O2O / O2O-w-diff-ckpts /ifql /20260317_094137 /online_agent.csv
Tiredsheep's picture
Upload folder using huggingface_hub
ecf7b02 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
0.34779033,1.8531777,-18.76663,-162.73466,-196.78458,21.039865,-14.798652,119.25896,-13.659783,-162.53792,-196.7694,0.14402616,505000
0.39802086,1.260288,-3.7558906,-161.01031,-191.73724,4.2990746,-3.1978462,66.31867,-0.8975121,-160.80978,-191.69298,0.23955698,510000
0.343274,0.8665619,-29.651426,-164.60542,-194.15639,5.64817,-5.5665007,67.77022,-30.602077,-164.51735,-194.31339,0.18806246,515000
0.29793453,0.74356234,-21.246954,-164.84491,-202.18437,1.4551791,-1.7620168,36.712803,-22.898956,-164.65182,-202.20761,0.1264447,520000
0.3018235,1.1517464,0.0,-162.22748,-198.92563,4.5574193,-16.567232,84.91958,-0.04475382,-161.93854,-198.92422,0.43658656,525000
0.3229984,0.7402398,0.0,-162.45554,-196.5967,1.7008084,-3.8110228,34.858837,1.2517078,-162.37625,-196.74713,0.14312705,530000
0.35290903,2.2329793,0.0,-161.69336,-197.63007,26.915236,-13.852765,156.3352,-5.1666946,-161.45305,-197.32515,0.8862858,535000
0.32358804,1.3809534,-4.7031174,-162.57544,-194.1724,15.897423,-8.333341,93.303215,-1.7535516,-162.30902,-194.12354,0.14260286,540000
0.31515414,2.8348937,-66.27833,-165.48985,-197.59486,41.570877,-46.632607,291.60083,-63.766525,-165.27489,-197.58635,0.23879786,545000
0.30639404,5.163997,0.0,-163.45174,-200.88771,31.811563,-21.332882,268.2061,-0.85691166,-163.04599,-200.87428,1.4108671,550000
0.31559888,2.6688402,0.0,-161.68135,-203.30547,25.306341,-27.231112,298.8014,-1.2964475,-161.66638,-202.3252,0.6524079,555000
0.3461988,5.0336285,-37.61145,-164.5679,-207.88686,16.437408,-20.864779,194.1073,-38.073257,-164.43642,-207.97548,0.62174714,560000
0.33019876,1.2450293,-35.070004,-166.53543,-198.01231,15.435133,-5.540908,74.32572,-35.123085,-166.31468,-198.00581,0.303545,565000
0.31681952,1.3955075,-15.967898,-165.36398,-197.78955,101.61668,-33.623142,432.31763,-17.30152,-165.3816,-197.77972,1.3991597,570000
0.3472898,1.8998216,0.0,-167.16516,-211.36499,11.545614,-6.209779,114.18072,1.2983601,-166.96405,-211.29765,0.41879424,575000
0.33300376,1.118637,-30.837934,-164.17456,-192.43561,8.914438,-4.3177576,64.681885,-24.655386,-164.02121,-192.40239,0.1967095,580000
0.32085693,2.9585507,-27.113794,-165.64575,-198.16125,9.95353,-16.31087,152.83578,-25.952839,-165.38867,-198.15747,0.49469513,585000
0.3168386,1.0919303,-20.420748,-163.48206,-198.22221,7.0155754,-6.473722,65.79309,-21.807684,-163.27176,-198.21693,0.38011634,590000
0.32099152,1.3170836,0.0,-161.29495,-198.20067,17.883612,-17.139534,138.56259,0.3247266,-161.29398,-198.22275,0.4903153,595000
0.33761233,1.8508176,-0.14520705,-164.85062,-198.40549,18.077139,-38.079304,238.87917,-0.31380945,-164.33777,-198.39365,1.9157536,600000
0.34471333,2.8847888,-50.715076,-166.54822,-194.40544,37.82858,-51.7417,385.70172,-13.4351,-166.2235,-194.37495,3.4390233,605000
0.31038338,1.965659,-23.557714,-162.93036,-201.14294,27.342686,-42.096935,262.45023,-24.262362,-162.65869,-201.16301,0.50075996,610000
0.28560355,0.620667,-20.302197,-169.4055,-198.2816,3.9532032,-6.764418,51.66081,-23.351923,-169.32208,-198.26994,0.21876064,615000
0.32041514,1.3131337,-31.48319,-168.42227,-197.78796,5.8541465,-4.896258,60.449696,-30.37698,-168.29367,-197.76395,0.26619995,620000
