O2O / O2O-w-diff-ckpts /cgql /20260317_071429 /online_agent_sv.csv
Tiredsheep's picture
Upload folder using huggingface_hub
c491899 verified
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
0.3443981,0.25579247,-5.3519278,-161.96933,-208.59694,0.56308067,-0.57833815,13.583535,505000
0.40635496,0.4061775,-8.629857,-158.9218,-209.02243,3.0975492,-2.3853621,33.777466,510000
0.33662528,0.26012298,-5.4064507,-165.45262,-211.8761,1.8838185,-1.7206088,26.900629,515000
0.29733294,0.2110558,-16.866838,-164.73329,-209.46133,1.5205721,-2.499127,20.955006,520000
0.31329706,0.3549642,0.0593372,-162.01335,-210.56339,2.100661,-2.0018926,28.267395,525000
0.32272947,0.32199648,0.3418841,-162.95723,-207.1439,1.2492584,-1.6593876,23.540768,530000
0.3532054,0.4253761,0.6764766,-163.48845,-218.20062,2.628896,-2.6873536,29.237743,535000
0.32287997,0.28096107,-5.773243,-163.68326,-208.47652,1.0186874,-0.77462554,17.041855,540000
0.31693098,0.2257431,-8.529599,-166.61758,-212.72069,0.86635655,-0.6643578,13.359153,545000
0.32420337,0.313826,-0.66126823,-165.74506,-212.97688,0.98555684,-1.8405315,22.620615,550000
0.31267372,0.26226842,0.65207756,-163.324,-208.66777,1.1923578,-1.2906388,20.80989,555000
0.32060707,0.21668954,-35.57045,-167.96971,-208.9829,2.9637957,-1.757416,31.714712,560000
0.35048884,0.22157137,-9.887765,-169.47993,-213.01302,1.0264592,-1.129112,18.710659,565000
0.32572895,0.29732004,-14.707364,-168.8174,-212.41281,1.3788985,-2.5621085,19.14661,570000
0.34636787,0.2969279,-1.3865404,-171.82735,-210.63622,2.5816338,-2.6051893,29.825932,575000
0.31513196,0.5549297,-11.966988,-169.34737,-212.30554,5.3091774,-2.651498,50.28061,580000
0.33471182,0.22374073,-3.935435,-171.73955,-213.82454,2.2352545,-1.1041244,17.449038,585000
0.35100666,0.33464754,-18.615755,-169.66849,-211.30154,2.2545264,-1.1805655,21.355164,590000
0.32307404,0.41704312,0.04429987,-164.89763,-211.11018,4.0235267,-2.0734854,32.90075,595000
0.3238899,0.3070471,-5.2261004,-167.38799,-208.54689,2.6963618,-2.5241137,33.608234,600000
0.33710653,0.24634276,-6.6133747,-172.16043,-210.49747,2.1860273,-1.2290689,21.253708,605000
0.29192317,0.27551934,-7.781213,-167.41936,-207.23813,3.6182141,-4.451338,35.373837,610000
0.32342166,0.26906076,-9.808537,-173.07854,-208.49344,1.596414,-3.3741422,32.447037,615000
0.32418722,0.24568759,-18.931501,-173.53862,-208.76065,1.3468955,-1.2017556,16.827812,620000
0.31560564,0.2996919,-4.409719,-171.57054,-208.28485,1.2608454,-1.5335131,19.960455,625000
0.30359578,0.28102186,-4.58022,-173.0129,-214.41121,1.3055782,-2.2176096,20.830303,630000
0.3381145,0.2261379,-58.151775,-173.41756,-207.9625,2.0412178,-3.020679,31.227375,635000
0.30221495,0.910569,-7.6522,-173.4456,-208.6904,9.294845,-5.7906046,72.77631,640000
0.31157744,0.65387195,-14.615815,-172.58623,-207.45798,1.7332196,-2.2927322,25.63237,645000
0.32685906,0.24698189,-2.8666549,-172.31427,-212.4027,0.8966364,-1.9766506,16.150045,650000
0.3259822,0.2640659,-1.4976525,-173.59398,-208.76656,2.1495383,-1.5742698,19.75263,655000
0.3308565,0.7485824,-1.9713035,-167.83089,-208.35895,8.267575,-5.095381,86.25739,660000
