Tiredsheep commited on
Commit
98d6166
·
verified ·
1 Parent(s): 4c04aa5

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +10 -0
  2. O2O-w-diff-ckpts/dsrl/20260317_210355/env.csv +0 -0
  3. O2O-w-diff-ckpts/dsrl/20260317_210355/env_sv.csv +0 -0
  4. O2O-w-diff-ckpts/dsrl/20260317_210355/eval.csv +11 -0
  5. O2O-w-diff-ckpts/dsrl/20260317_210355/eval_sv.csv +11 -0
  6. O2O-w-diff-ckpts/dsrl/20260317_210355/online_agent.csv +101 -0
  7. O2O-w-diff-ckpts/dsrl/20260317_210355/online_agent_sv.csv +101 -0
  8. O2O-w-diff-ckpts/dsrl/20260317_210355/params_1000000.pkl +3 -0
  9. O2O-w-diff-ckpts/dsrl/20260317_210355/params_1050000.pkl +3 -0
  10. O2O-w-diff-ckpts/dsrl/20260317_210355/params_1100000.pkl +3 -0
  11. O2O-w-diff-ckpts/dsrl/20260317_210355/params_1150000.pkl +3 -0
  12. O2O-w-diff-ckpts/dsrl/20260317_210355/params_1200000.pkl +3 -0
  13. O2O-w-diff-ckpts/dsrl/20260317_210355/params_1250000.pkl +3 -0
  14. O2O-w-diff-ckpts/dsrl/20260317_210355/params_1300000.pkl +3 -0
  15. O2O-w-diff-ckpts/dsrl/20260317_210355/params_850000.pkl +3 -0
  16. O2O-w-diff-ckpts/dsrl/20260317_210355/params_900000.pkl +3 -0
  17. O2O-w-diff-ckpts/dsrl/20260317_210355/params_950000.pkl +3 -0
  18. O2O-w-diff-ckpts/dsrl/20260317_210355/progress.tk +1 -0
  19. O2O-w-diff-ckpts/dsrl/20260317_210355/token.tk +1 -0
  20. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1000000.png +3 -0
  21. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1050000.png +3 -0
  22. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1100000.png +3 -0
  23. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1150000.png +3 -0
  24. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1200000.png +3 -0
  25. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1250000.png +3 -0
  26. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1300000.png +3 -0
  27. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_850000.png +3 -0
  28. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_900000.png +3 -0
  29. O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_950000.png +3 -0
.gitattributes CHANGED
@@ -593,3 +593,13 @@ O2O-w-diff-ckpts/cgql/20260318_085240/visited_states_1350000.png filter=lfs diff
593
  O2O-w-diff-ckpts/cgql/20260318_085240/visited_states_1400000.png filter=lfs diff=lfs merge=lfs -text
594
  O2O-w-diff-ckpts/cgql/20260318_085240/visited_states_1450000.png filter=lfs diff=lfs merge=lfs -text
595
  O2O-w-diff-ckpts/cgql/20260318_085240/visited_states_1500000.png filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
593
  O2O-w-diff-ckpts/cgql/20260318_085240/visited_states_1400000.png filter=lfs diff=lfs merge=lfs -text
594
  O2O-w-diff-ckpts/cgql/20260318_085240/visited_states_1450000.png filter=lfs diff=lfs merge=lfs -text
595
  O2O-w-diff-ckpts/cgql/20260318_085240/visited_states_1500000.png filter=lfs diff=lfs merge=lfs -text
596
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1000000.png filter=lfs diff=lfs merge=lfs -text
597
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1050000.png filter=lfs diff=lfs merge=lfs -text
598
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1100000.png filter=lfs diff=lfs merge=lfs -text
599
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1150000.png filter=lfs diff=lfs merge=lfs -text
600
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1200000.png filter=lfs diff=lfs merge=lfs -text
601
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1250000.png filter=lfs diff=lfs merge=lfs -text
602
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1300000.png filter=lfs diff=lfs merge=lfs -text
603
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
604
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
605
+ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
O2O-w-diff-ckpts/dsrl/20260317_210355/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/dsrl/20260317_210355/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/dsrl/20260317_210355/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
+ 0.0,0.0,19.338104327861817,2.637783846636676,0.02108272140147291,2.635827949819745,-0.016552291750777378,0.0,25500.0,-1.0,-1000.0,1000.0,1.6035127115249634,850000
3
+ 0.0,0.0,16.584909444785463,2.1996718650190394,0.015072683103414641,2.204626687436449,0.04599153017529042,0.0,77500.0,-1.0,-1000.0,1000.0,1.6901580905914306,900000
4
+ 0.0,0.0,26.283076818121813,3.5615366404986273,0.0066260804911207035,3.5629421959818712,-0.027464191062600365,0.0,129500.0,-1.0,-1000.0,1000.0,1.6079348850250244,950000
5
+ 0.0,0.0,28.332383015923707,3.792767887039486,-0.11124956493697628,3.787291594687436,0.034127364401854925,0.04,181476.54,-0.96,-998.56,998.6,1.6032567739486694,1000000
6
+ 0.0,0.0,31.229820009307304,4.2136594982604585,0.036462926000688116,4.220754118957561,0.1127447825958696,0.18,233034.82,-0.82,-982.12,982.3,1.6628662109375,1050000
7
+ 0.0,0.0,30.46895153353242,4.123232910903076,0.11896267068134518,4.132894081812245,0.09225386516906144,0.18,284336.74,-0.82,-988.14,988.32,1.576693959236145,1100000
8
+ 0.0,0.0,33.47386700881862,4.530736779267449,0.10161396937723469,4.542981062511164,0.12785254300642923,0.38,335322.84,-0.62,-968.5,968.88,1.5662234210968018,1150000
9
+ 0.0,0.0,35.268027965251385,4.767084277813275,0.06529497266168112,4.775746442440369,0.10087761383218286,0.24,385449.72,-0.76,-973.5,973.74,1.5508340406417847,1200000
10
+ 0.0,0.0,33.61196404729605,4.546941432708294,0.0956908840984689,4.555775575786038,0.06093985775979329,0.38,436274.8,-0.62,-973.94,974.32,1.5664929723739625,1250000
11
+ 0.0,0.0,26.403912037989194,3.5820786286261797,0.0672364347841285,3.5851570423804406,0.012640519043934683,0.22,486857.42,-0.78,-975.24,975.46,1.559081654548645,1300000
O2O-w-diff-ckpts/dsrl/20260317_210355/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
+ 0.0,0.0,19.338104327861817,2.637783846636676,0.02108272140147291,2.635827949819745,-0.016552291750777378,0.0,25500.0,-1.0,-1000.0,1000.0,1.6035127115249634,850000
3
+ 0.0,0.0,16.584909444785463,2.1996718650190394,0.015072683103414641,2.204626687436449,0.04599153017529042,0.0,77500.0,-1.0,-1000.0,1000.0,1.6901580905914306,900000
4
+ 0.0,0.0,26.283076818121813,3.5615366404986273,0.0066260804911207035,3.5629421959818712,-0.027464191062600365,0.0,129500.0,-1.0,-1000.0,1000.0,1.6079348850250244,950000
5
+ 0.0,0.0,28.332383015923707,3.792767887039486,-0.11124956493697628,3.787291594687436,0.034127364401854925,0.04,181476.54,-0.96,-998.56,998.6,1.6032567739486694,1000000
6
+ 0.0,0.0,31.229820009307304,4.2136594982604585,0.036462926000688116,4.220754118957561,0.1127447825958696,0.18,233034.82,-0.82,-982.12,982.3,1.6628662109375,1050000
7
+ 0.0,0.0,30.46895153353242,4.123232910903076,0.11896267068134518,4.132894081812245,0.09225386516906144,0.18,284336.74,-0.82,-988.14,988.32,1.576693959236145,1100000
8
