O2O / O2O-w-diff-ckpts /fql /20260317_094459 /online_agent_sv.csv
Tiredsheep's picture
Upload folder using huggingface_hub
30941d5 verified
actor/actor_loss,actor/bc_flow_loss,actor/distill_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
156.57028,0.34267497,0.05476255,0.11754544,-4.479921,-156.36295,-207.35289,0.882236,-0.5639714,14.81117,705000
152.9401,0.27273077,0.06455529,0.13656595,-7.454178,-152.83194,-205.96913,1.2835666,-0.5178353,14.733909,710000
160.44914,0.29449832,0.05126518,0.17268561,-5.102799,-160.24678,-208.71422,0.6394001,-1.7137442,20.690033,715000
157.92918,0.3096155,0.0531845,0.17376323,-17.243975,-157.7216,-206.12753,2.6216362,-1.3516862,19.469149,720000
154.71288,0.31664705,0.054029126,0.28845268,-0.19999757,-154.56741,-217.61218,1.827037,-1.9957694,24.69922,725000
156.86725,0.31010827,0.05563712,0.16085172,0.6195527,-156.66791,-208.62418,0.83160466,-0.43287194,12.544613,730000
156.29286,0.3196793,0.057441574,0.19601938,0.7113022,-156.0771,-208.0714,0.8939272,-0.79630136,15.652663,735000
156.18459,0.2693907,0.04864809,0.12895738,-4.746067,-155.98047,-209.29948,1.1162149,-1.436824,18.405361,740000
159.37053,0.28769922,0.051622942,0.17447247,-9.429716,-159.19075,-209.51537,1.2001361,-1.5143787,22.638813,745000
159.42941,0.2983524,0.050401434,0.2768061,0.1683321,-159.22583,-210.72777,2.7861857,-1.1778816,27.108976,750000
155.54292,0.31251824,0.044386573,0.1644432,0.9612249,-155.31108,-206.54875,1.503209,-0.89605135,24.978004,755000
161.66881,0.3432064,0.042922825,0.15804994,-31.630877,-161.4063,-207.53276,1.4554707,-1.9969943,26.882322,760000
163.50859,0.32285854,0.050353356,0.20843303,-15.234352,-163.26677,-206.95847,1.7619604,-1.7828422,22.34628,765000
162.9335,0.3327493,0.057627063,0.12026588,-12.293184,-162.74059,-206.88757,0.5828349,-0.84108955,15.155037,770000
167.43398,0.3336395,0.048781484,0.22770551,-0.51006097,-167.22343,-207.58304,1.3057656,-2.733771,21.304579,775000
162.80873,0.3527449,0.05122861,0.20860155,-2.1296778,-162.55884,-208.98572,0.9788035,-1.5166396,19.849636,780000
165.0865,0.34114623,0.043148015,0.1898322,-2.5875304,-164.82922,-208.83424,1.2510201,-1.8866043,19.507805,785000
163.65831,0.338591,0.04999936,0.13559052,-15.364307,-163.38707,-211.35457,1.3091025,-0.7994675,14.210407,790000
159.15353,0.31972936,0.06101422,0.3951684,0.34812632,-158.96819,-207.4104,4.3012486,-2.7144606,31.06607,795000
162.89934,0.32194692,0.0563045,0.28153786,-5.4615307,-162.70398,-206.7782,1.8542134,-3.4418702,38.556767,800000
167.1241,0.33052665,0.04684,0.13465951,-3.5878732,-166.87161,-209.82625,0.81658965,-1.1093131,19.509188,805000
162.13576,0.32867587,0.048825957,0.1574326,-11.266908,-161.87796,-213.1967,0.9654294,-1.3688873,20.482962,810000
169.71547,0.361587,0.03690504,0.14266989,-14.741972,-169.40326,-208.94862,0.6509899,-1.5829854,19.127956,815000
170.29616,0.32226995,0.038571123,0.19983946,-18.744678,-170.06528,-208.4938,2.1354928,-3.728791,36.95744,820000
