O2O / O2O-w-diff-ckpts /fql /20260317_161917 /online_agent.csv
Tiredsheep's picture
Upload folder using huggingface_hub
1f1f3be 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
156.16383,0.34574628,0.054264687,0.11459885,-6.7077637,-155.93675,-207.60103,0.6889934,-0.7185288,12.980727,905000
152.24348,0.29379165,0.07175185,0.13929997,-7.4723034,-152.10051,-205.21841,1.8834002,-1.2535149,21.233171,910000
159.93677,0.37574023,0.047667373,0.14047639,-4.1113853,-159.64815,-211.8501,1.1375117,-0.8808064,19.103817,915000
158.20844,0.3018623,0.050229654,0.13256866,-15.727817,-158.0039,-204.6144,1.174146,-0.75558156,19.005732,920000
155.1133,0.3013361,0.05889026,0.36197966,0.6212538,-155.01904,-211.8301,1.3470253,-1.4115775,19.621069,925000
157.20749,0.26039886,0.048925683,0.12339862,0.19461435,-157.06544,-210.82149,0.511307,-0.62939566,11.226688,930000
157.07129,0.34608644,0.051294252,0.4845627,0.52990055,-156.86418,-206.69296,4.516032,-2.2760148,30.341599,935000
156.78569,0.37281853,0.042747267,0.12970054,-6.601308,-156.51741,-208.75044,1.8158715,-0.8355565,15.286725,940000
159.98248,0.30698583,0.052191105,0.11610744,-10.152624,-159.78555,-206.15933,0.75393337,-1.2504119,14.21939,945000
160.02196,0.34761137,0.046024922,0.16505444,0.0881961,-159.78514,-212.29759,1.1848297,-0.7614364,17.78151,950000
158.0964,0.29767078,0.045373596,0.15029068,0.60571265,-157.88396,-208.38538,1.2375438,-1.156592,19.873573,955000
163.15585,0.29293287,0.047567748,0.16762738,-32.45651,-162.94803,-208.58594,1.4939533,-1.1825912,19.649582,960000
165.22296,0.35124168,0.049147584,0.11519199,-16.424175,-164.95224,-207.16025,0.96636885,-0.5384295,13.62652,965000
164.8956,0.28268275,0.05447577,0.13110295,-14.190176,-164.75574,-213.31339,1.0696119,-1.4343467,18.092508,970000
167.55159,0.2795363,0.043414712,0.11307623,-6.5270553,-167.35423,-208.3027,0.9288886,-0.93054175,15.016438,975000
163.98544,0.32047072,0.04575327,0.21510294,-10.560713,-163.76309,-208.43321,1.7588027,-1.629389,26.82818,980000
166.81117,0.28405884,0.042850666,0.19065122,-5.9601836,-166.60973,-205.65271,2.1688788,-1.1058316,24.65396,985000
163.15338,0.35454404,0.047384188,0.14542177,-11.052345,-162.8626,-206.33786,0.93458605,-0.89128876,17.06222,990000
163.50409,0.34080726,0.05320469,0.83302367,0.24151814,-163.29129,-209.60187,7.818411,-6.3269587,60.134014,995000
164.88663,0.26128334,0.061027087,0.1667168,-3.379004,-164.72441,-205.19873,2.31835,-1.984661,31.349548,1000000
169.0164,0.26286137,0.046958566,0.0961467,-25.38344,-168.83739,-212.09055,0.5019778,-0.78966737,12.940231,1005000
164.84627,0.25272775,0.037181824,0.110430025,-8.379867,-164.65259,-212.89069,0.57055926,-0.5983249,12.08514,1010000
169.34727,0.33669046,0.040819608,0.1468734,-12.44782,-169.06921,-210.35594,1.1359597,-1.0726618,21.51466,1015000
167.69797,0.33376563,0.046275504,0.18750702,-19.725655,-167.46529,-210.53604,1.6082904,-2.2834723,25.01955,1020000
