O2O / O2O-w-diff-ckpts /ifql /20260317_195838 /online_agent.csv
Tiredsheep's picture
Upload folder using huggingface_hub
f35b90d verified
actor/actor_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,value/v_max,value/v_mean,value/v_min,value/value_loss,step
0.3453843,1.3171874,-14.823327,-165.77829,-198.18434,5.6234927,-3.99412,78.40985,-16.882051,-165.5833,-198.19713,0.298878,705000
0.27225292,2.9580789,-16.511824,-164.2392,-192.28908,11.469556,-19.319775,155.94254,-10.136645,-164.12315,-192.22934,0.1942123,710000
0.2986796,0.765644,-37.131844,-167.55847,-195.39249,4.9471474,-4.564268,63.79653,-37.198788,-167.40073,-195.37122,0.24375226,715000
0.3141302,0.975832,-31.05062,-167.16058,-196.12097,7.0060334,-8.811797,78.81155,-30.346596,-167.0597,-196.08833,0.2341108,720000
0.30940735,0.95324963,0.0,-166.15079,-198.92293,4.7379146,-10.716026,68.104034,-0.8494803,-165.86536,-198.91498,0.29913503,725000
0.30086118,3.6112823,0.0,-165.38815,-196.95338,17.749159,-24.00965,136.20213,0.90665597,-165.31033,-195.25995,0.70900196,730000
0.31027403,1.2633015,0.0,-164.80396,-196.95966,22.118412,-7.9940734,107.41377,0.46338856,-164.56927,-196.99396,0.401563,735000
0.28167903,1.5779656,-6.3086195,-165.04352,-197.06396,9.653615,-7.9918456,131.6228,-6.2776847,-164.8045,-197.08499,0.7074737,740000
0.28480038,1.8225338,-71.952446,-168.19305,-197.09439,29.606121,-41.429394,231.23744,-70.11051,-167.95921,-197.0916,0.2603226,745000
0.29060304,3.9221246,0.0,-166.46272,-198.1841,51.745846,-69.29171,490.62308,-1.8798379,-166.0549,-197.98996,4.55456,750000
0.30361992,7.038585,0.0,-164.33298,-197.02121,56.425884,-61.606087,421.74686,-4.187642,-164.1522,-197.04672,0.82629204,755000
0.36156738,1.8920987,-47.624134,-167.10278,-192.95734,53.333775,-18.82296,231.26416,-47.471924,-166.92691,-192.92952,0.38203806,760000
0.30883592,1.4882101,-44.47474,-169.14325,-197.08844,27.552511,-7.626311,117.3096,-44.25882,-168.89888,-197.07683,0.49848425,765000
0.32160282,0.8075585,-9.012039,-168.36525,-195.27362,2.0909863,-3.3899982,48.080944,-8.902641,-168.26385,-195.2537,0.11846997,770000
0.32506502,1.572267,0.0,-169.65201,-196.79066,68.0253,-85.18212,489.20776,1.1106172,-169.53273,-196.76186,1.4115348,775000
0.33044565,0.8578836,-44.670017,-167.04384,-195.54565,13.5835085,-14.359959,102.70108,-42.450294,-166.93225,-195.52289,0.21686125,780000
0.3213535,1.4907969,-32.470398,-168.99135,-194.03664,7.1489353,-21.441935,131.57953,-32.168636,-168.68405,-194.04356,0.36458638,785000
0.34174168,1.1174561,-28.920258,-166.45654,-205.13156,6.0539293,-14.551716,85.6405,-28.294563,-166.3201,-205.15213,0.4209213,790000
0.30785334,2.0285122,0.0,-164.15338,-198.04999,13.960102,-29.118744,177.59784,-2.2453594,-164.00095,-198.04288,0.7920011,795000
0.34008592,8.535503,-3.0339694,-167.4484,-194.87903,43.813126,-41.13842,584.26245,-2.5376134,-166.94177,-194.86227,3.4907322,800000
0.33358914,0.9724556,-67.50562,-169.65619,-202.72258,4.6645694,-4.063275,51.69365,-67.640114,-169.48474,-202.74673,0.19445479,805000
0.31536418,1.10712,-34.56085,-165.71208,-202.86835,6.2230196,-8.86833,72.67877,-32.948383,-165.42621,-202.87474,0.2988491,810000
0.34820017,0.5726675,-26.356287,-172.1611,-195.49869,14.605104,-4.9209046,100.477066,-27.173117,-172.05226,-195.47284,0.22776373,815000
0.3140061,0.6386292,-42.747078,-171.08449,-196.05812,3.4085226,-2.5511036,45.292633,-41.31163,-170.99802,-196.03554,0.10746615,820000
