.66402924,-0.42915884,28.115992,775000 | |
| 1.0,1.0,0.008097691,0.80976915,1.0080976,2.1645653,-100.43023,-266.3774,-306.28375,0.4952232,-0.6729416,28.879734,780000 | |
| 1.0,1.0,0.007701687,0.7701688,1.0077016,1.643857,-100.55803,-262.15582,-305.73782,0.30008242,-0.38279253,25.339813,785000 | |
| 1.0,1.0000001,0.007789804,0.7789804,1.00779,1.5498767,-100.549324,-265.04227,-306.71915,0.26115397,-0.60246885,23.962006,790000 | |
| 1.0,1.0,0.0077009266,0.77009267,1.0077009,1.8509899,-100.46483,-269.32858,-306.07965,0.26680398,-0.37292302,26.806116,795000 | |
| 1.0,1.0,0.008151526,0.8151525,1.0081515,2.0041852,-100.900154,-263.64215,-306.04785,2.469689,-3.4815269,49.105072,800000 | |
| 1.0,0.99999994,0.008600295,0.8600295,1.0086002,1.6280781,-100.69205,-263.54147,-307.0325,0.564957,-0.49422085,28.702646,805000 | |
| 1.0,1.0000001,0.007985593,0.7985593,1.0079857,1.7020016,-100.35052,-265.77484,-306.20178,0.38983166,-0.36674333,25.286327,810000 | |
| 1.0,1.0,0.0074706255,0.74706256,1.0074706,1.2590772,-100.53794,-262.23477,-307.32,0.49726537,-0.32626885,22.57565,815000 | |
| 1.0,0.99999994,0.0077934577,0.77934575,1.0077934,1.7021748,-100.36264,-268.3416,-308.26685,0.23281041,-0.3191223,22.64048,820000 | |
| 1.0,1.0000001,0.006966346,0.6966346,1.0069665,1.9623555,-100.735016,-268.69067,-306.658,1.4937825,-0.5661268,36.545517,825000 | |
| 1.0,0.99999994,0.007675007,0.76750064,1.0076749,1.7933114,-100.30485,-269.1529,-307.04587,0.29726422,-0.31963393,24.770767,830000 | |
| 1.0,1.0,0.007084734,0.70847344,1.0070847,1.4708885,-37.97389,-266.77554,-306.4952,0.5290093,-0.34460205,24.927853,835000 | |
| 1.0,1.0,0.007472287,0.74722874,1.0074723,1.9048722,-99.71624,-268.3276,-306.9303,0.41819346,-0.2885177,28.455502,840000 | |
| 1.0,1.0,0.007548889,0.7548889,1.0075489,1.6468785,-42.27764,-260.42123,-307.56906,0.2721579,-0.31416422,26.187204,845000 | |
| 1.0,1.0,0.0074844407,0.7484441,1.0074844,1.4655763,-100.443016,-271.91946,-307.08105,0.3536068,-0.35975608,21.937767,850000 | |
| 1.0,1.0,0.0071305507,0.7130551,1.0071305,1.521149,-100.52601,-263.90524,-306.4784,0.38007796,-0.42834452,25.701614,855000 | |
| 1.0,1.0,0.006872245,0.6872245,1.0068723,1.4690231,-100.19421,-265.24982,-306.7828,0.6527201,-0.70081854,27.777792,860000 | |
| 1.0,0.9999999,0.0071885604,0.71885604,1.0071884,1.3795394,-100.073425,-264.85947,-306.3558,0.24415766,-0.25364423,21.201933,865000 | |
| 1.0,0.99999994,0.007153243,0.7153243,1.0071532,1.586574,-100.589966,-267.25235,-306.72794,0.45801413,-0.42212754,24.834408,870000 | |
| 1.0,0.99999994,0.007395585,0.73955846,1.0073955,1.9842824,-45.810303,-261.1286,-307.00974,0.36545599,-0.34177595,25.946175,875000 | |
| 1.0,1.0,0.008108743,0.8108742,1.0081087,1.1879137,-100.05564,-261.62564,-307.07468,0.86400664,-0.40995812,26.994904,880000 | |
| 1.0,1.0,0.007319123,0.7319123,1.0073191,1.5975733,-100.570915,-267.23145,-306.73145,0.78154886,-0.5266981,30.032522,885000 | |
