Upload folder using huggingface_hub

.gitattributes

@@ -573,3 +573,13 @@ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1300000.png filter=lfs diff
 O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1350000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1400000.png filter=lfs diff=lfs merge=lfs -text
 O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_1000000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_1050000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_1100000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_1150000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_1200000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_750000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_800000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
+O2O-w-diff-ckpts/dsrl/20260317_155656/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text

O2O-w-diff-ckpts/dsrl/20260317_155656/eval.csv

@@ -0,0 +1,11 @@
+avg_gripper_contact_length,num_gripper_contacts,xy,prev_qpos,prev_qvel,qpos,qvel,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
+0.0,0.0,17.34280373319957,2.3625345843136754,0.018049782584268183,2.3613489955148372,-0.004516919928165574,0.0,25500.0,-1.0,-1000.0,1000.0,1.8647330379486085,750000
+0.0,0.0,16.270590330243184,2.2104304045387866,0.0855296975255384,2.214867662620143,0.00513757893050142,0.0,77500.0,-1.0,-1000.0,1000.0,1.5636668348312377,800000
+0.0,0.0,26.825457254419803,3.6525008759794098,0.04628143387475446,3.6557177871075157,0.04563480768352722,0.02,129448.64,-0.98,-997.84,997.86,1.583714532852173,850000
+0.0,0.0,24.71339219057755,3.3476814037828686,-0.007678678802192793,3.350768875481453,0.011912863536998896,0.02,181352.44,-0.98,-998.94,998.96,1.5449309206008912,900000
+0.0,0.0,27.476364973063845,3.7134319511437366,0.07097619385079158,3.7200692950443535,0.09895903698054317,0.02,233288.46,-0.98,-998.56,998.58,1.5596337938308715,950000
+0.0,0.0,26.957721432356134,3.672982633887562,0.0571732668175575,3.6772014283935204,0.032339901595061865,0.18,285073.2,-0.82,-990.48,990.66,1.5578432607650756,1000000
+0.0,0.0,29.115697054368848,3.9452670708693187,0.05762846593548737,3.9508877214562395,0.06846165315072038,0.12,336375.7,-0.88,-986.86,986.98,1.5029949760437011,1050000
+0.0,0.0,31.45229184841901,4.273073460249474,0.11409615799057037,4.2799478842509275,0.03920132464348965,0.42,386864.72,-0.58,-948.4,948.82,1.4456405639648438,1100000
+0.0,0.0,21.51601753819546,2.9361050285359003,0.06776239727461479,2.9385829865756508,0.04412627010713206,0.18,436980.86,-0.82,-983.1,983.28,1.4946752500534057,1150000
+0.0,0.0,21.2951515966511,2.915122883843428,0.026502480727948047,2.920614843030653,0.03999243961389183,0.08,488358.22,-0.92,-995.88,995.96,1.5169894790649414,1200000

O2O-w-diff-ckpts/dsrl/20260317_155656/eval_sv.csv

@@ -0,0 +1,11 @@
+avg_gripper_contact_length,num_gripper_contacts,xy,prev_qpos,prev_qvel,qpos,qvel,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
+0.0,0.0,17.34280373319957,2.3625345843136754,0.018049782584268183,2.3613489955148372,-0.004516919928165574,0.0,25500.0,-1.0,-1000.0,1000.0,1.8647330379486085,750000
+0.0,0.0,16.270590330243184,2.2104304045387866,0.0855296975255384,2.214867662620143,0.00513757893050142,0.0,77500.0,-1.0,-1000.0,1000.0,1.5636668348312377,800000
+0.0,0.0,26.825457254419803,3.6525008759794098,0.04628143387475446,3.6557177871075157,0.04563480768352722,0.02,129448.64,-0.98,-997.84,997.86,1.583714532852173,850000
+0.0,0.0,24.71339219057755,3.3476814037828686,-0.007678678802192793,3.350768875481453,0.011912863536998896,0.02,181352.44,-0.98,-998.94,998.96,1.5449309206008912,900000
+0.0,0.0,27.476364973063845,3.7134319511437366,0.07097619385079158,3.7200692950443535,0.09895903698054317,0.02,233288.46,-0.98,-998.56,998.58,1.5596337938308715,950000
+0.0,0.0,26.957721432356134,3.672982633887562,0.0571732668175575,3.6772014283935204,0.032339901595061865,0.18,285073.2,-0.82,-990.48,990.66,1.5578432607650756,1000000
+0.0,0.0,29.115697054368848,3.9452670708693187,0.05762846593548737,3.9508877214562395,0.06846165315072038,0.12,336375.7,-0.88,-986.86,986.98,1.5029949760437011,1050000
+0.0,0.0,31.45229184841901,4.273073460249474,0.11409615799057037,4.2799478842509275,0.03920132464348965,0.42,386864.72,-0.58,-948.4,948.82,1.4456405639648438,1100000
+0.0,0.0,21.51601753819546,2.9361050285359003,0.06776239727461479,2.9385829865756508,0.04412627010713206,0.18,436980.86,-0.82,-983.1,983.28,1.4946752500534057,1150000
+0.0,0.0,21.2951515966511,2.915122883843428,0.026502480727948047,2.920614843030653,0.03999243961389183,0.08,488358.22,-0.92,-995.88,995.96,1.5169894790649414,1200000

