Tiredsheep commited on
Commit
61ba704
·
verified ·
1 Parent(s): 98d6166

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +10 -0
  2. O2O-w-diff-ckpts/dsrl/20260318_021110/env.csv +0 -0
  3. O2O-w-diff-ckpts/dsrl/20260318_021110/env_sv.csv +0 -0
  4. O2O-w-diff-ckpts/dsrl/20260318_021110/eval.csv +11 -0
  5. O2O-w-diff-ckpts/dsrl/20260318_021110/eval_sv.csv +11 -0
  6. O2O-w-diff-ckpts/dsrl/20260318_021110/online_agent.csv +101 -0
  7. O2O-w-diff-ckpts/dsrl/20260318_021110/online_agent_sv.csv +101 -0
  8. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1000000.pkl +3 -0
  9. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1050000.pkl +3 -0
  10. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1100000.pkl +3 -0
  11. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1150000.pkl +3 -0
  12. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1200000.pkl +3 -0
  13. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1250000.pkl +3 -0
  14. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1300000.pkl +3 -0
  15. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1350000.pkl +3 -0
  16. O2O-w-diff-ckpts/dsrl/20260318_021110/params_1400000.pkl +3 -0
  17. O2O-w-diff-ckpts/dsrl/20260318_021110/params_950000.pkl +3 -0
  18. O2O-w-diff-ckpts/dsrl/20260318_021110/progress.tk +1 -0
  19. O2O-w-diff-ckpts/dsrl/20260318_021110/token.tk +1 -0
  20. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1000000.png +3 -0
  21. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1050000.png +3 -0
  22. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1100000.png +3 -0
  23. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1150000.png +3 -0
  24. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1200000.png +3 -0
  25. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1250000.png +3 -0
  26. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1300000.png +3 -0
  27. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1350000.png +3 -0
  28. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1400000.png +3 -0
  29. O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_950000.png +3 -0
.gitattributes CHANGED
@@ -603,3 +603,13 @@ O2O-w-diff-ckpts/dsrl/20260317_210355/visited_states_1300000.png filter=lfs diff
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
 
 
 
 
 
 
 
 
 
 
 
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
606
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1000000.png filter=lfs diff=lfs merge=lfs -text
607
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1050000.png filter=lfs diff=lfs merge=lfs -text
608
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1100000.png filter=lfs diff=lfs merge=lfs -text
609
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1150000.png filter=lfs diff=lfs merge=lfs -text
610
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1200000.png filter=lfs diff=lfs merge=lfs -text
611
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1250000.png filter=lfs diff=lfs merge=lfs -text
612
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1300000.png filter=lfs diff=lfs merge=lfs -text
613
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1350000.png filter=lfs diff=lfs merge=lfs -text
614
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1400000.png filter=lfs diff=lfs merge=lfs -text
615
+ O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
O2O-w-diff-ckpts/dsrl/20260318_021110/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/dsrl/20260318_021110/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/dsrl/20260318_021110/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
+ 0.0,0.0,21.033191385608895,2.8273709728031013,-0.004613190964673227,2.8254592951118047,-0.005848919072025535,0.0,25500.0,-1.0,-1000.0,1000.0,1.5780560684204101,950000
3
+ 0.0,0.0,20.90152590899254,2.783818903703402,0.029480962442978025,2.782493013506819,-0.0425375815547661,0.02,77398.68,-0.98,-997.0,997.02,1.676076512336731,1000000
4
+ 0.0,0.0,25.53636225414844,3.4295919781793116,0.013192785809654158,3.4287867532240646,0.0012737222574394531,0.08,129181.12,-0.92,-993.82,993.9,1.606523699760437,1050000
5