| 1.0,1.0,0.007392781,0.7392781,1.0073928,1.6275218,-100.56482,-260.89966,-308.46378,0.28888774,-0.69959784,30.269875,890000 | |
| 1.0,0.99999994,0.007821377,0.78213775,1.0078213,1.0757413,-100.507935,-266.37662,-306.0633,0.7456508,-0.4742229,21.596626,895000 | |
| 1.0,1.0000001,0.0075217355,0.75217354,1.0075219,1.6618828,-100.480965,-260.74606,-305.59912,0.2526071,-0.47502568,23.105053,900000 | |
| 1.0,1.0,0.0072320616,0.72320616,1.0072321,1.6203291,-100.42319,-261.00153,-306.66864,0.378586,-0.90314436,27.259447,905000 | |
| 1.0,0.99999994,0.008386923,0.83869237,1.0083869,1.7493114,-100.395775,-259.8615,-307.27734,0.43628758,-0.35625118,24.935871,910000 | |
| 1.0,1.0,0.0084531605,0.8453161,1.0084531,1.9757451,-100.469086,-255.8861,-306.3751,0.5242338,-0.80781895,32.612556,915000 | |
| 1.0,1.0,0.0067308233,0.67308235,1.0067308,1.886697,-100.54134,-252.19511,-306.70868,1.0262381,-1.8876047,43.475395,920000 | |
| 1.0,0.99999994,0.007922389,0.79223895,1.0079223,1.3664669,-100.06662,-262.8461,-307.37634,0.37092823,-0.26643395,22.765099,925000 | |
| 1.0,0.9999999,0.0077056913,0.77056915,1.0077056,1.7493156,-81.11521,-257.84335,-306.45407,0.31487334,-0.8786442,29.896132,930000 | |
| 1.0,1.0,0.008037176,0.8037176,1.0080372,2.1546285,-100.44813,-257.32602,-306.57254,0.55093867,-0.683087,39.614258,935000 | |
| 1.0,1.0,0.008601138,0.8601138,1.0086012,1.509661,-100.408775,-264.1974,-306.3838,0.5519631,-0.27054304,24.919937,940000 | |
| 1.0,0.9999999,0.0075208247,0.75208247,1.0075207,1.9960285,-100.544106,-265.85992,-306.5938,0.62497354,-0.5850145,31.964579,945000 | |
| 1.0,1.0,0.007924385,0.79243857,1.0079244,1.8641701,-100.38891,-257.3608,-305.8338,0.62206185,-0.39814532,28.512589,950000 | |
| 1.0,0.9999999,0.00785976,0.78597605,1.0078596,1.7735653,-100.366646,-259.68146,-306.40796,0.517322,-1.839623,30.379833,955000 | |
| 1.0,1.0,0.0076808836,0.7680884,1.0076809,1.5027107,-100.62754,-258.83136,-306.30972,0.5065699,-0.36203992,26.777431,960000 | |
| 1.0,0.9999999,0.0067267762,0.67267764,1.0067266,1.0809207,-100.47417,-262.69415,-306.6467,0.46365935,-0.39452916,18.564896,965000 | |
| 1.0,1.0,0.0077598747,0.7759874,1.0077599,1.1436567,-100.3741,-254.11519,-306.30402,0.2893365,-0.21047485,18.539831,970000 | |
| 1.0,0.99999994,0.0071167024,0.7116703,1.0071167,1.4179598,-100.88885,-261.89624,-306.10168,0.31322306,-0.7330575,23.147339,975000 | |
| 1.0,0.99999994,0.007856697,0.7856697,1.0078566,1.4987935,-99.498955,-260.83487,-306.56442,0.3835861,-0.49322143,27.5102,980000 | |
| 1.0,1.0,0.0076056453,0.76056457,1.0076057,2.0371063,-51.268238,-259.27448,-306.46927,0.5279259,-0.82715416,43.270836,985000 | |
| 1.0,0.9999999,0.00798228,0.7982281,1.0079821,1.2314638,-100.63978,-256.9134,-307.2392,0.4189304,-0.3643111,22.722494,990000 | |
