Tiredsheep commited on
Commit
5d07bce
·
verified ·
1 Parent(s): 22f0d36

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +10 -0
  2. O2O-w-diff-ckpts/dsrl/20260317_054138/env.csv +0 -0
  3. O2O-w-diff-ckpts/dsrl/20260317_054138/env_sv.csv +0 -0
  4. O2O-w-diff-ckpts/dsrl/20260317_054138/eval.csv +11 -0
  5. O2O-w-diff-ckpts/dsrl/20260317_054138/eval_sv.csv +11 -0
  6. O2O-w-diff-ckpts/dsrl/20260317_054138/online_agent.csv +101 -0
  7. O2O-w-diff-ckpts/dsrl/20260317_054138/online_agent_sv.csv +101 -0
  8. O2O-w-diff-ckpts/dsrl/20260317_054138/params_1000000.pkl +3 -0
  9. O2O-w-diff-ckpts/dsrl/20260317_054138/params_550000.pkl +3 -0
  10. O2O-w-diff-ckpts/dsrl/20260317_054138/params_600000.pkl +3 -0
  11. O2O-w-diff-ckpts/dsrl/20260317_054138/params_650000.pkl +3 -0
  12. O2O-w-diff-ckpts/dsrl/20260317_054138/params_700000.pkl +3 -0
  13. O2O-w-diff-ckpts/dsrl/20260317_054138/params_750000.pkl +3 -0
  14. O2O-w-diff-ckpts/dsrl/20260317_054138/params_800000.pkl +3 -0
  15. O2O-w-diff-ckpts/dsrl/20260317_054138/params_850000.pkl +3 -0
  16. O2O-w-diff-ckpts/dsrl/20260317_054138/params_900000.pkl +3 -0
  17. O2O-w-diff-ckpts/dsrl/20260317_054138/params_950000.pkl +3 -0
  18. O2O-w-diff-ckpts/dsrl/20260317_054138/progress.tk +1 -0
  19. O2O-w-diff-ckpts/dsrl/20260317_054138/token.tk +1 -0
  20. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_1000000.png +3 -0
  21. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_550000.png +3 -0
  22. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_600000.png +3 -0
  23. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_650000.png +3 -0
  24. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_700000.png +3 -0
  25. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_750000.png +3 -0
  26. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_800000.png +3 -0
  27. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_850000.png +3 -0
  28. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_900000.png +3 -0
  29. O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_950000.png +3 -0
.gitattributes CHANGED
@@ -543,3 +543,13 @@ O2O-w-diff-ckpts/cgql/20260317_223700/visited_states_1300000.png filter=lfs diff
543
  O2O-w-diff-ckpts/cgql/20260317_223700/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
544
  O2O-w-diff-ckpts/cgql/20260317_223700/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
545
  O2O-w-diff-ckpts/cgql/20260317_223700/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
543
  O2O-w-diff-ckpts/cgql/20260317_223700/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
544
  O2O-w-diff-ckpts/cgql/20260317_223700/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
545
  O2O-w-diff-ckpts/cgql/20260317_223700/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
546
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_1000000.png filter=lfs diff=lfs merge=lfs -text
547
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_550000.png filter=lfs diff=lfs merge=lfs -text
548
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_600000.png filter=lfs diff=lfs merge=lfs -text
549
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_650000.png filter=lfs diff=lfs merge=lfs -text
550
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_700000.png filter=lfs diff=lfs merge=lfs -text
551
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_750000.png filter=lfs diff=lfs merge=lfs -text
552
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_800000.png filter=lfs diff=lfs merge=lfs -text
553
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
554
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
555
+ O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
O2O-w-diff-ckpts/dsrl/20260317_054138/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/dsrl/20260317_054138/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/dsrl/20260317_054138/eval.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 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
2
+ 0.0,0.0,15.1539314881915,2.088214492887367,0.038409404877659675,2.0875543539537342,-0.00836405831537267,0.0,25500.0,-1.0,-1000.0,1000.0,1.5979345703125,550000
3
+ 0.0,0.0,15.446768698464782,2.086587722565154,-0.002413834179939468,2.085030762492805,0.044109665681005765,0.0,77500.0,-1.0,-1000.0,1000.0,1.5871505069732665,600000
4
+ 0.0,0.0,13.401207413045045,1.7801180978737436,-0.03038743764739102,1.7793199601535399,-0.00150269244006949,0.0,129500.0,-1.0,-1000.0,1000.0,1.5972118139266969,650000
5
+ 0.0,0.0,19.8181457646422,2.686270210800407,0.03760915042841794,2.6915981039650956,0.0569531170251842,0.0,181500.0,-1.0,-1000.0,1000.0,1.6075196695327758,700000
6
+ 0.0,0.0,24.752018770966018,3.3285201703411276,0.039335817917762445,3.328605220008997,-0.007151621068294278,0.04,233352.08,-0.96,-996.94,996.98,1.6016970348358155,750000
7
+ 0.0,0.0,28.43263438915389,3.8322829897239776,0.014304574579740326,3.832832957136306,0.027161504288680832,0.1,285283.26,-0.9,-995.18,995.28,1.6021946811676024,800000
8
+ 0.0,0.0,25.45601077237084,3.4257153586810105,0.009074864792539623,3.4287529467559428,0.027242802712763615,0.1,336920.86,-0.9,-991.98,992.08,1.5761069011688233,850000
9
+ 0.0,0.0,28.489100735756622,3.849511526251458,0.028531554693627826,3.853735346831373,0.06550075315654054,0.32,387853.26,-0.68,-962.82,963.14,1.5342680883407593,900000
10
+ 0.0,0.0,26.78067637910393,3.6287143016631793,0.020515598293663877,3.632193077635425,0.0686973447511531,0.18,438403.7,-0.82,-982.84,983.02,1.5724893522262573,950000
11
+ 0.0,0.0,24.08975251717619,3.2506850169165045,0.05609145881467624,3.255095379863493,0.06608243067726632,0.22,489557.6,-0.78,-978.06,978.28,1.5713529253005982,1000000
O2O-w-diff-ckpts/dsrl/20260317_054138/eval_sv.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 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
2
+ 0.0,0.0,15.1539314881915,2.088214492887367,0.038409404877659675,2.0875543539537342,-0.00836405831537267,0.0,25500.0,-1.0,-1000.0,1000.0,1.5979345703125,550000
3
+ 0.0,0.0,15.446768698464782,2.086587722565154,-0.002413834179939468,2.085030762492805,0.044109665681005765,0.0,77500.0,-1.0,-1000.0,1000.0,1.5871505069732665,600000
4
+ 0.0,0.0,13.401207413045045,1.7801180978737436,-0.03038743764739102,1.7793199601535399,-0.00150269244006949,0.0,129500.0,-1.0,-1000.0,1000.0,1.5972118139266969,650000
5
+ 0.0,0.0,19.8181457646422,2.686270210800407,0.03760915042841794,2.6915981039650956,0.0569531170251842,0.0,181500.0,-1.0,-1000.0,1000.0,1.6075196695327758,700000
6
+ 0.0,0.0,24.752018770966018,3.3285201703411276,0.039335817917762445,3.328605220008997,-0.007151621068294278,0.04,233352.08,-0.96,-996.94,996.98,1.6016970348358155,750000
7
+ 0.0,0.0,28.43263438915389,3.8322829897239776,0.014304574579740326,3.832832957136306,0.027161504288680832,0.1,285283.26,-0.9,-995.18,995.28,1.6021946811676024,800000
8
