O2O / O2O-w-diff-ckpts /cube-triple-play-singletask-task1-v0 /rebrac /20260324_112642 /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 | |
| 1.0,0.9999999,0.012059895,1.2059896,1.0120598,6.7048717,-123.08677,-264.19415,-310.00662,1.4759508,-2.0628328,74.01593,105000 | |
| 1.0,1.0,0.011495486,1.1495486,1.0114955,5.9449325,-146.8958,-264.05066,-310.52612,2.044624,-1.3532896,82.099556,110000 | |
| 1.0,1.0,0.011562042,1.1562042,1.011562,6.8897586,-121.405235,-260.92795,-308.5011,1.9089075,-2.3326116,99.64841,115000 | |
| 1.0,1.0,0.011347694,1.1347694,1.0113477,6.2705474,-171.11322,-267.57706,-309.43054,0.7673544,-0.6896754,69.721855,120000 | |
| 1.0,0.99999994,0.011538059,1.153806,1.011538,6.0008063,-100.841034,-268.0533,-311.64197,2.5394254,-2.2243462,79.38674,125000 | |
| 1.0,0.9999711,0.0105982395,1.0598239,1.0105693,5.615629,3.5379815,-266.34198,-312.2433,0.7692989,-0.7858698,66.65705,130000 | |
| 1.0,0.99999994,0.010875659,1.0875659,1.0108756,5.0399356,-113.408264,-270.2445,-310.88156,0.73389757,-0.7881953,64.99785,135000 | |
| 1.0,1.0000001,0.010461694,1.0461694,1.0104618,5.4983964,-99.816605,-266.63004,-309.8541,2.608728,-2.3217897,82.664246,140000 | |
| 1.0,0.99999994,0.01027949,1.027949,1.0102794,5.3959107,-79.971756,-268.51508,-309.81516,1.3832054,-0.45404547,65.465836,145000 | |
| 1.0,1.0,0.009331047,0.93310475,1.009331,5.9667296,-100.66482,-267.98218,-312.5213,1.2082195,-1.0386688,76.522675,150000 | |
| 1.0,1.0,0.009563737,0.9563737,1.0095637,6.2828493,-94.59699,-267.46664,-311.92892,1.3896599,-1.1023946,82.64547,155000 | |
| 1.0,0.99999994,0.010263775,1.0263774,1.0102637,5.309801,-99.70585,-268.4654,-310.27533,0.89663696,-0.7530199,66.80292,160000 | |
| 1.0,1.0,0.01148425,1.1484251,1.0114843,5.5049844,-85.794205,-269.69373,-310.0209,0.97445154,-0.5818959,58.140514,165000 | |
| 1.0,1.0,0.010245806,1.0245805,1.0102458,5.1747756,-98.18382,-263.76382,-309.45218,1.532124,-0.5547272,64.53575,170000 | |
| 1.0,1.0,0.010203965,1.0203966,1.010204,5.304199,-33.47626,-261.17416,-309.55328,3.0057669,-2.3213415,100.69795,175000 | |
| 1.0,0.99999994,0.0105939135,1.0593913,1.0105939,5.4947968,-52.11161,-263.81793,-311.2895,0.96447784,-0.4562161,58.22,180000 | |
| 1.0,1.0,0.010394365,1.0394365,1.0103943,4.47685,-29.410576,-266.32654,-310.55435,0.9525189,-1.033912,59.14894,185000 | |
| 1.0,0.9999999,0.009521616,0.95216155,1.0095215,3.8670979,-94.06424,-266.5673,-310.98395,1.112679,-0.37816635,50.15999,190000 | |
| 1.0,1.0000001,0.010615628,1.061563,1.0106157,4.447414,-100.5329,-267.23956,-310.2803,0.9217174,-1.366242,72.89798,195000 | |
