O2O / O2O-w-diff-ckpts /ifql /20260318_010445 /online_agent_sv.csv
Tiredsheep's picture
Upload folder using huggingface_hub
73dda2e 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
0.3556872,1.6501617,-33.94551,-167.22318,-200.7932,4.6806645,-11.996777,72.46727,-33.59417,-167.07397,-200.81104,0.2877505,805000
0.32459787,1.5871753,-37.681282,-165.62967,-193.02733,4.294736,-11.35283,126.26851,-6.2295203,-165.25462,-192.96283,0.46624118,810000
0.36987144,1.1827554,-41.493984,-168.79486,-195.23572,6.543738,-5.091483,77.22642,-41.098644,-168.67462,-195.30666,0.21042566,815000
0.32171726,0.8748189,-32.362633,-168.66347,-196.988,20.290512,-5.88947,86.13903,-34.043804,-168.51553,-196.95612,0.13442555,820000
0.28726178,1.3289617,0.0,-167.0886,-201.28117,11.652324,-20.437288,92.7509,-3.8826509,-166.869,-201.29865,0.50134194,825000
0.322443,0.716706,0.0,-166.9073,-204.55807,1.9707091,-1.9575692,27.583878,1.6523187,-166.76685,-203.54039,0.10928015,830000
0.3329652,2.6017916,0.0,-165.85025,-196.58,28.972725,-7.0561604,130.8284,-0.37056893,-165.70789,-196.57529,0.6177522,835000
0.31585136,1.2114124,-7.748046,-166.19131,-197.7619,6.795949,-6.9138293,80.04788,-4.9426165,-165.9398,-197.74667,0.25050467,840000
0.33210212,2.9451032,-76.75105,-169.59247,-195.54134,75.569954,-108.69132,541.9384,-75.52397,-169.3759,-195.52925,0.18043408,845000
0.29550952,2.067376,0.0,-167.36166,-200.42886,11.069254,-8.38313,121.55799,-0.48754486,-167.22351,-200.47707,0.23035178,850000
0.29764992,2.8764951,0.0,-165.52899,-196.73833,60.141678,-38.21115,447.68817,-3.3042183,-165.53796,-196.72285,0.71816784,855000
0.344677,1.6485049,-53.959965,-168.14847,-195.84258,16.215788,-28.916601,130.12485,-53.771557,-168.0353,-195.85701,0.12772915,860000
0.2958349,1.3151077,-48.868813,-170.06598,-197.66127,9.3146105,-8.45282,101.94349,-49.693493,-169.83025,-197.65346,0.47045696,865000
0.26947933,1.543985,-13.091789,-169.42607,-198.96863,3.5309887,-7.231165,70.28922,-10.134096,-169.32074,-198.96657,0.232786,870000
0.27442306,2.1272745,0.0,-170.20511,-195.78888,8.636552,-8.88827,76.55233,2.4841359,-170.12364,-195.79883,0.33384216,875000
0.32599717,1.0436581,-49.366714,-167.99582,-198.77332,3.3436778,-3.4643438,63.753212,-48.63745,-167.84189,-198.7702,0.19011205,880000
0.26448238,3.823874,-40.936253,-170.5516,-195.44421,33.158764,-55.0676,311.54742,-39.27669,-170.20705,-195.40294,1.3305782,885000
0.32014185,0.820209,-29.469706,-168.06847,-208.02773,4.207891,-7.782035,57.653984,-27.546186,-168.01227,-208.0176,0.25645506,890000
0.29095623,1.0678906,0.0,-165.29669,-196.68576,7.6544285,-12.352014,77.27386,-1.0298553,-165.1846,-196.66989,0.2498647,895000
0.341003,6.1136045,-2.4658527,-168.69368,-196.37837,33.780872,-23.942934,310.65445,-1.953058,-168.36139,-196.3469,2.0351646,900000
0.33827904,0.6467581,-70.60738,-170.71124,-201.03358,1.7405856,-2.7437544,39.098755,-71.32375,-170.57315,-201.03444,0.20829083,905000
0.28685975,1.9527673,-36.41679,-166.22447,-200.77464,9.990886,-5.405458,84.22853,-37.2339,-165.8573,-200.76828,0.74736357,910000
0.37084794,0.47895747,-25.946306,-173.21536,-196.96204,6.4335346,-2.576159,57.118073,-26.035353,-173.11974,-196.94762,0.14481413,915000
0.29589856,0.65798134,-43.559128,-171.53802,-197.07791,4.6395097,-7.9397135,43.764244,-45.855377,-171.45358,-197.06035,0.14203638,920000