+ 0.0,0.0,25.45601077237084,3.4257153586810105,0.009074864792539623,3.4287529467559428,0.027242802712763615,0.1,336920.86,-0.9,-991.98,992.08,1.5761069011688233,850000
9
+ 0.0,0.0,28.489100735756622,3.849511526251458,0.028531554693627826,3.853735346831373,0.06550075315654054,0.32,387853.26,-0.68,-962.82,963.14,1.5342680883407593,900000
10
+ 0.0,0.0,26.78067637910393,3.6287143016631793,0.020515598293663877,3.632193077635425,0.0686973447511531,0.18,438403.7,-0.82,-982.84,983.02,1.5724893522262573,950000
11
+ 0.0,0.0,24.08975251717619,3.2506850169165045,0.05609145881467624,3.255095379863493,0.06608243067726632,0.22,489557.6,-0.78,-978.06,978.28,1.5713529253005982,1000000
O2O-w-diff-ckpts/dsrl/20260317_054138/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 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
2
+ 0.63704056,172.68146,0.005568238,-0.0014906396,-4.267704,0.34527475,-172.6577,173.02524,1.5810488,2.8784258,2.536345,-173.10855,-273.32114,4.4594746,5.653263,-12.180874,135.82132,505000
3
+ 0.63981926,173.46613,0.0050929277,0.0004870497,-3.9043674,0.39212477,-173.44623,173.85873,1.2523123,1.3765509,-0.6253342,-173.83003,-331.78745,2.6288633,3.9857726,-4.0958614,92.15857,510000
4
+ 0.63971126,179.77234,0.005219775,0.002388307,-3.5424502,0.33938706,-179.75385,180.11412,0.9972378,2.3639297,-3.2336879,-179.83104,-319.81046,3.3611674,5.5261626,-5.853299,112.92213,515000
5
+ 0.64353037,175.94241,0.0055062664,0.002748885,-3.5007715,0.29334772,-175.92316,176.23851,1.0827324,1.0742651,-20.420893,-176.251,-258.48325,2.1569977,3.4647691,-4.742348,72.91887,520000
6
+ 0.64608985,180.78452,0.0050581275,-0.002453002,-4.4849625,0.30202872,-180.76183,181.08409,1.5261774,1.9871594,2.1344717,-180.84729,-1337.966,3.5133367,3.9631171,-3.927553,112.39899,525000
7
+ 0.62303054,175.82486,0.0044799387,0.00017158502,-3.9616992,0.31660116,-175.80713,176.14163,1.06886,1.428377,0.6566494,-176.1303,-268.82538,2.4972372,5.569451,-7.400394,110.02732,530000
8
+ 0.64864236,176.24318,0.004918695,0.0023254806,-3.527216,0.35123688,-176.22583,176.59674,1.7345494,1.4776616,1.2366979,-176.37944,-269.56674,3.2122111,4.0883303,-5.38965,95.009796,535000
9
+ 0.65486157,175.4672,0.0047375946,-0.0018066774,-4.381349,0.31768876,-175.44643,175.78308,6.974415,18.215546,3.353236,-175.88103,-273.83615,25.18996,1076.2538,-273.1936,2878.6177,540000
10
+ 0.6408864,176.30917,0.0045374264,-0.0016417975,-4.3618345,0.30725488,-176.2894,176.61478,1.0124514,1.4863526,-4.104755,-176.50867,-274.01477,2.498804,3.5159867,-3.9683585,81.99196,545000
11
+ 0.6389148,181.87201,0.0047284425,0.0007980658,-3.8312201,0.3106472,-181.85388,182.18346,0.7785124,0.9088232,-1.2937614,-182.10559,-1193.4249,1.6873356,5.6091304,-3.4095366,84.111145,550000
12
+ 0.6415953,182.24783,0.0047710626,-0.0011670443,-4.244609,0.30640793,-182.2276,182.55309,1.6204166,2.0459473,1.2423189,-182.64725,-1153.7437,3.666364,6.2670307,-7.222324,172.11353,555000
13
+ 0.6386602,181.96906,0.0045444677,-0.0036109018,-4.794571,0.3470077,-181.94727,182.31244,1.5699705,2.6099389,-39.254215,-181.98253,-1115.2194,4.179909,6.6510386,-4.589148,139.4181,560000
14
+ 0.6545363,180.09561,0.0047630114,0.002154039,-3.547757,0.3184762,-180.0787,180.41624,2.8145616,4.471589,-5.864073,-180.29402,-347.57535,7.286151,193.03964,-71.38838,696.0832,565000
15
+ 0.64477855,183.00623,0.004559047,-0.0017965452,-4.3940616,0.31536126,-182.9862,183.3198,1.7819748,7.5409503,-5.313883,-183.01509,-948.54517,9.322926,10.37472,-8.351334,156.35347,570000
16
+ 0.6518612,181.57729,0.0049741077,0.0007044327,-3.85838,0.34529242,-181.5581,181.92328,0.67230827,1.1564744,1.8660059,-181.95206,-379.30997,1.8287826,5.663767,-2.3251193,66.585106,575000
17
+ 0.65015537,179.28282,0.0049622534,4.7288245e-06,-3.999047,0.32391173,-179.26299,179.60674,0.8943987,2.991659,-3.3414752,-179.68155,-375.34515,3.8860576,33.57468,-28.491556,244.55971,580000
18
+ 0.64875436,186.04947,0.004645538,-0.0014594705,-4.314166,0.3115008,-186.02942,186.35951,1.0524393,2.2988403,-3.7776146,-186.07455,-817.05695,3.3512797,10.377242,-6.4261255,125.54842,585000
19
+ 0.64300954,177.656,0.0046110963,-0.0011027746,-4.2391567,0.31016174,-177.63647,177.96507,1.6249396,3.0614567,-12.637913,-177.97977,-312.01962,4.686396,11.929806,-16.28604,155.23853,590000
20
+ 0.64306927,178.28812,0.004295318,-0.0052107135,-5.2131147,0.31137386,-178.26573,178.59428,2.594013,9.171195,0.9441607,-178.28868,-713.9005,11.765208,279.1766,-247.28322,1639.0293,595000
21
+ 0.64677924,178.01096,0.0045511797,0.0011822314,-3.7402363,0.3404982,-177.99393,178.35263,1.5946294,2.0337846,-1.6762562,-178.14299,-297.94437,3.6284142,5.462074,-8.433543,128.39708,600000
22
+ 0.64051014,182.15952,0.0043903715,-0.0012729669,-4.289945,0.33557025,-182.14066,182.49382,1.6644766,2.1186364,-4.2278743,-182.3419,-471.1939,3.783113,5.655275,-7.8138776,120.68301,605000
23
+ 0.6337491,179.78148,0.0042675817,-0.0036081304,-4.8454742,0.31143677,-179.7608,180.08931,1.124002,5.278055,-9.36452,-180.08704,-583.1947,6.402057,105.7918,-165.48067,782.6417,610000
24
+ 0.64719766,184.35416,0.0045705135,-0.0019773373,-4.432629,0.28032506,-184.33391,184.63249,0.797017,0.9508938,-5.0430236,-184.43468,-369.45575,1.7479107,3.520837,-2.2633967,64.72811,615000
25
+ 0.6526998,183.81992,0.0042402996,0.00215031,-3.4928873,0.3088707,-183.80511,184.13094,0.7779123,1.4095594,-11.902292,-184.49498,-371.46072,2.1874716,3.3418376,-2.1094756,80.90558,620000
26
+ 0.6434793,179.72107,0.004134054,-0.00017452052,-4.0422153,0.28914356,-179.70435,180.01004,0.6219792,0.9398618,-27.584486,-180.15031,-367.79987,1.561841,9.85242,-5.150415,65.39648,625000
27
+ 0.65122116,179.60947,0.004122721,-0.00070776505,-4.1716743,0.28042114,-179.59227,179.88919,2.1435068,1.850869,-8.40634,-179.99788,-275.8481,3.9943757,7.027765,-13.054695,155.65448,630000
28
+ 0.66404665,184.71405,0.0038759566,0.0027211707,-3.2979357,0.3286185,-184.70128,185.04538,0.58653957,1.2581071,-73.30088,-184.758,-449.593,1.8446467,2.2987669,-2.9432223,73.8465,635000
29
+ 0.66122025,181.52902,0.0040601976,0.0004520413,-3.8886652,0.28982735,-181.51321,181.8193,0.61316687,0.97412235,-8.465174,-181.94943,-312.24722,1.5872892,3.8927462,-3.0396166,75.53074,640000
30
+ 0.6471399,177.32971,0.003975006,-0.0006265118,-4.157613,0.30281478,-177.3132,177.6319,0.8483,1.24182,-3.7949743,-177.61736,-306.6334,2.0901198,5.7462063,-3.1020672,74.55975,645000
31
+ 0.665399,181.57402,0.0038908983,0.0021949736,-3.4358697,0.31276247,-181.56067,181.88898,1.893742,0.7287103,-12.646954,-181.83586,-302.1868,2.6224523,2.148365,-2.9363465,62.296394,650000
32
+ 0.6605941,180.44046,0.0036986787,0.0016912089,-3.5427532,0.35607034,-180.42737,180.79822,1.1721592,1.4826334,-6.058944,-180.4731,-262.19943,2.6547925,6.981049,-8.144122,89.91376,655000
33
+ 0.6539801,175.28485,0.0038046518,-0.0008624377,-4.22668,0.30897456,-175.26875,175.59296,0.9202854,2.9899604,0.73112446,-175.67276,-292.67728,3.910246,21.573925,-13.437153,201.14182,660000
