O2O / O2O-w-diff-ckpts /cube-triple-play-singletask-task1-v0 /rebrac /20260325_005247 /online_agent_sv.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 | |
| 1.0,1.0,0.008926662,0.8926662,1.0089266,8.0473175,-131.35216,-276.07257,-310.84354,1.5323952,-1.340019,87.38807,205000 | |
| 1.0,1.0,0.00916649,0.91664904,1.0091665,4.564348,-145.34326,-273.2437,-309.25473,1.7682012,-1.0428317,75.45473,210000 | |
| 1.0,1.0,0.0091302935,0.91302943,1.0091302,5.647957,-113.88151,-268.46872,-309.355,1.1041224,-0.607111,71.428986,215000 | |
| 1.0,1.0,0.009056992,0.9056992,1.009057,5.1427774,-176.73827,-275.30466,-310.63773,0.84815776,-0.92416126,65.794334,220000 | |
| 1.0,0.99999994,0.009733928,0.97339284,1.0097339,3.7804585,-105.37915,-274.48813,-309.62802,0.6923016,-0.76719135,53.682434,225000 | |
| 1.0,0.99999994,0.008439276,0.8439276,1.0084392,3.091837,1.7055953,-273.12872,-308.98672,0.4175319,-0.41139227,43.828125,230000 | |
| 1.0,0.9999999,0.008961145,0.8961145,1.0089611,3.668884,-111.59223,-277.18024,-310.16278,0.7792293,-1.2934012,58.076385,235000 | |
| 1.0,1.0,0.008645065,0.8645065,1.008645,3.4217153,-99.355034,-273.74106,-309.5889,0.6697245,-0.46027598,50.864395,240000 | |
| 1.0,1.0,0.008489646,0.8489646,1.0084896,3.6356714,-100.27354,-275.11734,-309.91748,1.3551924,-0.6055666,55.665924,245000 | |
| 1.0,1.0,0.007916754,0.7916754,1.0079168,3.956218,-101.48153,-273.16537,-309.28268,1.3758881,-0.8502641,57.936245,250000 | |
| 1.0,0.99999994,0.007994037,0.7994038,1.0079939,3.153121,-101.22011,-271.50546,-308.46573,0.4867981,-1.0228906,53.325554,255000 | |
| 1.0,1.0,0.009290532,0.9290532,1.0092906,3.6974888,-100.993225,-272.80087,-309.92615,0.38588032,-0.36372128,47.497055,260000 | |
| 1.0,1.0,0.009400287,0.9400287,1.0094002,3.6155717,-100.72543,-273.68213,-310.82938,0.49362653,-0.7547839,49.133163,265000 | |
| 1.0,1.0,0.008902894,0.8902894,1.0089029,3.2511723,-97.974396,-267.22565,-308.93314,0.5170422,-0.5058284,47.375458,270000 | |
| 1.0,1.0,0.00886648,0.886648,1.0088664,4.531195,-29.170937,-264.31323,-309.50955,2.4968288,-1.4182811,72.45772,275000 | |
| 1.0,1.0,0.009263812,0.92638123,1.0092638,3.6597707,-97.38244,-266.90765,-307.95114,0.7413409,-1.6872016,63.022938,280000 | |
| 1.0,0.99999994,0.009214908,0.9214908,1.0092149,3.2565887,-81.29622,-268.41544,-309.14667,0.4522869,-0.453812,44.747375,285000 | |
| 1.0,1.0,0.008862498,0.8862498,1.0088625,2.7535195,-100.0808,-269.37363,-308.52386,1.1749048,-0.81936,48.076622,290000 | |
| 1.0,0.9999999,0.010134404,1.0134404,1.0101343,3.3255463,-100.02304,-270.5085,-309.26584,0.48730883,-0.5801985,44.684544,295000 | |