+ 0.0,0.0,33.47386700881862,4.530736779267449,0.10161396937723469,4.542981062511164,0.12785254300642923,0.38,335322.84,-0.62,-968.5,968.88,1.5662234210968018,1150000
9
+ 0.0,0.0,35.268027965251385,4.767084277813275,0.06529497266168112,4.775746442440369,0.10087761383218286,0.24,385449.72,-0.76,-973.5,973.74,1.5508340406417847,1200000
10
+ 0.0,0.0,33.61196404729605,4.546941432708294,0.0956908840984689,4.555775575786038,0.06093985775979329,0.38,436274.8,-0.62,-973.94,974.32,1.5664929723739625,1250000
11
+ 0.0,0.0,26.403912037989194,3.5820786286261797,0.0672364347841285,3.5851570423804406,0.012640519043934683,0.22,486857.42,-0.78,-975.24,975.46,1.559081654548645,1300000
O2O-w-diff-ckpts/dsrl/20260317_210355/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
+ 0.65248126,170.43422,0.0040408736,-0.0026740455,-4.6617494,0.3453765,-170.41539,170.77693,0.5621449,0.74613893,-1.5765696,-170.72115,-235.7158,1.3082838,2.5015533,-2.2941387,42.035847,805000
3
+ 0.65425897,168.45583,0.0040861946,-0.0013552245,-4.3316593,0.32632804,-168.43813,168.78079,0.69979304,2.2784956,-2.5692391,-168.60649,-223.71725,2.9782887,51.834457,-14.056904,223.18285,810000
4
+ 0.65934277,175.1708,0.003984067,0.0013917673,-3.6506667,0.36998954,-175.15625,175.54219,0.45501843,0.59567326,-3.9093843,-175.45149,-285.13446,1.0506917,3.0823832,-2.1583934,45.191628,815000
5
+ 0.6558094,172.4635,0.0038997398,0.0006255114,-3.8396018,0.3229397,-172.44852,172.78706,0.6791763,0.7669601,-18.039482,-172.50696,-216.62921,1.4461364,3.25417,-3.3693175,67.14663,820000
6
+ 0.66262996,172.3088,0.003916379,-0.0012600078,-4.3217278,0.2852732,-172.29189,172.59282,1.0702647,0.9404341,-0.21409816,-172.2899,-234.58353,2.0106988,4.290267,-8.230618,80.024895,825000
7
+ 0.64948535,170.84456,0.003819049,-0.0006334391,-4.165863,0.31929195,-170.82864,171.16321,0.5179897,0.744051,0.9069618,-170.788,-236.00401,1.2620406,2.7210567,-1.978744,55.105972,830000
8
+ 0.6579559,171.62897,0.0037072708,-0.0003795249,-4.102373,0.32354832,-171.61374,171.95213,1.2139338,2.6786973,0.99666107,-171.99612,-227.6873,3.892631,18.312902,-21.969135,179.06865,835000
9
+ 0.6579062,170.28514,0.0038211476,-0.00044357084,-4.116083,0.32359445,-170.26941,170.60829,0.617889,0.8446091,-1.8431194,-170.66441,-227.4598,1.4624981,2.993755,-1.7645732,53.992794,840000
10
+ 0.65841126,172.9555,0.0034903793,0.0008459737,-3.757627,0.32899952,-172.94238,173.28534,0.52825433,0.5709612,-4.9746633,-173.00925,-221.33682,1.0992155,2.790904,-2.378603,49.067345,845000
11
+ 0.6540127,173.25912,0.0035276483,-8.110648e-05,-4.0229917,0.3035951,-173.24493,173.56264,0.5750025,0.8558449,-0.19625002,-173.4781,-229.90433,1.4308474,9.251238,-7.5693307,77.76999,850000
12
+ 0.6593282,170.1417,0.0033521592,-0.00041535308,-4.123906,0.29572347,-170.12787,170.43701,0.637402,1.1854523,0.8896258,-170.34962,-229.40947,1.8228543,5.4008746,-7.6547966,87.90232,855000
13
+ 0.6511518,173.9816,0.003351555,-0.0012462374,-4.3718386,0.3390497,-173.96693,174.3194,0.5826209,1.15464,-39.27309,-174.27962,-274.0485,1.7372608,4.184668,-5.020544,76.01138,860000
14
+ 0.6602924,176.87292,0.003302268,0.00016838378,-3.9490097,0.29518783,-176.85986,177.16827,1.1375093,1.5366205,-11.635074,-176.93729,-233.21548,2.67413,12.816653,-11.011774,152.83942,865000
15
+ 0.6632719,175.34944,0.003226022,-0.0008924127,-4.2766294,0.27620292,-175.33565,175.62476,1.4737082,3.4881904,-1.7916465,-175.52878,-236.11562,4.961899,9.239059,-8.974409,156.89008,870000
16
+ 0.66121125,177.75665,0.0031165802,0.0019451936,-3.3758564,0.26510534,-177.74612,178.0237,0.4162472,0.8152459,1.5756845,-177.93199,-230.84259,1.2314931,3.513638,-2.4905312,58.03761,875000
17
+ 0.6571703,175.75638,0.003160052,0.0011992832,-3.6204863,0.32450265,-175.74495,176.08209,0.9063902,0.65449935,-0.92629063,-175.95036,-244.8503,1.5608895,2.6523535,-4.3062987,47.690735,880000
18
+ 0.6474816,177.6029,0.003008585,-0.0007809201,-4.259564,0.25528476,-177.59009,177.8574,1.9300957,1.2053291,-3.2105887,-177.97702,-249.7172,3.1354246,3.1824622,-2.9067285,68.16919,885000
19
+ 0.6555559,176.11224,0.0030995163,-0.0014949493,-4.482317,0.31392246,-176.09834,176.42467,0.7305532,1.101433,-15.304167,-176.01672,-251.38885,1.8319862,6.195334,-4.123494,78.00604,890000
20
+ 0.65515566,171.70468,0.0030221122,-0.0018373082,-4.607955,0.27117234,-171.69075,171.97403,0.84262174,1.1253909,2.56746,-171.87611,-221.36252,1.9680126,2.8867986,-7.511916,90.45363,895000
21
+ 0.6554468,174.5848,0.0029431896,-4.312997e-05,-4.014654,0.33624053,-174.57298,174.92099,0.5711957,0.8788981,-0.10868496,-174.76,-220.46393,1.4500937,4.480286,-3.2037132,61.136696,900000
22
+ 0.6506264,178.46451,0.0028592544,-0.0005343991,-4.1869016,0.31849056,-178.45255,178.78247,0.62119085,0.76984787,-3.9733262,-178.58017,-254.50891,1.3910387,2.1260705,-2.800685,55.96211,905000
23
+ 0.6577034,173.80414,0.0029150029,0.00022089867,-3.92422,0.27383825,-173.7927,174.07819,0.5558913,0.83786553,-14.502045,-173.89307,-253.71382,1.3937569,2.4680157,-3.7010126,55.654285,910000
24
+ 0.65976536,181.62715,0.0027334397,0.0014975935,-3.4521213,0.35612577,-181.61772,181.98477,0.7607002,1.0497082,-6.032939,-181.6374,-223.19833,1.8104085,6.9995384,-4.000905,94.46781,915000
25
+ 0.6550689,179.97433,0.002803323,0.0009951778,-3.6450007,0.29048654,-179.96411,180.26581,0.304423,0.4812703,-12.284696,-180.2689,-211.65779,0.7856933,1.814212,-2.554605,38.178814,920000
26
+ 0.6511414,178.75943,0.0025586998,-0.0010856361,-4.424292,0.2985925,-178.74812,179.05695,0.4561921,0.5010623,-27.473742,-179.13924,-233.80252,0.9572544,1.5296707,-2.235042,40.812996,925000
27
+ 0.6605681,178.06876,0.002783645,0.0005947927,-3.786326,0.28042,-178.05823,178.34978,0.99794066,1.8736542,-1.8307453,-177.99413,-249.9055,2.871595,35.778774,-11.309971,167.4173,930000
28
+ 0.669477,182.10516,0.0026567348,0.0012778064,-3.5190313,0.3162309,-182.09581,182.42268,0.27680093,1.1450537,-72.97711,-181.93231,-221.42603,1.4218547,4.2184067,-11.482321,69.75514,935000
29
+ 0.6693598,182.16684,0.0026928997,0.00077061617,-3.713834,0.3204943,-182.15683,182.48811,0.81097597,0.92073613,-4.4923863,-182.35501,-247.96156,1.7317121,4.763552,-4.762294,79.380165,940000
30
+ 0.66061586,176.84265,0.0027238205,0.00041824955,-3.8464475,0.31178123,-176.83218,177.15485,1.0172871,0.6027021,-5.7060337,-177.07637,-233.67827,1.6199892,2.9656696,-2.7799025,51.225353,945000
31
+ 0.6742782,181.91327,0.0027071806,0.0028296558,-2.9547591,0.34102422,-181.90527,182.25711,0.47102532,0.6189367,-8.939527,-182.25533,-220.49356,1.089962,2.2602048,-5.0939236,51.001347,950000
32
+ 0.6589843,182.91391,0.0025378752,0.0014706266,-3.4205284,0.3156201,-182.90524,183.23099,0.55220926,0.73031753,-11.050966,-183.11475,-242.39221,1.2825267,5.910697,-3.7408102,75.89187,955000
33
+ 0.6559348,178.06989,0.0024410128,-0.001318702,-4.5402274,0.28902265,-178.05879,178.35759,0.49300694,0.558908,-0.79517627,-178.19511,-219.36322,1.0519149,2.859947,-2.2217534,44.32652,960000
34