+ 0.0,0.0,18.02138407088422,2.4716366040073248,0.012991373808802215,2.473462652672856,0.058647051164242174,0.0,181046.0,-1.0,-1000.0,1000.0,1.6054920387268066,1100000
6
+ 0.0,0.0,29.51251817277734,3.9869487908098926,0.023928249059039643,3.989563547101928,0.013381563097478443,0.1,232926.4,-0.9,-995.42,995.52,1.6775905561447144,1150000
7
+ 0.0,0.0,31.552278999630374,4.275911102464532,0.034885591828726366,4.28082902999933,0.0817521849514656,0.22,284199.44,-0.78,-979.64,979.86,1.5817009973526002,1200000
8
+ 0.0,0.0,32.84275349242796,4.429826670520814,0.0261722317841118,4.433683886319382,0.04058240621702744,0.1,335691.28,-0.9,-995.38,995.48,1.5895652627944947,1250000
9
+ 0.0,0.0,33.42920345568806,4.515540300087746,0.034447885366475695,4.51942024547321,0.04042707285480112,0.44,386238.86,-0.56,-953.22,953.66,1.5310829305648803,1300000
10
+ 0.0,0.0,34.7513554739718,4.686679806743199,0.08948851552087006,4.694426758760625,0.03252495563824892,0.32,436498.86,-0.68,-975.26,975.58,1.5473057222366333,1350000
11
+ 0.0,0.0,29.44766910235354,3.9662346169282356,0.044975727653589294,3.9719448365235435,0.06245705590017654,0.28,487356.9,-0.72,-974.9,975.18,1.5591465139389038,1400000
O2O-w-diff-ckpts/dsrl/20260318_021110/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
+ 0.0,0.0,21.033191385608895,2.8273709728031013,-0.004613190964673227,2.8254592951118047,-0.005848919072025535,0.0,25500.0,-1.0,-1000.0,1000.0,1.5780560684204101,950000
3
+ 0.0,0.0,20.90152590899254,2.783818903703402,0.029480962442978025,2.782493013506819,-0.0425375815547661,0.02,77398.68,-0.98,-997.0,997.02,1.676076512336731,1000000
4
+ 0.0,0.0,25.53636225414844,3.4295919781793116,0.013192785809654158,3.4287867532240646,0.0012737222574394531,0.08,129181.12,-0.92,-993.82,993.9,1.606523699760437,1050000
5
+ 0.0,0.0,18.02138407088422,2.4716366040073248,0.012991373808802215,2.473462652672856,0.058647051164242174,0.0,181046.0,-1.0,-1000.0,1000.0,1.6054920387268066,1100000
6
+ 0.0,0.0,29.51251817277734,3.9869487908098926,0.023928249059039643,3.989563547101928,0.013381563097478443,0.1,232926.4,-0.9,-995.42,995.52,1.6775905561447144,1150000
7
+ 0.0,0.0,31.552278999630374,4.275911102464532,0.034885591828726366,4.28082902999933,0.0817521849514656,0.22,284199.44,-0.78,-979.64,979.86,1.5817009973526002,1200000
8
+ 0.0,0.0,32.84275349242796,4.429826670520814,0.0261722317841118,4.433683886319382,0.04058240621702744,0.1,335691.28,-0.9,-995.38,995.48,1.5895652627944947,1250000
9
+ 0.0,0.0,33.42920345568806,4.515540300087746,0.034447885366475695,4.51942024547321,0.04042707285480112,0.44,386238.86,-0.56,-953.22,953.66,1.5310829305648803,1300000
10
+ 0.0,0.0,34.7513554739718,4.686679806743199,0.08948851552087006,4.694426758760625,0.03252495563824892,0.32,436498.86,-0.68,-975.26,975.58,1.5473057222366333,1350000
11
+ 0.0,0.0,29.44766910235354,3.9662346169282356,0.044975727653589294,3.9719448365235435,0.06245705590017654,0.28,487356.9,-0.72,-974.9,975.18,1.5591465139389038,1400000
O2O-w-diff-ckpts/dsrl/20260318_021110/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
+ 0.6670393,171.63437,0.003717795,-0.0007967843,-4.2143164,0.35432175,-171.61871,171.9879,0.546954,0.92647237,-3.0514758,-171.75552,-251.43164,1.4734263,2.5538383,-1.5377582,47.9585,905000
3
+ 0.64601505,168.94278,0.003760823,-0.0016240772,-4.431841,0.29595375,-168.92612,169.23712,0.6053365,1.0440401,-4.2486334,-169.09857,-223.19434,1.6493766,61.301525,-27.14174,175.2456,910000
4
+ 0.6602789,175.35785,0.0035566897,0.0006971938,-3.8039768,0.37324038,-175.34433,175.7318,0.4569896,0.50286627,-1.6633203,-175.63213,-231.47339,0.95985585,1.6192876,-2.3922966,43.339737,915000
5
+ 0.6671524,173.12746,0.0034958909,0.0015648054,-3.5523872,0.3065601,-173.11502,173.4356,0.5694782,0.6343562,-18.112164,-173.25157,-226.28853,1.2038344,4.0310445,-2.4829094,44.172153,920000
6
+ 0.6518918,171.79073,0.0033977418,-0.002337451,-4.6879425,0.29718727,-171.7748,172.08557,0.5868878,0.65039635,0.1978268,-172.05862,-240.60893,1.2372842,1.6366937,-2.2579749,42.120716,925000
7
+ 0.6467501,171.73918,0.0032856693,0.0005732983,-3.8255155,0.26927468,-171.72661,172.00903,0.44286314,0.75887525,0.59330946,-171.73962,-214.51923,1.2017384,2.2846277,-2.3720517,50.5952,930000
8