34
+ 0.66780525,182.91751,0.0036891093,0.0019165293,-3.48049,0.31018904,-182.9047,183.22963,0.5313732,0.91637576,-39.79789,-183.06297,-325.5538,1.4477489,2.3349123,-1.8937906,55.223976,665000
35
+ 0.66319644,180.50568,0.0037212945,0.0014980434,-3.5974402,0.29078025,-180.49228,180.79796,0.9992382,1.3089653,-0.6621237,-180.7542,-342.4005,2.3082035,5.639639,-8.727231,108.02182,670000
36
+ 0.6615773,180.13864,0.0035009054,0.0003388003,-3.903225,0.31315812,-180.12497,180.45213,0.5117052,0.6904535,-35.80043,-180.2747,-254.28989,1.2021587,2.1619124,-1.7015254,46.860386,675000
37
+ 0.6489575,174.8408,0.003527396,-0.0018972012,-4.5378475,0.32111257,-174.82478,175.16002,0.768773,1.2722,-0.8097933,-175.19194,-252.56764,2.040973,4.075497,-3.1640968,68.48954,680000
38
+ 0.6608804,182.6618,0.0033688755,0.0001477748,-3.9561353,0.29798037,-182.64847,182.95993,0.9513585,1.0909111,-3.14435,-182.8513,-403.97214,2.0422697,2.661257,-2.9717462,71.55664,685000
39
+ 0.65993476,178.4072,0.0033810176,-0.00031591603,-4.093438,0.3077386,-178.39337,178.71461,0.74309635,1.5877607,-42.26664,-178.50748,-340.36374,2.330857,14.673603,-11.508816,109.70051,690000
40
+ 0.6535851,181.49127,0.0034272755,0.00013162594,-3.9615946,0.33864182,-181.47769,181.83005,1.1372117,1.2859102,-0.12007165,-181.5714,-271.91797,2.423122,14.064836,-11.252796,142.34518,695000
41
+ 0.66051865,178.37088,0.0033783102,-0.00075274153,-4.222816,0.33621538,-178.35661,178.70634,2.0760562,3.9224262,-1.1425408,-178.81876,-377.3742,5.9984827,24.532536,-23.622345,294.60526,700000
42
+ 0.6607219,177.60135,0.003221856,-7.8607896e-05,-4.0243983,0.30701855,-177.5884,177.9083,0.6779539,0.8310853,-15.519812,-177.81041,-266.7507,1.5090392,2.9157777,-4.613861,65.13596,705000
43
+ 0.66264254,180.77829,0.0032350197,8.7555934e-05,-3.972935,0.27354592,-180.76544,181.05193,0.49016628,0.7130419,-22.15641,-180.92516,-250.55498,1.2032082,1.3073505,-1.269218,41.725044,710000
44
+ 0.6758112,183.9049,0.0031903263,0.00289301,-3.093193,0.3050747,-183.89505,184.21288,0.5117387,0.7201163,1.8993669,-184.16602,-316.3831,1.231855,1.7795631,-1.6681516,48.740746,715000
45
+ 0.6595159,181.65974,0.0030932678,-0.00070978637,-4.2294617,0.2780378,-181.64667,181.93706,0.8924387,0.9733597,-0.10182923,-181.7769,-270.93253,1.8657985,1.8007283,-2.9697492,48.377052,720000
46
+ 0.6687963,180.23474,0.0032967033,0.001751545,-3.468698,0.28697678,-180.2233,180.52347,0.5346902,0.7592651,1.3355873,-180.15593,-231.95628,1.2939553,1.7877051,-2.4449072,50.2543,725000
47
+ 0.67068577,181.86395,0.00312089,0.0021070053,-3.3248703,0.27635795,-181.85358,182.14241,0.4756421,0.94529766,-19.756443,-181.86998,-259.54898,1.4209398,2.977397,-3.7031858,58.801086,730000
48
+ 0.6718178,182.92567,0.0029559222,0.0018217555,-3.383693,0.29629156,-182.91568,183.22379,0.70864844,0.82708055,2.9513607,-183.1418,-235.43146,1.5357289,3.3873973,-3.7972262,61.651352,735000
49
+ 0.66551805,184.7251,0.0031389368,0.0012948485,-3.5874882,0.26810068,-184.71382,184.99449,0.8781358,1.7418072,-47.619797,-184.77483,-278.7365,2.6199431,10.308254,-5.611003,94.79639,740000
50
+ 0.6567745,184.32965,0.0028673017,-8.644896e-05,-4.03015,0.2515376,-184.3181,184.5811,0.42389274,0.6186901,-21.09283,-184.3283,-308.8487,1.0425828,3.8442934,-1.5136876,44.560722,745000
51
+ 0.67019606,182.476,0.0029271182,-0.0005255646,-4.17955,0.2364057,-182.46376,182.71188,0.7291565,1.0955768,-2.3747,-182.9511,-298.60025,1.8247333,3.1963232,-3.7759032,71.342926,750000
52
+ 0.65053403,180.16095,0.0028133465,-0.002140693,-4.760906,0.3123824,-180.14755,180.47119,0.44028106,0.51200783,0.40595567,-180.30602,-291.1606,0.95228887,1.2025484,-1.4662485,38.37507,755000
53
+ 0.66322553,181.01517,0.0027970022,0.0013354297,-3.5225496,0.30802584,-181.00531,181.32454,0.45580983,0.702692,-1.2850101,-181.18823,-232.20978,1.1585019,7.001488,-3.9892735,73.82751,760000
54
+ 0.6628042,184.1684,0.002912062,-9.897516e-05,-4.033988,0.31119475,-184.15665,184.47949,0.64490926,0.95710105,-68.35413,-184.05145,-250.33179,1.6020103,5.151052,-13.341756,77.25849,765000
55
+ 0.6543245,182.59317,0.002868427,-0.0029919615,-5.043067,0.32137698,-182.5787,182.91156,0.49781132,0.80456156,-5.8762407,-182.875,-267.01715,1.3023729,3.0164094,-1.6238742,47.181313,770000
56
+ 0.6782483,182.21944,0.0027533234,0.0019719838,-3.2837806,0.28310508,-182.2104,182.50452,0.7767435,0.799242,-19.291502,-182.35986,-226.77682,1.5759854,12.270592,-5.4877033,96.63354,775000
57
+ 0.6620662,182.83546,0.0026156572,-0.00039992956,-4.1528983,0.30596873,-182.82458,183.14104,0.52364343,0.8709242,0.39585227,-182.8809,-253.70384,1.3945676,6.573963,-6.9766884,79.576256,780000
58
+ 0.65475416,181.83844,0.002578013,-0.0014536321,-4.5638576,0.3041646,-181.82668,182.14116,0.8758265,0.68748254,-0.8092253,-181.93729,-284.45175,1.563309,14.436024,-4.554233,82.75136,785000
59
+ 0.67158425,187.42772,0.0024119045,-0.0006684804,-4.2771587,0.30603206,-187.4174,187.73308,0.31925502,0.99197143,-24.464684,-187.64153,-215.241,1.3112265,5.1898317,-3.4609902,63.67356,790000
60
+ 0.66107595,183.62491,0.002448185,-0.0018061452,-4.7377486,0.28672147,-183.61331,183.90984,0.42208004,0.74737495,0.23236293,-183.8736,-226.614,1.169455,2.1553836,-3.0851126,50.459442,795000
61
+ 0.66199595,185.64557,0.0024262185,0.0012315903,-3.4923828,0.2804917,-185.63708,185.92729,0.46831018,0.9244218,-60.261307,-186.009,-219.8921,1.3927319,7.359783,-5.1387167,83.06351,800000
62
+ 0.6562557,186.92673,0.002412726,5.2993866e-05,-3.9780357,0.3265991,-186.91711,187.25337,0.3578708,0.77054566,-10.096821,-186.81267,-222.28084,1.1284164,6.011696,-4.6593494,67.209114,805000
63
+ 0.6744156,186.78699,0.002322089,0.00093445403,-3.5975804,0.27911577,-186.77863,187.06703,0.5532755,0.49926144,-49.13274,-186.86784,-225.94441,1.052537,1.3686887,-2.0050704,39.17994,810000
64
+ 0.6615092,181.52359,0.0023487532,0.0003683008,-3.843193,0.31246302,-181.51456,181.83643,0.89809626,1.6315901,-0.37009257,-181.64587,-222.99968,2.5296865,14.403782,-8.337594,121.08943,815000
65
+ 0.6729023,186.96558,0.002386776,0.0010892077,-3.543649,0.26504827,-186.95712,187.2317,0.7458691,1.4052229,4.676727,-187.24583,-227.45851,2.151092,10.253995,-13.310304,160.95294,820000
66
+ 0.6606271,182.28949,0.002218292,-0.0005444587,-4.2454405,0.2687757,-182.28008,182.55771,1.2431574,1.7692826,-32.702152,-182.33951,-216.60524,3.01244,8.406172,-7.262328,114.43327,825000
67
+ 0.667366,185.93874,0.0022512071,-0.0003835341,-4.170368,0.30207682,-185.92935,186.24043,0.54161185,0.8484365,-26.229898,-186.12016,-223.92302,1.3900483,5.1935587,-4.405667,68.67694,830000
68
+ 0.6556363,184.45123,0.0021465984,-0.0013487317,-4.628311,0.29543665,-184.4413,184.74533,0.7812212,1.231665,-19.474258,-184.46294,-215.59732,2.0128863,33.371067,-11.020658,163.48758,835000
69
