O2O / O2O-w-diff-ckpts /fql /20260317_062940 /online_agent_sv.csv
Tiredsheep's picture
Upload folder using huggingface_hub
23d2811 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
155.90096,0.35579377,0.053795237,0.12623318,-5.4958453,-155.69493,-207.80025,0.9366551,-0.38345012,12.258959,605000
152.29375,0.30755702,0.06831296,0.1654879,-7.654736,-152.13382,-206.03397,1.536001,-0.9587141,18.709408,610000
160.4203,0.31654614,0.046517678,0.16201481,-3.5022428,-160.18706,-214.29855,0.47293946,-1.3005431,15.956497,615000
157.70314,0.30102783,0.061454233,0.2706657,-15.6160965,-157.51118,-207.51799,1.696587,-1.4940059,22.685724,620000
153.96327,0.3228745,0.056072354,1.8056335,-0.25581333,-153.81749,-215.03563,1.9988446,-1.5997379,34.38186,625000
155.67188,0.29476836,0.05254322,0.166207,0.15883109,-155.50798,-207.58777,0.6127794,-1.8838227,22.361298,630000
155.62021,0.3472004,0.055790294,0.30129293,0.5375715,-155.3903,-209.55049,2.8547835,-1.2022736,26.458221,635000
156.52377,0.30649012,0.047198147,0.15659975,-5.304731,-156.28903,-208.85349,2.057722,-1.7977562,26.186369,640000
159.53024,0.2990952,0.058146216,0.24807373,-11.890839,-159.32693,-206.01683,1.5913463,-3.6126614,42.569588,645000
159.00485,0.33778495,0.047505736,0.20648876,-0.10577807,-158.7617,-214.88528,1.5579067,-1.2874084,24.334373,650000
156.24126,0.35099927,0.04715918,0.13212787,0.35644594,-155.95284,-204.4897,0.7964571,-1.0756632,17.319557,655000
162.22984,0.3185264,0.047341283,0.33282563,-34.116096,-161.9793,-209.24884,2.590395,-5.2094646,58.00105,660000
162.8648,0.3175178,0.04939436,0.20298862,-15.747726,-162.62755,-206.98833,1.7113911,-0.6780804,19.08309,665000
163.22017,0.30288056,0.05389728,0.2194004,-11.610312,-163.04594,-204.11786,2.2397108,-2.8864663,25.820498,670000
166.30211,0.342734,0.046409152,0.21727204,-0.37638754,-166.09444,-208.61649,1.754453,-2.2447047,29.570606,675000
163.40306,0.322157,0.05108017,0.47750473,-7.3882957,-163.18736,-206.9814,1.9481297,-2.977862,41.1332,680000
165.42911,0.29969773,0.043089375,0.14440106,-3.2184699,-165.22273,-208.68036,1.2219299,-1.3981826,18.104425,685000
163.60146,0.34797147,0.04555478,0.16488115,-17.527863,-163.33691,-208.19626,1.9370759,-0.7458485,26.727478,690000
158.63782,0.35160512,0.056522503,0.34504867,0.5816859,-158.41077,-204.40031,2.369644,-2.1567855,27.585522,695000
162.98128,0.33998328,0.050824434,0.27634415,-4.7641535,-162.74937,-205.11977,2.6596768,-4.361244,48.90676,700000
167.54433,0.32891932,0.051731814,0.1316575,-15.907274,-167.29544,-210.12186,0.7849461,-0.7179712,13.944746,705000
162.04045,0.28760237,0.048660673,0.17426969,-8.419728,-161.826,-209.9958,2.525981,-1.2398121,31.471586,710000
169.26027,0.3066405,0.038058706,0.15730618,-10.165906,-168.99295,-205.46275,1.7945442,-1.1088288,26.102642,715000
168.56989,0.30586702,0.03752493,0.14845303,-18.365133,-168.34142,-206.33005,1.0031823,-1.9937884,24.194023,720000