0.30551806,1.0276763,-49.25818,-171.20311,-196.89993,5.7868137,-1.6281898,50.020187,-48.61131,-170.96791,-196.79225,0.26642054,925000
0.27905488,1.0324602,-49.410664,-170.0516,-201.78946,9.246643,-3.6165214,54.564648,-40.37781,-169.87398,-201.8109,0.401183,930000
0.3312394,0.8732147,-72.42809,-171.06192,-197.06836,4.4022007,-3.944341,65.141815,-71.1791,-171.02478,-197.09047,0.17640448,935000
0.3265754,0.85954154,-64.71954,-173.2745,-200.20746,0.96722573,-1.5204426,30.659752,-64.756065,-173.17181,-200.21481,0.12099503,940000
0.3232677,1.4599863,-37.52527,-168.10904,-196.4664,8.610747,-9.729019,109.46107,-35.27573,-167.84381,-196.36577,0.57376295,945000
0.33339667,1.5266054,-36.26863,-172.01944,-196.28131,6.352336,-12.491831,103.596344,-35.501324,-171.75218,-196.31084,0.34654817,950000
0.29688606,3.2587903,-70.56659,-171.18797,-200.361,13.123685,-15.586278,140.63025,-71.81768,-171.25818,-200.37148,1.7666385,955000
0.29240465,1.1961685,0.0,-169.51567,-197.16068,3.909771,-7.8660784,50.46714,-0.3229747,-169.34995,-197.22597,0.32148248,960000
0.34919602,0.74603283,-48.23824,-172.39479,-198.6732,2.8394747,-3.0911856,32.571396,-48.108658,-172.28247,-198.65182,0.08800681,965000
0.31405196,0.84931624,0.0,-171.39363,-201.10326,14.265113,-8.864263,106.81731,-0.9158648,-171.11592,-201.1055,0.4484153,970000
0.28942165,0.32394424,-29.253881,-171.02194,-201.20235,1.120869,-1.0705943,16.720781,-29.401709,-170.93684,-201.21768,0.07410821,975000
0.32852238,0.86686784,-1.194004,-167.469,-201.54239,8.707585,-4.1317205,51.03681,0.009740591,-167.33871,-201.54617,0.31600988,980000
0.2908667,1.4556576,-2.2932796,-174.13445,-196.5728,81.12662,-25.680397,226.2403,-2.2878294,-174.0581,-196.57858,0.19507572,985000
0.33925426,0.8037325,-59.482067,-171.04402,-198.20323,7.991265,-3.9980717,64.702644,-56.722027,-170.88809,-198.1869,0.16325828,990000
0.3260259,1.772961,0.0,-173.5092,-196.97456,26.057384,-33.895447,290.1737,-2.8996449,-173.40884,-196.95778,0.7842085,995000
0.25611234,1.4654279,0.0,-170.94266,-200.26901,6.01812,-7.9285207,92.15021,4.6271,-170.82138,-200.27808,0.31545705,1000000
0.269655,1.09957,-38.044,-168.21808,-205.67606,4.161476,-1.6619151,49.396202,-36.215736,-168.00325,-205.71819,0.16429669,1005000
0.27512,0.87425816,-73.48731,-173.86691,-197.86241,16.261751,-4.6474166,90.46724,-73.61801,-173.65652,-197.84184,0.63556945,1010000
0.32462317,0.71891886,0.0,-173.66415,-197.07579,5.805115,-5.3486524,62.11097,0.9637853,-173.52493,-197.06665,0.16548392,1015000
0.31467694,0.58211136,0.0,-171.84567,-195.65163,3.571161,-3.5404334,47.51242,0.41928765,-171.67955,-195.64426,0.13855559,1020000
0.33211094,2.152998,0.0,-170.86995,-196.62514,12.579245,-16.415833,141.05376,-2.6933868,-170.78587,-196.61281,0.5222689,1025000
0.29495403,1.17766,-45.98742,-173.19345,-199.93184,9.217322,-7.9437733,86.78826,-48.39502,-173.02795,-199.94142,0.25625825,1030000
0.3254249,0.58778375,0.0,-173.95766,-196.55281,6.38011,-3.7041817,64.981125,-1.003935,-173.87419,-196.56488,0.16751184,1035000
0.2562703,0.5590461,-69.315216,-175.81241,-197.81067,1.9799311,-2.120191,31.21258,-66.300575,-175.66083,-197.74539,0.18528557,1040000
0.273405,0.5357586,-36.99131,-175.0292,-196.36726,5.6050363,-4.8532934,49.51692,-38.213715,-174.82988,-196.4116,0.18658918,1045000
0.2819497,0.9427698,-2.9771996,-173.97372,-198.51416,16.659748,-15.54516,99.89943,-1.164563,-173.71576,-198.50574,0.40855318,1050000