+ 0.67327344,187.47089,0.0021255773,0.00064838736,-3.6949594,0.29356995,-187.46303,187.76509,1.6202837,1.2185011,-8.141873,-187.61989,-211.69183,2.8387847,8.444018,-10.02328,141.8413,840000
70
+ 0.66903645,187.73251,0.0021201991,0.0011729453,-3.446776,0.290177,-187.7252,188.02386,0.46659786,1.4058058,-31.543983,-187.52257,-220.84105,1.8724036,7.239326,-2.9912012,86.67843,845000
71
+ 0.6743864,189.5454,0.0021103842,0.0010302305,-3.511828,0.27644166,-189.538,189.82288,0.9234064,0.7088705,0.22374278,-189.68152,-246.82101,1.6322769,2.5677943,-3.0591826,55.473877,850000
72
+ 0.65554214,185.6628,0.0021374598,-0.00078806723,-4.3686934,0.29234114,-185.65344,185.95435,0.7085871,1.7029192,0.3272732,-186.09991,-218.89053,2.4115064,8.022858,-8.402829,139.68697,855000
73
+ 0.665993,189.30756,0.0021509747,0.00037886566,-3.8238633,0.28102088,-189.29932,189.58896,0.39030516,0.9524932,-27.640364,-189.39885,-214.01974,1.3427984,4.532054,-6.405879,80.599884,860000
74
+ 0.6534803,187.89163,0.0020084875,-0.0012369978,-4.6158853,0.28597426,-187.88235,188.17638,0.39597675,0.66354686,-1.0122902,-188.01183,-219.66214,1.0595236,5.796769,-4.79772,68.88988,865000
75
+ 0.67004365,186.90277,0.002059101,-0.00035540824,-4.1726036,0.2569776,-186.89417,187.1594,1.2424068,1.9119419,1.8751718,-186.93842,-219.40631,3.1543489,9.398819,-7.5221257,127.59928,870000
76
+ 0.66898215,188.9762,0.002008653,0.0017692293,-3.1191962,0.22327222,-188.96994,189.20123,0.45694062,0.5791428,1.341844,-188.84268,-215.71547,1.0360835,5.017931,-3.8860092,58.316025,875000
77
+ 0.6711163,186.27899,0.0020060132,-0.00088978076,-4.443557,0.28583884,-186.2701,186.56395,0.8227528,1.5518748,-12.160845,-186.26543,-211.07556,2.3746276,8.108567,-11.679619,137.41809,880000
78
+ 0.651449,186.37753,0.0019012439,-0.0018552311,-4.9757986,0.2561307,-186.3681,186.6318,0.7622844,1.7066475,-17.500776,-186.51534,-210.52895,2.468932,11.062569,-13.847535,147.74991,885000
79
+ 0.6550098,185.83702,0.0018322557,-0.0008096472,-4.4418855,0.29388732,-185.82889,186.1301,1.0369444,1.5768964,2.316952,-185.86095,-244.25432,2.6138408,12.976603,-35.225624,161.16232,890000
80
+ 0.6606079,189.29916,0.0018779616,-2.7982018e-05,-4.0149,0.26667008,-189.29163,189.5658,0.70349944,0.8636551,-14.724599,-189.52527,-215.38042,1.5671545,6.1827335,-3.2515283,75.243095,895000
81
+ 0.6472118,187.22919,0.0018618054,-0.000477099,-4.256256,0.3094131,-187.22127,187.53813,0.9274532,0.6077428,-0.17624438,-187.40965,-210.47272,1.5351961,6.0090346,-6.1954236,82.36924,900000
82
+ 0.67816544,189.05174,0.0018081033,0.00061754236,-3.6584585,0.29231966,-189.04512,189.34467,0.4100903,0.5543047,-2.2709956,-189.16466,-262.73715,0.96439505,4.827779,-3.094995,56.487206,905000
83
+ 0.6572523,186.65297,0.0018622351,0.0006266105,-3.663517,0.28644434,-186.64615,186.94003,0.83532184,1.5704268,-2.9094045,-186.96454,-214.01659,2.4057486,9.5023155,-15.830365,180.65271,910000
84
+ 0.6732341,190.96443,0.0017908453,0.0023163324,-2.7065704,0.32655627,-190.9596,191.2933,0.61612916,2.3195615,-1.3218482,-191.03717,-219.9522,2.9356906,18.20665,-11.349497,160.54959,915000
85
+ 0.6487163,187.9651,0.0017298077,-0.0021992023,-5.2713566,0.27435738,-187.95601,188.23726,2.9567356,3.835732,2.5915718,-188.13042,-246.25883,6.7924676,25.116564,-58.25962,449.53625,920000
86
+ 0.6753124,190.13849,0.0017766412,0.0016133639,-3.0919023,0.26188117,-190.133,190.402,0.82806283,0.84312916,-30.934772,-190.34996,-285.3355,1.6711919,13.849997,-4.2790203,102.19084,925000
87
+ 0.6780982,190.95831,0.0016991424,0.00094192306,-3.445648,0.23751327,-190.95245,191.19678,0.54972976,1.0019674,-22.043144,-191.06212,-299.11972,1.5516973,7.7319393,-5.535671,87.99416,930000
88
+ 0.6671511,189.37637,0.001679024,0.00056231295,-3.6650953,0.26544353,-189.37021,189.64238,0.6422019,0.8318454,-45.503246,-189.64119,-220.3242,1.4740473,7.850281,-9.989333,123.594154,935000
89
+ 0.66878355,190.73236,0.0016061709,0.000863337,-3.4624875,0.3052559,-190.7268,191.03848,0.777821,0.8395387,1.8923812,-190.9742,-217.7134,1.6173596,15.524619,-8.802437,124.52517,940000
90
+ 0.6586511,189.32849,0.0016299427,-0.00040502578,-4.248491,0.27628085,-189.32158,189.60435,0.42138734,1.7752389,-16.560669,-189.30376,-299.11932,2.1966262,10.51325,-12.986462,131.0337,945000
91
+ 0.647382,185.70047,0.0015392214,-0.00089315197,-4.580262,0.29544663,-185.69342,185.99501,1.1449589,1.2345687,0.16789794,-185.61148,-210.00433,2.3795276,17.532055,-53.34354,185.071,950000
92
+ 0.6766742,189.36829,0.0016243254,0.000891862,-3.450934,0.24888355,-189.36269,189.61806,0.7391076,0.90062904,-1.7399527,-189.14056,-218.6423,1.6397367,13.953127,-6.360866,119.72951,955000
93
+ 0.66717434,188.25554,0.0016995379,-0.0011367666,-4.668868,0.26315898,-188.24759,188.51756,0.665703,0.8535184,-33.32986,-188.26753,-290.46902,1.5192214,9.460906,-13.686193,119.89159,960000
94
+ 0.66711015,189.4623,0.0016091046,0.00038717606,-3.7593842,0.3192395,-189.45624,189.78192,0.32618764,0.5042482,-24.478836,-189.72,-209.0928,0.8304359,3.7542155,-5.6926146,61.16417,965000
95
+ 0.6578791,188.26773,0.0016249078,-0.000526098,-4.323771,0.26387662,-188.26071,188.53108,0.5661728,0.77391684,-18.587093,-188.44017,-210.19363,1.3400896,16.943092,-24.635355,117.95216,970000
96
+ 0.66835773,190.22101,0.0014332721,0.00018242073,-3.8727243,0.25350994,-190.21547,190.4747,0.8412339,0.8782709,-1.127544,-190.37169,-222.25897,1.7195048,5.664166,-8.474815,104.18511,975000
97
+ 0.6553285,189.0329,0.0014876173,-0.0014551623,-4.9781833,0.28676838,-189.02551,189.31822,0.5670072,2.1280227,-0.6942984,-189.35472,-211.17102,2.6950297,7.969744,-10.039169,128.9953,980000
98
+ 0.676937,190.61774,0.001630801,-0.00021185112,-4.129906,0.26995218,-190.61101,190.88748,0.269561,0.45915708,-4.6473308,-190.74602,-265.44394,0.72871804,3.1917195,-2.256601,47.33716,985000
99
+ 0.67415226,190.16617,0.0014657248,0.0010486568,-3.2845473,0.29539025,-190.16138,190.46262,0.5357403,0.673454,-2.2889118,-190.18947,-213.26797,1.2091943,26.473215,-7.184746,119.189575,990000
100
+ 0.67900753,194.16399,0.0015088442,0.0017870414,-2.8156223,0.2843079,-194.15973,194.45007,0.3823631,0.4845658,-105.22764,-194.41408,-216.40463,0.86692894,3.44645,-2.2965682,54.722214,995000
101
+ 0.6861307,193.48642,0.0014972773,0.0015344934,-2.9751441,0.22278619,-193.48196,193.71075,0.4152259,0.541785,-5.3674297,-193.70319,-212.30986,0.95701087,4.162127,-4.632647,67.81322,1000000
O2O-w-diff-ckpts/dsrl/20260317_054138/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 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
2
+ 0.63704056,172.68146,0.005568238,-0.0014906396,-4.267704,0.34527475,-172.6577,173.02524,1.5810488,2.8784258,2.536345,-173.10855,-273.32114,4.4594746,5.653263,-12.180874,135.82132,505000
3
+ 0.63981926,173.46613,0.0050929277,0.0004870497,-3.9043674,0.39212477,-173.44623,173.85873,1.2523123,1.3765509,-0.6253342,-173.83003,-331.78745,2.6288633,3.9857726,-4.0958614,92.15857,510000
4