O2O-w-diff-ckpts/dsrl/20260317_155656/online_agent.csv

@@ -0,0 +1,101 @@
+actor/action_std,actor/actor_loss,actor/alpha,actor/alpha_loss,actor/entropy,actor/flow_loss,actor/q,actor/total_loss,critic/critic_loss,critic/distill_loss,critic/q_max,critic/q_mean,critic/q_min,critic/total_loss,grad/max,grad/min,grad/norm,step
+0.6496232,171.50206,0.004210169,-0.00022136616,-4.052579,0.34410596,-171.48499,171.84593,0.4905737,0.5678915,-1.9423368,-171.64017,-230.26544,1.0584652,1.2007079,-2.0536103,34.81398,705000
+0.6545079,169.79042,0.004189504,0.0008298752,-3.8019156,0.27170366,-169.7745,170.06294,1.0181779,1.3484273,-1.4562513,-169.93526,-236.69429,2.3666053,11.804882,-9.241452,99.76379,710000
+0.659034,175.443,0.003999513,0.001605074,-3.5986826,0.2977104,-175.4286,175.74231,0.7084817,0.9761173,-2.336735,-175.85478,-287.3107,1.684599,3.0114787,-5.056738,73.165565,715000
+0.65981257,173.21341,0.004081305,0.00043622818,-3.8931155,0.3107875,-173.19754,173.52464,0.67347157,0.7113277,-18.01319,-173.42064,-244.88875,1.3847992,3.0280988,-2.0119908,54.58591,720000
+0.64910483,173.34015,0.0039116554,-0.0014532285,-4.3715124,0.31178564,-173.32306,173.65048,0.9475531,1.0420613,0.8436885,-173.14215,-255.54901,1.9896145,3.1509042,-4.643108,86.379,725000
+0.64903367,172.2172,0.003984428,2.8406703e-05,-3.9928706,0.3098619,-172.20128,172.52708,0.50895053,0.72073597,0.8783986,-172.1927,-282.41577,1.2296865,2.1038013,-1.8094043,50.31658,730000
+0.6490887,171.7738,0.0040129926,-0.0024812198,-4.6182966,0.30542612,-171.75528,172.07674,1.2128547,1.4067744,0.8089568,-172.16605,-245.90387,2.6196291,8.002079,-12.339584,120.785866,735000
+0.65358156,170.97095,0.0040173694,-0.0008745545,-4.2176933,0.26823053,-170.95401,171.23831,0.64240164,1.1149371,-1.2407365,-171.41364,-243.77882,1.7573388,5.557062,-4.3953805,71.383865,740000
+0.6504848,172.75394,0.0037689372,-0.0013243413,-4.351383,0.2839107,-172.73755,173.03651,0.5566872,0.79212,-4.795005,-172.93968,-229.8665,1.3488071,4.448088,-2.399415,52.48,745000
+0.65976644,172.46274,0.0036089544,4.5276447e-05,-3.9874544,0.2952748,-172.44836,172.75806,0.47396874,0.7277588,-0.6753116,-172.67082,-239.02869,1.2017276,6.950539,-3.6268,61.352547,750000
+0.6446055,169.66325,0.0036621338,-0.0011436974,-4.3123035,0.30534774,-169.64746,169.96745,0.93452185,2.0990193,1.8938103,-169.7109,-227.76219,3.0335412,20.443272,-15.497633,125.51166,755000
+0.64938104,174.27216,0.0037599462,-0.0008278507,-4.220176,0.35486346,-174.25629,174.62619,0.6239667,1.2885685,-38.285072,-174.43987,-246.05847,1.9125352,5.3350005,-5.0864344,78.68906,760000
+0.648599,177.09747,0.0037380098,-5.1039653e-05,-4.013654,0.31097052,-177.08246,177.4084,0.91844386,1.2662492,-7.8215346,-177.16014,-224.56577,2.184693,61.43333,-21.96762,240.4072,765000
+0.6631999,175.83966,0.0037140986,0.0014641343,-3.6057901,0.3294012,-175.82626,176.17053,1.1501786,2.3555303,-2.6549206,-175.94302,-234.9795,3.5057087,12.23717,-7.332762,115.548325,770000
+0.65964365,177.66838,0.0035419955,0.0015706185,-3.5565724,0.3256585,-177.65579,177.9956,0.4076728,2.4158547,-0.65706706,-177.81784,-235.11613,2.8235276,64.586876,-30.17391,228.49146,775000
+0.6602604,174.53091,0.0035820855,0.0012288489,-3.656946,0.320565,-174.51782,174.85272,1.2695334,1.5546861,-1.9311217,-174.68051,-229.10704,2.8242195,6.463845,-3.5879264,83.07346,780000
+0.65816665,177.59949,0.0035129723,0.0014567083,-3.5853345,0.31330842,-177.58688,177.91425,1.0698849,0.8309495,-3.0387273,-178.03008,-267.18115,1.9008343,13.696468,-6.1505384,79.56483,785000
+0.65871966,175.70612,0.003436428,-0.0019412297,-4.5648975,0.33011883,-175.69043,176.0343,0.6099538,1.0451726,-15.807207,-175.68095,-285.96906,1.6551263,1.9607112,-2.2137983,51.63118,790000
+0.64890367,172.32945,0.0034309432,-0.0040395996,-5.177402,0.2889789,-172.31169,172.6144,0.80417055,1.0667353,2.2359889,-172.30034,-286.00656,1.8709059,2.283526,-2.7605782,65.62399,795000
+0.64964044,174.13528,0.0033274477,-0.0019172024,-4.576178,0.34946793,-174.12006,174.48283,0.69270635,1.1530436,-1.3695567,-174.1986,-232.7201,1.84575,4.4108124,-5.6870756,72.967384,800000
+0.6580225,176.78252,0.0034664369,0.001853992,-3.4651592,0.32135624,-176.77051,177.10573,0.8588581,0.6523817,-3.6352844,-176.74399,-224.3017,1.5112398,2.6232467,-5.051784,64.08478,805000
+0.6534786,173.16464,0.0034458665,0.00061630533,-3.8211465,0.3229466,-173.15146,173.4882,0.5429938,0.93390197,-10.295264,-173.29497,-240.15121,1.4768958,3.7464507,-4.0164022,64.7404,810000
+0.65742195,180.44958,0.0033543387,0.0019122455,-3.4299188,0.3291637,-180.43808,180.78065,0.5684683,0.69741964,-3.2791522,-180.41154,-226.69186,1.265888,2.2138524,-2.2082808,60.61293,815000
+0.65367985,177.54803,0.003496908,0.0010578688,-3.6974845,0.3131011,-177.53513,177.86218,0.39644846,0.7125875,-2.0700438,-177.87743,-269.79193,1.109036,2.2194047,-4.205892,53.505764,820000
+0.6571018,177.53162,0.0032894125,-0.00024756487,-4.075261,0.27746493,-177.51822,177.80884,0.586497,0.5761659,-28.40344,-177.91026,-229.35164,1.162663,1.715561,-3.2244072,48.851936,825000
+0.65730476,178.3074,0.00325307,8.149459e-05,-3.9749484,0.30364597,-178.29448,178.61113,0.85473365,1.4831548,-9.906389,-178.6096,-288.0091,2.3378885,10.736361,-6.392549,112.256226,830000
+0.66171896,180.67102,0.0031160407,0.0023389175,-3.2493944,0.32220647,-180.66089,180.99556,0.29155645,0.72461975,-71.3556,-180.53072,-288.1901,1.0161762,1.2332768,-2.8375752,44.37702,835000
+0.64836323,180.57327,0.0032162087,-0.0011560826,-4.359455,0.28309524,-180.55925,180.85521,0.47839743,0.68253493,-2.9268475,-180.82738,-222.32738,1.1609323,4.518052,-3.5314856,64.0507,840000
+0.6509564,173.19675,0.0030463072,-0.0017723445,-4.581801,0.30744863,-173.18279,173.50243,0.34759292,0.6116487,-5.3034706,-173.44731,-214.01338,0.9592416,2.241649,-2.8789344,47.514214,845000
+0.66298753,178.88156,0.0029298887,0.0014084248,-3.5192907,0.3022017,-178.87125,179.18517,0.9251656,1.1184357,-12.391917,-179.16692,-237.99843,2.0436013,8.391869,-5.143858,93.54848,850000
+0.6615427,181.34557,0.003102688,0.0026363214,-3.1503105,0.28249198,-181.33578,181.63069,0.77347785,1.4865601,-5.213316,-181.5865,-256.7642,2.260038,5.2007895,-4.757878,93.58428,855000
+0.65109426,176.28047,0.0029967343,-0.0013827519,-4.4614196,0.31254464,-176.2671,176.59163,0.843414,1.3173473,-0.74431586,-176.37117,-256.33533,2.1607614,4.560138,-5.4492483,96.67438,860000