+ 0.66115457,171.65857,0.0033324033,-0.00029899995,-4.089725,0.31668395,-171.64494,171.97495,1.0384396,1.4933469,1.0089396,-171.95,-215.39809,2.5317864,8.098605,-15.730571,102.23421,935000
9
+ 0.64322114,170.76164,0.0034070676,-0.003326516,-4.9763575,0.3742746,-170.74469,171.13258,1.0071714,1.0930716,-1.7197161,-171.10107,-261.33893,2.100243,3.7107546,-4.33632,70.374016,940000
10
+ 0.6593921,174.0731,0.0033491617,0.0011303695,-3.6624918,0.30076712,-174.06085,174.375,0.45140058,0.6764469,-5.1621847,-174.14864,-222.45581,1.1278474,3.6562161,-3.4717953,53.93437,945000
11
+ 0.6508026,173.1756,0.0032657913,0.0006441303,-3.8027644,0.34829175,-173.1632,173.52454,0.5446626,0.592905,-0.33503687,-173.39003,-257.29242,1.1375675,3.269103,-2.2007213,55.595238,950000
12
+ 0.6508588,170.25632,0.0031250834,-0.00011033561,-4.0353065,0.30279428,-170.24371,170.559,0.642277,1.5223633,0.4133668,-170.48694,-219.83696,2.1646404,6.8680167,-4.399269,78.53927,955000
13
+ 0.6527693,174.85956,0.0031066823,-1.5061207e-05,-4.004848,0.32239616,-174.84714,175.18195,0.5540362,0.6867876,-38.337452,-174.98706,-227.80893,1.2408237,10.762796,-23.3983,90.42193,960000
14
+ 0.6565124,177.55652,0.0029454373,0.0015168815,-3.4850063,0.3397419,-177.54625,177.89777,0.3072182,0.61548865,-9.691139,-177.75543,-246.6361,0.92270684,3.4108377,-3.092408,46.657845,965000
15
+ 0.6628132,176.41843,0.0030052243,-0.00044672997,-4.148651,0.30144268,-176.40594,176.71942,0.5722946,1.3021895,-9.396207,-176.59648,-243.6751,1.8744841,12.066142,-6.2584233,90.438736,970000
16
+ 0.6649392,178.19687,0.0029268933,0.0012507214,-3.5726795,0.28146532,-178.18643,178.47958,0.30394173,0.93667364,0.2099005,-178.23184,-236.98915,1.2406154,6.3716707,-3.7097645,65.15209,975000
17
+ 0.6550263,176.30978,0.0029276193,-0.00034242566,-4.116964,0.32639277,-176.29774,176.63583,1.4550374,0.75594777,-2.5710967,-176.42493,-237.15431,2.2109852,5.209263,-1.8835897,54.23706,980000
18
+ 0.65452373,177.92142,0.0028750396,0.00032222993,-3.8879216,0.28468478,-177.91025,178.20642,1.819178,0.9510689,-2.3604553,-178.17114,-235.33762,2.770247,6.9548144,-5.1091614,78.539,985000
19
+ 0.65901995,176.12352,0.0028490564,-0.0005667092,-4.198911,0.35067058,-176.11156,176.47363,0.6683327,0.9234495,-15.04683,-176.08034,-231.53021,1.5917822,2.4958692,-3.2826424,58.45881,990000
20
+ 0.64836246,172.62901,0.0027137734,-0.0021100524,-4.7775345,0.3355679,-172.61604,172.96248,0.51121104,0.9549416,-0.010196388,-172.7786,-230.44182,1.4661527,2.131986,-2.7457473,47.52372,995000
21
+ 0.6466563,175.0625,0.0028109099,-0.0012757737,-4.453865,0.2659074,-175.04999,175.32713,0.8521881,0.97333765,-2.255432,-175.30034,-208.0188,1.8255258,7.750038,-5.5237103,79.32136,1000000
22
+ 0.65324974,178.6568,0.0027306231,0.0006924655,-3.7464075,0.28494483,-178.64658,178.94243,0.6047665,0.822179,-7.3125763,-178.84625,-223.7352,1.4269454,1.9837848,-2.6112099,52.571083,1005000
23
+ 0.64563257,174.6177,0.0028416624,-0.0006888533,-4.242412,0.26219165,-174.60564,174.87921,0.44961658,0.8148325,-13.968877,-174.82362,-253.59209,1.2644491,3.7973754,-3.1867151,52.78823,1010000
24
+ 0.6642746,182.33032,0.0026756853,0.0016923561,-3.3675056,0.33371565,-182.32129,182.66573,0.48722735,0.589461,-5.8730993,-182.3372,-215.28543,1.0766884,2.4794695,-2.6647391,57.501755,1015000
25
+ 0.64914346,179.19789,0.0026871008,-0.00075325364,-4.280322,0.29071906,-179.18637,179.48787,0.3105507,0.6007785,-11.97488,-179.54668,-212.16644,0.9113292,4.1640363,-4.3929086,56.179016,1020000
26
+ 0.6545262,180.41614,0.0025269121,-0.00081536354,-4.322672,0.3062793,-180.40521,180.7216,0.5372907,0.47476378,-28.993893,-180.63878,-248.50159,1.0120544,2.030898,-1.0736467,34.987965,1025000
27
+ 0.659256,179.90298,0.0026642135,-0.0012515865,-4.469777,0.29961598,-179.89108,180.20135,0.7248029,1.4473318,-9.496902,-179.88513,-215.71385,2.1721346,6.470054,-4.0958767,80.77707,1030000
28
+ 0.6586937,182.04391,0.0026041057,0.00046966987,-3.8196425,0.3209787,-182.03397,182.36537,0.31630212,0.5191948,-72.71835,-182.00221,-219.0787,0.8354969,2.0034523,-1.1856773,39.49557,1035000
29
+ 0.6604303,182.3504,0.0025016563,-0.00069840177,-4.2791758,0.2490398,-182.3397,182.59874,0.3665025,0.9885956,-10.69245,-182.64319,-215.29366,1.3550981,4.849765,-4.647144,72.6219,1040000