+ 0.6663641,183.55121,0.0026029362,0.0010380383,-3.6012049,0.3363462,-183.54182,183.8886,0.6050739,0.97929794,-46.86855,-183.85237,-250.74368,1.5843718,3.4212008,-2.2694573,76.34569,965000
35
+ 0.65913475,180.86041,0.0024854357,-0.00021831613,-4.087838,0.30332696,-180.85025,181.16353,0.5569636,0.916636,-0.43417686,-180.7985,-235.36015,1.4735997,2.7469752,-4.240775,74.80313,970000
36
+ 0.6647407,181.31519,0.0024118335,0.001440858,-3.4025881,0.27656323,-181.30698,181.59319,0.59755296,0.5101115,-51.766354,-181.58801,-222.06538,1.1076645,7.210548,-6.087767,66.456406,975000
37
+ 0.654214,177.90321,0.0024265447,-0.0011863451,-4.488903,0.31105766,-177.89232,178.21307,0.42754793,0.79187435,-3.0502825,-178.1554,-230.68419,1.2194223,3.0451083,-5.454179,59.4058,980000
38
+ 0.66761136,183.35399,0.0023738833,0.0009194056,-3.6126997,0.28331074,-183.3454,183.63821,0.6240904,2.0015619,-5.9003267,-183.28242,-219.29454,2.6256523,4.839738,-6.7898073,91.52127,985000
39
+ 0.6599628,180.2141,0.0023593921,-0.0009997326,-4.4237247,0.32172298,-180.20366,180.5348,1.2345085,1.4181925,-3.3760123,-180.48651,-226.97215,2.652701,11.383143,-13.392401,187.77895,990000
40
+ 0.6694889,184.53648,0.0023104313,0.0016367217,-3.2915947,0.28798544,-184.52887,184.8261,0.6864125,0.6797186,0.74160004,-184.4557,-215.07353,1.3661311,13.439897,-4.7534122,92.624146,995000
41
+ 0.6592324,180.70409,0.0023024972,-0.0008434906,-4.3663373,0.23780775,-180.69403,180.94106,0.9510722,1.30385,0.91648835,-180.92633,-222.75638,2.2549224,10.980577,-7.2062764,144.33095,1000000
42
+ 0.6646912,181.95135,0.0022261026,0.0007976677,-3.6416752,0.27603352,-181.94324,182.22818,0.5298559,0.94824713,-19.360893,-182.17552,-221.58246,1.478103,3.6260707,-6.511091,72.076675,1005000
43
+ 0.658268,183.75804,0.0022675323,0.00038592936,-3.829802,0.2576951,-183.74936,184.01611,0.29877058,0.6287408,-41.799644,-183.7924,-229.77917,0.92751133,2.7942557,-2.2897737,49.437965,1010000
44
+ 0.67403686,183.90543,0.0022188358,0.0004961061,-3.7764115,0.32499224,-183.89703,184.23093,3.695797,0.6709486,1.0625539,-184.01529,-214.82022,4.3667455,2.8405428,-2.810028,61.550285,1015000
45
+ 0.66717744,184.9242,0.0022188157,0.001995944,-3.1004462,0.31221282,-184.91733,185.2384,0.20988512,0.4589568,-0.00987494,-185.16191,-212.74217,0.66884196,3.9206178,-1.6754044,40.552696,1020000
46
+ 0.66327363,184.03905,0.0021061627,0.0008421464,-3.6001513,0.29349694,-184.03146,184.33339,1.0758727,1.3742801,1.8246698,-184.0236,-209.69557,2.4501529,8.149399,-2.9858112,109.9104,1025000
47
+ 0.66280115,184.39926,0.0021546443,-0.0004586635,-4.212872,0.27964634,-184.39018,184.67845,0.40764284,0.6126146,-27.19604,-184.69543,-250.30057,1.0202575,4.0268974,-6.9392405,62.69468,1030000
48
+ 0.6656438,185.82275,0.0021156315,0.0011028935,-3.478693,0.29678947,-185.81538,186.12064,0.99824333,0.52882755,-1.5806997,-185.88982,-225.76624,1.5270709,2.0334656,-2.923397,47.19291,1035000
49
+ 0.67397255,185.56952,0.002174784,0.0010146182,-3.5334625,0.2352382,-185.56184,185.80577,1.1621493,2.1775653,-3.745329,-185.78131,-215.40623,3.3397145,31.674187,-21.657774,254.80405,1040000
50
+ 0.66471696,186.5369,0.0020521162,-0.00020225237,-4.098558,0.27805793,-186.52847,186.81476,0.57636803,0.5842287,-13.385086,-186.68773,-242.77681,1.1605967,4.02668,-8.140201,66.55481,1045000
51
+ 0.65615225,182.93965,0.002086048,-0.0014844314,-4.7116,0.27969843,-182.92981,183.21786,1.4443207,2.259946,-5.197251,-183.10143,-211.95079,3.7042668,27.10686,-40.110985,309.7966,1050000
52
+ 0.6463645,180.65613,0.002041546,-0.0022751784,-5.114439,0.29054672,-180.64569,180.9444,0.9526438,1.0252818,-1.6722863,-180.97752,-213.53018,1.9779255,6.6893587,-18.476252,121.35408,1055000
53
+ 0.659066,182.78044,0.0019624045,0.00022828914,-3.8836687,0.2992217,-182.77281,183.0799,0.41239196,0.54980516,0.9099683,-182.86287,-212.13281,0.9621971,4.4799495,-6.005502,72.328415,1060000
54
+ 0.661012,188.38223,0.0019215228,0.00088290183,-3.5405197,0.2921454,-188.37543,188.67526,0.38658625,0.82545245,-12.804912,-188.38998,-216.38023,1.2120388,9.833946,-11.189581,88.96404,1065000
55
+ 0.6573627,185.83789,0.0019188877,-0.0010725008,-4.558918,0.3439675,-185.82913,186.18079,0.3459485,0.54281324,-16.908092,-186.09833,-214.42859,0.88876176,2.941687,-4.298089,46.326775,1070000
56
+ 0.68464994,185.62103,0.0020230608,0.0022684806,-2.8786888,0.30027974,-185.61522,185.92358,0.4622781,0.7843682,-26.069994,-185.7028,-218.6988,1.2466463,10.925058,-28.974844,115.86657,1075000
57
+ 0.66077816,187.24765,0.0017655079,0.0013044368,-3.261155,0.28877813,-187.24188,187.53772,0.44067827,0.59742403,0.9286087,-187.1964,-224.94511,1.0381023,7.0147276,-4.7764153,68.76906,1080000
58
+ 0.6494507,183.45346,0.0017898524,-0.00013901119,-4.0776663,0.3111043,-183.44617,183.76443,0.54191935,0.71422195,-2.0863876,-183.59343,-210.14404,1.2561413,8.0117855,-2.2688131,69.68814,1085000
59
+ 0.6546681,189.73558,0.001759619,0.001101432,-3.3740509,0.27967995,-189.72964,190.01636,0.3117069,0.49074307,-25.541634,-190.10571,-237.24205,0.80244994,1.9776813,-2.6040118,50.98844,1090000
60
+ 0.659106,183.79904,0.001794119,0.00021813263,-3.878418,0.26657903,-183.79208,184.06584,0.6387095,1.4162372,0.37416643,-184.00418,-215.00146,2.0549467,6.2518005,-24.273579,114.955086,1095000
61
+ 0.66060495,189.8172,0.001725329,0.0016323152,-3.0539107,0.29104906,-189.81192,190.10988,0.34663066,0.5864641,-61.87074,-189.90309,-210.34674,0.93309474,8.099939,-3.6272943,68.528656,1100000
62
+ 0.67078716,190.1287,0.0017143218,0.00052891043,-3.6914754,0.32071856,-190.12238,190.44995,1.4467789,1.0971321,-17.382374,-190.16602,-211.57051,2.543911,11.305864,-21.66899,142.18561,1105000
63
+ 0.6702797,188.66998,0.0017194919,0.00089821895,-3.4776254,0.23067987,-188.664,188.90157,0.31174454,0.538365,-39.67434,-188.65456,-213.04616,0.8501096,2.5561202,-4.698317,47.666153,1110000
64
+ 0.66577685,186.15842,0.0016644292,0.00023616038,-3.8581133,0.22913888,-186.152,186.38779,1.052213,1.2616175,-1.9974835,-186.32027,-208.40274,2.3138304,23.903603,-15.109661,161.42722,1115000
65
+ 0.6610365,188.87538,0.0015584833,0.0010221892,-3.3441129,0.27811772,-188.87018,189.15453,0.75598663,0.7180671,1.4225149,-189.00569,-218.44972,1.4740537,9.155812,-5.097465,96.515175,1120000
66
+ 0.65249455,184.5758,0.0015437176,-0.00083988125,-4.544064,0.3212091,-184.56879,184.89618,0.5482461,1.0622125,0.82299936,-184.69238,-210.13396,1.6104586,6.563508,-16.689365,97.94157,1125000
67
+ 0.6644075,188.83788,0.0016013866,-0.00026720372,-4.1668577,0.2793461,-188.8312,189.11694,0.5395832,0.9947446,-25.361244,-188.92949,-211.57034,1.5343277,12.7525215,-23.632116,174.2224,1130000
68
+ 0.6531354,189.04483,0.0017065086,-0.0015704323,-4.9202604,0.30358484,-189.03644,189.34685,0.29997322,0.54196936,-8.880045,-189.14665,-211.7709,0.84194255,4.167777,-7.7009187,76.39613,1135000
69