+ 0.63971126,179.77234,0.005219775,0.002388307,-3.5424502,0.33938706,-179.75385,180.11412,0.9972378,2.3639297,-3.2336879,-179.83104,-319.81046,3.3611674,5.5261626,-5.853299,112.92213,515000
5
+ 0.64353037,175.94241,0.0055062664,0.002748885,-3.5007715,0.29334772,-175.92316,176.23851,1.0827324,1.0742651,-20.420893,-176.251,-258.48325,2.1569977,3.4647691,-4.742348,72.91887,520000
6
+ 0.64608985,180.78452,0.0050581275,-0.002453002,-4.4849625,0.30202872,-180.76183,181.08409,1.5261774,1.9871594,2.1344717,-180.84729,-1337.966,3.5133367,3.9631171,-3.927553,112.39899,525000
7
+ 0.62303054,175.82486,0.0044799387,0.00017158502,-3.9616992,0.31660116,-175.80713,176.14163,1.06886,1.428377,0.6566494,-176.1303,-268.82538,2.4972372,5.569451,-7.400394,110.02732,530000
8
+ 0.64864236,176.24318,0.004918695,0.0023254806,-3.527216,0.35123688,-176.22583,176.59674,1.7345494,1.4776616,1.2366979,-176.37944,-269.56674,3.2122111,4.0883303,-5.38965,95.009796,535000
9
+ 0.65486157,175.4672,0.0047375946,-0.0018066774,-4.381349,0.31768876,-175.44643,175.78308,6.974415,18.215546,3.353236,-175.88103,-273.83615,25.18996,1076.2538,-273.1936,2878.6177,540000
10
+ 0.6408864,176.30917,0.0045374264,-0.0016417975,-4.3618345,0.30725488,-176.2894,176.61478,1.0124514,1.4863526,-4.104755,-176.50867,-274.01477,2.498804,3.5159867,-3.9683585,81.99196,545000
11
+ 0.6389148,181.87201,0.0047284425,0.0007980658,-3.8312201,0.3106472,-181.85388,182.18346,0.7785124,0.9088232,-1.2937614,-182.10559,-1193.4249,1.6873356,5.6091304,-3.4095366,84.111145,550000
12
+ 0.6415953,182.24783,0.0047710626,-0.0011670443,-4.244609,0.30640793,-182.2276,182.55309,1.6204166,2.0459473,1.2423189,-182.64725,-1153.7437,3.666364,6.2670307,-7.222324,172.11353,555000
13
+ 0.6386602,181.96906,0.0045444677,-0.0036109018,-4.794571,0.3470077,-181.94727,182.31244,1.5699705,2.6099389,-39.254215,-181.98253,-1115.2194,4.179909,6.6510386,-4.589148,139.4181,560000
14
+ 0.6545363,180.09561,0.0047630114,0.002154039,-3.547757,0.3184762,-180.0787,180.41624,2.8145616,4.471589,-5.864073,-180.29402,-347.57535,7.286151,193.03964,-71.38838,696.0832,565000
15
+ 0.64477855,183.00623,0.004559047,-0.0017965452,-4.3940616,0.31536126,-182.9862,183.3198,1.7819748,7.5409503,-5.313883,-183.01509,-948.54517,9.322926,10.37472,-8.351334,156.35347,570000
16
+ 0.6518612,181.57729,0.0049741077,0.0007044327,-3.85838,0.34529242,-181.5581,181.92328,0.67230827,1.1564744,1.8660059,-181.95206,-379.30997,1.8287826,5.663767,-2.3251193,66.585106,575000
17
+ 0.65015537,179.28282,0.0049622534,4.7288245e-06,-3.999047,0.32391173,-179.26299,179.60674,0.8943987,2.991659,-3.3414752,-179.68155,-375.34515,3.8860576,33.57468,-28.491556,244.55971,580000
18
+ 0.64875436,186.04947,0.004645538,-0.0014594705,-4.314166,0.3115008,-186.02942,186.35951,1.0524393,2.2988403,-3.7776146,-186.07455,-817.05695,3.3512797,10.377242,-6.4261255,125.54842,585000
19
+ 0.64300954,177.656,0.0046110963,-0.0011027746,-4.2391567,0.31016174,-177.63647,177.96507,1.6249396,3.0614567,-12.637913,-177.97977,-312.01962,4.686396,11.929806,-16.28604,155.23853,590000
20
+ 0.64306927,178.28812,0.004295318,-0.0052107135,-5.2131147,0.31137386,-178.26573,178.59428,2.594013,9.171195,0.9441607,-178.28868,-713.9005,11.765208,279.1766,-247.28322,1639.0293,595000
21
+ 0.64677924,178.01096,0.0045511797,0.0011822314,-3.7402363,0.3404982,-177.99393,178.35263,1.5946294,2.0337846,-1.6762562,-178.14299,-297.94437,3.6284142,5.462074,-8.433543,128.39708,600000
22
+ 0.64051014,182.15952,0.0043903715,-0.0012729669,-4.289945,0.33557025,-182.14066,182.49382,1.6644766,2.1186364,-4.2278743,-182.3419,-471.1939,3.783113,5.655275,-7.8138776,120.68301,605000
23
+ 0.6337491,179.78148,0.0042675817,-0.0036081304,-4.8454742,0.31143677,-179.7608,180.08931,1.124002,5.278055,-9.36452,-180.08704,-583.1947,6.402057,105.7918,-165.48067,782.6417,610000
24
+ 0.64719766,184.35416,0.0045705135,-0.0019773373,-4.432629,0.28032506,-184.33391,184.63249,0.797017,0.9508938,-5.0430236,-184.43468,-369.45575,1.7479107,3.520837,-2.2633967,64.72811,615000
25
+ 0.6526998,183.81992,0.0042402996,0.00215031,-3.4928873,0.3088707,-183.80511,184.13094,0.7779123,1.4095594,-11.902292,-184.49498,-371.46072,2.1874716,3.3418376,-2.1094756,80.90558,620000
26
+ 0.6434793,179.72107,0.004134054,-0.00017452052,-4.0422153,0.28914356,-179.70435,180.01004,0.6219792,0.9398618,-27.584486,-180.15031,-367.79987,1.561841,9.85242,-5.150415,65.39648,625000
27
+ 0.65122116,179.60947,0.004122721,-0.00070776505,-4.1716743,0.28042114,-179.59227,179.88919,2.1435068,1.850869,-8.40634,-179.99788,-275.8481,3.9943757,7.027765,-13.054695,155.65448,630000
28
+ 0.66404665,184.71405,0.0038759566,0.0027211707,-3.2979357,0.3286185,-184.70128,185.04538,0.58653957,1.2581071,-73.30088,-184.758,-449.593,1.8446467,2.2987669,-2.9432223,73.8465,635000
29
+ 0.66122025,181.52902,0.0040601976,0.0004520413,-3.8886652,0.28982735,-181.51321,181.8193,0.61316687,0.97412235,-8.465174,-181.94943,-312.24722,1.5872892,3.8927462,-3.0396166,75.53074,640000
30
+ 0.6471399,177.32971,0.003975006,-0.0006265118,-4.157613,0.30281478,-177.3132,177.6319,0.8483,1.24182,-3.7949743,-177.61736,-306.6334,2.0901198,5.7462063,-3.1020672,74.55975,645000
31
+ 0.665399,181.57402,0.0038908983,0.0021949736,-3.4358697,0.31276247,-181.56067,181.88898,1.893742,0.7287103,-12.646954,-181.83586,-302.1868,2.6224523,2.148365,-2.9363465,62.296394,650000
32
+ 0.6605941,180.44046,0.0036986787,0.0016912089,-3.5427532,0.35607034,-180.42737,180.79822,1.1721592,1.4826334,-6.058944,-180.4731,-262.19943,2.6547925,6.981049,-8.144122,89.91376,655000
33
+ 0.6539801,175.28485,0.0038046518,-0.0008624377,-4.22668,0.30897456,-175.26875,175.59296,0.9202854,2.9899604,0.73112446,-175.67276,-292.67728,3.910246,21.573925,-13.437153,201.14182,660000
34
+ 0.66780525,182.91751,0.0036891093,0.0019165293,-3.48049,0.31018904,-182.9047,183.22963,0.5313732,0.91637576,-39.79789,-183.06297,-325.5538,1.4477489,2.3349123,-1.8937906,55.223976,665000
35
+ 0.66319644,180.50568,0.0037212945,0.0014980434,-3.5974402,0.29078025,-180.49228,180.79796,0.9992382,1.3089653,-0.6621237,-180.7542,-342.4005,2.3082035,5.639639,-8.727231,108.02182,670000
36
+ 0.6615773,180.13864,0.0035009054,0.0003388003,-3.903225,0.31315812,-180.12497,180.45213,0.5117052,0.6904535,-35.80043,-180.2747,-254.28989,1.2021587,2.1619124,-1.7015254,46.860386,675000
37
+ 0.6489575,174.8408,0.003527396,-0.0018972012,-4.5378475,0.32111257,-174.82478,175.16002,0.768773,1.2722,-0.8097933,-175.19194,-252.56764,2.040973,4.075497,-3.1640968,68.48954,680000
38
+ 0.6608804,182.6618,0.0033688755,0.0001477748,-3.9561353,0.29798037,-182.64847,182.95993,0.9513585,1.0909111,-3.14435,-182.8513,-403.97214,2.0422697,2.661257,-2.9717462,71.55664,685000
39
+ 0.65993476,178.4072,0.0033810176,-0.00031591603,-4.093438,0.3077386,-178.39337,178.71461,0.74309635,1.5877607,-42.26664,-178.50748,-340.36374,2.330857,14.673603,-11.508816,109.70051,690000
40