0.2859246,1.459394,-48.74393,-170.31822,-198.33359,10.926887,-11.7978525,112.06166,-52.079624,-170.12862,-198.06021,0.4174716,825000
0.32380483,0.8424134,-42.25582,-169.3302,-203.01074,3.3428836,-3.6284738,46.7788,-37.7374,-169.2363,-203.03848,0.19524416,830000
0.30679202,0.6681706,-52.21694,-170.81635,-197.91158,1.9388568,-1.5748475,39.96974,-57.134033,-170.73756,-197.89441,0.12209919,835000
0.28434414,1.1649204,-61.09923,-172.66132,-196.68976,18.939278,-21.390574,222.77005,-61.95837,-172.50908,-196.66757,0.3924418,840000
0.31892213,2.2602293,-33.02181,-167.59901,-197.77657,11.341257,-11.726734,99.70923,-32.88316,-167.37416,-197.76231,0.372796,845000
0.31649673,0.7063729,-35.586655,-171.30286,-195.79431,6.095192,-3.3340628,60.866726,-35.52892,-171.09348,-195.83469,0.22241643,850000
0.28614786,0.8741623,-64.54502,-170.56683,-197.91386,3.4414086,-9.637179,52.068398,-61.506535,-170.54984,-197.90895,0.21483168,855000
0.32421643,1.5610838,0.0,-168.2951,-195.73367,25.223516,-33.724277,161.9798,0.22842768,-168.11475,-195.72127,0.51112777,860000
0.30589187,0.46362123,-45.687332,-171.07806,-197.75684,1.7046913,-3.696402,37.786346,-45.218094,-170.89673,-197.75858,0.2370654,865000
0.28866303,1.1291097,0.0,-170.91685,-198.24197,8.802632,-4.80588,102.5466,-0.9335865,-170.56789,-198.24208,0.40469104,870000
0.2845554,0.4387848,-25.504112,-170.13913,-204.17972,0.74648255,-0.8646622,23.30889,-26.42199,-170.03287,-204.20177,0.07801871,875000
0.3042168,0.72550344,-4.150029,-166.655,-204.22119,5.8173375,-4.7695794,42.915085,-2.3288639,-166.46352,-204.2449,0.33022454,880000
0.27927756,2.0342133,-1.6520461,-173.27777,-197.3379,17.936573,-9.921688,135.41412,-0.71514285,-173.1642,-197.33896,0.25221187,885000
0.30481428,0.6043167,-57.24922,-170.28554,-197.6362,2.5145082,-3.724505,42.660786,-53.207977,-170.16351,-197.64093,0.108096056,890000
0.2816713,0.9226099,0.0,-172.71912,-197.60847,2.5543773,-4.2559986,55.406372,0.48873916,-172.5415,-197.589,0.17655301,895000
0.3267084,3.1015196,0.0,-169.73337,-199.18788,14.057476,-36.802826,220.60796,-1.5141888,-169.60954,-199.17784,0.85676473,900000
0.33680987,1.1579069,-36.47333,-167.62183,-205.58276,3.704018,-2.6294262,52.01401,-35.554108,-167.3605,-205.68103,0.17291942,905000
0.30693245,1.5148579,-70.718346,-171.91171,-197.33946,16.081034,-10.531817,91.07286,-70.23869,-171.60202,-197.3345,0.68456936,910000
0.36798373,1.0578434,0.0,-172.49567,-197.96906,3.4530709,-10.8247385,72.342865,-6.4212694,-172.39313,-197.96234,0.24136344,915000
0.28667295,1.0990976,0.0,-171.15887,-194.463,5.1329255,-1.9076747,48.56507,-3.8780506,-171.00131,-194.42744,0.26807612,920000
0.30665088,2.7815685,0.0,-169.8584,-197.03053,45.096336,-41.563267,301.03815,-2.3062365,-169.86655,-197.01825,0.3316626,925000
0.2824902,1.2649144,-43.214474,-172.66959,-202.21898,49.908276,-9.002572,162.73267,-46.9245,-172.658,-202.22173,0.6114279,930000
0.29663447,0.75716656,0.0,-173.06227,-196.71109,3.531463,-1.9518702,44.00213,-0.15980524,-172.97467,-196.69121,0.19278224,935000
0.3489325,0.7682604,-62.910225,-174.2262,-194.92755,5.6366587,-4.634326,44.161034,-60.66729,-174.1011,-194.90535,0.15286157,940000
0.33876786,1.191746,-35.667057,-172.83151,-196.5505,4.1030416,-5.503499,60.799408,-35.308624,-172.67313,-196.5724,0.18177217,945000