164.96098,0.30828705,0.051480666,0.14439145,-12.318659,-164.78862,-210.85008,0.81151867,-0.40868822,13.724915,1025000
168.6403,0.32677993,0.043269765,0.18198423,-14.476173,-168.37633,-207.42136,1.5935155,-1.7903962,25.32741,1030000
168.4318,0.3368019,0.046657026,0.13902865,-34.46609,-168.19493,-206.39041,0.9742156,-0.695417,15.39863,1035000
167.86853,0.2500948,0.041310214,0.26985258,-6.7710476,-167.71745,-209.42276,4.5066404,-2.0335023,52.12516,1040000
164.02675,0.30325985,0.047321856,0.2653918,-7.6173954,-163.81067,-207.1243,1.2061869,-0.9926512,18.804602,1045000
168.1182,0.32334962,0.042481028,0.12653612,-11.905333,-167.85725,-204.0629,0.81470823,-0.7403521,15.007739,1050000
168.07048,0.28418937,0.04103198,0.20854464,-6.973678,-167.85686,-207.58217,3.101427,-2.6513195,42.09361,1055000
164.23181,0.30547494,0.049348578,0.3244896,0.03286013,-164.01294,-209.45923,2.6290402,-3.2014947,50.30058,1060000
166.64326,0.33162686,0.038453557,0.15144716,0.17188576,-166.35002,-204.87405,3.1959767,-2.2477508,20.727169,1065000
167.78693,0.34776777,0.040827073,0.19004677,-13.252357,-167.53787,-211.69878,1.3686999,-0.9972228,16.950499,1070000
168.37483,0.31067604,0.039264448,0.15981403,-16.658947,-168.13759,-204.09439,1.2463217,-1.4771025,18.157454,1075000
162.96902,0.3265588,0.05251148,0.44030157,-7.5233827,-162.8164,-204.60808,2.7446759,-2.6042845,41.095295,1080000
168.66035,0.33012378,0.04702705,0.21430533,-4.106489,-168.40398,-211.8126,2.012401,-2.132951,26.262688,1085000
164.23296,0.31453374,0.044271585,0.2867921,-2.7347682,-164.01018,-209.60255,1.435461,-1.1478496,25.284073,1090000
169.77713,0.28933024,0.038504288,0.21908341,0.821714,-169.5688,-206.0059,3.3064408,-4.358805,48.213795,1095000
165.04958,0.31810313,0.049255256,0.38793615,0.17467391,-164.84726,-209.86224,2.7460747,-2.6019127,46.225594,1100000
167.32628,0.32912162,0.04221268,0.12948343,-0.16635418,-167.0579,-209.2736,0.8790506,-0.6865179,13.492918,1105000
167.23306,0.29340315,0.040148538,0.1521943,-0.5638944,-166.99754,-206.85905,1.2607967,-1.1445081,19.221283,1110000
166.54742,0.2828127,0.04083652,0.36792114,0.10461259,-166.33975,-215.51768,3.455014,-4.936677,51.20691,1115000
164.11719,0.2997102,0.043640003,0.2670463,-0.12216088,-163.89809,-206.7415,1.9543296,-2.8115838,32.77096,1120000
168.19942,0.303625,0.05158194,0.14292914,0.51061094,-167.96565,-208.64633,0.8764446,-0.7217677,14.725781,1125000
166.79494,0.31609192,0.047762506,0.12423599,-13.652272,-166.58801,-208.83075,1.1805196,-0.7346082,14.631462,1130000
166.2416,0.32191658,0.040476024,0.21107045,-3.879205,-165.97093,-206.76091,1.408884,-3.9018674,36.366074,1135000
166.82362,0.29458576,0.042229462,0.19708166,-3.5339766,-166.56691,-205.03488,1.5373712,-1.9629242,23.174805,1140000
162.98268,0.31053233,0.039478913,0.22127366,-9.180813,-162.77097,-207.25558,3.5943017,-2.6218195,37.935265,1145000