0.30506897,1.1940287,-40.184547,-167.68597,-198.10161,4.437198,-3.3217163,53.123512,-36.009212,-167.37912,-198.07329,0.21312496,625000
0.30272204,3.7242603,-29.409657,-166.00552,-196.54022,9.896025,-28.767263,185.22836,-25.175447,-165.60605,-196.2505,1.2288743,630000
0.33376557,3.200278,-63.892204,-167.93185,-192.66858,4.057773,-6.0483036,94.40995,-64.22688,-167.85974,-192.54161,0.41277868,635000
0.3048464,4.385674,-55.02997,-169.66931,-199.8039,87.551285,-44.73099,574.1201,-55.27008,-169.62204,-200.09094,1.9644467,640000
0.31716287,1.1014725,-30.856003,-165.04747,-200.4823,6.857729,-5.0524135,82.899635,-29.440714,-164.76883,-200.65802,0.48230088,645000
0.3163827,0.683998,-31.068512,-169.12897,-200.46632,11.42578,-4.0572524,64.874405,-31.185171,-168.87335,-200.42003,0.19438109,650000
0.36025035,0.85711366,-58.169514,-168.307,-194.89859,2.6138816,-11.56995,48.32338,-58.36186,-168.25565,-194.87875,0.19418393,655000
0.3173821,0.6846257,0.0,-166.08525,-192.15488,3.9756293,-3.5559742,52.557278,-0.3849051,-165.85109,-192.13516,0.2866244,660000
0.32279938,0.60660166,-40.92961,-168.68985,-194.9931,4.0100636,-2.1110666,37.473366,-40.87771,-168.57335,-194.97371,0.12543455,665000
0.31198132,1.1713809,0.0,-167.99869,-194.93646,7.694274,-4.0889797,83.081726,-2.5376182,-167.63617,-194.9147,0.25650746,670000
0.31627116,0.43889618,-26.787964,-167.87656,-194.50014,1.023445,-2.5735404,31.07036,-27.58736,-167.7651,-194.36624,0.07946628,675000
0.32913196,0.9591765,-1.7476599,-163.96275,-200.07616,3.5419652,-6.7424803,56.00341,-1.4200472,-163.75888,-200.13681,0.19821283,680000
0.31145263,2.150906,-3.0117276,-171.03018,-193.95877,17.907108,-6.207053,102.01533,-2.0569863,-170.78107,-193.85306,0.1972658,685000
0.33383393,0.99554026,-46.33661,-166.48499,-194.89178,3.5578628,-5.0624466,53.704174,-44.4502,-166.2699,-194.86972,0.24662606,690000
0.34961274,1.1885207,0.0,-170.17679,-194.29979,9.431266,-22.276733,133.00163,-1.6133289,-169.91649,-194.27232,1.0814297,695000
0.35969186,1.0575327,0.0,-167.84427,-193.8191,6.388653,-20.494343,91.508545,1.1068838,-167.67624,-193.78902,0.54683924,700000
0.32691836,1.6930195,-32.347176,-164.91074,-196.09557,8.78425,-4.218672,81.67247,-31.464643,-164.70311,-196.2006,0.38223648,705000
0.2806484,2.0045474,-63.710102,-169.72726,-193.51913,27.57943,-6.8711953,108.93654,-63.07454,-169.52237,-193.51645,0.9219161,710000
0.3199215,0.5682961,0.0,-170.46368,-199.10085,6.692469,-15.757357,68.31832,-3.806767,-170.38934,-199.12302,0.18347618,715000
0.3006537,0.9495289,0.0,-169.00177,-195.42035,3.7918348,-3.2112184,36.684593,0.110304266,-168.85968,-195.41525,0.16559762,720000
0.29962265,20.01531,0.0,-167.66988,-196.82484,498.21716,-282.82867,1843.5094,1.3998965,-167.3874,-196.80916,9.863422,725000
0.29620492,0.59830195,-32.571037,-170.89716,-196.89764,9.562481,-2.358527,57.336094,-37.254898,-170.79599,-196.88332,0.22817671,730000
0.32310665,1.5212197,0.0,-170.21106,-197.32217,15.551842,-12.0619545,109.23268,-3.1560712,-170.21718,-196.96092,0.38790363,735000
0.2917348,0.5161819,-57.04711,-172.74393,-195.88779,2.425691,-2.9058504,35.373062,-53.307804,-172.54726,-195.8718,0.124094374,740000
0.28517538,0.9209561,-30.430998,-171.62683,-196.86183,2.8035212,-3.2211626,43.996796,-29.587584,-171.4701,-196.86125,0.1981412,745000