| 1.0,0.99999994,0.009361852,0.93618524,1.0093617,4.2588143,-74.26947,-263.60672,-309.5032,0.55760354,-0.6177246,50.95528,200000 | |
| 1.0,1.0,0.009507792,0.95077926,1.0095078,4.159681,-91.79437,-268.32346,-309.25677,2.2473328,-2.2673974,80.44311,205000 | |
| 1.0,1.0,0.010284379,1.0284379,1.0102844,4.6793175,-37.459675,-269.6432,-310.12238,0.7899349,-0.7562008,60.265465,210000 | |
| 1.0,1.0000001,0.008744638,0.8744638,1.0087447,4.2057633,-89.18324,-265.42545,-311.4017,0.93394417,-0.5225478,58.36578,215000 | |
| 1.0,0.9999999,0.009299715,0.92997146,1.0092996,3.7758381,-28.717657,-261.90207,-308.95966,0.58100307,-0.4867447,48.17943,220000 | |
| 1.0,1.0,0.008952734,0.89527345,1.0089527,3.999831,-47.28158,-268.91113,-309.08685,0.37750238,-0.78570527,54.244843,225000 | |
| 1.0,1.0,0.009708774,0.9708775,1.0097088,4.1581774,-43.400314,-267.3983,-308.95212,0.52683747,-0.91116107,60.855236,230000 | |
| 1.0,1.0,0.008420893,0.84208935,1.008421,5.392417,-46.360085,-265.64923,-310.0568,1.6347054,-1.8083304,84.382706,235000 | |
| 1.0,1.0,0.009411723,0.9411723,1.0094117,3.9497926,-56.762814,-263.8247,-309.22345,0.36571822,-1.0705105,52.366287,240000 | |
| 1.0,1.0,0.009723831,0.97238314,1.0097238,4.469263,-29.065916,-259.99078,-310.25354,0.9091656,-0.5594352,59.2772,245000 | |
| 1.0,0.99999994,0.00950174,0.9501741,1.0095017,4.5367036,-41.77444,-264.02902,-309.56433,0.56114876,-0.70158756,58.71436,250000 | |
| 1.0,0.99999994,0.008956841,0.89568424,1.0089568,7.2498207,-40.137592,-263.9047,-308.8831,3.9429927,-2.8477283,154.26266,255000 | |
| 1.0,1.0,0.009056209,0.9056208,1.0090562,4.199264,-12.293596,-256.48083,-310.5937,1.101593,-0.61231667,59.82779,260000 | |
| 1.0,1.0,0.009999056,0.9999057,1.009999,4.2816715,-38.830383,-261.63678,-309.14438,0.7246029,-0.55318266,57.319405,265000 | |
| 1.0,1.0000001,0.009975549,0.9975549,1.0099757,15.28981,-8.600288,-259.17346,-310.0368,6.1985126,-7.359632,196.0104,270000 | |
| 1.0,1.0,0.010012684,1.0012685,1.0100126,3.9638116,-6.531775,-259.60187,-309.34995,1.9364567,-0.9810986,70.4838,275000 | |
| 1.0,0.9999999,0.010847548,1.0847547,1.0108474,4.9450874,-6.516555,-257.7165,-309.8698,0.9013319,-0.6502381,58.401436,280000 | |
| 1.0,1.0,0.009333022,0.93330216,1.009333,4.1401124,-31.630423,-254.98535,-310.7904,0.5230709,-0.6751269,51.446785,285000 | |
| 1.0,1.0,0.010067213,1.0067213,1.0100672,3.5439408,-25.248419,-258.08978,-309.5956,0.8494429,-0.610005,48.15445,290000 | |
| 1.0,1.0,0.00945814,0.945814,1.0094582,3.827627,-31.955816,-263.77637,-308.442,0.44755998,-0.6361191,49.75518,295000 | |