166.5031,0.30075866,0.04415537,0.16464567,-2.104316,-166.2655,-207.06223,1.6478183,-2.0742712,29.650414,1150000
163.52861,0.3150253,0.052561462,0.21294801,-2.7240787,-163.3294,-217.23949,1.5957772,-1.5663357,22.831522,1155000
167.90787,0.31539807,0.034694225,0.17297728,-3.2723553,-167.63225,-206.00806,1.0994717,-1.1063019,17.937105,1160000
160.20425,0.30573344,0.040950984,0.20377028,-13.210061,-159.9685,-217.64929,0.8723324,-1.5934653,21.459156,1165000
163.2868,0.28125542,0.035797402,0.15050733,0.15372598,-163.07225,-218.62576,1.1097611,-0.74728304,17.962723,1170000
163.98982,0.2650726,0.04274174,0.25809166,-14.743049,-163.80846,-207.22943,2.0451407,-1.2922121,27.271782,1175000
160.33595,0.3481422,0.051069185,0.17712386,-1.1236424,-160.11444,-218.73274,1.2980968,-1.0673755,18.247408,1180000
162.80408,0.31147224,0.047596358,0.20953338,-3.5395646,-162.59781,-207.39027,2.4922855,-1.8320299,26.668587,1185000
169.07948,0.2743399,0.03577599,0.1509087,-13.899413,-168.86041,-208.4768,0.7020157,-0.8702069,15.776316,1190000
167.30197,0.32393873,0.036838505,0.15120704,-29.368963,-167.08218,-219.36452,1.8062814,-1.672786,24.427921,1195000
161.63164,0.33156097,0.038375944,0.16637078,0.81671035,-161.37166,-205.47609,1.9718254,-1.137962,26.374063,1200000
163.94199,0.28160486,0.053461708,0.20242257,-1.0407432,-163.7688,-207.14157,3.6605413,-1.1507115,31.615925,1205000
167.10999,0.30363065,0.037542686,0.114965074,-22.139397,-166.86519,-207.21509,0.8679125,-1.0697268,15.651569,1210000
160.08511,0.35721642,0.043643236,0.16926847,-1.8269513,-159.82835,-207.6271,2.3666847,-2.4709973,35.03849,1215000
168.15897,0.34875426,0.04283497,0.21343851,-1.6244925,-167.91812,-207.52045,1.4071705,-2.3516712,27.40665,1220000
160.89885,0.32262498,0.052498184,0.4246362,-5.456977,-160.69951,-205.09726,4.1707897,-2.712376,40.58455,1225000
165.79881,0.31742746,0.048797622,0.19957815,-4.0509562,-165.59521,-207.64926,1.0414709,-1.1944331,19.008911,1230000
166.12694,0.3047064,0.038201902,0.14020792,0.1908477,-165.87688,-205.77148,1.0593239,-1.2960683,17.942093,1235000
163.932,0.35309753,0.043656148,0.2755564,-0.3366554,-163.69377,-210.08914,2.9197292,-2.6007838,43.373318,1240000
164.60475,0.29864797,0.045154057,0.17341296,-7.968183,-164.4006,-207.37294,1.6328583,-1.809841,27.370335,1245000
163.13008,0.30320013,0.036499474,0.15095071,-1.2920591,-162.90388,-210.27902,1.1855918,-1.1917866,19.481354,1250000
168.70396,0.3084092,0.029630601,0.12593953,-17.806915,-168.44383,-205.26715,0.5801727,-0.6089442,12.106012,1255000
165.62079,0.30108237,0.04288681,0.19172041,-6.9428387,-165.36243,-209.78557,1.2860181,-1.6448452,28.838957,1260000
161.15984,0.31422114,0.04432276,0.295646,-10.718233,-160.92822,-207.97604,1.0733879,-1.4220626,22.099243,1265000
158.7296,0.25504887,0.04093375,0.13494734,-2.312612,-158.54727,-210.96231,1.3606586,-2.1146781,23.094538,1270000