166.96992,0.27236775,0.04833372,0.127959,-17.034008,-166.81815,-212.1783,1.6203991,-1.2403597,21.210852,825000
167.63817,0.33669832,0.04452157,0.14173621,-9.1961565,-167.36307,-206.70667,1.2391815,-1.7112211,25.37439,830000
168.13303,0.31105787,0.045484483,0.15021764,-41.57155,-167.9201,-205.96559,0.35091642,-0.94718397,15.238205,835000
170.04506,0.28710693,0.041710384,0.1546248,-9.290697,-169.86745,-211.50508,2.1521163,-1.912586,31.789558,840000
165.82066,0.32317767,0.05041755,0.28079605,-16.996214,-165.59428,-208.43958,0.9681567,-0.9001459,21.20478,845000
168.50114,0.3072273,0.04095476,0.17443737,-17.195658,-168.26675,-205.78413,1.0904142,-0.8761937,16.510683,850000
168.25858,0.28823555,0.04123974,0.14264338,-18.301552,-168.02827,-211.58252,1.0745357,-0.9069523,15.908754,855000
163.12231,0.34618205,0.04158973,0.41371402,-0.09383106,-162.84044,-206.73479,2.297036,-4.3655214,63.282047,860000
166.34454,0.27974027,0.036304813,0.16066001,0.113401204,-166.10048,-211.40045,1.5342202,-0.8230465,19.175346,865000
169.03133,0.3178069,0.047013592,0.20872688,-8.08727,-168.80421,-211.43265,2.600872,-2.0106297,32.326744,870000
169.45554,0.28658706,0.036264263,0.1514594,-31.09995,-169.22408,-206.15114,1.040787,-0.7191289,16.903635,875000
164.26073,0.31173295,0.056492805,0.49459305,-7.282592,-164.15427,-206.7976,3.2165263,-2.8019724,38.902958,880000
170.47293,0.28062004,0.043740217,0.94608366,-3.923197,-170.31348,-207.24791,4.554591,-4.373451,48.09705,885000
165.48286,0.31648213,0.04525002,0.25572076,-30.075745,-165.28343,-207.03818,3.5463386,-1.6160206,29.34049,890000
170.44315,0.29315713,0.0365204,0.26964542,0.51071465,-170.22519,-207.11833,5.4970145,-4.576279,57.682766,895000
166.18518,0.3211754,0.045684174,0.26718912,-0.5155097,-165.979,-207.89899,3.1908514,-2.3708637,41.660316,900000
163.17041,0.33951432,0.038432114,0.1723327,0.18667156,-162.88745,-206.28958,1.9974048,-0.7600488,20.032461,905000
169.89267,0.32362956,0.0345649,0.18290798,-12.323662,-169.6454,-214.34981,1.6441103,-0.6543777,25.33071,910000
173.04202,0.34778312,0.03663016,0.14917764,0.2902544,-172.76701,-204.59567,0.6915281,-1.8893553,24.344296,915000
166.38577,0.30751812,0.039695334,0.19650927,0.13025743,-166.14452,-208.30269,1.8911604,-2.215685,33.13548,920000
169.14642,0.30101237,0.044170983,0.116365075,0.6048695,-168.91147,-205.29039,1.155327,-0.6788216,13.512176,925000
170.01659,0.30591747,0.044418402,0.14531708,-9.004696,-169.77396,-208.32185,1.5179484,-0.9313869,16.072239,930000
170.3255,0.3165346,0.031359017,0.13709922,-3.1220348,-170.0454,-213.83696,0.926385,-1.0710617,15.871089,935000
171.02957,0.33581662,0.042305835,0.32299083,-20.889973,-170.72543,-215.04895,3.5081577,-1.741888,40.242626,940000
168.70956,0.32341707,0.03669523,0.19757816,-15.946449,-168.46214,-208.36212,2.3187594,-1.4208783,33.606583,945000