0.32576257,1.411413,-5.057082,-173.07202,-199.29262,11.923848,-9.002444,93.73258,-4.871355,-172.88289,-199.28802,0.3894961,950000
0.3166847,2.1193514,-32.558403,-170.37538,-197.09567,6.30997,-14.304418,99.01642,-35.854687,-170.04492,-197.0876,0.3110242,955000
0.2850631,0.77513516,0.0,-172.49042,-198.85695,3.9221,-3.9852579,40.19868,-1.2893931,-172.2843,-198.8568,0.10402581,960000
0.35494748,0.47686908,-59.15937,-173.22525,-196.65388,1.6793252,-1.6564821,21.344364,-57.59864,-173.10733,-196.57231,0.0571776,965000
0.29947984,1.0054436,-48.696323,-173.50607,-205.20784,9.584577,-7.7190943,68.096275,-46.66108,-173.26706,-205.24486,0.31114098,970000
0.2745692,1.6818005,-41.943775,-171.30037,-198.77939,6.9605546,-15.096161,86.57505,-41.526615,-171.14444,-198.77928,0.20193374,975000
0.32980707,1.2676632,0.0,-171.24713,-202.05923,25.111923,-14.436504,190.94525,-12.686372,-171.22916,-202.04654,0.7731421,980000
0.29574317,0.64459854,0.0,-171.41736,-202.77745,27.957573,-35.553043,190.64465,0.32935938,-171.3883,-202.79279,1.69132,985000
0.3182094,0.9168707,-97.8815,-175.31073,-200.04825,3.9602692,-6.68282,64.43989,-89.65597,-175.10158,-200.05328,0.17362612,990000
0.32105833,1.9713967,0.0,-169.364,-199.53282,63.552517,-32.145,262.15256,-0.23141867,-169.29445,-199.53027,0.13363577,995000
0.25333157,0.7062754,-57.30749,-172.98573,-199.78137,4.4794626,-1.8466979,51.389137,-55.802402,-172.7745,-199.77693,0.25295568,1000000
0.3011526,1.9073089,-60.259792,-174.89699,-196.53688,8.806584,-43.04758,192.98581,-59.924133,-174.64923,-196.53133,0.97902024,1005000
0.2471866,2.3384697,-44.712597,-173.69624,-194.16052,15.173523,-20.745655,117.73801,-45.162216,-173.53894,-194.13722,0.61911535,1010000
0.30818886,0.9406342,0.0,-171.27304,-199.98502,20.149897,-10.266899,111.322075,-0.76179534,-170.96805,-199.99066,0.41886848,1015000
0.28862536,2.9785187,0.0,-173.79907,-204.06952,14.827107,-19.252481,122.36293,-2.2295926,-173.57755,-204.17464,0.6065442,1020000
0.3067206,0.8472506,0.0,-169.8511,-203.82101,3.457266,-4.9837546,44.39115,-0.58776665,-169.73093,-203.80423,0.24403697,1025000
0.29344073,0.36627802,-35.920673,-174.7311,-203.68341,2.6358497,-3.5348506,36.043148,-36.642956,-174.5875,-203.69072,0.116105676,1030000
0.32991812,0.6210189,-56.038197,-172.76578,-200.57677,1.7604868,-2.7488654,33.24914,-56.752373,-172.66031,-200.58719,0.14580224,1035000
0.25589788,2.0906923,-57.171917,-174.55246,-201.75165,9.908097,-16.960058,130.73164,-56.23601,-174.39107,-201.76376,0.4093427,1040000
0.29896763,1.3264458,-41.325603,-171.83928,-201.55553,4.8797507,-4.373455,51.2519,-42.120262,-171.70619,-201.5706,0.1183604,1045000
0.30599886,1.4432542,0.0,-174.65913,-205.2448,10.335308,-10.636039,107.8742,1.1086206,-174.54062,-205.31783,0.13135958,1050000
0.29473385,0.8219909,0.0,-171.5064,-206.08667,88.64839,-22.276587,302.24734,-9.629705,-171.34589,-206.11787,0.3972484,1055000
0.303329,1.1289428,-39.506313,-177.06958,-201.615,19.898531,-23.574461,126.11939,-37.81853,-176.94989,-201.57877,0.40668082,1060000
0.31373584,0.92286366,0.0,-172.60751,-200.92357,5.2614822,-8.034981,66.426796,-3.9653246,-172.6115,-200.93457,0.2373334,1065000
0.34391823,0.81836814,0.0,-172.87743,-201.15292,8.843101,-7.746164,61.366817,-1.7772982,-172.77664,-201.15274,0.13441151,1070000
0.3018782,0.76324654,0.0,-173.56589,-196.8997,4.926606,-16.926989,87.22836,-3.9244363,-173.4625,-196.87946,0.20506163,1075000