+ 0.666884,188.75854,0.0015254301,0.000618252,-3.5947032,0.2937239,-188.75305,189.05289,0.71317524,1.4598658,-10.810992,-188.79372,-208.8547,2.173041,18.455652,-54.81407,272.8496,1140000
70
+ 0.6626635,187.95169,0.0014791167,-0.00091950805,-4.62166,0.28546906,-187.94485,188.23624,0.34330067,0.5970816,-16.000523,-188.20264,-220.46617,0.94038224,5.3269835,-7.7177267,79.15354,1145000
71
+ 0.6698371,190.3536,0.0015533804,0.00039918465,-3.743022,0.29699624,-190.34781,190.651,0.4816602,1.3319525,1.2602799,-190.32732,-210.17883,1.8136127,6.441722,-5.4998164,77.250984,1150000
72
+ 0.65375215,186.77109,0.0014960968,-0.00091903267,-4.614287,0.33716375,-186.76419,187.10733,0.48826653,1.0432588,0.21788895,-187.1364,-225.1382,1.5315254,7.3374214,-11.279683,96.63593,1155000
73
+ 0.66938794,190.3572,0.001575439,-0.0011422855,-4.7250586,0.29770362,-190.34976,190.65375,0.70788395,1.2830538,-27.376793,-190.60191,-218.83713,1.9909377,10.203221,-9.421048,127.8169,1160000
74
+ 0.67523825,188.80473,0.0014451657,0.0009886071,-3.3159213,0.29058847,-188.79994,189.09631,0.28826204,0.5546989,0.27665317,-188.72507,-213.21469,0.84296095,3.4973896,-2.2757664,49.207306,1165000
75
+ 0.66357195,189.20663,0.0014914598,0.0007396034,-3.5041077,0.2682222,-189.20142,189.47559,0.565124,1.802187,0.1781218,-189.35234,-217.8764,2.367311,23.074121,-14.456553,157.49971,1170000
76
+ 0.6846639,189.17168,0.0014668364,0.0007965555,-3.4569569,0.21960533,-189.1666,189.39207,0.26340213,0.70288366,0.5332999,-189.12582,-214.56071,0.9662858,10.370231,-4.587406,80.77166,1175000
77
+ 0.6729951,190.32117,0.0014442647,0.0010267264,-3.289101,0.31610528,-190.31644,190.63829,0.32437927,0.68433326,-3.9205241,-190.30821,-208.95143,1.0087125,16.121574,-7.7552485,89.54242,1180000
78
+ 0.6623801,186.43271,0.0014084773,-0.0015306332,-5.086729,0.2898342,-186.42552,186.72102,0.5446014,1.19462,-5.459181,-186.67876,-213.20552,1.7392213,53.6002,-11.789024,248.3999,1185000
79
+ 0.661216,186.12735,0.0014459654,-0.0010524679,-4.727865,0.26586348,-186.1205,186.39217,0.81457835,1.4962009,-2.5156255,-186.18106,-215.99406,2.3107793,13.370547,-15.840844,131.00372,1190000
80
+ 0.67040884,192.18727,0.001300718,-4.040803e-05,-4.031066,0.28331587,-192.182,192.47054,0.37932009,0.4779539,-59.766953,-192.4915,-209.30472,0.857274,2.2371328,-4.301054,47.554222,1195000
81
+ 0.6659585,188.75859,0.0013600003,0.00016217721,-3.880752,0.27817523,-188.7533,189.03693,0.56352586,1.9522148,-0.20084286,-188.98534,-210.35698,2.5157406,34.46636,-27.492931,204.95326,1200000
82
+ 0.67395496,186.64798,0.0014208921,-0.00057966635,-4.4079595,0.27596438,-186.64172,186.92337,0.49620676,0.79927015,-9.621678,-186.67334,-222.13997,1.2954769,8.327216,-3.5530972,74.8561,1205000
83
+ 0.6773862,188.09381,0.0014186215,-0.0016112154,-5.1357613,0.28142685,-188.08655,188.37363,0.85592747,1.6233352,-14.45825,-188.18489,-212.1174,2.4792628,10.33833,-18.878685,161.86295,1210000
84
+ 0.6588026,190.88785,0.001377696,-0.0008369872,-4.607527,0.29850036,-190.8815,191.18552,0.63362175,1.1402925,-0.16054118,-190.86797,-212.63466,1.7739143,18.53664,-8.768319,124.27507,1215000
85
+ 0.6755557,190.23663,0.0013654163,-0.00014207895,-4.1040554,0.30164975,-190.23102,190.53815,0.5471906,1.0077368,-8.117364,-190.29318,-217.43466,1.5549273,4.4037566,-29.53756,132.3195,1220000
86
+ 0.67854965,189.75296,0.0013619629,0.0014178009,-2.9590018,0.29571044,-189.74896,190.0501,0.814425,1.2965635,-7.754253,-189.93053,-213.69525,2.1109886,13.221599,-12.7555,157.7226,1225000
87
+ 0.67139363,188.70525,0.0013604304,0.00034485967,-3.746507,0.2927143,-188.70016,188.9983,0.7391239,1.293363,-27.549395,-188.96233,-215.4503,2.032487,6.9920454,-12.414979,130.90384,1230000
88
+ 0.6561971,189.21234,0.0013653598,-0.0032444254,-6.376242,0.2776913,-189.20363,189.48679,1.5686328,4.426973,-48.273327,-189.52278,-213.94693,5.9956055,46.201313,-20.03597,440.36942,1235000
89
+ 0.6797511,191.32407,0.0013786785,0.0007239733,-3.4748788,0.33755144,-191.31927,191.66234,0.6415319,0.69893205,1.4967402,-191.44388,-214.15738,1.3404639,4.270765,-4.4645805,71.5539,1240000
90
+ 0.65944266,187.52019,0.0013029112,-0.00080106023,-4.6148233,0.26927856,-187.51416,187.78867,0.84529173,1.4920939,-8.159115,-187.34651,-220.03195,2.3373857,12.09857,-13.078935,135.82265,1245000
91
+ 0.67009914,185.32053,0.0014086755,-0.0009318549,-4.6615114,0.30244142,-185.31395,185.62204,1.1578712,1.6421336,-3.387908,-185.07109,-213.56796,2.800005,56.87662,-23.57811,299.5103,1250000
92
+ 0.6603492,185.85721,0.0013568614,-0.0007631951,-4.562471,0.26703888,-185.85101,186.12349,1.5036772,4.346457,0.68157256,-186.2481,-214.05182,5.8501344,41.97448,-34.98622,361.7815,1255000
93
+ 0.6630215,186.91791,0.0012743835,-0.0001494427,-4.1172667,0.28556833,-186.91266,187.20332,0.42302138,0.6773302,-37.188488,-186.86656,-226.20992,1.1003516,6.733042,-3.357666,62.832924,1260000
94
+ 0.65707433,186.49124,0.0012895636,-0.0004671178,-4.3622293,0.27728462,-186.48563,186.76805,0.76005286,1.005154,-19.446352,-186.42697,-215.96983,1.7652068,8.260324,-10.376853,108.68802,1265000
95
+ 0.656726,186.04628,0.001378714,-0.000470822,-4.3414936,0.22990291,-186.0403,186.27571,0.5524161,0.63043755,-3.1109934,-186.06735,-213.23811,1.1828537,8.531865,-4.8013945,69.329414,1270000
96
+ 0.6707826,188.44934,0.0012240413,0.0003045427,-3.751199,0.31322157,-188.44475,188.76286,0.71856415,0.50169414,-1.7969768,-188.55823,-231.7049,1.2202582,2.1735544,-4.0291452,52.047264,1275000
97
+ 0.6543228,186.62164,0.0012077041,-0.0011440505,-4.9472938,0.28063995,-186.61566,186.90114,1.3006768,2.5426953,-1.7508414,-187.09715,-232.0803,3.843372,13.368669,-11.69472,222.69049,1280000
98
+ 0.6783483,191.3523,0.0012989789,0.0007409224,-3.4296117,0.28331196,-191.34784,191.63635,0.2401077,0.4138607,-26.193491,-191.2553,-213.53168,0.6539684,2.883823,-3.0752518,41.906464,1285000
99
+ 0.6675923,187.54117,0.0011952611,-0.00034478874,-4.288463,0.29363906,-187.53604,187.83446,0.60793155,0.66160554,-4.759765,-187.92204,-216.9264,1.2695371,8.451031,-18.757502,94.93582,1290000
100
+ 0.67397237,191.85107,0.0013014657,0.000101273625,-3.922185,0.31667742,-191.84595,192.16786,0.4531196,0.6305973,-63.293896,-192.12454,-214.49692,1.0837169,13.095474,-8.170705,89.41637,1295000
101
+ 0.6671679,190.33157,0.0012161012,0.00035821184,-3.7054424,0.28384095,-190.32707,190.61577,0.85799426,0.462838,-33.770657,-190.47319,-214.74864,1.3208323,8.765744,-33.871765,168.5904,1300000
O2O-w-diff-ckpts/dsrl/20260317_210355/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
+ 0.65248126,170.43422,0.0040408736,-0.0026740455,-4.6617494,0.3453765,-170.41539,170.77693,0.5621449,0.74613893,-1.5765696,-170.72115,-235.7158,1.3082838,2.5015533,-2.2941387,42.035847,805000
3
+ 0.65425897,168.45583,0.0040861946,-0.0013552245,-4.3316593,0.32632804,-168.43813,168.78079,0.69979304,2.2784956,-2.5692391,-168.60649,-223.71725,2.9782887,51.834457,-14.056904,223.18285,810000
4