164.25963,0.33556765,0.040379714,0.15919803,-2.5510519,-163.98343,-216.32222,2.51908,-2.337304,28.875902,950000
164.2419,0.31474417,0.04705845,1.7152153,-7.2377167,-164.06029,-207.85068,39.04145,-30.841814,164.82623,955000
162.91396,0.28715128,0.03641875,0.24276672,-8.021255,-162.66153,-205.61438,2.7310398,-1.9258608,32.182495,960000
164.67067,0.33663476,0.039426915,0.2658895,-11.951333,-164.4122,-214.62549,2.7039313,-1.741511,40.736805,965000
168.1465,0.30187213,0.04279545,0.22353017,-0.22259995,-167.88835,-208.1844,2.354214,-2.6090925,35.750916,970000
167.00618,0.28931653,0.04681987,0.14517413,-0.8584659,-166.80717,-214.7055,1.0193563,-1.1933585,20.429398,975000
164.29591,0.3292465,0.0398125,0.1621857,-12.018713,-164.08458,-208.11908,0.87399685,-1.0220665,17.186417,980000
167.2087,0.29702958,0.04528271,0.13501248,-1.7150562,-167.00352,-205.43132,0.8522243,-1.1845167,17.875134,985000
168.36662,0.31331164,0.034363225,0.17744893,-6.5951,-168.11649,-207.92168,0.7272005,-0.63162655,14.1578665,990000
170.75114,0.3054139,0.037176196,0.09933535,-0.035277456,-170.5102,-206.15497,0.958819,-0.82313806,14.621871,995000
164.10532,0.25118044,0.037975043,0.29060823,0.5297581,-163.9146,-205.67387,2.4910085,-1.1936213,31.718803,1000000
169.46736,0.28675956,0.051314346,0.15902059,-21.820496,-169.27672,-207.81172,1.6239405,-0.6769357,17.270876,1005000
170.99644,0.24771744,0.033462837,0.16659789,-17.771385,-170.79152,-207.70552,0.6064113,-0.8951503,13.569541,1010000
166.87639,0.31918833,0.041112605,0.21989775,-0.96612847,-166.62398,-208.69781,1.2447631,-1.913369,27.260818,1015000
171.02763,0.29033497,0.039285965,0.30901363,-2.154909,-170.82442,-207.09326,3.6236746,-2.4859862,39.25739,1020000
164.45428,0.2983796,0.047545068,0.15240932,-5.3655233,-164.27132,-209.11867,1.6332866,-1.3268225,18.085718,1025000
168.23347,0.3089025,0.047135912,0.15527712,-10.479229,-168.03905,-210.9086,1.236326,-0.8812031,18.830833,1030000
166.62373,0.31937495,0.037203573,0.2998203,-0.10189977,-166.3734,-207.07516,3.4124537,-3.2677147,58.365166,1035000
164.06248,0.2596074,0.03878275,0.1803351,-1.3082945,-163.89896,-209.22324,1.3737048,-2.042973,30.152784,1040000
163.41603,0.30627492,0.045903232,0.12033238,-4.892899,-163.19652,-209.42589,1.0724038,-0.75374746,17.21156,1045000
165.32309,0.3024553,0.043821726,0.1676658,-23.720905,-165.08504,-209.84236,1.6185473,-1.6380329,19.006731,1050000
169.62372,0.26468295,0.03355861,0.12003137,-0.5670988,-169.40027,-204.58449,0.8297661,-0.6674738,15.242789,1055000
168.51689,0.29584664,0.040521808,0.13679044,-10.794643,-168.2672,-211.07793,1.4514431,-0.9100111,17.069012,1060000
163.66866,0.31370062,0.040251806,0.6418187,-0.22420406,-163.41858,-207.41786,3.4915357,-2.4988444,37.105232,1065000
164.1316,0.3204761,0.03828997,0.14745174,-0.28420117,-163.89954,-212.82387,0.7679145,-1.7232609,19.702526,1070000
163.06734,0.31860858,0.037078027,0.21297882,0.27338532,-162.83104,-211.5103,1.4898423,-1.5792521,27.599268,1075000