30
+ 0.6543116,177.9975,0.0024374665,0.00044477577,-3.8175254,0.31447965,-177.98819,178.31242,0.83896464,0.9874582,-11.049606,-178.3857,-258.79648,1.8264229,3.1093462,-2.203848,61.10648,1045000
31
+ 0.6597304,181.27579,0.0025489067,0.0017508048,-3.3131154,0.30089414,-181.26735,181.57843,0.88224185,1.1367028,-17.254019,-181.33455,-232.76534,2.0189447,4.3702936,-8.649059,96.575165,1050000
32
+ 0.66755486,184.20451,0.0026356403,0.00081175234,-3.6920094,0.29619622,-184.1948,184.50153,0.5802807,0.99680007,-11.375803,-184.28197,-278.29633,1.5770807,4.7658377,-5.666466,83.88017,1055000
33
+ 0.658281,177.64429,0.002400562,-0.0015611359,-4.650321,0.31549945,-177.63312,177.95824,0.8582784,0.8336277,0.36313218,-177.86546,-246.80037,1.6919061,5.6338105,-7.92807,102.64229,1060000
34
+ 0.66897416,184.50726,0.0026806968,0.0029478841,-2.900329,0.28242588,-184.49948,184.79263,0.954665,1.2229525,-44.92341,-184.40338,-319.98465,2.1776175,13.944182,-9.904698,118.21959,1065000
35
+ 0.6501375,181.41827,0.0024257419,7.821496e-06,-3.9967756,0.33475012,-181.40858,181.75304,25.700043,4.0307627,1.6313651,-181.63136,-213.78761,29.730804,62.956093,-229.32312,1065.835,1070000
36
+ 0.66251415,182.56795,0.0023171483,0.0016612345,-3.2830694,0.3141258,-182.56035,182.88374,0.7354744,1.02433,-0.74320936,-182.80157,-248.32593,1.7598045,4.5233727,-7.6934576,96.051216,1075000
37
+ 0.6423167,176.13144,0.0024010015,-0.0013412188,-4.558608,0.2847976,-176.1205,176.41489,0.8764009,0.849346,-1.7038842,-176.34155,-217.1039,1.7257469,6.003276,-11.860834,98.0921,1080000
38
+ 0.6506604,186.0116,0.002336332,-0.0002748907,-4.117659,0.30434188,-186.00197,186.31566,1.3902026,2.223037,-7.5813756,-186.46422,-232.31345,3.6132398,9.594994,-8.594264,146.37076,1085000
39
+ 0.652061,183.2174,0.0023334573,-0.001554958,-4.666375,0.29976183,-183.20651,183.51561,0.7915159,4.4025683,-48.24972,-183.38266,-245.62697,5.194084,16.519905,-36.865257,285.03165,1090000
40
+ 0.6567608,186.47813,0.0023156593,0.0013362423,-3.4229538,0.31650367,-186.47021,186.79597,0.7491216,1.2969416,0.323345,-186.18817,-211.55882,2.0460632,6.2805576,-7.159275,94.24598,1095000
41
+ 0.6436409,182.1963,0.0022645986,-0.00074935285,-4.330899,0.3053896,-182.1865,182.50095,0.66368645,0.7930439,4.2188425,-182.42897,-221.49084,1.4567304,4.5064898,-6.8867426,84.16779,1100000
42
+ 0.655128,182.07822,0.0021947452,-0.0003744192,-4.170598,0.34229472,-182.06906,182.42014,0.6151415,0.67463297,-8.587779,-182.21861,-216.79861,1.2897744,3.907357,-13.458316,77.543785,1105000
43
+ 0.6652458,187.41064,0.0022122331,0.0003859376,-3.8255439,0.27877766,-187.40218,187.6898,0.30980536,0.52310896,-38.40468,-187.49355,-249.47319,0.83291435,4.0658436,-2.0563478,38.74371,1110000
44
+ 0.6575564,187.17654,0.0021328754,0.00070915866,-3.6675105,0.23865625,-187.16872,187.41591,0.7333812,0.79869324,1.410733,-187.1395,-217.79248,1.5320745,5.9407444,-21.820446,114.63686,1115000
45
+ 0.6676979,187.98389,0.0020810836,0.001414541,-3.3202863,0.29076773,-187.97699,188.27608,0.3966453,0.76981974,0.6973159,-187.96904,-229.99965,1.166465,2.8445241,-1.8834102,49.761215,1120000
46
+ 0.66437435,185.94025,0.0019960946,0.0011225481,-3.4376278,0.30806768,-185.93338,186.24945,1.2258366,1.1876472,1.7314005,-186.147,-213.1374,2.4134839,4.9485245,-3.7659798,73.601074,1125000
47
+ 0.66271317,187.0163,0.0021663825,-0.0018907213,-4.872755,0.30348355,-187.00574,187.31789,0.9031753,2.2473264,-36.184795,-187.18187,-260.57977,3.1505017,20.14508,-12.116455,156.49402,1130000
48
+ 0.66359174,187.67207,0.0018972148,0.0014071722,-3.2582958,0.29552713,-187.66588,187.96901,0.31484076,0.594236,-0.38659585,-187.84175,-245.0254,0.9090768,2.4164066,-1.278304,37.667725,1135000
49
+ 0.6635903,188.55565,0.0020219828,-0.00046983734,-4.2323647,0.28295422,-188.54709,188.83813,0.6003941,0.68671215,-57.1251,-188.69202,-213.08112,1.2871063,5.735427,-9.153477,72.11002,1140000
50
+ 0.65965366,187.42276,0.0019339497,-0.000655934,-4.339168,0.3020659,-187.41437,187.72417,0.3606383,0.98102057,-3.9209325,-187.51787,-280.9202,1.3416588,5.4048357,-7.31367,74.38152,1145000
51
+ 0.6651617,186.78256,0.0019910857,-0.00022401936,-4.112511,0.26183033,-186.77437,187.04416,1.5413059,4.9389343,-8.242328,-186.82028,-212.7199,6.4802403,15.669991,-30.480188,270.63315,1150000