| 1.0,0.99999994,0.007942798,0.7942798,1.0079428,1.3867259,-95.676956,-258.91428,-305.5788,0.43873128,-0.5274869,23.927998,995000 | |
| 1.0,1.0,0.007862441,0.7862442,1.0078624,1.1871728,-98.78211,-256.15335,-305.41116,0.20301278,-0.65786546,19.581993,1000000 | |
| 1.0,1.0,0.007668153,0.76681536,1.0076681,1.2151641,-100.52604,-258.18582,-306.02133,0.4934066,-0.40798968,20.343052,1005000 | |
| 1.0,0.99999994,0.008143199,0.8143199,1.0081432,1.5982364,-100.56182,-258.5794,-305.70932,0.33573014,-0.59345573,26.883429,1010000 | |
| 1.0,0.99999994,0.007824552,0.78245527,1.0078245,1.1844679,-100.262665,-251.6936,-305.8689,0.32487535,-0.48718393,21.629776,1015000 | |
| 1.0,0.99999994,0.0070709456,0.70709455,1.0070709,1.1204001,-95.65195,-257.29034,-306.12625,0.26312876,-0.31203496,18.12083,1020000 | |
| 1.0,0.99999994,0.0073754746,0.7375475,1.0073754,1.2449459,-100.33451,-260.52975,-306.33878,0.23781574,-0.6150384,23.053085,1025000 | |
| 1.0,1.0,0.007779697,0.7779697,1.0077797,1.499412,-53.02363,-255.07133,-305.66272,0.6993952,-0.35236588,25.792572,1030000 | |
| 1.0,1.0,0.008013496,0.80134964,1.0080135,1.4741096,-100.59654,-253.7325,-305.52982,0.55758464,-0.32019138,23.34971,1035000 | |
| 1.0,1.0,0.008353354,0.8353355,1.0083534,1.6392828,-100.46802,-252.55437,-306.76025,3.3420072,-2.3695455,52.9387,1040000 | |
| 1.0,1.0,0.0082900645,0.82900643,1.00829,1.2702006,-40.366802,-249.33751,-306.29315,0.32646197,-0.3900365,21.73524,1045000 | |
| 1.0,0.9999999,0.008230228,0.8230228,1.0082301,1.4102969,-95.712616,-254.62163,-306.92654,0.5282599,-0.7413483,27.939392,1050000 | |
| 1.0,1.0,0.008113143,0.81131434,1.0081131,1.3055047,-100.27173,-255.43565,-306.92435,0.35056335,-0.32563043,22.8342,1055000 | |
| 1.0,1.0,0.0082479995,0.82479995,1.008248,1.5397013,-100.311165,-246.90764,-306.02585,0.25194883,-0.6011394,23.767277,1060000 | |
| 1.0,1.0,0.00723288,0.72328806,1.0072329,1.1438417,-91.955475,-250.91795,-305.68134,0.34989572,-0.27636844,21.540932,1065000 | |
| 1.0,1.0,0.0075513716,0.7551372,1.0075513,1.391984,-98.98456,-255.2061,-306.40616,0.33904284,-0.8513846,24.645386,1070000 | |
| 1.0,1.0,0.00755181,0.75518095,1.0075518,1.3262446,-100.57907,-251.5783,-306.80774,0.4436863,-0.40336537,24.874023,1075000 | |
| 1.0,1.0,0.008247068,0.8247068,1.008247,1.3159509,-99.12318,-260.39517,-306.07852,0.6720545,-0.23210013,23.288357,1080000 | |
| 1.0,1.0,0.0073755574,0.7375558,1.0073756,1.3913096,-59.600132,-258.36865,-306.65765,0.36568713,-0.5112938,24.52487,1085000 | |
| 1.0,0.99999994,0.008256326,0.82563263,1.0082563,1.5012703,-100.5675,-251.42113,-306.99625,0.70401907,-0.35071945,25.076195,1090000 | |
| 1.0,1.0,0.008027425,0.8027426,1.0080274,1.2891846,-100.265656,-248.57463,-305.22284,0.45721883,-0.3239353,25.640661,1095000 | |
| 1.0,0.99999994,0.0072685727,0.7268573,1.0072685,1.6880273,-100.188774,-257.55203,-305.7854,1.7675934,-0.40936816,33.567406,1100000 | |