0.3284397,0.28439078,0.20922726,-174.04387,-209.59831,1.4293702,-1.427923,17.741425,665000
0.32459638,0.32554242,-1.4498992,-175.38158,-220.33775,1.5705906,-2.0477629,28.435091,670000
0.33186656,0.23258631,-13.465273,-174.53929,-210.16669,3.4877572,-1.4746567,25.428162,675000
0.32269013,0.3874253,-9.813116,-168.8142,-207.81972,2.392606,-1.6614505,24.038242,680000
0.31617346,1.1748146,-2.174219,-174.49942,-210.89209,23.213043,-9.0816,108.85678,685000
0.30724382,0.37233156,-0.4617796,-173.85652,-225.62161,3.5546296,-2.9793212,30.42781,690000
0.32736367,0.5197549,0.3780437,-173.76653,-215.02216,3.4388816,-5.300501,35.24563,695000
0.36540478,0.5410134,-0.90829635,-171.42145,-212.07225,6.213863,-3.3264544,43.966316,700000
0.3203576,0.25782433,-0.2494959,-168.57698,-208.12871,3.610234,-1.7628902,25.722605,705000
0.28110087,0.32719794,-14.732163,-171.21289,-210.48933,1.7585797,-1.8395742,20.991776,710000
0.32186186,0.20164691,-0.051270455,-173.90137,-212.59348,2.32122,-1.326883,25.60947,715000
0.33508605,0.31140533,-0.07334104,-170.85338,-209.76096,3.296744,-1.7753844,30.184126,720000
0.29733074,0.23449357,-0.14134571,-174.4059,-211.82225,0.9703058,-1.3449895,17.46387,725000
0.32470798,0.2421505,-26.286068,-175.99106,-209.90535,2.4893801,-1.3880225,22.409323,730000
0.3011272,0.17086877,-0.6947125,-170.8326,-211.88353,0.56316024,-0.5759253,12.422925,735000
0.2636865,0.30532047,-25.361814,-177.02635,-210.41595,1.8576059,-4.4980702,33.53293,740000
0.2882126,0.2455707,-12.202288,-172.28963,-210.0518,1.5269277,-3.635824,26.756487,745000
0.27785575,0.36309454,-4.220861,-172.54546,-209.8371,6.7391944,-3.270038,45.55653,750000
0.30832118,0.4152329,-10.826684,-171.3726,-213.37535,3.6500554,-2.276774,34.897896,755000
0.36075264,0.23139672,-10.978866,-172.1706,-208.01079,0.9803059,-1.4946942,18.029083,760000
0.3443067,0.20733109,-20.475826,-172.67413,-207.439,0.8711454,-1.3121171,16.239841,765000
0.33394426,0.308187,-1.6062335,-171.94579,-211.07492,4.8818727,-2.291089,38.557102,770000
0.33694735,0.23550569,-0.78252614,-172.80965,-209.88187,3.1043286,-1.4649801,24.0321,775000
0.32079583,0.26801512,-29.760069,-176.4716,-211.03487,4.930401,-1.8093598,27.641073,780000
0.32118544,0.37595326,0.8144077,-172.29254,-213.30635,5.572153,-3.3640637,39.028004,785000
0.33417818,0.22772126,-19.721329,-175.69014,-209.64615,2.6172338,-1.466332,26.555065,790000
0.2987554,0.26782528,-0.26486242,-175.1183,-208.95464,1.1945624,-1.327864,16.108469,795000
0.3397544,2.0021226,1.3501338,-170.8577,-209.22081,39.43719,-54.787136,284.77814,800000
0.3317383,0.19327815,-12.350279,-176.71092,-209.755,0.9487981,-1.6349149,18.160421,805000
0.3233953,1.7792625,-13.635453,-174.45401,-211.56674,17.793835,-9.065606,83.92958,810000
0.33999693,0.49356183,-7.530399,-174.03484,-209.50058,1.9555703,-2.4703994,29.46907,815000
0.3095147,0.61834556,-5.603682,-172.09102,-215.76315,2.8208845,-5.4328737,54.88524,820000
0.2791888,0.64162827,0.29527372,-167.19475,-209.03006,7.5838747,-12.467892,100.09919,825000
0.31832176,0.35843572,-11.665064,-171.9957,-208.20294,3.0855153,-1.5577774,25.455051,830000