+ 0.65934277,175.1708,0.003984067,0.0013917673,-3.6506667,0.36998954,-175.15625,175.54219,0.45501843,0.59567326,-3.9093843,-175.45149,-285.13446,1.0506917,3.0823832,-2.1583934,45.191628,815000
5
+ 0.6558094,172.4635,0.0038997398,0.0006255114,-3.8396018,0.3229397,-172.44852,172.78706,0.6791763,0.7669601,-18.039482,-172.50696,-216.62921,1.4461364,3.25417,-3.3693175,67.14663,820000
6
+ 0.66262996,172.3088,0.003916379,-0.0012600078,-4.3217278,0.2852732,-172.29189,172.59282,1.0702647,0.9404341,-0.21409816,-172.2899,-234.58353,2.0106988,4.290267,-8.230618,80.024895,825000
7
+ 0.64948535,170.84456,0.003819049,-0.0006334391,-4.165863,0.31929195,-170.82864,171.16321,0.5179897,0.744051,0.9069618,-170.788,-236.00401,1.2620406,2.7210567,-1.978744,55.105972,830000
8
+ 0.6579559,171.62897,0.0037072708,-0.0003795249,-4.102373,0.32354832,-171.61374,171.95213,1.2139338,2.6786973,0.99666107,-171.99612,-227.6873,3.892631,18.312902,-21.969135,179.06865,835000
9
+ 0.6579062,170.28514,0.0038211476,-0.00044357084,-4.116083,0.32359445,-170.26941,170.60829,0.617889,0.8446091,-1.8431194,-170.66441,-227.4598,1.4624981,2.993755,-1.7645732,53.992794,840000
10
+ 0.65841126,172.9555,0.0034903793,0.0008459737,-3.757627,0.32899952,-172.94238,173.28534,0.52825433,0.5709612,-4.9746633,-173.00925,-221.33682,1.0992155,2.790904,-2.378603,49.067345,845000
11
+ 0.6540127,173.25912,0.0035276483,-8.110648e-05,-4.0229917,0.3035951,-173.24493,173.56264,0.5750025,0.8558449,-0.19625002,-173.4781,-229.90433,1.4308474,9.251238,-7.5693307,77.76999,850000
12
+ 0.6593282,170.1417,0.0033521592,-0.00041535308,-4.123906,0.29572347,-170.12787,170.43701,0.637402,1.1854523,0.8896258,-170.34962,-229.40947,1.8228543,5.4008746,-7.6547966,87.90232,855000
13
+ 0.6511518,173.9816,0.003351555,-0.0012462374,-4.3718386,0.3390497,-173.96693,174.3194,0.5826209,1.15464,-39.27309,-174.27962,-274.0485,1.7372608,4.184668,-5.020544,76.01138,860000
14
+ 0.6602924,176.87292,0.003302268,0.00016838378,-3.9490097,0.29518783,-176.85986,177.16827,1.1375093,1.5366205,-11.635074,-176.93729,-233.21548,2.67413,12.816653,-11.011774,152.83942,865000
15
+ 0.6632719,175.34944,0.003226022,-0.0008924127,-4.2766294,0.27620292,-175.33565,175.62476,1.4737082,3.4881904,-1.7916465,-175.52878,-236.11562,4.961899,9.239059,-8.974409,156.89008,870000
16
+ 0.66121125,177.75665,0.0031165802,0.0019451936,-3.3758564,0.26510534,-177.74612,178.0237,0.4162472,0.8152459,1.5756845,-177.93199,-230.84259,1.2314931,3.513638,-2.4905312,58.03761,875000
17
+ 0.6571703,175.75638,0.003160052,0.0011992832,-3.6204863,0.32450265,-175.74495,176.08209,0.9063902,0.65449935,-0.92629063,-175.95036,-244.8503,1.5608895,2.6523535,-4.3062987,47.690735,880000
18
+ 0.6474816,177.6029,0.003008585,-0.0007809201,-4.259564,0.25528476,-177.59009,177.8574,1.9300957,1.2053291,-3.2105887,-177.97702,-249.7172,3.1354246,3.1824622,-2.9067285,68.16919,885000
19
+ 0.6555559,176.11224,0.0030995163,-0.0014949493,-4.482317,0.31392246,-176.09834,176.42467,0.7305532,1.101433,-15.304167,-176.01672,-251.38885,1.8319862,6.195334,-4.123494,78.00604,890000
20
+ 0.65515566,171.70468,0.0030221122,-0.0018373082,-4.607955,0.27117234,-171.69075,171.97403,0.84262174,1.1253909,2.56746,-171.87611,-221.36252,1.9680126,2.8867986,-7.511916,90.45363,895000
21
+ 0.6554468,174.5848,0.0029431896,-4.312997e-05,-4.014654,0.33624053,-174.57298,174.92099,0.5711957,0.8788981,-0.10868496,-174.76,-220.46393,1.4500937,4.480286,-3.2037132,61.136696,900000
22
+ 0.6506264,178.46451,0.0028592544,-0.0005343991,-4.1869016,0.31849056,-178.45255,178.78247,0.62119085,0.76984787,-3.9733262,-178.58017,-254.50891,1.3910387,2.1260705,-2.800685,55.96211,905000
23
+ 0.6577034,173.80414,0.0029150029,0.00022089867,-3.92422,0.27383825,-173.7927,174.07819,0.5558913,0.83786553,-14.502045,-173.89307,-253.71382,1.3937569,2.4680157,-3.7010126,55.654285,910000
24
+ 0.65976536,181.62715,0.0027334397,0.0014975935,-3.4521213,0.35612577,-181.61772,181.98477,0.7607002,1.0497082,-6.032939,-181.6374,-223.19833,1.8104085,6.9995384,-4.000905,94.46781,915000
25
+ 0.6550689,179.97433,0.002803323,0.0009951778,-3.6450007,0.29048654,-179.96411,180.26581,0.304423,0.4812703,-12.284696,-180.2689,-211.65779,0.7856933,1.814212,-2.554605,38.178814,920000
26
+ 0.6511414,178.75943,0.0025586998,-0.0010856361,-4.424292,0.2985925,-178.74812,179.05695,0.4561921,0.5010623,-27.473742,-179.13924,-233.80252,0.9572544,1.5296707,-2.235042,40.812996,925000
27
+ 0.6605681,178.06876,0.002783645,0.0005947927,-3.786326,0.28042,-178.05823,178.34978,0.99794066,1.8736542,-1.8307453,-177.99413,-249.9055,2.871595,35.778774,-11.309971,167.4173,930000
28
+ 0.669477,182.10516,0.0026567348,0.0012778064,-3.5190313,0.3162309,-182.09581,182.42268,0.27680093,1.1450537,-72.97711,-181.93231,-221.42603,1.4218547,4.2184067,-11.482321,69.75514,935000
29
+ 0.6693598,182.16684,0.0026928997,0.00077061617,-3.713834,0.3204943,-182.15683,182.48811,0.81097597,0.92073613,-4.4923863,-182.35501,-247.96156,1.7317121,4.763552,-4.762294,79.380165,940000
30
+ 0.66061586,176.84265,0.0027238205,0.00041824955,-3.8464475,0.31178123,-176.83218,177.15485,1.0172871,0.6027021,-5.7060337,-177.07637,-233.67827,1.6199892,2.9656696,-2.7799025,51.225353,945000
31
+ 0.6742782,181.91327,0.0027071806,0.0028296558,-2.9547591,0.34102422,-181.90527,182.25711,0.47102532,0.6189367,-8.939527,-182.25533,-220.49356,1.089962,2.2602048,-5.0939236,51.001347,950000
32
+ 0.6589843,182.91391,0.0025378752,0.0014706266,-3.4205284,0.3156201,-182.90524,183.23099,0.55220926,0.73031753,-11.050966,-183.11475,-242.39221,1.2825267,5.910697,-3.7408102,75.89187,955000
33
+ 0.6559348,178.06989,0.0024410128,-0.001318702,-4.5402274,0.28902265,-178.05879,178.35759,0.49300694,0.558908,-0.79517627,-178.19511,-219.36322,1.0519149,2.859947,-2.2217534,44.32652,960000
34
+ 0.6663641,183.55121,0.0026029362,0.0010380383,-3.6012049,0.3363462,-183.54182,183.8886,0.6050739,0.97929794,-46.86855,-183.85237,-250.74368,1.5843718,3.4212008,-2.2694573,76.34569,965000
35
+ 0.65913475,180.86041,0.0024854357,-0.00021831613,-4.087838,0.30332696,-180.85025,181.16353,0.5569636,0.916636,-0.43417686,-180.7985,-235.36015,1.4735997,2.7469752,-4.240775,74.80313,970000
36
+ 0.6647407,181.31519,0.0024118335,0.001440858,-3.4025881,0.27656323,-181.30698,181.59319,0.59755296,0.5101115,-51.766354,-181.58801,-222.06538,1.1076645,7.210548,-6.087767,66.456406,975000
37
+ 0.654214,177.90321,0.0024265447,-0.0011863451,-4.488903,0.31105766,-177.89232,178.21307,0.42754793,0.79187435,-3.0502825,-178.1554,-230.68419,1.2194223,3.0451083,-5.454179,59.4058,980000
38
+ 0.66761136,183.35399,0.0023738833,0.0009194056,-3.6126997,0.28331074,-183.3454,183.63821,0.6240904,2.0015619,-5.9003267,-183.28242,-219.29454,2.6256523,4.839738,-6.7898073,91.52127,985000
39
+ 0.6599628,180.2141,0.0023593921,-0.0009997326,-4.4237247,0.32172298,-180.20366,180.5348,1.2345085,1.4181925,-3.3760123,-180.48651,-226.97215,2.652701,11.383143,-13.392401,187.77895,990000
40