0.26529443,1.7254963,-1.6527634,-170.72243,-196.71161,11.414633,-10.4992,100.75047,-0.68819964,-170.61855,-196.70624,0.46009645,750000
0.33618927,1.8530911,-21.325836,-168.03738,-195.28635,4.5697904,-13.036383,99.46482,-20.691511,-167.81287,-195.26544,0.3342198,755000
0.35045725,1.2253424,0.0,-170.3368,-195.3119,10.770719,-25.993082,92.62959,-3.477035,-170.17014,-195.30774,0.23941365,760000
0.338233,0.43799147,-55.613094,-171.25085,-195.13274,2.4817092,-4.1811275,31.577747,-54.343933,-171.163,-195.10681,0.18004376,765000
0.33864903,1.9762734,-39.79097,-171.06277,-203.29193,5.2194943,-8.042761,90.2686,-38.853218,-170.95404,-203.31143,0.3568989,770000
0.29776338,4.700777,-36.778008,-169.46075,-195.42056,14.798938,-6.881212,120.13429,-36.208893,-169.41617,-195.38907,0.44393486,775000
0.32794556,1.3155003,0.0,-169.62628,-199.04141,32.99141,-13.265338,105.989746,0.38949633,-169.49072,-199.06273,0.30185503,780000
0.31721997,0.72823733,0.0,-169.12958,-199.28043,12.175176,-18.718609,89.19274,-2.2108183,-169.03781,-199.27936,0.2336261,785000
0.33045357,2.7222316,-56.437447,-173.54834,-197.9571,6.9742885,-8.28847,108.85744,-60.761166,-173.37045,-197.67638,0.66287524,790000
0.2970885,2.3328035,0.0,-167.1252,-195.03105,11.308402,-4.358903,84.55318,2.5602202,-166.9274,-195.0199,0.11862397,795000
0.29613793,0.89949495,-49.467903,-170.52896,-195.14514,4.0459538,-3.3762767,37.752068,-47.4397,-170.3524,-195.12003,0.19841348,800000
0.3360365,1.0271976,-57.133007,-173.19063,-197.75562,9.910936,-3.542051,67.828255,-57.679436,-173.02571,-197.74261,0.27616698,805000
0.32318726,3.1246955,-39.481457,-171.82434,-195.0108,9.716457,-6.1547523,92.54376,-35.464466,-171.6319,-194.99043,0.94144845,810000
0.32886872,2.2355068,0.0,-168.93216,-197.99417,20.112558,-24.567373,145.15955,-0.10760921,-168.67676,-197.97115,0.3435517,815000
0.2981451,3.7529836,0.0,-171.6998,-201.52422,20.608524,-13.428866,204.614,-5.1088557,-171.323,-201.21681,1.2010288,820000
0.27063662,0.62698793,0.0,-167.69867,-201.22269,8.094292,-2.162541,53.73269,0.5003896,-167.61392,-201.23375,0.17114061,825000
0.30355215,0.53009933,-32.81107,-173.21,-201.3591,2.0118701,-2.7524567,32.268208,-30.903814,-173.05391,-201.37459,0.12390259,830000
0.30052614,0.7120374,-52.14756,-170.87851,-198.1679,4.2922616,-3.1032534,41.514095,-51.78474,-170.7161,-198.1554,0.16769281,835000
0.3082096,4.0923543,-53.38402,-172.72531,-196.94221,37.64696,-43.26024,308.8739,-52.39521,-172.6142,-196.92992,0.28992593,840000
0.28649506,1.0434722,-37.10379,-171.02892,-197.15276,16.019114,-16.79979,99.79222,-36.67933,-170.91107,-197.13542,0.14401409,845000
0.30106288,1.0376078,0.0,-172.70543,-202.00177,16.05788,-9.762302,74.41603,-1.3820803,-172.56296,-201.76363,0.30063096,850000
0.2929955,0.6566334,0.0,-169.9838,-206.15033,6.699751,-6.5422435,59.751175,-0.7853655,-169.80132,-206.1839,0.16906516,855000
0.3369264,0.5580409,-27.553413,-175.22058,-197.50569,2.426567,-4.1492043,37.20325,-27.27099,-175.13394,-197.39449,0.16120407,860000
0.2907855,0.6088847,0.0,-171.32669,-197.3517,5.5685234,-3.202569,51.03698,2.273585,-171.26254,-197.36252,0.1595426,865000
0.29872003,2.716326,0.0,-170.59198,-195.71776,29.445086,-11.331553,160.3657,-3.3297179,-170.41933,-195.7002,0.8720765,870000
0.26177716,1.7838986,0.0,-172.33856,-197.10973,22.011011,-15.183547,148.95921,-1.4005635,-172.1153,-197.11258,0.23999926,875000