+0.66849357,181.19862,0.0031083964,0.0013654149,-3.5607333,0.2758955,-181.18756,181.47588,0.5115494,0.66715366,-43.85694,-181.14914,-256.95303,1.1787031,3.209015,-2.4992023,59.039566,865000
+0.6543268,178.8197,0.0029410124,-0.0011027085,-4.374942,0.29199106,-178.80684,179.1106,0.5201362,0.81703854,-1.9440029,-178.82202,-259.69333,1.3371747,3.798352,-3.9152641,67.46879,870000
+0.65802443,179.57698,0.0029883822,0.0009665583,-3.6765614,0.27272853,-179.566,179.85068,0.6302106,1.1156449,-45.905354,-179.90897,-229.0941,1.7458556,5.198327,-5.0397577,90.89314,875000
+0.6584203,173.79373,0.0029731116,-0.0006318928,-4.212536,0.31490403,-173.78119,174.10802,0.5521763,0.6971795,0.033789814,-173.99336,-329.27524,1.2493558,3.7995365,-3.9454577,58.40434,880000
+0.65551496,183.13824,0.0028921762,-0.0012307034,-4.4255285,0.24418151,-183.12543,183.3812,1.1274318,1.4523302,-9.307394,-183.4591,-347.9167,2.579762,5.066439,-21.151857,173.85867,885000
+0.6518427,179.4873,0.0029873552,-0.00011974338,-4.0400834,0.2927355,-179.47523,179.77992,0.53403085,1.0296532,-8.117391,-179.68925,-266.54913,1.563684,2.467561,-6.083226,60.12365,890000
+0.66753006,184.74347,0.0028512366,0.0009547218,-3.6651552,0.26177102,-184.73302,185.0062,0.68107617,1.060501,-0.009895861,-184.59026,-622.7018,1.7415771,10.138819,-3.3416722,85.43618,895000
+0.6542667,180.18903,0.0026937423,-4.2842425e-05,-4.0159044,0.29982045,-180.1782,180.4888,0.9642817,0.90711516,-14.584773,-180.20306,-265.65308,1.8713968,9.694177,-5.094434,110.821434,900000
+0.6710146,180.61327,0.0027436106,0.0004279683,-3.8440127,0.3132778,-180.60272,180.92697,0.6337945,2.070336,-22.638226,-180.82536,-244.60292,2.7041306,7.069112,-5.891639,103.34377,905000
+0.65910465,182.44116,0.0026715002,-9.6956835e-05,-4.036293,0.2831837,-182.43039,182.72426,0.31366357,0.5867046,-45.30243,-182.59283,-242.29512,0.9003682,2.1726284,-1.3520631,39.12622,910000
+0.66503656,182.91508,0.0027755585,0.00084208604,-3.6966066,0.32664055,-182.90482,183.24257,0.3657789,0.55176795,1.177696,-182.96548,-271.9042,0.91754687,4.6066513,-3.1573346,59.27692,915000
+0.6669063,184.7294,0.0028480121,0.002165067,-3.239797,0.2827438,-184.72015,185.01431,0.48901686,0.8330774,-1.109398,-185.06058,-288.12048,1.3220942,2.5725493,-2.31261,61.030483,920000
+0.6695285,184.24454,0.0025973557,0.0013874101,-3.4658375,0.3023913,-184.23553,184.54832,0.54390156,1.0462874,2.1995754,-184.51701,-243.24382,1.590189,7.5134177,-3.6051602,90.60429,925000
+0.64466906,185.0767,0.0024814296,-0.0011851097,-4.4775915,0.248422,-185.06558,185.32394,0.46802083,0.6825196,-25.381733,-185.31824,-246.39992,1.1505405,1.5369223,-1.5408517,40.112297,930000
+0.6563844,185.60843,0.002490087,0.0016833175,-3.3239925,0.29978895,-185.60013,185.9099,0.36577573,0.83785075,-1.5251126,-185.76276,-216.59302,1.2036265,8.048101,-4.691617,64.744545,935000
+0.66669583,185.64337,0.0023406774,0.00032877774,-3.8595374,0.3458267,-185.63434,185.98953,1.1393973,1.3130347,-15.180008,-185.80473,-241.05693,2.452432,9.822387,-10.491994,131.66756,940000
+0.66938055,186.18376,0.0024086658,0.00026423228,-3.8902993,0.30116835,-186.17441,186.48518,0.4077293,0.55759513,-25.747875,-186.27023,-299.86996,0.9653244,3.1754296,-3.9942462,57.15799,945000
+0.6572315,185.27625,0.0024277044,-0.00087784615,-4.361595,0.3110932,-185.26564,185.58646,0.9731868,1.3325185,-9.141388,-185.62521,-233.9023,2.3057053,11.4266205,-8.897952,95.72032,950000
+0.64973456,181.37204,0.0022906188,-0.00041336173,-4.1804585,0.2922265,-181.36246,181.66385,0.71428186,0.9607568,-4.645712,-181.64066,-264.6274,1.6750386,4.295484,-5.6898904,90.804184,955000
+0.6572405,184.33214,0.0022568554,0.0002817717,-3.8751485,0.2601287,-184.3234,184.59254,0.6066341,0.9032715,-0.09179938,-184.37492,-220.18506,1.5099056,6.1113186,-7.8554215,86.5574,960000
+0.67814505,189.66354,0.002318228,0.0031024325,-2.6617224,0.32305,-189.65736,189.98969,0.6263578,1.0741416,-76.410065,-189.73154,-257.7765,1.7004994,7.403528,-14.712784,98.11322,965000
+0.65921295,185.78143,0.0023330245,-0.0005750005,-4.2464614,0.28860885,-185.77151,186.06946,0.41549167,0.69785917,-18.89949,-186.0573,-248.07993,1.1133509,3.7697926,-3.784218,52.7267,970000
+0.67067313,185.92398,0.0023907651,2.9713106e-05,-3.9875717,0.27964705,-185.91443,186.20366,0.5232317,0.69792014,-27.875345,-185.83354,-256.47083,1.2211518,3.2235749,-5.3801847,70.39475,975000
+0.6598139,185.7237,0.0023548761,-0.001637248,-4.6952586,0.30179483,-185.71263,186.02385,0.5946218,1.2038351,-0.87071747,-185.66194,-256.30295,1.7984569,14.208836,-5.2639265,118.12314,980000
+0.6412954,185.13573,0.0020982139,-0.0012534093,-4.5973697,0.26647797,-185.12607,185.40096,1.028509,2.1961944,-0.23613274,-185.56215,-256.75504,3.2247033,15.6955805,-33.273453,187.06541,985000
+0.6743464,189.86984,0.002128198,0.00070570223,-3.6684039,0.3160876,-189.86201,190.18663,0.40848956,0.74006027,-26.316608,-189.90892,-258.8063,1.1485498,3.6552742,-5.7226315,58.540237,990000
+0.6570722,184.67172,0.0020718544,-0.00065701874,-4.3171163,0.29033858,-184.66278,184.96141,0.39861685,1.1647367,0.17107469,-185.02376,-242.71986,1.5633535,10.791437,-16.31756,107.77841,995000
+0.6720329,187.43784,0.0020403909,0.0015584178,-3.236216,0.24725711,-187.43121,187.68665,0.55822873,1.438491,-16.16343,-187.68742,-259.11688,1.9967197,10.203766,-9.812226,116.75256,1000000
+0.6532778,189.13705,0.0019293966,-0.0011514305,-4.5967827,0.27747482,-189.12819,189.41339,0.45732233,0.900651,-17.559278,-189.23451,-226.97433,1.3579733,5.496628,-4.304539,78.387535,1005000
+0.6755955,189.77786,0.0019419764,0.001649599,-3.1505566,0.24045163,-189.77173,190.01996,0.4743198,0.4151956,-50.019325,-189.90714,-242.5373,0.8895154,1.4994928,-1.8617011,39.43342,1010000
+0.66283023,185.85886,0.0019042263,-0.00094771385,-4.4976897,0.2885952,-185.85028,186.1465,1.877742,1.8047093,-2.62569,-186.31384,-260.76028,3.6824512,17.917963,-30.752777,212.81073,1015000
+0.6687863,188.88635,0.0019469341,0.00077208073,-3.6034377,0.26503572,-188.87933,189.15216,0.6878835,0.8445549,1.1059271,-189.11124,-259.2514,1.5324384,4.3398576,-6.656891,79.736206,1020000
+0.6732477,184.41193,0.0018295998,0.00028449218,-3.8445058,0.28418797,-184.4049,184.69641,1.1862526,1.1890266,0.114899635,-184.37608,-247.4578,2.3752792,5.4454226,-18.113583,116.297264,1025000
+0.6565507,186.90216,0.0017686172,-8.723618e-05,-4.0493245,0.2653717,-186.895,187.16743,0.95508116,1.1273458,-22.59947,-187.21269,-245.78853,2.082427,32.366737,-33.38383,196.13846,1030000