52
+ 0.6412491,183.8808,0.0019808733,-0.0025341476,-5.2793083,0.35885623,-183.87033,184.23712,1.6459633,1.4377335,-6.3845572,-184.02109,-226.51802,3.0836968,17.45944,-25.389326,200.579,1155000
53
+ 0.6625606,185.1886,0.0018586724,-0.0005678112,-4.305493,0.29028505,-185.1806,185.47832,0.749879,1.1323298,-0.35623384,-185.29268,-237.60846,1.8822088,6.9356008,-10.002862,96.60294,1160000
54
+ 0.684578,189.9986,0.0018355735,0.00053188123,-3.710237,0.29534695,-189.99176,190.29448,0.35125598,0.96093637,-47.67652,-190.22746,-240.8643,1.3121923,9.135215,-10.291422,80.63627,1165000
55
+ 0.66897213,187.25061,0.0017760245,0.001033352,-3.4181657,0.29828075,-187.24454,187.54993,0.39274785,0.76781255,-18.745111,-187.33206,-214.44073,1.1605604,3.9177527,-2.7622867,47.753395,1170000
56
+ 0.680139,186.06433,0.0018642617,0.0012665811,-3.320599,0.24527708,-186.05814,186.31087,0.6147364,0.66490066,-30.592094,-186.07072,-230.59204,1.2796371,6.7922378,-7.491382,78.51149,1175000
57
+ 0.6696539,188.01462,0.0017443235,0.00086263317,-3.5054626,0.33126038,-188.0085,188.34674,0.6247472,0.55617696,-0.4407962,-188.03061,-229.30049,1.1809242,29.061659,-18.670643,148.81482,1180000
58
+ 0.644456,185.49583,0.0017406752,-0.0031835015,-5.828889,0.3024999,-185.48569,185.79515,2.0113702,1.2702777,-0.8049642,-185.62553,-236.13219,3.281648,20.689247,-16.937656,143.2643,1185000
59
+ 0.66383713,191.40607,0.0017571715,1.2315648e-05,-3.9929912,0.2840946,-191.39906,191.69017,0.22074628,0.3342249,-22.662098,-191.73994,-235.87083,0.5549712,1.4654535,-1.606861,36.17539,1190000
60
+ 0.66767955,185.06189,0.0017427141,0.00058739254,-3.6629438,0.29949197,-185.0555,185.36197,0.7817203,1.0410947,0.8614138,-185.13731,-223.08038,1.822815,6.9324923,-9.057613,93.56229,1195000
61
+ 0.66876,189.94522,0.001729595,0.0006419854,-3.6288233,0.27812645,-189.93895,190.22398,0.58780986,0.81608737,-65.83135,-190.13255,-255.14702,1.4038973,4.2788177,-3.6268425,74.738464,1200000
62
+ 0.6558011,190.2015,0.0015415895,-0.0009019255,-4.585062,0.27192885,-190.19446,190.47253,1.2333082,1.212839,-19.169046,-190.19174,-218.19025,2.4461472,9.163995,-21.323908,141.52603,1205000
63
+ 0.6711917,189.36993,0.0015630581,0.00041140517,-3.7367947,0.28113383,-189.36409,189.65147,2.2042122,2.281865,-47.717094,-189.37433,-218.41667,4.4860773,18.297009,-35.996246,247.66118,1210000
64
+ 0.65276635,186.03577,0.0016190315,-0.00052695157,-4.3254733,0.31283137,-186.02878,186.34807,0.59829426,0.9340796,0.106386065,-186.27869,-215.31453,1.5323739,6.733148,-6.636025,84.21106,1215000
65
+ 0.65899605,189.50648,0.0015477265,-0.00019628354,-4.1268206,0.32201314,-189.50009,189.8283,0.5395903,0.80041903,0.2826603,-189.7017,-225.51933,1.3400093,4.8356028,-7.152608,84.37147,1220000
66
+ 0.6603303,184.99875,0.0016244717,-0.00056068256,-4.3451476,0.33500856,-184.9917,185.33319,1.1913587,1.8695863,1.61325,-185.26549,-251.88588,3.060945,7.614193,-7.7456226,124.9681,1225000
67
+ 0.6634073,188.66718,0.0015307033,-0.0009460681,-4.618061,0.27876443,-188.6601,188.94499,1.0020288,1.4237286,-8.167051,-188.89143,-213.05287,2.4257574,7.538858,-15.709928,151.12758,1230000
68
+ 0.6478219,189.18188,0.0015219718,-0.0012715955,-4.835492,0.29118016,-189.17451,189.4718,0.4577872,1.0503892,-26.699345,-189.20609,-216.46574,1.5081763,5.5687094,-8.489463,76.80682,1235000
69
+ 0.67438126,189.64641,0.0014525312,0.0012371046,-3.1483111,0.3233869,-189.64182,189.97102,0.84964335,0.6814948,-7.4888473,-189.87157,-223.38509,1.5311382,6.752016,-11.91947,114.96374,1240000
70
+ 0.6636891,189.64005,0.0014129002,-0.00032577757,-4.2305737,0.29718095,-189.63406,189.9369,0.32748538,0.74015343,-33.90202,-189.8833,-253.56633,1.0676389,11.806709,-5.2704186,73.08186,1245000
71
+ 0.6676886,191.59473,0.0014261608,0.00014190869,-3.900496,0.32033437,-191.58917,191.91519,0.45286036,2.1346624,0.258246,-191.72298,-214.11177,2.5875227,19.192015,-43.500847,267.83157,1250000
72
+ 0.6589515,188.48468,0.001334333,-0.0007590996,-4.568898,0.30203694,-188.47858,188.78595,0.7608811,1.1714209,-0.16646016,-188.5987,-247.2255,1.932302,7.5328364,-11.227447,102.84806,1255000
73