+ 0.6694889,184.53648,0.0023104313,0.0016367217,-3.2915947,0.28798544,-184.52887,184.8261,0.6864125,0.6797186,0.74160004,-184.4557,-215.07353,1.3661311,13.439897,-4.7534122,92.624146,995000
41
+ 0.6592324,180.70409,0.0023024972,-0.0008434906,-4.3663373,0.23780775,-180.69403,180.94106,0.9510722,1.30385,0.91648835,-180.92633,-222.75638,2.2549224,10.980577,-7.2062764,144.33095,1000000
42
+ 0.6646912,181.95135,0.0022261026,0.0007976677,-3.6416752,0.27603352,-181.94324,182.22818,0.5298559,0.94824713,-19.360893,-182.17552,-221.58246,1.478103,3.6260707,-6.511091,72.076675,1005000
43
+ 0.658268,183.75804,0.0022675323,0.00038592936,-3.829802,0.2576951,-183.74936,184.01611,0.29877058,0.6287408,-41.799644,-183.7924,-229.77917,0.92751133,2.7942557,-2.2897737,49.437965,1010000
44
+ 0.67403686,183.90543,0.0022188358,0.0004961061,-3.7764115,0.32499224,-183.89703,184.23093,3.695797,0.6709486,1.0625539,-184.01529,-214.82022,4.3667455,2.8405428,-2.810028,61.550285,1015000
45
+ 0.66717744,184.9242,0.0022188157,0.001995944,-3.1004462,0.31221282,-184.91733,185.2384,0.20988512,0.4589568,-0.00987494,-185.16191,-212.74217,0.66884196,3.9206178,-1.6754044,40.552696,1020000
46
+ 0.66327363,184.03905,0.0021061627,0.0008421464,-3.6001513,0.29349694,-184.03146,184.33339,1.0758727,1.3742801,1.8246698,-184.0236,-209.69557,2.4501529,8.149399,-2.9858112,109.9104,1025000
47
+ 0.66280115,184.39926,0.0021546443,-0.0004586635,-4.212872,0.27964634,-184.39018,184.67845,0.40764284,0.6126146,-27.19604,-184.69543,-250.30057,1.0202575,4.0268974,-6.9392405,62.69468,1030000
48
+ 0.6656438,185.82275,0.0021156315,0.0011028935,-3.478693,0.29678947,-185.81538,186.12064,0.99824333,0.52882755,-1.5806997,-185.88982,-225.76624,1.5270709,2.0334656,-2.923397,47.19291,1035000
49
+ 0.67397255,185.56952,0.002174784,0.0010146182,-3.5334625,0.2352382,-185.56184,185.80577,1.1621493,2.1775653,-3.745329,-185.78131,-215.40623,3.3397145,31.674187,-21.657774,254.80405,1040000
50
+ 0.66471696,186.5369,0.0020521162,-0.00020225237,-4.098558,0.27805793,-186.52847,186.81476,0.57636803,0.5842287,-13.385086,-186.68773,-242.77681,1.1605967,4.02668,-8.140201,66.55481,1045000
51
+ 0.65615225,182.93965,0.002086048,-0.0014844314,-4.7116,0.27969843,-182.92981,183.21786,1.4443207,2.259946,-5.197251,-183.10143,-211.95079,3.7042668,27.10686,-40.110985,309.7966,1050000
52
+ 0.6463645,180.65613,0.002041546,-0.0022751784,-5.114439,0.29054672,-180.64569,180.9444,0.9526438,1.0252818,-1.6722863,-180.97752,-213.53018,1.9779255,6.6893587,-18.476252,121.35408,1055000
53
+ 0.659066,182.78044,0.0019624045,0.00022828914,-3.8836687,0.2992217,-182.77281,183.0799,0.41239196,0.54980516,0.9099683,-182.86287,-212.13281,0.9621971,4.4799495,-6.005502,72.328415,1060000
54
+ 0.661012,188.38223,0.0019215228,0.00088290183,-3.5405197,0.2921454,-188.37543,188.67526,0.38658625,0.82545245,-12.804912,-188.38998,-216.38023,1.2120388,9.833946,-11.189581,88.96404,1065000
55
+ 0.6573627,185.83789,0.0019188877,-0.0010725008,-4.558918,0.3439675,-185.82913,186.18079,0.3459485,0.54281324,-16.908092,-186.09833,-214.42859,0.88876176,2.941687,-4.298089,46.326775,1070000
56
+ 0.68464994,185.62103,0.0020230608,0.0022684806,-2.8786888,0.30027974,-185.61522,185.92358,0.4622781,0.7843682,-26.069994,-185.7028,-218.6988,1.2466463,10.925058,-28.974844,115.86657,1075000
57
+ 0.66077816,187.24765,0.0017655079,0.0013044368,-3.261155,0.28877813,-187.24188,187.53772,0.44067827,0.59742403,0.9286087,-187.1964,-224.94511,1.0381023,7.0147276,-4.7764153,68.76906,1080000
58
+ 0.6494507,183.45346,0.0017898524,-0.00013901119,-4.0776663,0.3111043,-183.44617,183.76443,0.54191935,0.71422195,-2.0863876,-183.59343,-210.14404,1.2561413,8.0117855,-2.2688131,69.68814,1085000
59
+ 0.6546681,189.73558,0.001759619,0.001101432,-3.3740509,0.27967995,-189.72964,190.01636,0.3117069,0.49074307,-25.541634,-190.10571,-237.24205,0.80244994,1.9776813,-2.6040118,50.98844,1090000
60
+ 0.659106,183.79904,0.001794119,0.00021813263,-3.878418,0.26657903,-183.79208,184.06584,0.6387095,1.4162372,0.37416643,-184.00418,-215.00146,2.0549467,6.2518005,-24.273579,114.955086,1095000
61
+ 0.66060495,189.8172,0.001725329,0.0016323152,-3.0539107,0.29104906,-189.81192,190.10988,0.34663066,0.5864641,-61.87074,-189.90309,-210.34674,0.93309474,8.099939,-3.6272943,68.528656,1100000
62
+ 0.67078716,190.1287,0.0017143218,0.00052891043,-3.6914754,0.32071856,-190.12238,190.44995,1.4467789,1.0971321,-17.382374,-190.16602,-211.57051,2.543911,11.305864,-21.66899,142.18561,1105000
63
+ 0.6702797,188.66998,0.0017194919,0.00089821895,-3.4776254,0.23067987,-188.664,188.90157,0.31174454,0.538365,-39.67434,-188.65456,-213.04616,0.8501096,2.5561202,-4.698317,47.666153,1110000
64
+ 0.66577685,186.15842,0.0016644292,0.00023616038,-3.8581133,0.22913888,-186.152,186.38779,1.052213,1.2616175,-1.9974835,-186.32027,-208.40274,2.3138304,23.903603,-15.109661,161.42722,1115000
65
+ 0.6610365,188.87538,0.0015584833,0.0010221892,-3.3441129,0.27811772,-188.87018,189.15453,0.75598663,0.7180671,1.4225149,-189.00569,-218.44972,1.4740537,9.155812,-5.097465,96.515175,1120000
66
+ 0.65249455,184.5758,0.0015437176,-0.00083988125,-4.544064,0.3212091,-184.56879,184.89618,0.5482461,1.0622125,0.82299936,-184.69238,-210.13396,1.6104586,6.563508,-16.689365,97.94157,1125000
67
+ 0.6644075,188.83788,0.0016013866,-0.00026720372,-4.1668577,0.2793461,-188.8312,189.11694,0.5395832,0.9947446,-25.361244,-188.92949,-211.57034,1.5343277,12.7525215,-23.632116,174.2224,1130000
68
+ 0.6531354,189.04483,0.0017065086,-0.0015704323,-4.9202604,0.30358484,-189.03644,189.34685,0.29997322,0.54196936,-8.880045,-189.14665,-211.7709,0.84194255,4.167777,-7.7009187,76.39613,1135000
69
+ 0.666884,188.75854,0.0015254301,0.000618252,-3.5947032,0.2937239,-188.75305,189.05289,0.71317524,1.4598658,-10.810992,-188.79372,-208.8547,2.173041,18.455652,-54.81407,272.8496,1140000
70
+ 0.6626635,187.95169,0.0014791167,-0.00091950805,-4.62166,0.28546906,-187.94485,188.23624,0.34330067,0.5970816,-16.000523,-188.20264,-220.46617,0.94038224,5.3269835,-7.7177267,79.15354,1145000
71
+ 0.6698371,190.3536,0.0015533804,0.00039918465,-3.743022,0.29699624,-190.34781,190.651,0.4816602,1.3319525,1.2602799,-190.32732,-210.17883,1.8136127,6.441722,-5.4998164,77.250984,1150000
72
+ 0.65375215,186.77109,0.0014960968,-0.00091903267,-4.614287,0.33716375,-186.76419,187.10733,0.48826653,1.0432588,0.21788895,-187.1364,-225.1382,1.5315254,7.3374214,-11.279683,96.63593,1155000
73
+ 0.66938794,190.3572,0.001575439,-0.0011422855,-4.7250586,0.29770362,-190.34976,190.65375,0.70788395,1.2830538,-27.376793,-190.60191,-218.83713,1.9909377,10.203221,-9.421048,127.8169,1160000
74
+ 0.67523825,188.80473,0.0014451657,0.0009886071,-3.3159213,0.29058847,-188.79994,189.09631,0.28826204,0.5546989,0.27665317,-188.72507,-213.21469,0.84296095,3.4973896,-2.2757664,49.207306,1165000
75