+0.65785795,188.46683,0.0016644531,-0.0016468589,-4.9894295,0.32426298,-188.45853,188.78944,0.4209085,0.87672776,-53.49496,-188.47438,-286.74768,1.2976363,2.8427541,-8.116869,70.62767,1035000
+0.67618704,190.18335,0.0017694244,0.00038822426,-3.780593,0.24159624,-190.17664,190.42532,0.6983039,0.9455189,-10.186071,-190.4608,-255.39821,1.6438228,4.5011754,-16.405144,125.955795,1040000
+0.66443014,188.70566,0.0016778435,0.00018939536,-3.8871198,0.27520117,-188.69913,188.98105,0.4234852,0.82657856,-33.946247,-188.86113,-261.4005,1.2500638,5.085625,-4.680219,72.66176,1045000
+0.6724781,191.21146,0.0016622489,0.0013650834,-3.1787732,0.28333497,-191.20618,191.49615,1.8320233,2.0182142,-0.14572561,-191.23395,-235.1913,3.8502374,29.371262,-14.81776,197.61581,1050000
+0.6573806,187.19049,0.0017219328,-0.0014574345,-4.8463945,0.27504757,-187.18214,187.46408,0.64413637,1.681778,2.1131542,-187.32567,-245.6656,2.3259144,22.3695,-11.741098,158.20038,1055000
+0.66721225,188.91422,0.0016617987,0.0005821627,-3.6496792,0.27020538,-188.90814,189.185,0.56776714,1.2817081,-4.1652746,-189.12097,-230.7308,1.8494753,9.675042,-9.313669,128.88983,1060000
+0.66004413,186.88438,0.001560428,0.0003818002,-3.7553234,0.30414265,-186.87852,187.1889,0.49941546,0.63628983,0.89500165,-186.85185,-214.45251,1.1357052,5.5801425,-3.3843496,68.42214,1065000
+0.65877366,189.2284,0.0016139058,0.0009919968,-3.385344,0.31792966,-189.22293,189.54732,0.4389103,1.0248569,1.9517498,-189.4108,-217.16728,1.4637673,8.962845,-12.284788,145.14398,1070000
+0.6793966,188.96156,0.0015723349,-0.00037381446,-4.237745,0.26581615,-188.9549,189.22702,0.49891683,0.9727815,1.9309793,-188.73984,-215.66628,1.4716983,18.487473,-5.830821,105.74634,1075000
+0.66844803,188.71193,0.0016319569,0.00023482718,-3.856107,0.30715522,-188.70563,189.01932,0.9068347,1.4008969,-5.8821096,-188.85764,-247.601,2.3077316,12.70764,-9.885952,170.31909,1080000
+0.67364055,188.95702,0.0015298452,0.00022629344,-3.8520808,0.2778441,-188.95111,189.23509,0.41143557,0.6018216,-16.340326,-189.07434,-241.75177,1.0132571,5.6075687,-3.3614352,60.301525,1085000
+0.6665464,188.19856,0.0016457152,-4.149303e-05,-4.025213,0.27903694,-188.19196,188.47755,0.45354706,1.0284008,-2.0364609,-188.40697,-256.14215,1.4819479,12.58564,-15.200231,117.324585,1090000
+0.6739349,192.07782,0.0014496257,0.0005169155,-3.6434145,0.2758897,-192.07254,192.35423,1.8993248,1.5730816,-57.859673,-192.10759,-213.25417,3.4724064,19.997528,-69.38095,463.42108,1095000
+0.6598387,190.04414,0.0013672198,2.7918404e-05,-3.9795802,0.3226657,-190.03871,190.36684,0.78486204,0.5924992,-0.050667405,-190.28035,-217.12302,1.3773613,24.681541,-12.180788,147.69653,1100000
+0.6689017,188.1778,0.0014401599,4.0104205e-05,-3.972153,0.29078078,-188.17209,188.46863,0.4201704,0.6729398,-7.36483,-188.16199,-217.90253,1.0931102,8.0911665,-8.599931,74.561325,1105000
+0.66448045,189.94327,0.0015083586,-0.00049707206,-4.329545,0.23297119,-189.93674,190.17574,1.0593961,1.0832864,-11.85798,-190.21495,-233.63394,2.1426826,48.997265,-15.880972,174.48505,1110000
+0.67627186,190.35822,0.001347707,0.00084221986,-3.375072,0.22161119,-190.35367,190.58067,2.2883737,2.0578787,-4.8134384,-190.5065,-214.75435,4.3462524,42.730873,-24.387875,269.34946,1115000
+0.66685295,193.12125,0.0014601881,0.00026000882,-3.8219347,0.26266205,-193.11566,193.38417,0.16676429,0.98075736,-97.647,-193.04195,-247.3496,1.1475216,10.800113,-17.23329,92.64795,1120000
+0.66627765,190.41916,0.0013146525,0.0010344008,-3.2131755,0.27061874,-190.41493,190.69081,0.67099696,0.78791094,-33.85355,-190.38885,-244.3015,1.4589078,10.798989,-4.3345947,65.16589,1125000
+0.67118853,189.5802,0.0012623112,0.0005638565,-3.5533142,0.26051277,-189.57573,189.84128,0.7411753,0.63668555,-27.95183,-189.81656,-214.09929,1.3778608,13.001288,-21.486979,157.49876,1130000
+0.65836394,190.77264,0.0012720837,-0.00027789467,-4.2184563,0.2959562,-190.76727,191.06833,0.8031139,0.85669345,-37.383556,-190.82751,-214.35652,1.6598073,8.1926155,-7.1994634,104.15196,1135000
+0.68248564,191.42633,0.0013499948,0.0013826598,-2.9758036,0.25742856,-191.42232,191.68515,0.8130831,0.66873485,1.4317799,-191.58405,-212.47087,1.481818,5.2539363,-9.594331,84.76933,1140000
+0.6392376,189.36014,0.0013014761,-0.0016322797,-5.2541757,0.28441864,-189.35333,189.64293,0.43193492,0.7436334,-18.679031,-189.41768,-251.01382,1.1755683,7.1861286,-3.9311998,69.36913,1145000
+0.64919066,184.95251,0.0012526044,-0.002243931,-5.7914124,0.25986463,-184.94525,185.21013,0.84978676,1.8735698,0.27170628,-185.0589,-204.44916,2.7233567,21.598,-33.59946,294.99158,1150000
+0.6597236,189.57436,0.0012771143,-0.00061008084,-4.4777026,0.32273877,-189.56863,189.89648,2.9141777,5.4779234,1.667577,-189.55591,-234.37668,8.392101,30.372005,-84.79362,453.575,1155000
+0.6749132,189.64938,0.0012369944,-0.00064204616,-4.5190372,0.2931791,-189.6438,189.94193,0.38102135,0.76711076,-1.7493392,-189.78336,-247.8672,1.1481321,4.5541487,-4.370795,58.173965,1160000
+0.6655092,190.97705,0.0011615938,-0.00038100174,-4.327999,0.28659034,-190.97202,191.26326,0.311079,0.87677187,-24.006998,-191.02011,-214.88992,1.1878508,3.7479076,-4.9446497,53.75477,1165000
+0.66519606,190.3818,0.0012671093,-4.347918e-05,-4.0343137,0.274042,-190.37671,190.6558,0.2267448,0.49521905,-26.290535,-190.41014,-225.91382,0.7219639,2.2064772,-2.2971284,39.690643,1170000
+0.6617087,190.34929,0.0011696838,0.00038152075,-3.6738257,0.22797115,-190.345,190.57764,0.3210545,0.35332286,-76.09387,-190.50029,-212.08316,0.6743773,3.2716641,-3.740558,42.404503,1175000
+0.66133964,189.70134,0.0012024611,-0.0006727147,-4.5594482,0.28482372,-189.69586,189.98549,0.8287762,1.2667581,0.48656368,-189.99063,-212.00146,2.0955343,11.814021,-12.111546,102.44026,1180000
+0.6837146,191.03186,0.0012397142,0.0004986819,-3.5977445,0.26172853,-191.0274,191.2941,0.63298005,1.5542353,-20.14326,-190.92271,-209.144,2.1872153,54.73885,-17.374237,255.26596,1185000
+0.6707122,190.00084,0.0011806956,-5.7791904e-06,-4.0048947,0.2818805,-189.99611,190.28271,0.4184896,1.4286385,-11.16553,-190.13802,-239.59248,1.847128,15.29461,-15.0350685,131.18906,1190000
+0.67773324,193.20819,0.0012139466,0.00010539326,-3.9131813,0.27168724,-193.20345,193.47998,0.7387132,1.0139034,-83.011894,-193.4551,-210.87872,1.7526166,10.676398,-4.58529,86.25931,1195000
+0.67332935,192.37689,0.001152424,-0.00021327256,-4.1850643,0.26480478,-192.37207,192.64148,0.6991269,0.4858663,-9.117987,-192.50816,-209.39565,1.1849933,6.0323095,-3.6899495,62.18177,1200000