+ 0.67489004,192.39638,0.0014136912,0.0006339777,-3.5515444,0.27905744,-192.39136,192.67607,0.7575829,1.1946213,-32.268173,-192.7069,-244.6381,1.9522042,9.652484,-7.703369,125.14337,1260000
74
+ 0.6729989,189.85245,0.0013004862,3.1992928e-05,-3.9753993,0.30166274,-189.84727,190.15414,0.4210177,1.1057855,1.472721,-189.94926,-236.23665,1.5268033,7.574065,-8.694388,71.572754,1265000
75
+ 0.65882593,189.55894,0.0012825095,-0.00029658558,-4.231254,0.25696045,-189.55351,189.81561,0.46703932,1.1755527,0.62234765,-189.71507,-213.04564,1.6425921,14.317837,-11.414072,106.28622,1270000
76
+ 0.68319213,190.5317,0.0013732393,0.0007882569,-3.4259872,0.2977566,-190.527,190.83025,0.5956725,2.1003444,0.34344178,-190.31625,-217.31012,2.6960168,12.811114,-28.88376,234.6852,1275000
77
+ 0.667497,189.89783,0.0012949534,-0.00019632342,-4.1516066,0.32844105,-189.89246,190.22607,0.5517094,1.0260916,-8.570631,-189.91032,-209.59491,1.577801,23.346142,-8.224873,122.62017,1280000
78
+ 0.6478355,189.3947,0.0012660892,-0.0019161766,-5.513461,0.31495532,-189.38773,189.70773,0.46424732,0.94187415,-19.431961,-189.58865,-229.73236,1.4061215,9.99692,-6.4547997,112.19078,1285000
79
+ 0.66811085,189.8552,0.0013130505,-0.00033728676,-4.2568727,0.30200303,-189.84961,190.15686,0.5318803,0.9720645,-1.7684671,-189.91533,-214.95042,1.5039449,9.5580435,-14.919923,97.965004,1290000
80
+ 0.6897229,193.9361,0.0012794408,0.0006059833,-3.5263686,0.30013862,-193.9316,194.23685,0.6155899,2.0100822,-56.650864,-194.24533,-230.51218,2.625672,9.039595,-13.824524,112.125916,1295000
81
+ 0.67239165,188.8928,0.0011562572,-0.000650978,-4.5630045,0.3134975,-188.88753,189.20564,1.7178701,3.8759668,-1.884011,-189.18369,-212.17557,5.593837,28.898293,-15.649969,281.90503,1300000
82
+ 0.6707265,189.641,0.0012659129,0.00023426262,-3.8149457,0.25783128,-189.63618,189.89906,0.9185651,1.3036112,-1.7179902,-189.78883,-223.6208,2.2221763,11.156598,-18.614403,128.08795,1305000
83
+ 0.6521983,190.77173,0.0011331359,-0.0007401456,-4.6531835,0.2820726,-190.76645,191.05305,0.51388365,1.9059056,-13.504359,-190.91954,-221.67256,2.4197893,25.948671,-67.03914,232.94257,1310000
84
+ 0.6788319,192.28644,0.001145226,0.0016204854,-2.5850081,0.29923537,-192.28346,192.5873,1.4801296,1.139309,-5.9369617,-192.29178,-226.2393,2.6194386,25.453903,-25.491425,159.44028,1315000
85
+ 0.6576946,189.32326,0.0011645893,-0.0017518986,-5.504306,0.29428604,-189.31686,189.61578,1.2485723,3.038218,2.6920884,-189.47063,-228.53975,4.2867904,29.616684,-59.355618,415.6256,1320000
86
+ 0.6766582,191.10506,0.0011396552,0.00076544884,-3.3283505,0.27516,-191.10126,191.38098,0.71745574,0.84171194,-19.883501,-191.25041,-245.19237,1.5591676,4.431915,-11.5639105,120.916115,1325000
87
+ 0.6755313,192.24911,0.0011133921,0.0003637327,-3.6733112,0.29380512,-192.24501,192.54329,0.6779932,1.9399832,-33.367584,-192.49596,-215.49455,2.6179764,16.188494,-45.45846,290.20746,1330000
88
+ 0.66944575,190.62897,0.0011105358,0.0004956512,-3.5536828,0.29074013,-190.625,190.9202,0.59080523,1.1538883,-27.686056,-190.63925,-206.60405,1.7446935,19.182175,-9.34041,126.958786,1335000
89
+ 0.6746665,191.68367,0.0011612128,0.00043918347,-3.621789,0.32288614,-191.67947,192.007,0.9456024,0.9943952,0.9420806,-191.66913,-214.68863,1.9399977,10.580227,-10.945002,103.724594,1340000
90
+ 0.6648619,190.11557,0.0011793822,-5.804648e-05,-4.0492177,0.27021506,-190.11081,190.38573,0.5894999,1.8403851,-1.0759437,-190.04137,-240.6017,2.429885,16.774399,-22.063086,175.72401,1345000
91
+ 0.66499615,188.07614,0.0011318453,-0.0002976235,-4.262954,0.27908766,-188.07132,188.35492,1.5095762,1.720603,-2.3393497,-188.14012,-211.24829,3.2301793,46.521484,-14.648386,225.22865,1350000
92
+ 0.6673101,186.82529,0.001099571,-0.00041705274,-4.379287,0.29642433,-186.82047,187.12129,0.7570882,1.458845,0.6311318,-187.18268,-208.62889,2.2159333,11.037621,-7.0275216,122.084015,1355000
93
+ 0.6628126,187.78026,0.0010589059,-0.00085754046,-4.8098364,0.27903196,-187.77516,188.05844,0.67444676,1.1782779,-7.7790756,-187.77623,-244.33675,1.8527246,10.777802,-19.4964,161.95267,1360000
94
+ 0.6651502,190.53473,0.0011664344,-0.00083391176,-4.714924,0.28134057,-190.52924,190.81523,0.43593,0.44178638,-33.873573,-190.65344,-208.68993,0.8777164,3.0523822,-2.2588813,43.05083,1365000