| 1.0,0.9999999,0.0113104945,1.1310495,1.0113103,4.936662,-25.483673,-255.00847,-310.55966,1.271534,-1.9472536,80.5147,300000 | |
| 1.0,0.99999994,0.011081889,1.1081889,1.0110818,4.69245,-8.068704,-252.78198,-309.31213,0.98647434,-1.4608839,70.88464,305000 | |
| 1.0,1.0,0.010025165,1.0025165,1.0100251,4.3933454,-2.673912,-256.87558,-309.48468,0.8098367,-0.55683434,54.523968,310000 | |
| 1.0,0.99999994,0.009935757,0.9935757,1.0099357,3.7543747,-1.1293322,-252.09937,-307.81833,1.3944762,-0.93033916,50.459724,315000 | |
| 1.0,0.9999999,0.010144768,1.0144769,1.0101446,3.5057175,-10.551281,-256.8793,-310.32077,0.46326935,-0.55925906,44.976585,320000 | |
| 1.0,1.0,0.009697935,0.9697936,1.0096979,3.8499367,-4.293494,-257.9365,-311.13318,0.62127376,-0.547738,52.32129,325000 | |
| 1.0,1.0,0.009406788,0.94067883,1.0094068,6.122124,-14.196939,-259.12088,-310.14523,1.0828297,-0.94028306,78.49297,330000 | |
| 1.0,0.9999999,0.009459974,0.9459976,1.0094599,3.6006393,-3.0243828,-255.20885,-308.60608,0.59138185,-0.46752003,46.974957,335000 | |
| 1.0,0.99999994,0.009711873,0.97118735,1.0097119,3.7834294,0.12036839,-258.9802,-308.85062,0.9880373,-0.9893693,56.68429,340000 | |
| 1.0,1.0,0.009601992,0.96019924,1.009602,4.6404963,-20.564735,-248.14299,-309.31592,0.86770236,-1.2993454,67.00876,345000 | |
| 1.0,1.0000001,0.0092736175,0.92736185,1.0092738,3.1114957,-3.875744,-261.7806,-309.83432,0.4299351,-0.60807014,44.14061,350000 | |
| 1.0,1.0,0.00910793,0.910793,1.009108,4.7782693,0.4666536,-251.0385,-308.66263,0.6284639,-1.6187084,66.22374,355000 | |
| 1.0,1.0,0.009164726,0.9164727,1.0091647,4.4051247,-5.828271,-252.53502,-309.39655,1.1093132,-0.9322318,54.955704,360000 | |
| 1.0,1.0000001,0.009672539,0.9672539,1.0096726,3.497753,-1.511214,-250.80577,-309.21393,0.61197966,-0.66544753,47.049023,365000 | |
| 1.0,1.0000001,0.009614119,0.96141195,1.0096142,4.3415194,-23.308962,-256.03036,-308.8743,0.8081999,-0.56824696,56.452324,370000 | |
| 1.0,1.0,0.010142572,1.0142572,1.0101426,4.5955544,-5.383862,-248.78653,-308.16605,0.4482528,-0.4581243,52.13402,375000 | |
| 1.0,1.0,0.01028224,1.028224,1.0102823,4.6857753,-6.470529,-247.34717,-308.56226,0.900622,-0.57785934,63.29608,380000 | |
| 1.0,1.0,0.009245571,0.9245571,1.0092455,4.134088,-3.7574723,-252.49902,-308.1538,0.9830713,-1.2730395,58.584007,385000 | |
| 1.0,0.99999994,0.009988001,0.9988001,1.009988,4.3189197,-7.370035,-247.95596,-309.53333,0.9093336,-0.5688335,52.62636,390000 | |
| 1.0,1.0,0.010785732,1.0785732,1.0107857,3.6065495,-5.1316996,-252.51811,-308.52682,0.56537366,-1.1226139,52.069893,395000 | |