165.62187,0.2870186,0.035404272,0.17185338,-0.97146,-165.40611,-212.52226,1.8772968,-1.213437,23.013428,1080000
166.20439,0.31410557,0.044391535,0.17543113,-0.49253052,-165.97546,-210.80142,1.4880922,-1.7569234,20.728523,1085000
167.36513,0.30551547,0.043794714,0.14167093,-9.606073,-167.14108,-210.76431,0.7559338,-0.86179274,17.842209,1090000
164.04219,0.31848305,0.036132097,0.1879453,-0.2059317,-163.78586,-203.93506,1.3615923,-1.2967194,23.516842,1095000
168.88191,0.28888115,0.049497187,0.436326,-4.3589897,-168.72742,-209.4903,5.3966746,-4.2888365,37.012154,1100000
166.98915,0.31038392,0.039488636,0.22970568,0.23502967,-166.71996,-208.38809,1.3742182,-1.3070145,19.976479,1105000
165.25165,0.28398362,0.042012136,0.29173216,-1.5804559,-165.05377,-208.01538,1.5902021,-0.64367074,21.293577,1110000
165.10548,0.2511084,0.035768203,0.17264703,0.9184494,-164.9262,-211.31451,1.2788041,-0.96774757,23.3045,1115000
167.10661,0.281141,0.034453988,0.19021662,0.18576705,-166.87248,-211.56667,1.0334822,-1.5463078,19.736506,1120000
167.39561,0.33100554,0.031667396,0.1295991,-13.473417,-167.0909,-211.77496,0.90072787,-0.9089248,15.25173,1125000
165.76535,0.2975159,0.033575043,0.13108893,-6.6869335,-165.51732,-212.89908,0.96874565,-1.4994506,18.729177,1130000
164.49527,0.29461387,0.038919408,0.16559184,-18.880447,-164.25833,-208.6128,0.7248087,-1.035885,14.480671,1135000
163.68094,0.29956615,0.041991,0.109735034,-0.0849289,-163.45927,-208.7426,0.9395469,-0.9899127,14.542363,1140000
165.1651,0.32021466,0.035298113,0.24378815,0.84553313,-164.89043,-207.66838,1.709006,-2.5413125,45.530903,1145000
164.86615,0.3080683,0.041346446,0.32901803,0.18275467,-164.58163,-208.50485,3.2507133,-3.880374,56.035175,1150000
166.62193,0.3344832,0.049569357,0.2002352,-6.292916,-166.35538,-207.02168,1.958443,-1.5896994,34.54765,1155000
159.3145,0.31397903,0.051250167,0.2688007,-4.295679,-159.08105,-208.66737,2.4743345,-1.2672219,23.978008,1160000
163.53345,0.31913888,0.036463033,0.09614968,1.1369166,-163.24837,-207.85538,1.1932139,-0.76822686,14.97684,1165000
162.65714,0.26244915,0.03731344,0.29871568,-1.6892256,-162.47076,-208.74802,3.3996065,-3.714188,48.784813,1170000
161.70033,0.25244847,0.04409015,0.13038206,-0.85086715,-161.54185,-209.41612,1.862221,-1.4761128,22.799488,1175000
159.24219,0.32759702,0.0373851,0.24076854,-0.09770736,-158.97375,-210.41257,1.9059228,-3.765822,44.366127,1180000
160.67154,0.28074732,0.04397398,0.17470877,-0.14653364,-160.44608,-212.06085,2.1746438,-2.2509143,24.094246,1185000
162.48456,0.30365908,0.034726143,0.15640877,-0.4177976,-162.26509,-209.27216,2.2389371,-0.9558775,26.404745,1190000
162.89723,0.3018057,0.036689457,0.1273235,-12.204649,-162.67381,-209.8528,0.8387927,-0.8960684,18.938688,1195000
163.03563,0.28845766,0.032353643,0.22359942,-15.403959,-162.77852,-207.547,1.0595655,-1.375113,23.123537,1200000