95
+ 0.65933543,189.21286,0.0010925618,-0.00056457124,-4.516741,0.29277897,-189.20792,189.50508,0.7423549,0.94796723,-30.778757,-189.34367,-208.29475,1.6903222,25.019537,-10.591511,116.96028,1370000
96
+ 0.6560611,189.20663,0.0011332964,-0.0018990617,-5.6756973,0.30328926,-189.20021,189.50803,0.54705566,1.1886309,-3.2238007,-189.31395,-253.3823,1.7356865,4.636482,-13.878847,100.28694,1375000
97
+ 0.6577573,190.05699,0.0010596467,-0.00053258473,-4.502606,0.26018685,-190.05222,190.31665,0.4905034,0.6707069,-0.58878696,-190.19266,-253.94662,1.1612103,11.340082,-4.046285,69.14705,1380000
98
+ 0.6762712,192.89609,0.0011564452,0.0008689783,-3.248578,0.24934614,-192.8923,193.1463,0.51565176,1.1313419,-33.38729,-193.10847,-288.62622,1.6469936,23.770477,-12.508214,135.57913,1385000
99
+ 0.6811887,190.10342,0.0010931684,0.00077544065,-3.2906485,0.23569907,-190.09984,190.3399,0.6655709,1.3018726,-4.550262,-190.32463,-210.89786,1.9674435,22.244179,-17.581743,143.3633,1390000
100
+ 0.674438,191.76791,0.001088434,0.0011208932,-2.9701781,0.2547149,-191.76468,192.02374,0.384879,0.93062776,-13.582942,-192.01184,-217.71571,1.3155067,17.247381,-7.557503,144.55774,1395000
101
+ 0.6831577,193.14474,0.0010726207,0.0013227422,-2.7668128,0.27333897,-193.14178,193.41942,0.35746703,0.52970934,-31.720692,-193.33586,-207.13063,0.8871764,6.3352184,-4.335554,59.85502,1400000
O2O-w-diff-ckpts/dsrl/20260318_021110/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
+ 0.6670393,171.63437,0.003717795,-0.0007967843,-4.2143164,0.35432175,-171.61871,171.9879,0.546954,0.92647237,-3.0514758,-171.75552,-251.43164,1.4734263,2.5538383,-1.5377582,47.9585,905000
3
+ 0.64601505,168.94278,0.003760823,-0.0016240772,-4.431841,0.29595375,-168.92612,169.23712,0.6053365,1.0440401,-4.2486334,-169.09857,-223.19434,1.6493766,61.301525,-27.14174,175.2456,910000
4
+ 0.6602789,175.35785,0.0035566897,0.0006971938,-3.8039768,0.37324038,-175.34433,175.7318,0.4569896,0.50286627,-1.6633203,-175.63213,-231.47339,0.95985585,1.6192876,-2.3922966,43.339737,915000
5
+ 0.6671524,173.12746,0.0034958909,0.0015648054,-3.5523872,0.3065601,-173.11502,173.4356,0.5694782,0.6343562,-18.112164,-173.25157,-226.28853,1.2038344,4.0310445,-2.4829094,44.172153,920000
6
+ 0.6518918,171.79073,0.0033977418,-0.002337451,-4.6879425,0.29718727,-171.7748,172.08557,0.5868878,0.65039635,0.1978268,-172.05862,-240.60893,1.2372842,1.6366937,-2.2579749,42.120716,925000
7
+ 0.6467501,171.73918,0.0032856693,0.0005732983,-3.8255155,0.26927468,-171.72661,172.00903,0.44286314,0.75887525,0.59330946,-171.73962,-214.51923,1.2017384,2.2846277,-2.3720517,50.5952,930000
8
+ 0.66115457,171.65857,0.0033324033,-0.00029899995,-4.089725,0.31668395,-171.64494,171.97495,1.0384396,1.4933469,1.0089396,-171.95,-215.39809,2.5317864,8.098605,-15.730571,102.23421,935000
9
+ 0.64322114,170.76164,0.0034070676,-0.003326516,-4.9763575,0.3742746,-170.74469,171.13258,1.0071714,1.0930716,-1.7197161,-171.10107,-261.33893,2.100243,3.7107546,-4.33632,70.374016,940000
10
+ 0.6593921,174.0731,0.0033491617,0.0011303695,-3.6624918,0.30076712,-174.06085,174.375,0.45140058,0.6764469,-5.1621847,-174.14864,-222.45581,1.1278474,3.6562161,-3.4717953,53.93437,945000
11
+ 0.6508026,173.1756,0.0032657913,0.0006441303,-3.8027644,0.34829175,-173.1632,173.52454,0.5446626,0.592905,-0.33503687,-173.39003,-257.29242,1.1375675,3.269103,-2.2007213,55.595238,950000
12
+ 0.6508588,170.25632,0.0031250834,-0.00011033561,-4.0353065,0.30279428,-170.24371,170.559,0.642277,1.5223633,0.4133668,-170.48694,-219.83696,2.1646404,6.8680167,-4.399269,78.53927,955000
13
+ 0.6527693,174.85956,0.0031066823,-1.5061207e-05,-4.004848,0.32239616,-174.84714,175.18195,0.5540362,0.6867876,-38.337452,-174.98706,-227.80893,1.2408237,10.762796,-23.3983,90.42193,960000
14
+ 0.6565124,177.55652,0.0029454373,0.0015168815,-3.4850063,0.3397419,-177.54625,177.89777,0.3072182,0.61548865,-9.691139,-177.75543,-246.6361,0.92270684,3.4108377,-3.092408,46.657845,965000
15
+ 0.6628132,176.41843,0.0030052243,-0.00044672997,-4.148651,0.30144268,-176.40594,176.71942,0.5722946,1.3021895,-9.396207,-176.59648,-243.6751,1.8744841,12.066142,-6.2584233,90.438736,970000