0.29819322,2.5456753,-28.229097,-172.12631,-198.35876,11.289419,-16.874937,120.91957,-41.610043,-171.93845,-198.32527,0.64310503,1055000
0.31527227,0.5395223,0.0,-173.28769,-198.50359,12.695442,-23.553041,70.87779,-1.381527,-173.12347,-198.49142,0.2616591,1060000
0.33482158,0.5051036,-60.91472,-174.52837,-197.47,2.909874,-3.648624,27.498837,-60.2292,-174.40141,-197.43977,0.10971007,1065000
0.34285304,0.7380677,-51.08563,-174.731,-203.28918,10.076539,-6.240943,60.382095,-51.989735,-174.54996,-203.30669,0.28734434,1070000
0.322067,1.2403265,-42.814564,-172.42255,-199.77303,14.436475,-5.4989676,88.96686,-42.176723,-172.34671,-199.78255,0.29673237,1075000
0.30319557,1.4017214,0.0,-172.35756,-198.38547,11.482595,-7.649589,60.217415,-0.4186204,-172.2432,-198.38208,0.4384899,1080000
0.30419362,1.0091883,0.0,-172.70734,-198.9918,40.425297,-47.761673,195.35783,-0.657157,-172.67206,-198.98695,0.5511963,1085000
0.29494143,0.52003556,-97.92207,-176.69598,-199.52946,8.416217,-6.5229363,54.77328,-90.87315,-176.51213,-199.53421,0.18296187,1090000
0.31480905,1.4889939,0.0,-169.87361,-199.8446,3.4504807,-3.3383927,49.04988,0.89671457,-169.7109,-199.8462,0.16150631,1095000
0.29408634,0.88545763,-55.885143,-173.93936,-199.68924,8.234261,-9.364855,53.088097,-53.807735,-173.7938,-199.69354,0.13215125,1100000
0.34472716,0.94094545,-63.737537,-176.67804,-197.31447,39.070644,-11.093166,152.52628,-63.544174,-176.48508,-197.3005,0.6244341,1105000
0.26707208,0.7033968,-46.418392,-175.05534,-196.35963,27.081745,-10.189885,97.07109,-47.18952,-174.85039,-196.35794,0.62256175,1110000
0.24076398,1.1095558,0.0,-172.25067,-199.45764,11.69835,-15.259031,117.20807,-1.3998747,-171.97116,-199.44746,0.6307626,1115000
0.3046003,1.1782279,0.0,-174.80675,-200.81154,4.8696876,-2.5523589,55.403484,-1.246509,-174.68579,-200.77094,0.15061155,1120000
0.31611615,0.9362335,0.0,-171.02461,-198.46396,2.1152418,-2.101198,31.896778,-0.1388067,-170.82762,-198.45485,0.17673749,1125000
0.32988304,0.7762215,-35.437843,-175.85583,-198.33894,3.0811543,-2.38139,47.18673,-37.77273,-175.68979,-198.33574,0.11669569,1130000
0.336455,0.3657043,-60.43385,-173.79688,-199.37811,1.5431279,-1.0689412,23.78344,-58.318554,-173.71983,-199.37689,0.07746947,1135000
0.28848413,1.8091904,-61.25269,-175.03372,-200.2932,12.417856,-5.722769,72.76817,-60.247288,-174.80247,-200.29851,0.32873467,1140000
0.32390562,1.1028538,-46.27339,-173.37119,-199.55972,6.4478707,-9.000209,58.607773,-46.95339,-173.2235,-199.55585,0.1435599,1145000
0.30296588,1.7516747,0.0,-175.59677,-197.70674,23.920282,-36.875126,248.03336,1.5813582,-175.53647,-197.69617,0.60560006,1150000
0.33923995,1.0344127,0.0,-172.23206,-200.12627,4.694363,-7.7286224,52.234802,-2.5347707,-171.96913,-200.13185,0.19459686,1155000
0.3166113,1.3867794,-33.195976,-177.80695,-200.57579,5.09376,-7.3489695,61.087883,-36.40025,-177.79254,-200.58827,0.07465802,1160000
0.31192216,4.8339157,0.0,-173.2823,-197.38693,13.464805,-22.468414,125.56845,-4.335313,-173.09076,-197.37712,0.35094965,1165000
0.29984528,9.401888,0.0,-172.80573,-196.37389,36.48433,-19.54312,336.0352,-7.9308405,-172.63399,-196.35567,1.7646303,1170000
0.2473835,1.5962892,0.0,-174.30815,-197.2542,31.769045,-19.536062,148.19089,-4.2165346,-174.20566,-197.25372,0.32244986,1175000