165.89046,0.28653502,0.048778877,0.12456479,-26.591002,-165.71196,-209.83888,1.0956236,-0.55246407,16.246382,725000
165.88405,0.3247211,0.047412515,0.21664949,-5.762544,-165.61665,-206.8867,1.6411933,-3.0310068,42.931873,730000
167.63858,0.32545093,0.04529182,0.1456936,-44.87754,-167.40913,-205.84428,0.42315146,-1.1105362,15.161933,735000
168.78471,0.26179427,0.05015931,0.31653237,-10.44093,-168.64104,-208.38928,1.7509565,-1.5509138,23.569206,740000
165.42093,0.29862833,0.047147907,0.18969373,-16.37758,-165.23248,-206.63947,0.7949325,-1.7844429,23.900497,745000
168.03297,0.30363876,0.041979335,0.12574343,-15.948858,-167.7928,-205.19759,1.7798187,-1.532092,20.871826,750000
167.47871,0.3113021,0.043108694,0.15502264,-2.8879125,-167.21545,-206.10783,1.2414931,-1.7310898,21.785118,755000
164.10039,0.36408532,0.046348922,0.1732844,0.030097723,-163.8012,-207.73315,1.6829875,-2.0467527,23.663197,760000
166.13689,0.31828034,0.054637387,0.3071148,-0.018664688,-165.9116,-209.82802,3.0825322,-1.5649939,42.421665,765000
167.89119,0.36004567,0.043350145,0.2322378,-7.1194897,-167.63492,-215.92516,3.0486686,-1.7068552,34.814083,770000
168.51096,0.2980133,0.041732498,0.23542683,-29.379984,-168.28638,-205.33955,1.2314196,-2.182524,23.254642,775000
160.81552,0.34319848,0.05783615,0.32324013,-8.491394,-160.62192,-207.49551,3.0899787,-3.6948607,29.668673,780000
168.1304,0.35109282,0.043729596,0.20925812,-10.711669,-167.85515,-209.49074,1.7514664,-1.3521148,23.74411,785000
163.7678,0.32921478,0.04764691,0.19265094,-2.2340908,-163.54613,-206.31474,0.86934257,-2.129207,21.721188,790000
169.67154,0.277256,0.041721642,0.18851328,0.33761895,-169.45117,-205.96509,1.5326146,-1.0261587,16.859154,795000
166.8062,0.32817942,0.044370852,0.22848569,-0.2564896,-166.59557,-208.50302,1.9089671,-1.8252844,31.263342,800000
165.46507,0.3078155,0.04108484,0.1868891,-0.7050762,-165.22604,-205.44353,1.1424136,-1.8388858,26.233236,805000
167.5604,0.3606716,0.04140394,0.16554368,-4.877201,-167.2581,-211.98235,2.115269,-0.87936085,24.39507,810000
169.57088,0.35345304,0.037194204,0.13140813,0.15875709,-169.28737,-217.21208,0.6619107,-1.6339148,15.965429,815000
165.41898,0.3008293,0.04570903,0.2059475,-0.43474224,-165.17552,-207.5613,1.1247768,-2.278871,32.471046,820000
169.37573,0.26613563,0.044390026,0.14503422,0.5457794,-169.20206,-207.35919,1.5175714,-0.62906796,18.720995,825000
167.59117,0.31612372,0.050682306,0.18961035,-15.907654,-167.35875,-207.54657,1.406689,-1.4592516,17.701824,830000
165.11983,0.31555247,0.043512054,0.15012658,-2.5827427,-164.86278,-206.4389,1.0966169,-1.468814,24.488546,835000
166.47989,0.31787938,0.041956685,0.17378153,-26.602545,-166.21043,-208.5453,0.8081372,-0.8091398,13.890958,840000
164.86864,0.29662937,0.04283369,0.19593747,-7.9144683,-164.67662,-211.1952,2.8394523,-2.0106685,37.810013,845000