161.55757,0.3582006,0.038192794,0.3059127,0.98420155,-161.24483,-204.87668,2.0237195,-1.3689709,31.172453,1275000
161.90215,0.30816454,0.036198296,0.15868933,-3.1168613,-161.654,-206.7614,1.6900004,-1.1440704,21.208609,1280000
162.94008,0.3437634,0.043660462,0.17753704,0.16983992,-162.67406,-206.90565,2.9627895,-2.7940586,24.817986,1285000
163.58572,0.3249222,0.043753125,0.16717152,-3.26971,-163.35747,-204.91245,2.2569606,-1.477895,32.80676,1290000
162.66194,0.32381004,0.03676382,0.20857672,-12.524302,-162.40584,-209.0588,1.2608802,-1.6495055,22.922022,1295000
164.33083,0.3016001,0.04659015,0.21097572,-4.731882,-164.1386,-209.12831,2.1024568,-1.3538235,28.110441,1300000
163.46759,0.28077534,0.0364756,0.18136941,0.13411438,-163.24988,-206.88884,0.73281825,-0.91743565,17.673298,1305000
163.54338,0.30767775,0.03825642,0.22928181,-16.427273,-163.34618,-208.14546,2.282706,-2.2787085,22.414385,1310000
166.93355,0.2866059,0.04256775,0.18978469,-4.0767546,-166.68863,-208.68329,1.67756,-1.887416,27.650211,1315000
163.7887,0.28104955,0.037429377,0.2545033,0.599657,-163.57555,-206.79167,2.7013578,-1.8702035,33.203762,1320000
163.25069,0.2854735,0.0322138,0.16622347,-10.369097,-163.01268,-208.33727,1.3800911,-2.1366704,25.58065,1325000
163.57655,0.3340257,0.033985693,0.45888662,0.18133208,-163.29396,-206.8299,1.9558718,-1.737417,32.46116,1330000
166.36316,0.33695683,0.037601985,0.15343194,-2.2484696,-166.08145,-206.0104,0.8608,-1.384106,22.997126,1335000
165.63383,0.32599783,0.037316017,0.20128639,0.31520703,-165.39197,-206.65329,1.5546595,-1.4651586,18.450317,1340000
160.37688,0.3177286,0.03649655,0.17729475,1.8379487,-160.11328,-208.83934,1.7442354,-1.932408,23.893688,1345000
162.98232,0.29548672,0.03737337,0.16490047,0.78675115,-162.73244,-209.88213,2.5419703,-2.784953,29.599497,1350000
163.7615,0.32516727,0.026895188,0.15777203,-5.0370135,-163.46806,-206.7141,1.5856891,-2.1074843,26.796814,1355000
162.5446,0.30576786,0.03788524,0.20172505,-5.4277225,-162.32722,-211.0471,1.3360281,-1.0209583,17.456924,1360000
159.38766,0.30671865,0.042018875,0.19974652,1.0269921,-159.15347,-209.43509,2.4076455,-3.0306153,37.738155,1365000
162.62631,0.31248122,0.033827983,0.17015202,-3.9165726,-162.37311,-206.83678,2.050838,-1.3525724,26.263899,1370000
157.55591,0.31370252,0.042422324,0.18947987,-6.1964,-157.3057,-209.46756,1.879182,-1.7750175,25.642813,1375000
157.50882,0.2934298,0.039123572,0.21865745,-0.56905353,-157.29204,-209.2559,2.5946019,-1.4542257,30.015446,1380000
162.38417,0.2826686,0.0405151,0.14193141,-4.9006124,-162.1658,-206.73093,1.2804428,-1.497982,21.357874,1385000
162.10663,0.2484135,0.034552284,0.21574064,-2.6181514,-161.94273,-210.76558,2.0150936,-2.6266103,31.874376,1390000
156.77591,0.28850028,0.040920496,0.19221531,-1.3526942,-156.56412,-208.37422,1.1981183,-1.7167636,26.521702,1395000
158.93166,0.28229922,0.03701132,0.3699978,-0.2986985,-158.72346,-210.33238,2.8023787,-2.3235862,35.99248,1400000