+ 0.6535851,181.49127,0.0034272755,0.00013162594,-3.9615946,0.33864182,-181.47769,181.83005,1.1372117,1.2859102,-0.12007165,-181.5714,-271.91797,2.423122,14.064836,-11.252796,142.34518,695000
41
+ 0.66051865,178.37088,0.0033783102,-0.00075274153,-4.222816,0.33621538,-178.35661,178.70634,2.0760562,3.9224262,-1.1425408,-178.81876,-377.3742,5.9984827,24.532536,-23.622345,294.60526,700000
42
+ 0.6607219,177.60135,0.003221856,-7.8607896e-05,-4.0243983,0.30701855,-177.5884,177.9083,0.6779539,0.8310853,-15.519812,-177.81041,-266.7507,1.5090392,2.9157777,-4.613861,65.13596,705000
43
+ 0.66264254,180.77829,0.0032350197,8.7555934e-05,-3.972935,0.27354592,-180.76544,181.05193,0.49016628,0.7130419,-22.15641,-180.92516,-250.55498,1.2032082,1.3073505,-1.269218,41.725044,710000
44
+ 0.6758112,183.9049,0.0031903263,0.00289301,-3.093193,0.3050747,-183.89505,184.21288,0.5117387,0.7201163,1.8993669,-184.16602,-316.3831,1.231855,1.7795631,-1.6681516,48.740746,715000
45
+ 0.6595159,181.65974,0.0030932678,-0.00070978637,-4.2294617,0.2780378,-181.64667,181.93706,0.8924387,0.9733597,-0.10182923,-181.7769,-270.93253,1.8657985,1.8007283,-2.9697492,48.377052,720000
46
+ 0.6687963,180.23474,0.0032967033,0.001751545,-3.468698,0.28697678,-180.2233,180.52347,0.5346902,0.7592651,1.3355873,-180.15593,-231.95628,1.2939553,1.7877051,-2.4449072,50.2543,725000
47
+ 0.67068577,181.86395,0.00312089,0.0021070053,-3.3248703,0.27635795,-181.85358,182.14241,0.4756421,0.94529766,-19.756443,-181.86998,-259.54898,1.4209398,2.977397,-3.7031858,58.801086,730000
48
+ 0.6718178,182.92567,0.0029559222,0.0018217555,-3.383693,0.29629156,-182.91568,183.22379,0.70864844,0.82708055,2.9513607,-183.1418,-235.43146,1.5357289,3.3873973,-3.7972262,61.651352,735000
49
+ 0.66551805,184.7251,0.0031389368,0.0012948485,-3.5874882,0.26810068,-184.71382,184.99449,0.8781358,1.7418072,-47.619797,-184.77483,-278.7365,2.6199431,10.308254,-5.611003,94.79639,740000
50
+ 0.6567745,184.32965,0.0028673017,-8.644896e-05,-4.03015,0.2515376,-184.3181,184.5811,0.42389274,0.6186901,-21.09283,-184.3283,-308.8487,1.0425828,3.8442934,-1.5136876,44.560722,745000
51
+ 0.67019606,182.476,0.0029271182,-0.0005255646,-4.17955,0.2364057,-182.46376,182.71188,0.7291565,1.0955768,-2.3747,-182.9511,-298.60025,1.8247333,3.1963232,-3.7759032,71.342926,750000
52
+ 0.65053403,180.16095,0.0028133465,-0.002140693,-4.760906,0.3123824,-180.14755,180.47119,0.44028106,0.51200783,0.40595567,-180.30602,-291.1606,0.95228887,1.2025484,-1.4662485,38.37507,755000
53
+ 0.66322553,181.01517,0.0027970022,0.0013354297,-3.5225496,0.30802584,-181.00531,181.32454,0.45580983,0.702692,-1.2850101,-181.18823,-232.20978,1.1585019,7.001488,-3.9892735,73.82751,760000
54
+ 0.6628042,184.1684,0.002912062,-9.897516e-05,-4.033988,0.31119475,-184.15665,184.47949,0.64490926,0.95710105,-68.35413,-184.05145,-250.33179,1.6020103,5.151052,-13.341756,77.25849,765000
55
+ 0.6543245,182.59317,0.002868427,-0.0029919615,-5.043067,0.32137698,-182.5787,182.91156,0.49781132,0.80456156,-5.8762407,-182.875,-267.01715,1.3023729,3.0164094,-1.6238742,47.181313,770000
56
+ 0.6782483,182.21944,0.0027533234,0.0019719838,-3.2837806,0.28310508,-182.2104,182.50452,0.7767435,0.799242,-19.291502,-182.35986,-226.77682,1.5759854,12.270592,-5.4877033,96.63354,775000
57
+ 0.6620662,182.83546,0.0026156572,-0.00039992956,-4.1528983,0.30596873,-182.82458,183.14104,0.52364343,0.8709242,0.39585227,-182.8809,-253.70384,1.3945676,6.573963,-6.9766884,79.576256,780000
58
+ 0.65475416,181.83844,0.002578013,-0.0014536321,-4.5638576,0.3041646,-181.82668,182.14116,0.8758265,0.68748254,-0.8092253,-181.93729,-284.45175,1.563309,14.436024,-4.554233,82.75136,785000
59
+ 0.67158425,187.42772,0.0024119045,-0.0006684804,-4.2771587,0.30603206,-187.4174,187.73308,0.31925502,0.99197143,-24.464684,-187.64153,-215.241,1.3112265,5.1898317,-3.4609902,63.67356,790000
60
+ 0.66107595,183.62491,0.002448185,-0.0018061452,-4.7377486,0.28672147,-183.61331,183.90984,0.42208004,0.74737495,0.23236293,-183.8736,-226.614,1.169455,2.1553836,-3.0851126,50.459442,795000
61
+ 0.66199595,185.64557,0.0024262185,0.0012315903,-3.4923828,0.2804917,-185.63708,185.92729,0.46831018,0.9244218,-60.261307,-186.009,-219.8921,1.3927319,7.359783,-5.1387167,83.06351,800000
62
+ 0.6562557,186.92673,0.002412726,5.2993866e-05,-3.9780357,0.3265991,-186.91711,187.25337,0.3578708,0.77054566,-10.096821,-186.81267,-222.28084,1.1284164,6.011696,-4.6593494,67.209114,805000
63
+ 0.6744156,186.78699,0.002322089,0.00093445403,-3.5975804,0.27911577,-186.77863,187.06703,0.5532755,0.49926144,-49.13274,-186.86784,-225.94441,1.052537,1.3686887,-2.0050704,39.17994,810000
64
+ 0.6615092,181.52359,0.0023487532,0.0003683008,-3.843193,0.31246302,-181.51456,181.83643,0.89809626,1.6315901,-0.37009257,-181.64587,-222.99968,2.5296865,14.403782,-8.337594,121.08943,815000
65
+ 0.6729023,186.96558,0.002386776,0.0010892077,-3.543649,0.26504827,-186.95712,187.2317,0.7458691,1.4052229,4.676727,-187.24583,-227.45851,2.151092,10.253995,-13.310304,160.95294,820000
66
+ 0.6606271,182.28949,0.002218292,-0.0005444587,-4.2454405,0.2687757,-182.28008,182.55771,1.2431574,1.7692826,-32.702152,-182.33951,-216.60524,3.01244,8.406172,-7.262328,114.43327,825000
67
+ 0.667366,185.93874,0.0022512071,-0.0003835341,-4.170368,0.30207682,-185.92935,186.24043,0.54161185,0.8484365,-26.229898,-186.12016,-223.92302,1.3900483,5.1935587,-4.405667,68.67694,830000
68
+ 0.6556363,184.45123,0.0021465984,-0.0013487317,-4.628311,0.29543665,-184.4413,184.74533,0.7812212,1.231665,-19.474258,-184.46294,-215.59732,2.0128863,33.371067,-11.020658,163.48758,835000
69
+ 0.67327344,187.47089,0.0021255773,0.00064838736,-3.6949594,0.29356995,-187.46303,187.76509,1.6202837,1.2185011,-8.141873,-187.61989,-211.69183,2.8387847,8.444018,-10.02328,141.8413,840000
70
+ 0.66903645,187.73251,0.0021201991,0.0011729453,-3.446776,0.290177,-187.7252,188.02386,0.46659786,1.4058058,-31.543983,-187.52257,-220.84105,1.8724036,7.239326,-2.9912012,86.67843,845000
71
+ 0.6743864,189.5454,0.0021103842,0.0010302305,-3.511828,0.27644166,-189.538,189.82288,0.9234064,0.7088705,0.22374278,-189.68152,-246.82101,1.6322769,2.5677943,-3.0591826,55.473877,850000
72
+ 0.65554214,185.6628,0.0021374598,-0.00078806723,-4.3686934,0.29234114,-185.65344,185.95435,0.7085871,1.7029192,0.3272732,-186.09991,-218.89053,2.4115064,8.022858,-8.402829,139.68697,855000
73
+ 0.665993,189.30756,0.0021509747,0.00037886566,-3.8238633,0.28102088,-189.29932,189.58896,0.39030516,0.9524932,-27.640364,-189.39885,-214.01974,1.3427984,4.532054,-6.405879,80.599884,860000
74
+ 0.6534803,187.89163,0.0020084875,-0.0012369978,-4.6158853,0.28597426,-187.88235,188.17638,0.39597675,0.66354686,-1.0122902,-188.01183,-219.66214,1.0595236,5.796769,-4.79772,68.88988,865000
75
+ 0.67004365,186.90277,0.002059101,-0.00035540824,-4.1726036,0.2569776,-186.89417,187.1594,1.2424068,1.9119419,1.8751718,-186.93842,-219.40631,3.1543489,9.398819,-7.5221257,127.59928,870000