O2O-w-diff-ckpts/dsrl/20260317_155656/online_agent_sv.csv

@@ -0,0 +1,101 @@
+actor/action_std,actor/actor_loss,actor/alpha,actor/alpha_loss,actor/entropy,actor/flow_loss,actor/q,actor/total_loss,critic/critic_loss,critic/distill_loss,critic/q_max,critic/q_mean,critic/q_min,critic/total_loss,grad/max,grad/min,grad/norm,step
+0.6496232,171.50206,0.004210169,-0.00022136616,-4.052579,0.34410596,-171.48499,171.84593,0.4905737,0.5678915,-1.9423368,-171.64017,-230.26544,1.0584652,1.2007079,-2.0536103,34.81398,705000
+0.6545079,169.79042,0.004189504,0.0008298752,-3.8019156,0.27170366,-169.7745,170.06294,1.0181779,1.3484273,-1.4562513,-169.93526,-236.69429,2.3666053,11.804882,-9.241452,99.76379,710000
+0.659034,175.443,0.003999513,0.001605074,-3.5986826,0.2977104,-175.4286,175.74231,0.7084817,0.9761173,-2.336735,-175.85478,-287.3107,1.684599,3.0114787,-5.056738,73.165565,715000
+0.65981257,173.21341,0.004081305,0.00043622818,-3.8931155,0.3107875,-173.19754,173.52464,0.67347157,0.7113277,-18.01319,-173.42064,-244.88875,1.3847992,3.0280988,-2.0119908,54.58591,720000
+0.64910483,173.34015,0.0039116554,-0.0014532285,-4.3715124,0.31178564,-173.32306,173.65048,0.9475531,1.0420613,0.8436885,-173.14215,-255.54901,1.9896145,3.1509042,-4.643108,86.379,725000
+0.64903367,172.2172,0.003984428,2.8406703e-05,-3.9928706,0.3098619,-172.20128,172.52708,0.50895053,0.72073597,0.8783986,-172.1927,-282.41577,1.2296865,2.1038013,-1.8094043,50.31658,730000
+0.6490887,171.7738,0.0040129926,-0.0024812198,-4.6182966,0.30542612,-171.75528,172.07674,1.2128547,1.4067744,0.8089568,-172.16605,-245.90387,2.6196291,8.002079,-12.339584,120.785866,735000
+0.65358156,170.97095,0.0040173694,-0.0008745545,-4.2176933,0.26823053,-170.95401,171.23831,0.64240164,1.1149371,-1.2407365,-171.41364,-243.77882,1.7573388,5.557062,-4.3953805,71.383865,740000
+0.6504848,172.75394,0.0037689372,-0.0013243413,-4.351383,0.2839107,-172.73755,173.03651,0.5566872,0.79212,-4.795005,-172.93968,-229.8665,1.3488071,4.448088,-2.399415,52.48,745000
+0.65976644,172.46274,0.0036089544,4.5276447e-05,-3.9874544,0.2952748,-172.44836,172.75806,0.47396874,0.7277588,-0.6753116,-172.67082,-239.02869,1.2017276,6.950539,-3.6268,61.352547,750000
+0.6446055,169.66325,0.0036621338,-0.0011436974,-4.3123035,0.30534774,-169.64746,169.96745,0.93452185,2.0990193,1.8938103,-169.7109,-227.76219,3.0335412,20.443272,-15.497633,125.51166,755000
+0.64938104,174.27216,0.0037599462,-0.0008278507,-4.220176,0.35486346,-174.25629,174.62619,0.6239667,1.2885685,-38.285072,-174.43987,-246.05847,1.9125352,5.3350005,-5.0864344,78.68906,760000
+0.648599,177.09747,0.0037380098,-5.1039653e-05,-4.013654,0.31097052,-177.08246,177.4084,0.91844386,1.2662492,-7.8215346,-177.16014,-224.56577,2.184693,61.43333,-21.96762,240.4072,765000
+0.6631999,175.83966,0.0037140986,0.0014641343,-3.6057901,0.3294012,-175.82626,176.17053,1.1501786,2.3555303,-2.6549206,-175.94302,-234.9795,3.5057087,12.23717,-7.332762,115.548325,770000
+0.65964365,177.66838,0.0035419955,0.0015706185,-3.5565724,0.3256585,-177.65579,177.9956,0.4076728,2.4158547,-0.65706706,-177.81784,-235.11613,2.8235276,64.586876,-30.17391,228.49146,775000
+0.6602604,174.53091,0.0035820855,0.0012288489,-3.656946,0.320565,-174.51782,174.85272,1.2695334,1.5546861,-1.9311217,-174.68051,-229.10704,2.8242195,6.463845,-3.5879264,83.07346,780000
+0.65816665,177.59949,0.0035129723,0.0014567083,-3.5853345,0.31330842,-177.58688,177.91425,1.0698849,0.8309495,-3.0387273,-178.03008,-267.18115,1.9008343,13.696468,-6.1505384,79.56483,785000
+0.65871966,175.70612,0.003436428,-0.0019412297,-4.5648975,0.33011883,-175.69043,176.0343,0.6099538,1.0451726,-15.807207,-175.68095,-285.96906,1.6551263,1.9607112,-2.2137983,51.63118,790000
+0.64890367,172.32945,0.0034309432,-0.0040395996,-5.177402,0.2889789,-172.31169,172.6144,0.80417055,1.0667353,2.2359889,-172.30034,-286.00656,1.8709059,2.283526,-2.7605782,65.62399,795000
+0.64964044,174.13528,0.0033274477,-0.0019172024,-4.576178,0.34946793,-174.12006,174.48283,0.69270635,1.1530436,-1.3695567,-174.1986,-232.7201,1.84575,4.4108124,-5.6870756,72.967384,800000
+0.6580225,176.78252,0.0034664369,0.001853992,-3.4651592,0.32135624,-176.77051,177.10573,0.8588581,0.6523817,-3.6352844,-176.74399,-224.3017,1.5112398,2.6232467,-5.051784,64.08478,805000
+0.6534786,173.16464,0.0034458665,0.00061630533,-3.8211465,0.3229466,-173.15146,173.4882,0.5429938,0.93390197,-10.295264,-173.29497,-240.15121,1.4768958,3.7464507,-4.0164022,64.7404,810000
+0.65742195,180.44958,0.0033543387,0.0019122455,-3.4299188,0.3291637,-180.43808,180.78065,0.5684683,0.69741964,-3.2791522,-180.41154,-226.69186,1.265888,2.2138524,-2.2082808,60.61293,815000
+0.65367985,177.54803,0.003496908,0.0010578688,-3.6974845,0.3131011,-177.53513,177.86218,0.39644846,0.7125875,-2.0700438,-177.87743,-269.79193,1.109036,2.2194047,-4.205892,53.505764,820000
+0.6571018,177.53162,0.0032894125,-0.00024756487,-4.075261,0.27746493,-177.51822,177.80884,0.586497,0.5761659,-28.40344,-177.91026,-229.35164,1.162663,1.715561,-3.2244072,48.851936,825000
+0.65730476,178.3074,0.00325307,8.149459e-05,-3.9749484,0.30364597,-178.29448,178.61113,0.85473365,1.4831548,-9.906389,-178.6096,-288.0091,2.3378885,10.736361,-6.392549,112.256226,830000
+0.66171896,180.67102,0.0031160407,0.0023389175,-3.2493944,0.32220647,-180.66089,180.99556,0.29155645,0.72461975,-71.3556,-180.53072,-288.1901,1.0161762,1.2332768,-2.8375752,44.37702,835000
+0.64836323,180.57327,0.0032162087,-0.0011560826,-4.359455,0.28309524,-180.55925,180.85521,0.47839743,0.68253493,-2.9268475,-180.82738,-222.32738,1.1609323,4.518052,-3.5314856,64.0507,840000
+0.6509564,173.19675,0.0030463072,-0.0017723445,-4.581801,0.30744863,-173.18279,173.50243,0.34759292,0.6116487,-5.3034706,-173.44731,-214.01338,0.9592416,2.241649,-2.8789344,47.514214,845000
+0.66298753,178.88156,0.0029298887,0.0014084248,-3.5192907,0.3022017,-178.87125,179.18517,0.9251656,1.1184357,-12.391917,-179.16692,-237.99843,2.0436013,8.391869,-5.143858,93.54848,850000
+0.6615427,181.34557,0.003102688,0.0026363214,-3.1503105,0.28249198,-181.33578,181.63069,0.77347785,1.4865601,-5.213316,-181.5865,-256.7642,2.260038,5.2007895,-4.757878,93.58428,855000
+0.65109426,176.28047,0.0029967343,-0.0013827519,-4.4614196,0.31254464,-176.2671,176.59163,0.843414,1.3173473,-0.74431586,-176.37117,-256.33533,2.1607614,4.560138,-5.4492483,96.67438,860000