| 1.0,0.99999994,0.00999694,0.99969405,1.0099969,3.545,-7.5992794,-247.60107,-307.9475,0.9247853,-0.46303353,42.84394,400000 | |
| 1.0,1.0,0.009265443,0.9265443,1.0092654,4.533161,-5.418306,-246.50847,-309.15976,0.9451407,-1.2862542,52.055363,405000 | |
| 1.0,1.0,0.010635458,1.0635457,1.0106355,3.4063728,-6.5749955,-243.55403,-309.1013,0.80706525,-1.1575785,48.940857,410000 | |
| 1.0,1.0,0.011882279,1.1882279,1.0118823,5.604014,-4.025361,-241.56628,-309.4486,0.7344375,-0.9055275,64.69679,415000 | |
| 1.0,1.0,0.009338947,0.93389475,1.009339,4.084189,-0.4327887,-233.10864,-308.2377,0.7116345,-0.6706,50.700573,420000 | |
| 1.0,0.9999999,0.010213111,1.021311,1.010213,4.4341826,-2.7663896,-249.74239,-309.31842,0.7633806,-1.1200495,58.118874,425000 | |
| 1.0,0.9999999,0.009695134,0.9695134,1.009695,4.25621,-8.251887,-242.65523,-308.3492,0.9280844,-1.0816884,53.411385,430000 | |
| 1.0,1.0,0.010072239,1.0072238,1.0100722,7.2634554,-4.4978013,-243.52823,-308.87137,0.85358566,-1.7564934,77.68912,435000 | |
| 1.0,1.0,0.01052822,1.0528221,1.0105282,3.979604,-5.321256,-251.77977,-308.50012,0.47658384,-1.066632,47.82544,440000 | |
| 1.0,1.0,0.009216596,0.9216597,1.0092165,4.230461,-8.7034025,-252.7314,-307.92596,1.9086914,-1.1664326,73.94843,445000 | |
| 1.0,1.0,0.010055998,1.0055999,1.010056,3.3864052,-1.1395618,-242.43929,-310.33572,0.8213413,-0.8371376,43.812088,450000 | |
| 1.0,1.0,0.010126156,1.0126157,1.0101261,3.5677247,-2.1814644,-245.30383,-310.01282,1.5364761,-1.0136278,51.983646,455000 | |
| 1.0,0.99999994,0.009555865,0.95558643,1.0095558,4.0916557,-5.6855736,-245.44034,-308.7075,0.9842938,-1.3353859,55.23797,460000 | |
| 1.0,0.99999994,0.009424625,0.94246256,1.0094246,3.3864763,-0.52159935,-248.85452,-308.11725,0.6031815,-1.0186718,49.460182,465000 | |
| 1.0,0.9999999,0.0106557235,1.0655725,1.0106556,3.4400055,-7.516156,-237.60051,-308.77478,0.5852302,-1.002896,44.53965,470000 | |
| 1.0,1.0,0.00899088,0.899088,1.0089909,3.4692085,-8.958147,-248.29361,-308.18796,1.0317472,-0.7683387,46.46183,475000 | |
| 1.0,1.0000001,0.009397473,0.9397472,1.0093976,3.6669977,-4.8045354,-245.11919,-309.3275,1.2699986,-1.3485979,59.124916,480000 | |
| 1.0,1.0,0.009298215,0.9298215,1.0092982,4.262656,-3.1394694,-243.69518,-309.56635,1.075134,-0.76366735,59.405937,485000 | |
| 1.0,1.0,0.010069717,1.0069716,1.0100697,4.9755244,-5.2254596,-239.55669,-308.1496,11.763453,-13.516028,172.67935,490000 | |
| 1.0,1.0,0.009845933,0.9845934,1.009846,7.6244845,-7.27082,-244.37125,-308.37695,1.6906012,-1.6801838,90.05339,495000 | |
| 1.0,1.0,0.0094286455,0.94286454,1.0094286,3.4735029,-2.3086138,-240.111,-308.1836,0.71360487,-0.5524941,45.388546,500000 | |