76
+ 0.66898215,188.9762,0.002008653,0.0017692293,-3.1191962,0.22327222,-188.96994,189.20123,0.45694062,0.5791428,1.341844,-188.84268,-215.71547,1.0360835,5.017931,-3.8860092,58.316025,875000
77
+ 0.6711163,186.27899,0.0020060132,-0.00088978076,-4.443557,0.28583884,-186.2701,186.56395,0.8227528,1.5518748,-12.160845,-186.26543,-211.07556,2.3746276,8.108567,-11.679619,137.41809,880000
78
+ 0.651449,186.37753,0.0019012439,-0.0018552311,-4.9757986,0.2561307,-186.3681,186.6318,0.7622844,1.7066475,-17.500776,-186.51534,-210.52895,2.468932,11.062569,-13.847535,147.74991,885000
79
+ 0.6550098,185.83702,0.0018322557,-0.0008096472,-4.4418855,0.29388732,-185.82889,186.1301,1.0369444,1.5768964,2.316952,-185.86095,-244.25432,2.6138408,12.976603,-35.225624,161.16232,890000
80
+ 0.6606079,189.29916,0.0018779616,-2.7982018e-05,-4.0149,0.26667008,-189.29163,189.5658,0.70349944,0.8636551,-14.724599,-189.52527,-215.38042,1.5671545,6.1827335,-3.2515283,75.243095,895000
81
+ 0.6472118,187.22919,0.0018618054,-0.000477099,-4.256256,0.3094131,-187.22127,187.53813,0.9274532,0.6077428,-0.17624438,-187.40965,-210.47272,1.5351961,6.0090346,-6.1954236,82.36924,900000
82
+ 0.67816544,189.05174,0.0018081033,0.00061754236,-3.6584585,0.29231966,-189.04512,189.34467,0.4100903,0.5543047,-2.2709956,-189.16466,-262.73715,0.96439505,4.827779,-3.094995,56.487206,905000
83
+ 0.6572523,186.65297,0.0018622351,0.0006266105,-3.663517,0.28644434,-186.64615,186.94003,0.83532184,1.5704268,-2.9094045,-186.96454,-214.01659,2.4057486,9.5023155,-15.830365,180.65271,910000
84
+ 0.6732341,190.96443,0.0017908453,0.0023163324,-2.7065704,0.32655627,-190.9596,191.2933,0.61612916,2.3195615,-1.3218482,-191.03717,-219.9522,2.9356906,18.20665,-11.349497,160.54959,915000
85
+ 0.6487163,187.9651,0.0017298077,-0.0021992023,-5.2713566,0.27435738,-187.95601,188.23726,2.9567356,3.835732,2.5915718,-188.13042,-246.25883,6.7924676,25.116564,-58.25962,449.53625,920000
86
+ 0.6753124,190.13849,0.0017766412,0.0016133639,-3.0919023,0.26188117,-190.133,190.402,0.82806283,0.84312916,-30.934772,-190.34996,-285.3355,1.6711919,13.849997,-4.2790203,102.19084,925000
87
+ 0.6780982,190.95831,0.0016991424,0.00094192306,-3.445648,0.23751327,-190.95245,191.19678,0.54972976,1.0019674,-22.043144,-191.06212,-299.11972,1.5516973,7.7319393,-5.535671,87.99416,930000
88
+ 0.6671511,189.37637,0.001679024,0.00056231295,-3.6650953,0.26544353,-189.37021,189.64238,0.6422019,0.8318454,-45.503246,-189.64119,-220.3242,1.4740473,7.850281,-9.989333,123.594154,935000
89
+ 0.66878355,190.73236,0.0016061709,0.000863337,-3.4624875,0.3052559,-190.7268,191.03848,0.777821,0.8395387,1.8923812,-190.9742,-217.7134,1.6173596,15.524619,-8.802437,124.52517,940000
90
+ 0.6586511,189.32849,0.0016299427,-0.00040502578,-4.248491,0.27628085,-189.32158,189.60435,0.42138734,1.7752389,-16.560669,-189.30376,-299.11932,2.1966262,10.51325,-12.986462,131.0337,945000
91
+ 0.647382,185.70047,0.0015392214,-0.00089315197,-4.580262,0.29544663,-185.69342,185.99501,1.1449589,1.2345687,0.16789794,-185.61148,-210.00433,2.3795276,17.532055,-53.34354,185.071,950000
92
+ 0.6766742,189.36829,0.0016243254,0.000891862,-3.450934,0.24888355,-189.36269,189.61806,0.7391076,0.90062904,-1.7399527,-189.14056,-218.6423,1.6397367,13.953127,-6.360866,119.72951,955000
93
+ 0.66717434,188.25554,0.0016995379,-0.0011367666,-4.668868,0.26315898,-188.24759,188.51756,0.665703,0.8535184,-33.32986,-188.26753,-290.46902,1.5192214,9.460906,-13.686193,119.89159,960000
94
+ 0.66711015,189.4623,0.0016091046,0.00038717606,-3.7593842,0.3192395,-189.45624,189.78192,0.32618764,0.5042482,-24.478836,-189.72,-209.0928,0.8304359,3.7542155,-5.6926146,61.16417,965000
95
+ 0.6578791,188.26773,0.0016249078,-0.000526098,-4.323771,0.26387662,-188.26071,188.53108,0.5661728,0.77391684,-18.587093,-188.44017,-210.19363,1.3400896,16.943092,-24.635355,117.95216,970000
96
+ 0.66835773,190.22101,0.0014332721,0.00018242073,-3.8727243,0.25350994,-190.21547,190.4747,0.8412339,0.8782709,-1.127544,-190.37169,-222.25897,1.7195048,5.664166,-8.474815,104.18511,975000
97
+ 0.6553285,189.0329,0.0014876173,-0.0014551623,-4.9781833,0.28676838,-189.02551,189.31822,0.5670072,2.1280227,-0.6942984,-189.35472,-211.17102,2.6950297,7.969744,-10.039169,128.9953,980000
98
+ 0.676937,190.61774,0.001630801,-0.00021185112,-4.129906,0.26995218,-190.61101,190.88748,0.269561,0.45915708,-4.6473308,-190.74602,-265.44394,0.72871804,3.1917195,-2.256601,47.33716,985000
99
+ 0.67415226,190.16617,0.0014657248,0.0010486568,-3.2845473,0.29539025,-190.16138,190.46262,0.5357403,0.673454,-2.2889118,-190.18947,-213.26797,1.2091943,26.473215,-7.184746,119.189575,990000
100
+ 0.67900753,194.16399,0.0015088442,0.0017870414,-2.8156223,0.2843079,-194.15973,194.45007,0.3823631,0.4845658,-105.22764,-194.41408,-216.40463,0.86692894,3.44645,-2.2965682,54.722214,995000
101
+ 0.6861307,193.48642,0.0014972773,0.0015344934,-2.9751441,0.22278619,-193.48196,193.71075,0.4152259,0.541785,-5.3674297,-193.70319,-212.30986,0.95701087,4.162127,-4.632647,67.81322,1000000
O2O-w-diff-ckpts/dsrl/20260317_054138/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a719211afa638dd28c5b01801a6e2f0ef7bbc8d859061d27a70df383347491cd
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_550000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f066e391fce8b4a7a431f6da6f36ff35644690712700c50ef33518becbe4a2
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_600000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200164b4748af47cbc810f7120fd4a48036367fa9e200c4d407daa34a663ff5f
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_650000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05a6078c0a627ea8d352e86cded39cf4f8db7181ec266083b3e6c8ae32068ae7
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_700000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3095fe5b03ee7c2ce72cb22ff8b2bf5c27537329ef50d763849603c1c96a89
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_750000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b74bb21c8e6ebea4ceb0afd28d878be18c99bfbe9990d0777a1cfa08172774
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_800000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a614d5b5c17079625e2ebb5d87a409c5b2ab9a6d107befd782455552b253dd7c
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f1740101454c5f553c579383d31c8b4b6882f7428d22049d68dd15ddd1eb2f
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9350353ce12d709f4be570bd996ce9cdfdcde78e70c2c33681d3e4f891750ed0
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b29d9b814bb6c14696c9e44fdc245f4df8e41236f2538311276f63fa40d80c
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_054138/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/dsrl/20260317_054138/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/doh8oebz
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_1000000.png ADDED