+0.66849357,181.19862,0.0031083964,0.0013654149,-3.5607333,0.2758955,-181.18756,181.47588,0.5115494,0.66715366,-43.85694,-181.14914,-256.95303,1.1787031,3.209015,-2.4992023,59.039566,865000
+0.6543268,178.8197,0.0029410124,-0.0011027085,-4.374942,0.29199106,-178.80684,179.1106,0.5201362,0.81703854,-1.9440029,-178.82202,-259.69333,1.3371747,3.798352,-3.9152641,67.46879,870000
+0.65802443,179.57698,0.0029883822,0.0009665583,-3.6765614,0.27272853,-179.566,179.85068,0.6302106,1.1156449,-45.905354,-179.90897,-229.0941,1.7458556,5.198327,-5.0397577,90.89314,875000
+0.6584203,173.79373,0.0029731116,-0.0006318928,-4.212536,0.31490403,-173.78119,174.10802,0.5521763,0.6971795,0.033789814,-173.99336,-329.27524,1.2493558,3.7995365,-3.9454577,58.40434,880000
+0.65551496,183.13824,0.0028921762,-0.0012307034,-4.4255285,0.24418151,-183.12543,183.3812,1.1274318,1.4523302,-9.307394,-183.4591,-347.9167,2.579762,5.066439,-21.151857,173.85867,885000
+0.6518427,179.4873,0.0029873552,-0.00011974338,-4.0400834,0.2927355,-179.47523,179.77992,0.53403085,1.0296532,-8.117391,-179.68925,-266.54913,1.563684,2.467561,-6.083226,60.12365,890000
+0.66753006,184.74347,0.0028512366,0.0009547218,-3.6651552,0.26177102,-184.73302,185.0062,0.68107617,1.060501,-0.009895861,-184.59026,-622.7018,1.7415771,10.138819,-3.3416722,85.43618,895000
+0.6542667,180.18903,0.0026937423,-4.2842425e-05,-4.0159044,0.29982045,-180.1782,180.4888,0.9642817,0.90711516,-14.584773,-180.20306,-265.65308,1.8713968,9.694177,-5.094434,110.821434,900000
+0.6710146,180.61327,0.0027436106,0.0004279683,-3.8440127,0.3132778,-180.60272,180.92697,0.6337945,2.070336,-22.638226,-180.82536,-244.60292,2.7041306,7.069112,-5.891639,103.34377,905000
+0.65910465,182.44116,0.0026715002,-9.6956835e-05,-4.036293,0.2831837,-182.43039,182.72426,0.31366357,0.5867046,-45.30243,-182.59283,-242.29512,0.9003682,2.1726284,-1.3520631,39.12622,910000
+0.66503656,182.91508,0.0027755585,0.00084208604,-3.6966066,0.32664055,-182.90482,183.24257,0.3657789,0.55176795,1.177696,-182.96548,-271.9042,0.91754687,4.6066513,-3.1573346,59.27692,915000
+0.6669063,184.7294,0.0028480121,0.002165067,-3.239797,0.2827438,-184.72015,185.01431,0.48901686,0.8330774,-1.109398,-185.06058,-288.12048,1.3220942,2.5725493,-2.31261,61.030483,920000
+0.6695285,184.24454,0.0025973557,0.0013874101,-3.4658375,0.3023913,-184.23553,184.54832,0.54390156,1.0462874,2.1995754,-184.51701,-243.24382,1.590189,7.5134177,-3.6051602,90.60429,925000
+0.64466906,185.0767,0.0024814296,-0.0011851097,-4.4775915,0.248422,-185.06558,185.32394,0.46802083,0.6825196,-25.381733,-185.31824,-246.39992,1.1505405,1.5369223,-1.5408517,40.112297,930000
+0.6563844,185.60843,0.002490087,0.0016833175,-3.3239925,0.29978895,-185.60013,185.9099,0.36577573,0.83785075,-1.5251126,-185.76276,-216.59302,1.2036265,8.048101,-4.691617,64.744545,935000
+0.66669583,185.64337,0.0023406774,0.00032877774,-3.8595374,0.3458267,-185.63434,185.98953,1.1393973,1.3130347,-15.180008,-185.80473,-241.05693,2.452432,9.822387,-10.491994,131.66756,940000
+0.66938055,186.18376,0.0024086658,0.00026423228,-3.8902993,0.30116835,-186.17441,186.48518,0.4077293,0.55759513,-25.747875,-186.27023,-299.86996,0.9653244,3.1754296,-3.9942462,57.15799,945000
+0.6572315,185.27625,0.0024277044,-0.00087784615,-4.361595,0.3110932,-185.26564,185.58646,0.9731868,1.3325185,-9.141388,-185.62521,-233.9023,2.3057053,11.4266205,-8.897952,95.72032,950000
+0.64973456,181.37204,0.0022906188,-0.00041336173,-4.1804585,0.2922265,-181.36246,181.66385,0.71428186,0.9607568,-4.645712,-181.64066,-264.6274,1.6750386,4.295484,-5.6898904,90.804184,955000
+0.6572405,184.33214,0.0022568554,0.0002817717,-3.8751485,0.2601287,-184.3234,184.59254,0.6066341,0.9032715,-0.09179938,-184.37492,-220.18506,1.5099056,6.1113186,-7.8554215,86.5574,960000
+0.67814505,189.66354,0.002318228,0.0031024325,-2.6617224,0.32305,-189.65736,189.98969,0.6263578,1.0741416,-76.410065,-189.73154,-257.7765,1.7004994,7.403528,-14.712784,98.11322,965000
+0.65921295,185.78143,0.0023330245,-0.0005750005,-4.2464614,0.28860885,-185.77151,186.06946,0.41549167,0.69785917,-18.89949,-186.0573,-248.07993,1.1133509,3.7697926,-3.784218,52.7267,970000
+0.67067313,185.92398,0.0023907651,2.9713106e-05,-3.9875717,0.27964705,-185.91443,186.20366,0.5232317,0.69792014,-27.875345,-185.83354,-256.47083,1.2211518,3.2235749,-5.3801847,70.39475,975000
+0.6598139,185.7237,0.0023548761,-0.001637248,-4.6952586,0.30179483,-185.71263,186.02385,0.5946218,1.2038351,-0.87071747,-185.66194,-256.30295,1.7984569,14.208836,-5.2639265,118.12314,980000
+0.6412954,185.13573,0.0020982139,-0.0012534093,-4.5973697,0.26647797,-185.12607,185.40096,1.028509,2.1961944,-0.23613274,-185.56215,-256.75504,3.2247033,15.6955805,-33.273453,187.06541,985000
+0.6743464,189.86984,0.002128198,0.00070570223,-3.6684039,0.3160876,-189.86201,190.18663,0.40848956,0.74006027,-26.316608,-189.90892,-258.8063,1.1485498,3.6552742,-5.7226315,58.540237,990000
+0.6570722,184.67172,0.0020718544,-0.00065701874,-4.3171163,0.29033858,-184.66278,184.96141,0.39861685,1.1647367,0.17107469,-185.02376,-242.71986,1.5633535,10.791437,-16.31756,107.77841,995000
+0.6720329,187.43784,0.0020403909,0.0015584178,-3.236216,0.24725711,-187.43121,187.68665,0.55822873,1.438491,-16.16343,-187.68742,-259.11688,1.9967197,10.203766,-9.812226,116.75256,1000000
+0.6532778,189.13705,0.0019293966,-0.0011514305,-4.5967827,0.27747482,-189.12819,189.41339,0.45732233,0.900651,-17.559278,-189.23451,-226.97433,1.3579733,5.496628,-4.304539,78.387535,1005000
+0.6755955,189.77786,0.0019419764,0.001649599,-3.1505566,0.24045163,-189.77173,190.01996,0.4743198,0.4151956,-50.019325,-189.90714,-242.5373,0.8895154,1.4994928,-1.8617011,39.43342,1010000
+0.66283023,185.85886,0.0019042263,-0.00094771385,-4.4976897,0.2885952,-185.85028,186.1465,1.877742,1.8047093,-2.62569,-186.31384,-260.76028,3.6824512,17.917963,-30.752777,212.81073,1015000
+0.6687863,188.88635,0.0019469341,0.00077208073,-3.6034377,0.26503572,-188.87933,189.15216,0.6878835,0.8445549,1.1059271,-189.11124,-259.2514,1.5324384,4.3398576,-6.656891,79.736206,1020000
+0.6732477,184.41193,0.0018295998,0.00028449218,-3.8445058,0.28418797,-184.4049,184.69641,1.1862526,1.1890266,0.114899635,-184.37608,-247.4578,2.3752792,5.4454226,-18.113583,116.297264,1025000
+0.6565507,186.90216,0.0017686172,-8.723618e-05,-4.0493245,0.2653717,-186.895,187.16743,0.95508116,1.1273458,-22.59947,-187.21269,-245.78853,2.082427,32.366737,-33.38383,196.13846,1030000