| 1.0,1.0,0.0082801115,0.8280112,1.0082802,3.5281847,-97.78146,-267.66928,-309.20193,0.7320089,-0.7427633,49.44786,300000 | |
| 1.0,0.99999994,0.008341111,0.83411115,1.0083411,2.8088143,-98.203445,-271.50266,-309.35886,0.41741937,-0.4569959,42.471344,305000 | |
| 1.0,0.9999999,0.00903834,0.90383404,1.0090382,3.176605,-100.973595,-272.87625,-308.925,0.8454725,-0.8106882,48.581703,310000 | |
| 1.0,0.99999994,0.007976251,0.7976251,1.0079762,3.7105453,-101.0276,-267.312,-309.17825,1.840493,-1.7854259,56.422535,315000 | |
| 1.0,1.0,0.008300189,0.83001894,1.0083002,2.6720486,-100.60374,-265.74695,-307.60468,0.4790418,-0.5562585,40.09713,320000 | |
| 1.0,0.99999994,0.007831655,0.7831655,1.0078316,2.437426,-100.50421,-273.33127,-307.82956,1.1350046,-1.0506511,49.38271,325000 | |
| 1.0,1.0,0.008079296,0.80792964,1.0080793,3.5510042,-101.16801,-270.33948,-308.12814,2.294501,-2.1994612,67.55091,330000 | |
| 1.0,0.99999994,0.007600279,0.760028,1.0076002,3.035305,-101.219,-271.28564,-308.6838,0.2690373,-0.5590787,40.0362,335000 | |
| 1.0,1.0000001,0.008206949,0.8206949,1.0082071,2.8830974,-96.664894,-266.8446,-308.2954,0.4695945,-0.8930049,40.787277,340000 | |
| 1.0,1.0,0.0086421985,0.8642199,1.0086422,2.666338,-99.41628,-265.1254,-309.8039,0.71306103,-0.46139887,40.365173,345000 | |
| 1.0,0.9999999,0.008159968,0.8159968,1.0081599,2.9150708,-59.452694,-267.63535,-307.30524,0.443595,-0.59442806,42.587738,350000 | |
| 1.0,1.0,0.007841762,0.78417623,1.0078417,2.8815324,-94.10724,-268.32602,-308.44348,0.40154046,-0.72788715,39.12893,355000 | |
| 1.0,1.0,0.008039078,0.80390775,1.0080391,2.6294975,-53.308086,-262.45337,-308.22787,0.51471364,-0.4017754,39.377823,360000 | |
| 1.0,1.0,0.008764148,0.8764148,1.0087641,2.6596944,-55.691166,-266.21042,-308.29895,0.40952042,-0.66260046,39.068386,365000 | |
| 1.0,0.99999994,0.008959983,0.89599824,1.0089599,16.760336,-29.936728,-264.66888,-307.71173,6.679659,-7.615482,225.62769,370000 | |
| 1.0,1.0,0.008443231,0.84432316,1.0084432,2.5656114,-72.34639,-264.78235,-308.39395,0.4832521,-0.82671684,36.544117,375000 | |
| 1.0,0.99999994,0.009440239,0.9440239,1.0094402,2.582208,-49.60892,-263.31403,-307.6298,0.47373667,-0.49397773,36.33131,380000 | |
| 1.0,0.99999994,0.008751549,0.87515485,1.0087515,2.9389052,-69.62801,-259.7385,-308.45435,1.1915438,-1.4454869,49.210464,385000 | |
| 1.0,1.0,0.0085683,0.85683006,1.0085683,2.3270469,-66.148285,-262.34567,-308.1598,0.9443929,-0.9146493,40.145348,390000 | |
| 1.0,0.99999994,0.0087315645,0.87315655,1.0087315,3.3632438,-61.480804,-267.479,-308.82596,1.642077,-0.8796353,60.34501,395000 | |