Git LFS Details

  • SHA256: 66154fa42c3fe44a65a2699133fafe2344b33c174e549f48846dcf0c46b29590
  • Pointer size: 131 Bytes
  • Size of remote file: 197 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_550000.png ADDED

Git LFS Details

  • SHA256: 726e65c39d28c32e5bf978124a9f978845c991812b76754da46563e6286418a7
  • Pointer size: 131 Bytes
  • Size of remote file: 220 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_600000.png ADDED

Git LFS Details

  • SHA256: b1b2e135279d83bbf384808ca921692e0d7a74e1baf33ec266ab1a249e97120e
  • Pointer size: 131 Bytes
  • Size of remote file: 132 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_650000.png ADDED

Git LFS Details

  • SHA256: 72b32a704dcc39653723420ef8d51a15de89af76e9ae535dcb2291027cf9a3c5
  • Pointer size: 131 Bytes
  • Size of remote file: 136 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_700000.png ADDED

Git LFS Details

  • SHA256: 7b7994622eea1130c7bde37d61423bdddc56a2e1ae9e4a95def0f7b7eb9256fe
  • Pointer size: 131 Bytes
  • Size of remote file: 184 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_750000.png ADDED

Git LFS Details

  • SHA256: 8d1ebd988f13352f30a1b80880745544e987bdb92a7a97c1f97ec12a5385d8aa
  • Pointer size: 131 Bytes
  • Size of remote file: 180 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_800000.png ADDED

Git LFS Details

  • SHA256: 17d64505f45785e4f22d42c786034c37a77790c3e1a4d106a04830ef2045ae7a
  • Pointer size: 131 Bytes
  • Size of remote file: 225 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_850000.png ADDED

Git LFS Details

  • SHA256: 9be55f987e737e0a810e1c0453b7089251f20daf0fe64ba7779b3ac95b6844af
  • Pointer size: 131 Bytes
  • Size of remote file: 200 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_900000.png ADDED

Git LFS Details

  • SHA256: 651007c510e62a125803b13420c3b08c0a5f912dc0f172714a86d3d56f804722
  • Pointer size: 131 Bytes
  • Size of remote file: 188 kB
O2O-w-diff-ckpts/dsrl/20260317_054138/visited_states_950000.png ADDED

Git LFS Details

  • SHA256: 855b0ea74ed18db115037e81deb40f715a529a70ca0a236bb740f612ad87dee9
  • Pointer size: 131 Bytes
  • Size of remote file: 186 kB