+ 0.66357195,189.20663,0.0014914598,0.0007396034,-3.5041077,0.2682222,-189.20142,189.47559,0.565124,1.802187,0.1781218,-189.35234,-217.8764,2.367311,23.074121,-14.456553,157.49971,1170000
76
+ 0.6846639,189.17168,0.0014668364,0.0007965555,-3.4569569,0.21960533,-189.1666,189.39207,0.26340213,0.70288366,0.5332999,-189.12582,-214.56071,0.9662858,10.370231,-4.587406,80.77166,1175000
77
+ 0.6729951,190.32117,0.0014442647,0.0010267264,-3.289101,0.31610528,-190.31644,190.63829,0.32437927,0.68433326,-3.9205241,-190.30821,-208.95143,1.0087125,16.121574,-7.7552485,89.54242,1180000
78
+ 0.6623801,186.43271,0.0014084773,-0.0015306332,-5.086729,0.2898342,-186.42552,186.72102,0.5446014,1.19462,-5.459181,-186.67876,-213.20552,1.7392213,53.6002,-11.789024,248.3999,1185000
79
+ 0.661216,186.12735,0.0014459654,-0.0010524679,-4.727865,0.26586348,-186.1205,186.39217,0.81457835,1.4962009,-2.5156255,-186.18106,-215.99406,2.3107793,13.370547,-15.840844,131.00372,1190000
80
+ 0.67040884,192.18727,0.001300718,-4.040803e-05,-4.031066,0.28331587,-192.182,192.47054,0.37932009,0.4779539,-59.766953,-192.4915,-209.30472,0.857274,2.2371328,-4.301054,47.554222,1195000
81
+ 0.6659585,188.75859,0.0013600003,0.00016217721,-3.880752,0.27817523,-188.7533,189.03693,0.56352586,1.9522148,-0.20084286,-188.98534,-210.35698,2.5157406,34.46636,-27.492931,204.95326,1200000
82
+ 0.67395496,186.64798,0.0014208921,-0.00057966635,-4.4079595,0.27596438,-186.64172,186.92337,0.49620676,0.79927015,-9.621678,-186.67334,-222.13997,1.2954769,8.327216,-3.5530972,74.8561,1205000
83
+ 0.6773862,188.09381,0.0014186215,-0.0016112154,-5.1357613,0.28142685,-188.08655,188.37363,0.85592747,1.6233352,-14.45825,-188.18489,-212.1174,2.4792628,10.33833,-18.878685,161.86295,1210000
84
+ 0.6588026,190.88785,0.001377696,-0.0008369872,-4.607527,0.29850036,-190.8815,191.18552,0.63362175,1.1402925,-0.16054118,-190.86797,-212.63466,1.7739143,18.53664,-8.768319,124.27507,1215000
85
+ 0.6755557,190.23663,0.0013654163,-0.00014207895,-4.1040554,0.30164975,-190.23102,190.53815,0.5471906,1.0077368,-8.117364,-190.29318,-217.43466,1.5549273,4.4037566,-29.53756,132.3195,1220000
86
+ 0.67854965,189.75296,0.0013619629,0.0014178009,-2.9590018,0.29571044,-189.74896,190.0501,0.814425,1.2965635,-7.754253,-189.93053,-213.69525,2.1109886,13.221599,-12.7555,157.7226,1225000
87
+ 0.67139363,188.70525,0.0013604304,0.00034485967,-3.746507,0.2927143,-188.70016,188.9983,0.7391239,1.293363,-27.549395,-188.96233,-215.4503,2.032487,6.9920454,-12.414979,130.90384,1230000
88
+ 0.6561971,189.21234,0.0013653598,-0.0032444254,-6.376242,0.2776913,-189.20363,189.48679,1.5686328,4.426973,-48.273327,-189.52278,-213.94693,5.9956055,46.201313,-20.03597,440.36942,1235000
89
+ 0.6797511,191.32407,0.0013786785,0.0007239733,-3.4748788,0.33755144,-191.31927,191.66234,0.6415319,0.69893205,1.4967402,-191.44388,-214.15738,1.3404639,4.270765,-4.4645805,71.5539,1240000
90
+ 0.65944266,187.52019,0.0013029112,-0.00080106023,-4.6148233,0.26927856,-187.51416,187.78867,0.84529173,1.4920939,-8.159115,-187.34651,-220.03195,2.3373857,12.09857,-13.078935,135.82265,1245000
91
+ 0.67009914,185.32053,0.0014086755,-0.0009318549,-4.6615114,0.30244142,-185.31395,185.62204,1.1578712,1.6421336,-3.387908,-185.07109,-213.56796,2.800005,56.87662,-23.57811,299.5103,1250000
92
+ 0.6603492,185.85721,0.0013568614,-0.0007631951,-4.562471,0.26703888,-185.85101,186.12349,1.5036772,4.346457,0.68157256,-186.2481,-214.05182,5.8501344,41.97448,-34.98622,361.7815,1255000
93
+ 0.6630215,186.91791,0.0012743835,-0.0001494427,-4.1172667,0.28556833,-186.91266,187.20332,0.42302138,0.6773302,-37.188488,-186.86656,-226.20992,1.1003516,6.733042,-3.357666,62.832924,1260000
94
+ 0.65707433,186.49124,0.0012895636,-0.0004671178,-4.3622293,0.27728462,-186.48563,186.76805,0.76005286,1.005154,-19.446352,-186.42697,-215.96983,1.7652068,8.260324,-10.376853,108.68802,1265000
95
+ 0.656726,186.04628,0.001378714,-0.000470822,-4.3414936,0.22990291,-186.0403,186.27571,0.5524161,0.63043755,-3.1109934,-186.06735,-213.23811,1.1828537,8.531865,-4.8013945,69.329414,1270000
96
+ 0.6707826,188.44934,0.0012240413,0.0003045427,-3.751199,0.31322157,-188.44475,188.76286,0.71856415,0.50169414,-1.7969768,-188.55823,-231.7049,1.2202582,2.1735544,-4.0291452,52.047264,1275000
97
+ 0.6543228,186.62164,0.0012077041,-0.0011440505,-4.9472938,0.28063995,-186.61566,186.90114,1.3006768,2.5426953,-1.7508414,-187.09715,-232.0803,3.843372,13.368669,-11.69472,222.69049,1280000
98
+ 0.6783483,191.3523,0.0012989789,0.0007409224,-3.4296117,0.28331196,-191.34784,191.63635,0.2401077,0.4138607,-26.193491,-191.2553,-213.53168,0.6539684,2.883823,-3.0752518,41.906464,1285000
99
+ 0.6675923,187.54117,0.0011952611,-0.00034478874,-4.288463,0.29363906,-187.53604,187.83446,0.60793155,0.66160554,-4.759765,-187.92204,-216.9264,1.2695371,8.451031,-18.757502,94.93582,1290000
100
+ 0.67397237,191.85107,0.0013014657,0.000101273625,-3.922185,0.31667742,-191.84595,192.16786,0.4531196,0.6305973,-63.293896,-192.12454,-214.49692,1.0837169,13.095474,-8.170705,89.41637,1295000
101
+ 0.6671679,190.33157,0.0012161012,0.00035821184,-3.7054424,0.28384095,-190.32707,190.61577,0.85799426,0.462838,-33.770657,-190.47319,-214.74864,1.3208323,8.765744,-33.871765,168.5904,1300000
O2O-w-diff-ckpts/dsrl/20260317_210355/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e197d8784f82cbf2d8085490ad70e2ffaca90996b47b6e60219ed69808d4f3f
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8fbe1f0f5f3fc9eebfa48d6a837a2588e0b5a77ee27f6037ed4c7e5437471f2
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5069d98bf253d81bb55ff0dd7b86ec61298e283efcffe055171d8c5c2beb2d
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f64ae544f4e2744f7bdb4c11ace1b1b4ed58e93b8d70cfe4bbbe3a523b5096
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a6bced39c61df1dce4750280334ce18c7dab96f44669fdf5bd41017f7227d9
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_1250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ef14400a160ff21ad0e9ed8b06a58767de3ad55283d67914ead1f92340cb03
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_1300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d710a8f1fd48a43c04398f99d816ab10b4c603b75e963f17666f553dfde8eae
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_850000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b52f9113d0188fe9a4021cfc7a36e56b02b64a36ee322b74974ffa28401aa0ea
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_900000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:115bc5c26374338a905275471a53149e45bc2ad6cfbdf9dedb565cf2d5d2a089
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e957fa60db4e71d20e19f1d74e942b2f7bab9d44cc30220ea1b2fd3d780298
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260317_210355/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/dsrl/20260317_210355/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/7i0irac0
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1000000.png ADDED