| 1.0,1.0,0.010095537,1.0095537,1.0100956,2.955176,-5.2750983,-243.65266,-309.73,0.5899432,-0.48759934,39.532906,505000 | |
| 1.0,1.0,0.00977658,0.97765803,1.0097766,3.7749894,-7.755893,-244.13065,-307.68195,0.75331014,-0.714671,47.663105,510000 | |
| 1.0,1.0,0.009836901,0.98369014,1.0098369,3.812288,-5.919566,-233.95142,-308.59726,0.47974283,-0.7375641,44.66854,515000 | |
| 1.0,1.0,0.009623444,0.9623443,1.0096234,3.3869057,-7.3097553,-242.13211,-308.05566,0.8965351,-1.1505446,51.21463,520000 | |
| 1.0,1.0000001,0.009595218,0.9595219,1.0095954,2.748505,-5.8430257,-245.74763,-309.98218,0.7421031,-0.6491479,38.93679,525000 | |
| 1.0,1.0,0.010174088,1.0174088,1.010174,4.766645,-3.2574196,-241.33427,-307.95264,1.9590207,-1.0804981,76.697105,530000 | |
| 1.0,1.0,0.010119996,1.0119996,1.01012,3.3450036,-7.632928,-237.03389,-307.59366,0.8726886,-0.6624348,44.629448,535000 | |
| 1.0,1.0,0.010704175,1.0704175,1.0107042,3.8794243,-4.098418,-235.03667,-308.6988,1.9080197,-1.6876508,65.58187,540000 | |
| 1.0,0.99999994,0.011454369,1.145437,1.0114543,3.0656703,-4.122874,-229.7476,-309.10648,0.5668536,-0.6010563,42.38939,545000 | |
| 1.0,1.0,0.010194462,1.0194463,1.0101944,3.343106,-2.796477,-235.78868,-307.92264,1.1899029,-0.7063941,44.558357,550000 | |
| 1.0,0.99999994,0.009883175,0.98831755,1.0098832,3.1061246,-0.07140736,-242.66893,-309.80652,0.543885,-0.7302643,43.16156,555000 | |
| 1.0,1.0,0.0100775175,1.0077517,1.0100775,4.1148243,-4.476666,-228.22806,-309.02505,0.68864334,-0.6083785,46.22555,560000 | |
| 1.0,1.0,0.009457338,0.9457338,1.0094573,3.49849,-3.9946923,-233.83482,-307.82596,1.5979007,-2.288736,57.296356,565000 | |
| 1.0,1.0000001,0.0092752,0.92752004,1.0092753,3.4450397,-0.32460338,-237.54381,-308.93222,1.0859642,-0.7507502,47.98779,570000 | |
| 1.0,1.0000001,0.010101141,1.0101142,1.0101013,3.0968573,-3.584468,-235.34244,-308.8125,0.6523916,-0.7066413,43.26193,575000 | |
| 1.0,0.99999994,0.010004656,1.0004656,1.0100046,3.647787,-2.2897723,-245.0774,-308.1222,1.3503286,-1.1173137,53.945282,580000 | |
| 1.0,1.0,0.009337769,0.933777,1.0093378,3.4866967,-3.5771716,-243.02022,-309.1817,1.4845022,-0.53420466,48.202217,585000 | |
| 1.0,1.0,0.010812428,1.0812428,1.0108124,4.7994876,-5.9265094,-232.14185,-307.86017,0.8844672,-0.8108642,61.75849,590000 | |
| 1.0,1.0,0.009793679,0.9793679,1.0097936,3.0638485,-3.3681965,-232.14697,-308.29752,0.37168407,-0.54198426,37.54035,595000 | |
| 1.0,0.99999994,0.0095789805,0.95789814,1.009579,4.6196527,-6.62464,-241.42188,-307.53864,0.87971985,-1.0775084,49.33479,600000 | |