165.19302,0.28945708,0.04543384,0.12422071,-5.773522,-164.98076,-215.64104,1.1444005,-1.3625301,18.240358,850000
162.0352,0.27155203,0.043767985,0.13837123,-6.2523665,-161.86967,-221.19572,1.0913817,-1.0854027,17.445883,855000
165.77911,0.31968632,0.036576357,0.20898926,-3.1617463,-165.51184,-207.46971,2.0108986,-0.8950372,31.021763,860000
160.10002,0.28225204,0.044791434,0.23724902,-16.52641,-159.88507,-223.60307,1.1377507,-2.6035287,40.22581,865000
163.34355,0.29148743,0.038294684,0.14850841,-0.4321802,-163.1247,-224.43828,1.049012,-1.5766338,20.21699,870000
164.83673,0.26503336,0.04219743,0.16924003,-12.944869,-164.66002,-208.51866,0.7275008,-1.0322421,20.160074,875000
162.8858,0.32764387,0.052862823,0.23131342,-2.508168,-162.66373,-219.58104,0.92799073,-1.718633,23.889294,880000
164.01747,0.26551643,0.04414492,0.20514484,-2.6324327,-163.85391,-206.93536,1.9408581,-1.2451124,21.22279,885000
169.53194,0.32226342,0.036846362,0.14507213,-1.8749824,-169.26912,-206.93954,1.3966163,-0.65917,20.495462,890000
168.52951,0.2583154,0.037987515,0.13241008,-18.681618,-168.33803,-218.89238,0.7066544,-1.8082072,19.055164,895000
163.24626,0.33724573,0.041461285,0.28213066,0.26684666,-162.98082,-211.60757,3.9388409,-2.6078668,46.890533,900000
164.88437,0.32081047,0.051275842,0.21989313,-2.8551993,-164.67032,-219.30879,1.4397948,-1.6544044,29.36641,905000
167.12064,0.26450327,0.035455745,0.12903795,-12.010109,-166.90614,-206.76051,0.86959136,-1.3514476,19.176046,910000
163.98085,0.33029032,0.04650274,0.26359266,-3.574769,-163.73836,-220.38512,2.3809009,-4.374573,52.045414,915000
169.82913,0.27413112,0.046311088,0.28083554,-7.4200544,-169.66455,-206.97316,3.945403,-4.086035,35.92582,920000
164.8785,0.29663825,0.05457909,0.19724782,-1.9803233,-164.70439,-205.81294,1.5059224,-0.80978024,22.710205,925000
171.41037,0.28845575,0.04670965,0.12068343,-34.25427,-171.20517,-216.62343,1.4872435,-0.64945954,18.342537,930000
165.60489,0.3076918,0.03945478,0.20412779,0.6453047,-165.33897,-213.67905,1.3676801,-2.1862824,29.64777,935000
162.9903,0.34441292,0.03862735,0.297585,-0.6622652,-162.7555,-209.90527,1.5622362,-2.4823487,33.43345,940000
163.72057,0.31890905,0.040683508,0.17859271,-4.30107,-163.47725,-208.91898,2.6066203,-2.269627,35.28908,945000
164.6584,0.32426304,0.03548065,0.21117802,-2.1227157,-164.39702,-216.79388,0.9225518,-1.8870062,26.778515,950000
167.14442,0.28615987,0.031050595,0.21355307,-1.0153968,-166.91942,-210.06787,1.6802253,-1.2931919,34.155304,955000
167.23492,0.27522415,0.043971263,0.40476272,-22.497255,-167.01607,-205.72833,2.9424162,-1.8006575,47.450645,960000
164.81252,0.3216304,0.040677086,0.2521194,-4.2128663,-164.57303,-206.15659,1.1245652,-2.3490336,30.93851,965000
159.05469,0.2798578,0.03939286,0.21425109,-0.54047763,-158.8557,-208.18001,1.9523953,-1.1020355,24.65316,970000
165.52435,0.2690512,0.036783084,0.13669156,0.18829674,-165.33672,-205.03763,0.59641284,-0.7571995,12.881663,975000