| 1.0,1.0,0.00950802,0.950802,1.009508,2.8732648,-37.227474,-260.42404,-308.7499,0.36256608,-0.3639005,39.15659,400000 | |
| 1.0,1.0,0.010015287,1.0015289,1.0100152,3.2225018,-19.291422,-259.3978,-307.63464,0.45028782,-0.42028773,42.8023,405000 | |
| 1.0,1.0,0.008857622,0.88576216,1.0088576,3.0866034,-50.681747,-262.15668,-307.3264,0.68608403,-1.0235609,48.221195,410000 | |
| 1.0,1.0,0.008718829,0.8718829,1.0087188,3.4857583,-18.317556,-257.51416,-307.79938,0.7427665,-0.4747651,45.49425,415000 | |
| 1.0,0.99999994,0.009511655,0.95116556,1.0095116,4.952935,-58.30425,-264.16397,-308.30704,0.5776817,-0.49902925,45.990246,420000 | |
| 1.0,0.99999994,0.008100249,0.8100249,1.0081002,3.3431785,-37.85935,-264.19553,-309.1664,0.65029615,-0.47751373,46.18175,425000 | |
| 1.0,1.0,0.008396782,0.8396783,1.0083967,3.8464792,-50.969837,-264.66364,-307.44238,1.0430357,-0.8210006,56.623528,430000 | |
| 1.0,1.0,0.009226361,0.92263603,1.0092263,2.8108566,-30.560324,-262.48264,-307.577,0.6247951,-0.57464707,36.591595,435000 | |
| 1.0,1.0,0.008837519,0.883752,1.0088375,3.186192,-39.803432,-263.32086,-307.18,0.9014262,-0.8102176,41.59619,440000 | |
| 1.0,1.0,0.009358707,0.93587065,1.0093588,3.4656396,-24.893484,-253.64561,-308.83203,0.7478282,-0.8648131,43.256706,445000 | |
| 1.0,0.99999994,0.008709314,0.8709315,1.0087093,2.7235692,-6.218421,-266.02194,-309.2175,0.7252406,-0.8189853,37.874233,450000 | |
| 1.0,1.0,0.008322578,0.83225787,1.0083226,3.769764,-20.355915,-257.09067,-308.50818,3.422837,-2.8522272,91.09404,455000 | |
| 1.0,0.99999994,0.008496305,0.8496305,1.0084963,3.3275635,-21.36335,-257.773,-308.46045,0.62366354,-1.1441834,49.61254,460000 | |
| 1.0,1.0,0.0092981225,0.9298123,1.0092981,3.1614869,-36.299885,-257.81686,-308.71606,0.89871085,-0.48338264,44.561523,465000 | |
| 1.0,0.9999999,0.008459682,0.8459681,1.0084596,4.9350243,-6.957124,-259.3045,-308.22305,1.5790098,-0.75102365,58.961586,470000 | |
| 1.0,1.0,0.009142162,0.9142162,1.0091422,3.1071074,-39.523,-253.41023,-308.2282,1.11653,-1.0815783,51.734627,475000 | |
| 1.0,0.9999999,0.008798902,0.8798902,1.0087988,3.3642693,-22.888979,-252.80186,-308.4933,0.37007815,-0.824038,45.637486,480000 | |
| 1.0,0.99999994,0.008781191,0.87811905,1.0087811,3.3138185,-7.884331,-258.0897,-307.9391,0.5230792,-1.0477029,45.352386,485000 | |
| 1.0,0.99999994,0.009014087,0.9014087,1.009014,3.436362,-3.9785283,-252.26561,-308.9134,0.4131814,-0.7989534,41.443504,490000 | |
| 1.0,1.0,0.008976167,0.89761674,1.0089762,2.820018,-13.134515,-257.07184,-307.2362,0.4933859,-0.4321205,39.388958,495000 | |