+0.65785795,188.46683,0.0016644531,-0.0016468589,-4.9894295,0.32426298,-188.45853,188.78944,0.4209085,0.87672776,-53.49496,-188.47438,-286.74768,1.2976363,2.8427541,-8.116869,70.62767,1035000
+0.67618704,190.18335,0.0017694244,0.00038822426,-3.780593,0.24159624,-190.17664,190.42532,0.6983039,0.9455189,-10.186071,-190.4608,-255.39821,1.6438228,4.5011754,-16.405144,125.955795,1040000
+0.66443014,188.70566,0.0016778435,0.00018939536,-3.8871198,0.27520117,-188.69913,188.98105,0.4234852,0.82657856,-33.946247,-188.86113,-261.4005,1.2500638,5.085625,-4.680219,72.66176,1045000
+0.6724781,191.21146,0.0016622489,0.0013650834,-3.1787732,0.28333497,-191.20618,191.49615,1.8320233,2.0182142,-0.14572561,-191.23395,-235.1913,3.8502374,29.371262,-14.81776,197.61581,1050000
+0.6573806,187.19049,0.0017219328,-0.0014574345,-4.8463945,0.27504757,-187.18214,187.46408,0.64413637,1.681778,2.1131542,-187.32567,-245.6656,2.3259144,22.3695,-11.741098,158.20038,1055000
+0.66721225,188.91422,0.0016617987,0.0005821627,-3.6496792,0.27020538,-188.90814,189.185,0.56776714,1.2817081,-4.1652746,-189.12097,-230.7308,1.8494753,9.675042,-9.313669,128.88983,1060000
+0.66004413,186.88438,0.001560428,0.0003818002,-3.7553234,0.30414265,-186.87852,187.1889,0.49941546,0.63628983,0.89500165,-186.85185,-214.45251,1.1357052,5.5801425,-3.3843496,68.42214,1065000
+0.65877366,189.2284,0.0016139058,0.0009919968,-3.385344,0.31792966,-189.22293,189.54732,0.4389103,1.0248569,1.9517498,-189.4108,-217.16728,1.4637673,8.962845,-12.284788,145.14398,1070000
+0.6793966,188.96156,0.0015723349,-0.00037381446,-4.237745,0.26581615,-188.9549,189.22702,0.49891683,0.9727815,1.9309793,-188.73984,-215.66628,1.4716983,18.487473,-5.830821,105.74634,1075000
+0.66844803,188.71193,0.0016319569,0.00023482718,-3.856107,0.30715522,-188.70563,189.01932,0.9068347,1.4008969,-5.8821096,-188.85764,-247.601,2.3077316,12.70764,-9.885952,170.31909,1080000
+0.67364055,188.95702,0.0015298452,0.00022629344,-3.8520808,0.2778441,-188.95111,189.23509,0.41143557,0.6018216,-16.340326,-189.07434,-241.75177,1.0132571,5.6075687,-3.3614352,60.301525,1085000
+0.6665464,188.19856,0.0016457152,-4.149303e-05,-4.025213,0.27903694,-188.19196,188.47755,0.45354706,1.0284008,-2.0364609,-188.40697,-256.14215,1.4819479,12.58564,-15.200231,117.324585,1090000
+0.6739349,192.07782,0.0014496257,0.0005169155,-3.6434145,0.2758897,-192.07254,192.35423,1.8993248,1.5730816,-57.859673,-192.10759,-213.25417,3.4724064,19.997528,-69.38095,463.42108,1095000
+0.6598387,190.04414,0.0013672198,2.7918404e-05,-3.9795802,0.3226657,-190.03871,190.36684,0.78486204,0.5924992,-0.050667405,-190.28035,-217.12302,1.3773613,24.681541,-12.180788,147.69653,1100000
+0.6689017,188.1778,0.0014401599,4.0104205e-05,-3.972153,0.29078078,-188.17209,188.46863,0.4201704,0.6729398,-7.36483,-188.16199,-217.90253,1.0931102,8.0911665,-8.599931,74.561325,1105000
+0.66448045,189.94327,0.0015083586,-0.00049707206,-4.329545,0.23297119,-189.93674,190.17574,1.0593961,1.0832864,-11.85798,-190.21495,-233.63394,2.1426826,48.997265,-15.880972,174.48505,1110000
+0.67627186,190.35822,0.001347707,0.00084221986,-3.375072,0.22161119,-190.35367,190.58067,2.2883737,2.0578787,-4.8134384,-190.5065,-214.75435,4.3462524,42.730873,-24.387875,269.34946,1115000
+0.66685295,193.12125,0.0014601881,0.00026000882,-3.8219347,0.26266205,-193.11566,193.38417,0.16676429,0.98075736,-97.647,-193.04195,-247.3496,1.1475216,10.800113,-17.23329,92.64795,1120000
+0.66627765,190.41916,0.0013146525,0.0010344008,-3.2131755,0.27061874,-190.41493,190.69081,0.67099696,0.78791094,-33.85355,-190.38885,-244.3015,1.4589078,10.798989,-4.3345947,65.16589,1125000
+0.67118853,189.5802,0.0012623112,0.0005638565,-3.5533142,0.26051277,-189.57573,189.84128,0.7411753,0.63668555,-27.95183,-189.81656,-214.09929,1.3778608,13.001288,-21.486979,157.49876,1130000
+0.65836394,190.77264,0.0012720837,-0.00027789467,-4.2184563,0.2959562,-190.76727,191.06833,0.8031139,0.85669345,-37.383556,-190.82751,-214.35652,1.6598073,8.1926155,-7.1994634,104.15196,1135000
+0.68248564,191.42633,0.0013499948,0.0013826598,-2.9758036,0.25742856,-191.42232,191.68515,0.8130831,0.66873485,1.4317799,-191.58405,-212.47087,1.481818,5.2539363,-9.594331,84.76933,1140000
+0.6392376,189.36014,0.0013014761,-0.0016322797,-5.2541757,0.28441864,-189.35333,189.64293,0.43193492,0.7436334,-18.679031,-189.41768,-251.01382,1.1755683,7.1861286,-3.9311998,69.36913,1145000
+0.64919066,184.95251,0.0012526044,-0.002243931,-5.7914124,0.25986463,-184.94525,185.21013,0.84978676,1.8735698,0.27170628,-185.0589,-204.44916,2.7233567,21.598,-33.59946,294.99158,1150000
+0.6597236,189.57436,0.0012771143,-0.00061008084,-4.4777026,0.32273877,-189.56863,189.89648,2.9141777,5.4779234,1.667577,-189.55591,-234.37668,8.392101,30.372005,-84.79362,453.575,1155000
+0.6749132,189.64938,0.0012369944,-0.00064204616,-4.5190372,0.2931791,-189.6438,189.94193,0.38102135,0.76711076,-1.7493392,-189.78336,-247.8672,1.1481321,4.5541487,-4.370795,58.173965,1160000
+0.6655092,190.97705,0.0011615938,-0.00038100174,-4.327999,0.28659034,-190.97202,191.26326,0.311079,0.87677187,-24.006998,-191.02011,-214.88992,1.1878508,3.7479076,-4.9446497,53.75477,1165000
+0.66519606,190.3818,0.0012671093,-4.347918e-05,-4.0343137,0.274042,-190.37671,190.6558,0.2267448,0.49521905,-26.290535,-190.41014,-225.91382,0.7219639,2.2064772,-2.2971284,39.690643,1170000
+0.6617087,190.34929,0.0011696838,0.00038152075,-3.6738257,0.22797115,-190.345,190.57764,0.3210545,0.35332286,-76.09387,-190.50029,-212.08316,0.6743773,3.2716641,-3.740558,42.404503,1175000
+0.66133964,189.70134,0.0012024611,-0.0006727147,-4.5594482,0.28482372,-189.69586,189.98549,0.8287762,1.2667581,0.48656368,-189.99063,-212.00146,2.0955343,11.814021,-12.111546,102.44026,1180000
+0.6837146,191.03186,0.0012397142,0.0004986819,-3.5977445,0.26172853,-191.0274,191.2941,0.63298005,1.5542353,-20.14326,-190.92271,-209.144,2.1872153,54.73885,-17.374237,255.26596,1185000
+0.6707122,190.00084,0.0011806956,-5.7791904e-06,-4.0048947,0.2818805,-189.99611,190.28271,0.4184896,1.4286385,-11.16553,-190.13802,-239.59248,1.847128,15.29461,-15.0350685,131.18906,1190000
+0.67773324,193.20819,0.0012139466,0.00010539326,-3.9131813,0.27168724,-193.20345,193.47998,0.7387132,1.0139034,-83.011894,-193.4551,-210.87872,1.7526166,10.676398,-4.58529,86.25931,1195000
+0.67332935,192.37689,0.001152424,-0.00021327256,-4.1850643,0.26480478,-192.37207,192.64148,0.6991269,0.4858663,-9.117987,-192.50816,-209.39565,1.1849933,6.0323095,-3.6899495,62.18177,1200000