0.29776245,2.3138514,-42.015156,-170.29108,-197.50871,11.588799,-22.550066,200.26648,-30.976883,-170.07605,-197.49167,0.5936929,880000
0.2671064,0.8445776,-30.57274,-169.6778,-197.22592,15.136251,-2.9965756,68.93333,-25.388323,-169.60287,-197.24974,0.11436066,885000
0.32630956,1.5869122,0.0,-173.08829,-194.4205,21.60833,-55.567265,194.58722,-0.090200156,-172.92677,-194.38762,0.14533639,890000
0.27317637,0.67794746,-50.090984,-173.41144,-197.32355,3.4488132,-4.609168,43.301403,-52.54172,-173.24774,-197.3132,0.13616642,895000
0.3301434,1.1052207,0.0,-171.982,-202.18367,53.753937,-45.518475,220.74701,-0.16749424,-171.8133,-202.19087,0.6928912,900000
0.32563224,0.8000477,-1.3349218,-169.81752,-196.9872,2.4913554,-4.081819,49.81698,-0.8827156,-169.65332,-196.96452,0.1386186,905000
0.27473837,0.70828825,-1.6821623,-172.78557,-205.48032,1.8949695,-1.3834656,25.586544,-1.916368,-172.68872,-205.50075,0.11165414,910000
0.3513801,0.8190528,0.0,-172.82642,-196.9996,1.9281777,-4.063173,41.685616,-0.1262492,-172.72589,-196.98282,0.11938175,915000
0.27950922,0.8089576,-72.914314,-173.81294,-199.45943,2.2657976,-4.173822,38.24198,-70.49621,-173.70435,-199.45332,0.15106897,920000
0.2853765,1.2945672,-40.332287,-174.08792,-199.52217,3.415248,-3.620325,53.07062,-38.492607,-173.90726,-199.51141,0.19322649,925000
0.27191085,0.79739875,-36.99439,-174.27234,-196.30396,5.3140206,-3.3920982,52.768795,-32.268593,-174.10092,-196.25874,0.30583835,930000
0.32106787,1.0883839,-50.738094,-172.08607,-205.82388,4.8253927,-7.089793,71.1389,-49.805836,-171.76483,-205.8558,0.6116886,935000
0.33160707,0.7603189,0.0,-173.52444,-200.78255,7.6468487,-5.1190314,72.33987,-1.4677684,-173.35205,-200.7919,0.27793524,940000
0.31052423,0.89143294,-23.388737,-171.37955,-197.13846,2.3455002,-3.2360125,40.102234,-25.990444,-171.33322,-197.4953,0.14143397,945000
0.3285656,1.2998269,0.0,-169.09174,-195.81874,20.541384,-7.0671654,91.45903,-0.41164252,-169.0016,-195.7964,0.46440876,950000
0.30869642,0.89776057,0.0,-171.38358,-205.30035,2.8986266,-3.8067183,40.11963,-0.12527245,-171.26698,-205.32527,0.23999964,955000
0.2817424,0.53572416,-37.978775,-169.72156,-201.26213,3.5464516,-3.162265,41.166195,-38.48024,-169.57957,-201.25414,0.17303312,960000
0.32940918,0.84185296,-68.462364,-169.58665,-196.15862,2.3070564,-4.2220974,46.57177,-62.512165,-169.46077,-196.13947,0.1698077,965000
0.28281617,0.93449086,-41.332718,-172.34708,-201.17053,21.722183,-5.3148384,91.640945,-37.202248,-172.13,-201.18239,0.31784284,970000
0.2803874,2.245155,-83.70884,-172.09839,-194.98277,9.765084,-6.622466,128.07512,-84.128624,-172.06236,-194.94618,0.51698565,975000
0.32323185,0.8295353,-0.9884119,-170.75095,-197.04108,5.20471,-2.0351512,38.72786,0.028107226,-170.58943,-197.05641,0.18871227,980000
0.2883178,0.5184817,-50.386333,-174.67264,-201.05644,1.1030432,-1.4512545,26.049519,-49.477608,-174.57784,-201.05748,0.068729386,985000
0.34944224,1.2412566,-40.72151,-173.59024,-203.76898,6.471911,-12.483805,109.256,-43.9315,-173.37181,-203.78706,0.33255076,990000
0.30170634,1.211495,-68.84839,-174.37787,-198.05049,7.6547227,-12.218495,80.62427,-68.4883,-174.28,-197.98628,0.23525622,995000
0.25995803,0.3400454,-41.484833,-176.42221,-201.31688,3.3879917,-1.3383536,25.823208,-41.924007,-176.29352,-201.32341,0.12093863,1000000