162.72209,0.2845773,0.029430944,0.16599758,-17.605865,-162.4944,-206.18068,1.0821899,-1.2408879,20.908617,980000
163.30899,0.28931695,0.04331122,0.12344444,0.42902127,-163.10416,-209.62532,1.2296861,-1.1434793,18.305147,985000
164.07585,0.33017433,0.044815965,0.12363561,-5.2060714,-163.82588,-207.32217,1.2915728,-1.5361506,19.253578,990000
163.88893,0.3164689,0.038121738,0.17148939,-13.020703,-163.6552,-204.21463,0.84662765,-2.591597,25.467283,995000
163.87755,0.23997205,0.051635917,0.23241106,-5.7363057,-163.74417,-205.88678,1.3090816,-1.6552716,21.266987,1000000
168.14331,0.25555512,0.038379457,0.17665294,0.098584324,-167.94627,-208.39429,1.0146825,-1.2308183,19.104568,1005000
162.07082,0.25262374,0.047641404,0.2417701,-1.4987637,-161.90215,-203.89458,2.1508641,-1.8975512,27.278942,1010000
163.98323,0.30721956,0.04063444,0.15076613,-3.9551778,-163.72586,-208.26164,0.8413174,-0.9129834,16.83647,1015000
162.83018,0.29926777,0.03632573,0.20677744,0.23222548,-162.6,-208.38391,2.8159733,-0.91278374,28.695408,1020000
161.909,0.28439337,0.0331136,0.15684873,-14.818519,-161.6598,-207.84862,0.65903926,-1.4915202,24.485775,1025000
161.13414,0.3223731,0.036652554,0.13159302,-16.09038,-160.87273,-207.37189,0.9024414,-1.1010734,16.86397,1030000
165.15489,0.32997316,0.038763992,0.1874986,-7.7689743,-164.88023,-204.52594,0.91272086,-1.6661817,22.428268,1035000
164.59302,0.25447243,0.03995049,0.21321182,-3.8237216,-164.40865,-208.02975,1.0915208,-1.2103051,21.499489,1040000
157.90999,0.31284615,0.034574285,0.19976108,1.1494129,-157.64177,-208.56392,1.8711313,-1.0497236,22.744923,1045000
161.8051,0.31002012,0.036050513,0.2564188,0.2375083,-161.54166,-208.04936,1.4366477,-3.9206116,40.418602,1050000
162.87225,0.28595895,0.031075729,0.13407008,-6.1993895,-162.60612,-207.80428,1.436476,-0.7346956,23.179058,1055000
159.74869,0.30878282,0.047017626,0.22709742,-0.35954523,-159.52501,-210.18216,1.7825485,-3.8624012,49.030476,1060000
156.50871,0.31776333,0.03892947,0.15281557,0.5264268,-156.26335,-208.8208,1.4801793,-1.6218615,21.656927,1065000
162.17812,0.32305235,0.029776849,0.16059363,-8.288626,-161.9217,-210.28947,1.7720094,-1.0145682,23.429676,1070000
159.27669,0.31845072,0.04183641,0.1973348,-2.4465334,-159.01749,-209.32927,1.2410147,-1.6244426,21.049648,1075000
160.12906,0.2927974,0.03809291,0.1428154,-0.30255583,-159.91714,-209.5787,1.8592299,-1.659433,23.864445,1080000
161.421,0.2880209,0.04427938,0.15699299,-3.5271666,-161.22487,-214.26749,1.4369931,-1.0327632,20.358519,1085000
161.40749,0.29564613,0.03574702,0.13872531,-0.294252,-161.19289,-209.69102,1.6141278,-0.8265751,26.638954,1090000
158.2835,0.30777442,0.038211986,0.16948275,-1.4171944,-158.03618,-210.08879,1.0942676,-0.8637136,18.84175,1095000
160.16534,0.30892354,0.038353156,0.21003647,-0.66852236,-159.90915,-208.50307,1.4017634,-2.5003097,31.02375,1100000