O2O-w-diff-ckpts/dsrl/20260317_155656/params_1000000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277dc826e2403116295014396cfdef95092081c9b23b19cde8f603cfd0dcec95
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_1050000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df18de7d9bc80924ecc5904f6561b5ee7d45bf8477aedd1de815279dc980dbc2
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_1100000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd22e0aca352cf4364b2c6abe648d622fa0292b1f9e3bf3d1f9f001cbbc4a96
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_1150000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a50d48c91e44780bc1eff38e0906004edb703cccb30d4a1d796c3a70dbf4d7
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_1200000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ec2c7e8206274840368d71f89a31d5cbb3ae85aa254666b406ca80132ac7fd
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_750000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937ae43dc854c7e68da9dca12a6de4ea5cd9a4f86636f3a9b76a473c93792285
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_800000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe24eff0aedb79b4d29026efa5c14d613edbd2b8faa31c00ad4cd1e0a337d5c4
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_850000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10cd604a0a229ed296056a2218296f04fd20724cca618773892b93ed9d79a951
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_900000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7907afb8aba2b9d839bf8b5822815f070c4888ff0c3d6c4526c054f02cee008
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/params_950000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f6b5a0fe0a94c88693385233e07c46f32616e12a957240a8aab4176db98583
+size 321574838

O2O-w-diff-ckpts/dsrl/20260317_155656/progress.tk

@@ -0,0 +1 @@
+online,500000

O2O-w-diff-ckpts/dsrl/20260317_155656/token.tk

@@ -0,0 +1 @@
+https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/ata8b58q