Git LFS Details

  • SHA256: 05b39819e1ab7a8a81455079d1b492201476c05dcd6b24aa3c972178dff9878f
  • Pointer size: 131 Bytes
  • Size of remote file: 197 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1050000.png ADDED

Git LFS Details

  • SHA256: 0adbca45c50cdd1897a5debccd3f7afad6b3c1690480f226691504561c7c48f3
  • Pointer size: 131 Bytes
  • Size of remote file: 209 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1100000.png ADDED

Git LFS Details

  • SHA256: ca0ea4be44a78e9a60b827672192438922a2addb26b8a69d29b3bd7d6edecce8
  • Pointer size: 131 Bytes
  • Size of remote file: 197 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1150000.png ADDED

Git LFS Details

  • SHA256: 06f9a6be1e1d4eb8d84f4614831d1b3db19a8f8525a332b08ffe2997b7c59e9b
  • Pointer size: 131 Bytes
  • Size of remote file: 196 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1200000.png ADDED

Git LFS Details

  • SHA256: b720d03ff5b8e22731a63133ce73506994cfa7b053f306043a2a9d34ea6305eb
  • Pointer size: 131 Bytes
  • Size of remote file: 160 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1250000.png ADDED

Git LFS Details

  • SHA256: e246394d83d4bfe088a6ab96cf19af41340b29cbd8603b348fbb4dceb59e9b64
  • Pointer size: 131 Bytes
  • Size of remote file: 182 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1300000.png ADDED

Git LFS Details

  • SHA256: 70e68dade3db03d4ed072e08e29b958cce2e8398992b7d51bd317f485366f1af
  • Pointer size: 131 Bytes
  • Size of remote file: 162 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_850000.png ADDED

Git LFS Details

  • SHA256: b2b59775bb8641d7b756cef331eee1b6a3ecfb8853222b0b492e42cbd18988c5
  • Pointer size: 131 Bytes
  • Size of remote file: 225 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_900000.png ADDED

Git LFS Details

  • SHA256: 3ebdc45388d25f13cc94738a4cf9e6ac3b418ea9c8b9e2fa16be8a9b7e1a6c86
  • Pointer size: 131 Bytes
  • Size of remote file: 168 kB
O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_950000.png ADDED

Git LFS Details

  • SHA256: 9ccadf348df0957bca443de041276931fe2c2b8a64759a672efb463bb9c00f7f
  • Pointer size: 131 Bytes
  • Size of remote file: 188 kB