| 1.0,1.0,0.009727163,0.9727163,1.0097271,3.45169,-22.525454,-250.9534,-307.50134,0.49001318,-0.90860754,47.634438,500000 | |
| 1.0,1.0,0.009055999,0.9055999,1.009056,2.7370498,-3.6265683,-250.95543,-308.1003,0.5709181,-1.1147485,40.15528,505000 | |
| 1.0,1.0,0.010014042,1.0014043,1.010014,3.694521,-4.5524554,-247.17378,-309.22412,0.68204504,-0.80954504,45.138454,510000 | |
| 1.0,1.0000001,0.0108098835,1.0809884,1.01081,4.1450577,-6.3114123,-244.29692,-308.48392,0.6153969,-0.9565017,55.76757,515000 | |
| 1.0,1.0,0.009280402,0.92804027,1.0092804,3.0996625,-11.922809,-238.1385,-307.6563,0.47114483,-0.321189,41.699562,520000 | |
| 1.0,0.9999999,0.009767518,0.9767518,1.0097674,4.0527472,-6.445026,-252.61429,-308.08148,1.2534789,-1.0113878,51.23816,525000 | |
| 1.0,1.0,0.010004736,1.0004735,1.0100048,5.2614884,-5.5608625,-245.87833,-307.99503,1.1604592,-0.7042073,62.88033,530000 | |
| 1.0,1.0,0.009995945,0.99959457,1.0099959,5.5988045,-2.0453112,-244.77013,-308.63474,1.1454593,-1.6134872,82.15166,535000 | |
| 1.0,1.0,0.010755038,1.0755038,1.0107551,7.024564,-7.7269645,-254.2168,-307.14325,0.93036246,-1.765542,72.4825,540000 | |
| 1.0,0.99999994,0.009327306,0.9327307,1.0093273,4.3456326,-7.78843,-255.11162,-309.20557,1.1928425,-0.9808539,64.86976,545000 | |
| 1.0,1.0,0.010088481,1.0088481,1.0100884,4.8730974,-11.659755,-245.97075,-308.5628,1.2339647,-0.57134765,53.025993,550000 | |
| 1.0,0.99999994,0.010244887,1.0244887,1.0102448,2.9367049,-5.0126762,-248.90965,-307.6179,0.47018617,-0.4467848,39.38128,555000 | |
| 1.0,1.0,0.009513347,0.9513347,1.0095134,3.4322453,-1.9510238,-248.32007,-308.03827,0.86878544,-0.5221016,48.015717,560000 | |
| 1.0,1.0,0.008945387,0.89453864,1.0089453,3.1727111,-8.616064,-251.95117,-308.8259,0.49229062,-0.63897985,39.875816,565000 | |
| 1.0,1.0,0.010096008,1.0096009,1.010096,2.815121,-4.540178,-240.47827,-307.9677,0.79750395,-0.45385844,40.899963,570000 | |
| 1.0,0.99999994,0.009067284,0.90672845,1.0090672,3.3743713,-9.123515,-251.35384,-309.01486,0.3372894,-0.68652415,40.045517,575000 | |
| 1.0,1.0,0.009616129,0.96161294,1.0096161,3.458197,-0.71049887,-248.59521,-307.74103,0.42378315,-1.0564828,44.332222,580000 | |
| 1.0,1.0,0.00979391,0.9793911,1.0097939,4.3331046,-4.382661,-246.86455,-308.36023,0.7607412,-1.3442649,54.4438,585000 | |
| 1.0,1.0,0.009822395,0.98223954,1.0098224,3.4735699,-0.3365723,-241.81306,-308.48557,0.63328385,-0.8237236,39.37022,590000 | |
| 1.0,1.0,0.009871803,0.98718035,1.0098718,2.8127904,-5.8368096,-246.03276,-307.84894,0.6491988,-1.1497502,46.440964,595000 | |
| 1.0,0.99999994,0.008822256,0.8822256,1.0088222,3.1858382,-3.6326365,-242.96138,-308.49304,0.36490637,-0.75410426,36.536106,600000 | |