0.31876242,1.1239828,-49.987377,-173.24896,-204.08229,41.675865,-128.55067,481.71555,-48.809036,-172.99979,-204.11009,0.98801476,1080000
0.33076787,0.74129826,-33.799767,-171.10233,-196.57764,5.244606,-13.32721,56.790596,-28.659714,-170.97565,-196.57347,0.18001798,1085000
0.32025123,1.0503746,0.0,-174.25858,-194.27165,3.5509746,-12.391876,52.846085,0.09651083,-174.0854,-194.24399,0.17196012,1090000
0.29863226,0.42790022,-59.385048,-174.85437,-195.58069,4.0164638,-1.3868071,26.384201,-61.244637,-174.73734,-195.56003,0.07554908,1095000
0.32186234,1.1877457,0.0,-173.36406,-207.15248,3.285185,-1.9494644,51.68396,-3.1141577,-173.19139,-207.18384,0.17779326,1100000
0.33241448,0.67853457,-0.47533482,-172.24055,-196.9842,1.5884988,-1.3178915,28.842875,-0.70686185,-172.13412,-196.96677,0.0928631,1105000
0.25985456,0.46773696,-1.3673563,-174.02167,-205.3503,2.0829635,-6.2358103,36.696598,-2.1405423,-173.85388,-205.34892,0.2179046,1110000
0.26830316,0.7248599,0.0,-175.61261,-197.46475,3.9916751,-2.0904229,34.86431,0.82869506,-175.45457,-197.46239,0.08079473,1115000
0.3199061,1.7432686,-78.718864,-175.4556,-205.6718,10.49938,-40.16396,142.98276,-75.84492,-175.2232,-205.69719,0.1635134,1120000
0.2877393,0.4526391,-53.319714,-176.31876,-200.77489,3.5526812,-1.805566,28.771397,-51.98594,-176.1923,-200.78001,0.117275245,1125000
0.2908741,0.5307626,-43.568707,-176.367,-198.02861,2.8330705,-2.1625867,25.872398,-40.32266,-176.23172,-198.05936,0.12809478,1130000
0.320131,0.66269,-57.801193,-173.46329,-212.84537,6.3840055,-6.874432,52.59837,-58.170956,-173.27106,-212.90874,0.34935766,1135000
0.32028311,1.2823442,0.0,-174.7121,-201.06999,24.826315,-20.65237,111.12865,-1.9790907,-174.64186,-201.08777,0.48515153,1140000
0.31641945,0.6915445,-37.971516,-173.75937,-197.56393,3.355802,-2.4114535,34.4961,-37.616364,-173.62445,-197.55048,0.12179729,1145000
0.2874445,10.109323,0.0,-169.87338,-193.72916,31.22275,-17.16394,257.85187,-0.7763106,-169.76501,-193.69775,2.4650517,1150000
0.3244179,1.4111632,0.0,-173.4429,-212.61331,4.561445,-4.733642,53.802635,-2.4122276,-173.36652,-212.57234,0.21196915,1155000
0.3145808,3.626133,-41.071293,-171.69077,-200.56226,6.595527,-20.593803,127.28254,-43.61218,-171.5796,-200.55157,0.6581522,1160000
0.3230942,0.87324494,-74.36148,-172.15329,-198.54234,4.7190065,-7.3756046,64.45933,-71.74433,-172.09003,-198.54237,0.21807241,1165000
0.28429466,0.6706373,-42.747536,-175.19672,-206.91386,3.637198,-2.0470076,41.984856,-42.40148,-175.02768,-206.95967,0.17694578,1170000
0.26845407,2.332546,-88.35351,-174.83289,-197.2952,4.359732,-13.025736,117.23567,-88.86867,-174.76924,-197.27551,0.3106259,1175000
0.34590954,0.65041614,-2.319583,-172.33484,-195.92874,4.012038,-2.2284927,40.2986,-1.3338507,-172.20795,-195.90431,0.17559922,1180000
0.30530742,0.9225583,-52.807705,-177.03165,-206.46367,2.7463408,-2.2261026,27.973671,-52.695236,-176.99918,-206.5028,0.116904095,1185000
0.27765444,0.99004585,-44.992535,-175.49826,-202.22336,8.9743805,-11.967129,64.577705,-45.952675,-175.34813,-202.23564,0.30624503,1190000
0.28727722,1.3195909,-73.44964,-176.68835,-195.85237,6.607828,-21.102266,101.08467,-73.50494,-176.56601,-195.82747,0.29351223,1195000
0.2846542,0.27201325,-48.139313,-177.76999,-197.48593,2.1717782,-1.8219199,18.648163,-50.385654,-177.65039,-197.47672,0.09458277,1200000