0.33992267,1.9067211,-51.17578,-173.20622,-199.48967,23.120321,-44.52742,285.43774,-50.841198,-173.01149,-199.48335,0.37852997,1180000
0.3258343,7.6814165,-15.347686,-171.91867,-197.1706,19.263735,-38.141636,201.8461,-14.406736,-172.0571,-197.16435,0.98145497,1185000
0.29783428,1.0620487,0.0,-175.37946,-194.73865,6.867226,-7.6453547,44.84286,0.53025234,-175.20775,-194.7144,0.16998784,1190000
0.31011105,1.6294965,-59.81777,-176.24126,-196.729,2.5592375,-2.2577057,39.326477,-62.328274,-176.12444,-196.71239,0.11017683,1195000
0.29398948,0.61307454,0.0,-173.56146,-197.81737,2.0842311,-4.108738,28.060741,-0.43719393,-173.4463,-197.84279,0.123365335,1200000
0.27342004,1.1931275,-3.8754287,-173.51021,-197.74988,1.8145093,-2.1769087,55.453102,-3.2181726,-173.34024,-197.74751,0.23083243,1205000
0.30818427,0.6536298,-3.3537447,-175.55673,-198.45023,6.112175,-0.83980274,34.39519,-3.8927476,-175.40228,-198.44952,0.16449079,1210000
0.36377573,0.694484,0.0,-175.75873,-197.96556,3.5285795,-2.611644,40.772446,1.3205146,-175.66502,-197.9457,0.104025766,1215000
0.34204963,1.5901712,-79.90391,-176.23344,-199.2631,2.211246,-2.574937,41.144676,-78.674126,-176.0527,-199.26137,0.16014679,1220000
0.32654566,0.6065738,-55.911945,-177.07591,-200.49074,3.044295,-4.6538734,48.518158,-54.842884,-176.95544,-200.49901,0.15040466,1225000
0.2922284,0.67663556,-45.737347,-177.21387,-198.44832,2.7622705,-2.2379713,31.94947,-40.89048,-177.07681,-198.4396,0.096787594,1230000
0.30851692,0.43762094,-62.538574,-174.81009,-198.22704,4.02966,-6.67164,40.658615,-62.4375,-174.58012,-198.17119,0.22575153,1235000
0.34169197,0.41968384,0.0,-176.37344,-200.28058,7.3471456,-4.795475,42.879143,-0.43382245,-176.24728,-200.29108,0.14600629,1240000
0.30688286,3.2462845,-31.233465,-174.2938,-197.59085,13.098717,-12.754263,131.70076,-34.91683,-174.20142,-197.58017,0.2476632,1245000
0.322927,1.6000134,0.0,-171.65387,-194.36284,10.880245,-15.543192,125.733,0.94971746,-171.50195,-194.33916,0.2626137,1250000
0.3131823,0.80701315,0.0,-173.85144,-198.8444,2.058493,-3.3725934,40.517563,0.9219816,-173.78764,-198.83296,0.13108453,1255000
0.31330383,0.35150766,-47.899246,-174.3498,-201.91959,0.8404609,-2.465319,28.541986,-45.703953,-174.23499,-201.91438,0.14968944,1260000
0.32118994,0.8533455,-73.20275,-173.10995,-198.59369,9.5944195,-3.0142612,58.23251,-81.001175,-173.06639,-198.59564,0.16537166,1265000
0.25977522,0.9407261,-44.930458,-175.71722,-201.59726,3.3075695,-6.133657,58.08385,-45.416622,-175.59302,-201.61095,0.14447126,1270000
0.3333729,1.3917124,-93.5437,-175.1151,-197.89658,70.01294,-39.40091,235.26657,-87.4001,-174.91586,-197.88641,1.6363816,1275000
0.34545818,0.6003327,-1.6833851,-174.06186,-196.51936,3.0839014,-2.1130228,39.440426,2.2903948,-173.90146,-196.45935,0.16348755,1280000
0.30793828,0.34579644,-58.018734,-178.3318,-198.0969,1.6682332,-0.918384,18.85062,-56.17701,-178.24748,-198.07884,0.055257007,1285000
0.33746585,0.59817153,-43.59349,-175.79443,-200.78093,1.4925237,-6.641895,45.174957,-47.069653,-175.63031,-200.78908,0.16682944,1290000
0.33054793,1.0327471,-75.3982,-177.91675,-196.20569,2.5926394,-4.2503233,52.19532,-75.600845,-177.76328,-196.06888,0.19819304,1295000
0.3020808,0.610088,-48.35461,-178.93623,-194.6244,2.2339754,-1.7886511,41.501137,-47.147808,-178.84642,-194.3422,0.08014326,1300000