0.3281309,0.32138914,-18.710754,-172.29387,-210.59705,2.7404451,-1.2754387,24.329817,835000
0.31066087,0.33715382,-0.6529349,-169.72127,-207.88652,4.9595,-2.8284779,44.36074,840000
0.26502797,0.36706102,-6.9780054,-175.47295,-218.17598,1.2238339,-1.9884905,22.56652,845000
0.30297622,0.26540744,0.44682473,-176.97647,-211.83482,3.2802243,-3.0067844,27.545319,850000
0.29240945,0.26027197,-14.008103,-175.59511,-213.24214,1.1145847,-2.3888285,19.379002,855000
0.34552214,0.5390585,-4.118867,-176.36296,-213.0996,22.264666,-10.645226,80.817986,860000
0.28900188,0.40637994,2.0772905,-172.14168,-212.97215,4.400397,-3.430012,43.13415,865000
0.3034529,0.31147337,1.0422533,-172.38756,-208.13672,1.253455,-4.4437447,25.058851,870000
0.26752794,0.20416291,0.5243865,-175.2526,-210.74617,2.0168002,-1.1390529,19.444857,875000
0.3139153,0.26780048,-2.1007948,-173.3396,-209.2786,1.2371309,-3.298257,21.391684,880000
0.31606102,0.3043681,-9.995129,-174.86215,-209.16873,1.8621391,-1.6904027,22.62394,885000
0.32391962,0.16192372,-19.41926,-172.42204,-210.34492,3.1205392,-1.5234681,21.747768,890000
0.31279194,0.27239355,-14.25477,-176.82466,-207.83707,4.603559,-2.4155118,31.262005,895000
0.32040262,0.39620027,-12.791233,-177.64975,-210.38528,3.0459163,-1.102227,23.7598,900000
0.359543,0.24585707,0.44145697,-175.34514,-210.37367,1.191268,-2.439071,18.099964,905000
0.29367957,0.39057937,0.18442315,-168.95984,-215.69347,7.4612384,-2.0089285,37.229904,910000
0.33474487,0.287796,0.11879796,-171.24426,-210.70357,1.4579103,-3.7440948,32.961563,915000
0.28400007,0.31199056,-0.0793567,-174.4705,-211.09125,1.6801897,-2.5311563,25.150707,920000
0.31140143,0.17496538,-3.5297534,-173.53694,-211.34944,1.4164717,-2.4090679,24.238039,925000
0.27413613,0.36967492,2.2654486,-173.557,-211.82498,5.343662,-6.487564,44.471897,930000
0.31951192,0.17359112,-18.965643,-175.03381,-211.21622,1.2779001,-0.6903305,12.893568,935000
0.368392,0.28338933,0.31390217,-169.26913,-210.20877,6.3101993,-2.3298483,33.119625,940000
0.34789467,0.32195598,0.049540043,-172.6665,-215.74753,1.7814317,-4.556218,37.737675,945000
0.33392164,0.39472753,-3.6740127,-171.38292,-212.55339,2.1641114,-5.839763,42.898167,950000
0.30988026,0.19730127,-0.8376319,-175.74303,-212.26198,4.2458024,-3.1529913,27.254728,955000
0.32823074,0.29162312,-5.126237,-171.00755,-211.8651,1.517982,-2.8163526,22.566734,960000
0.35306033,0.3866789,-22.639889,-172.00786,-211.85847,3.9531784,-6.289561,37.959217,965000
0.313129,0.24972907,-24.151337,-172.29668,-209.8876,1.7534983,-2.566138,20.944311,970000
0.2846272,0.42515945,0.4947753,-172.96391,-211.12941,2.9540431,-6.523899,50.603638,975000
0.33243603,0.33059254,-2.9320273,-169.80643,-212.18774,2.989802,-3.8443847,30.38756,980000
0.29524413,0.26215082,-1.7444301,-169.88043,-212.1259,2.8547175,-3.4636133,28.071814,985000
0.33885416,0.32365218,-4.1306705,-174.50682,-213.38533,2.044472,-3.9769144,40.62505,990000
0.3295281,0.42311677,-9.629019,-169.28596,-211.76305,6.242449,-5.9981394,47.828735,995000
0.2705195,0.28950948,-0.87233025,-174.205,-215.75415,1.0045736,-0.80033135,14.652052,1000000