| 1.0,1.0000001,0.01004284,1.004284,1.0100429,2.696903,-3.0793462,-245.20305,-308.09274,0.75818074,-0.6953015,41.31109,605000 | |
| 1.0,1.0,0.009856879,0.985688,1.0098568,4.066686,-8.605068,-247.15308,-308.51105,0.9960037,-2.5433874,66.970146,610000 | |
| 1.0,1.0,0.010056327,1.0056328,1.0100564,2.7801087,-3.7166626,-237.16197,-308.42386,0.5477153,-0.6454192,40.08552,615000 | |
| 1.0,1.0,0.009831097,0.9831097,1.0098311,2.5997987,-4.6449313,-243.65157,-307.10648,0.708082,-0.6849459,35.81948,620000 | |
| 1.0,0.99999994,0.009001184,0.9001184,1.0090011,2.6526825,-6.0470395,-248.07475,-307.60434,0.39939606,-0.46804065,33.606888,625000 | |
| 1.0,1.0,0.01013761,1.013761,1.0101376,2.7308779,-1.0915902,-242.62218,-309.58163,0.59087664,-0.4699232,39.58822,630000 | |
| 1.0,1.0,0.0101819085,1.0181909,1.0101819,2.9001179,-4.785976,-240.37029,-307.4539,0.49056542,-0.38343295,33.56981,635000 | |
| 1.0,1.0,0.010382332,1.0382332,1.0103823,3.4660923,-9.1551485,-237.60283,-307.2628,5.200869,-3.7188795,119.71042,640000 | |
| 1.0,1.0,0.0103338715,1.0333872,1.0103339,3.0602329,-1.4679368,-232.07018,-308.05246,0.56389725,-0.65961176,40.39706,645000 | |
| 1.0,1.0,0.009909713,0.9909713,1.0099097,3.529979,-2.2530947,-238.88066,-309.45438,0.70425236,-0.46692622,39.39323,650000 | |
| 1.0,1.0,0.0101060495,1.0106049,1.0101061,2.998811,-8.443303,-242.6355,-309.2497,0.84607893,-0.61097616,41.37388,655000 | |
| 1.0,1.0000001,0.009997089,0.9997089,1.0099972,3.0450647,-2.5085087,-229.19487,-307.68546,1.8722004,-0.5925164,48.160927,660000 | |
| 1.0,1.0000001,0.00945476,0.94547606,1.0094548,2.6694965,-5.078532,-235.89061,-307.99536,0.54941714,-0.36673823,34.680206,665000 | |
| 1.0,1.0,0.009522058,0.9522058,1.0095221,3.7437787,-4.2688494,-239.96533,-307.54385,1.0313113,-0.9470912,43.919678,670000 | |
| 1.0,1.0000001,0.009983293,0.99832934,1.0099834,3.3094273,-2.341229,-235.83174,-308.64145,1.3152828,-0.76887846,48.388435,675000 | |
| 1.0,1.0,0.010079194,1.0079194,1.0100791,3.196725,-3.3352199,-247.40929,-307.19208,0.8495803,-0.8761741,43.79409,680000 | |
| 1.0,0.99999994,0.0087934965,0.8793496,1.0087935,3.6597848,-5.7633,-243.55362,-308.4015,0.923818,-0.9341551,44.717445,685000 | |
| 1.0,1.0,0.010144305,1.0144305,1.0101444,3.6600225,-2.1352658,-234.60648,-307.5995,0.77360326,-1.936419,44.99128,690000 | |
| 1.0,1.0,0.009358829,0.9358828,1.0093589,2.825436,-5.977117,-233.22903,-306.93927,0.53081435,-1.1990664,36.279472,695000 | |
| 1.0,1.0,0.009641351,0.96413517,1.0096414,4.2758775,-1.9484893,-242.06047,-309.0393,1.4421825,-0.9906107,56.02877,700000 | |