16
+ 0.6649392,178.19687,0.0029268933,0.0012507214,-3.5726795,0.28146532,-178.18643,178.47958,0.30394173,0.93667364,0.2099005,-178.23184,-236.98915,1.2406154,6.3716707,-3.7097645,65.15209,975000
17
+ 0.6550263,176.30978,0.0029276193,-0.00034242566,-4.116964,0.32639277,-176.29774,176.63583,1.4550374,0.75594777,-2.5710967,-176.42493,-237.15431,2.2109852,5.209263,-1.8835897,54.23706,980000
18
+ 0.65452373,177.92142,0.0028750396,0.00032222993,-3.8879216,0.28468478,-177.91025,178.20642,1.819178,0.9510689,-2.3604553,-178.17114,-235.33762,2.770247,6.9548144,-5.1091614,78.539,985000
19
+ 0.65901995,176.12352,0.0028490564,-0.0005667092,-4.198911,0.35067058,-176.11156,176.47363,0.6683327,0.9234495,-15.04683,-176.08034,-231.53021,1.5917822,2.4958692,-3.2826424,58.45881,990000
20
+ 0.64836246,172.62901,0.0027137734,-0.0021100524,-4.7775345,0.3355679,-172.61604,172.96248,0.51121104,0.9549416,-0.010196388,-172.7786,-230.44182,1.4661527,2.131986,-2.7457473,47.52372,995000
21
+ 0.6466563,175.0625,0.0028109099,-0.0012757737,-4.453865,0.2659074,-175.04999,175.32713,0.8521881,0.97333765,-2.255432,-175.30034,-208.0188,1.8255258,7.750038,-5.5237103,79.32136,1000000
22
+ 0.65324974,178.6568,0.0027306231,0.0006924655,-3.7464075,0.28494483,-178.64658,178.94243,0.6047665,0.822179,-7.3125763,-178.84625,-223.7352,1.4269454,1.9837848,-2.6112099,52.571083,1005000
23
+ 0.64563257,174.6177,0.0028416624,-0.0006888533,-4.242412,0.26219165,-174.60564,174.87921,0.44961658,0.8148325,-13.968877,-174.82362,-253.59209,1.2644491,3.7973754,-3.1867151,52.78823,1010000
24
+ 0.6642746,182.33032,0.0026756853,0.0016923561,-3.3675056,0.33371565,-182.32129,182.66573,0.48722735,0.589461,-5.8730993,-182.3372,-215.28543,1.0766884,2.4794695,-2.6647391,57.501755,1015000
25
+ 0.64914346,179.19789,0.0026871008,-0.00075325364,-4.280322,0.29071906,-179.18637,179.48787,0.3105507,0.6007785,-11.97488,-179.54668,-212.16644,0.9113292,4.1640363,-4.3929086,56.179016,1020000
26
+ 0.6545262,180.41614,0.0025269121,-0.00081536354,-4.322672,0.3062793,-180.40521,180.7216,0.5372907,0.47476378,-28.993893,-180.63878,-248.50159,1.0120544,2.030898,-1.0736467,34.987965,1025000
27
+ 0.659256,179.90298,0.0026642135,-0.0012515865,-4.469777,0.29961598,-179.89108,180.20135,0.7248029,1.4473318,-9.496902,-179.88513,-215.71385,2.1721346,6.470054,-4.0958767,80.77707,1030000
28
+ 0.6586937,182.04391,0.0026041057,0.00046966987,-3.8196425,0.3209787,-182.03397,182.36537,0.31630212,0.5191948,-72.71835,-182.00221,-219.0787,0.8354969,2.0034523,-1.1856773,39.49557,1035000
29
+ 0.6604303,182.3504,0.0025016563,-0.00069840177,-4.2791758,0.2490398,-182.3397,182.59874,0.3665025,0.9885956,-10.69245,-182.64319,-215.29366,1.3550981,4.849765,-4.647144,72.6219,1040000
30
+ 0.6543116,177.9975,0.0024374665,0.00044477577,-3.8175254,0.31447965,-177.98819,178.31242,0.83896464,0.9874582,-11.049606,-178.3857,-258.79648,1.8264229,3.1093462,-2.203848,61.10648,1045000
31
+ 0.6597304,181.27579,0.0025489067,0.0017508048,-3.3131154,0.30089414,-181.26735,181.57843,0.88224185,1.1367028,-17.254019,-181.33455,-232.76534,2.0189447,4.3702936,-8.649059,96.575165,1050000
32
+ 0.66755486,184.20451,0.0026356403,0.00081175234,-3.6920094,0.29619622,-184.1948,184.50153,0.5802807,0.99680007,-11.375803,-184.28197,-278.29633,1.5770807,4.7658377,-5.666466,83.88017,1055000
33
+ 0.658281,177.64429,0.002400562,-0.0015611359,-4.650321,0.31549945,-177.63312,177.95824,0.8582784,0.8336277,0.36313218,-177.86546,-246.80037,1.6919061,5.6338105,-7.92807,102.64229,1060000
34
+ 0.66897416,184.50726,0.0026806968,0.0029478841,-2.900329,0.28242588,-184.49948,184.79263,0.954665,1.2229525,-44.92341,-184.40338,-319.98465,2.1776175,13.944182,-9.904698,118.21959,1065000
35
+ 0.6501375,181.41827,0.0024257419,7.821496e-06,-3.9967756,0.33475012,-181.40858,181.75304,25.700043,4.0307627,1.6313651,-181.63136,-213.78761,29.730804,62.956093,-229.32312,1065.835,1070000
36
+ 0.66251415,182.56795,0.0023171483,0.0016612345,-3.2830694,0.3141258,-182.56035,182.88374,0.7354744,1.02433,-0.74320936,-182.80157,-248.32593,1.7598045,4.5233727,-7.6934576,96.051216,1075000
37
+ 0.6423167,176.13144,0.0024010015,-0.0013412188,-4.558608,0.2847976,-176.1205,176.41489,0.8764009,0.849346,-1.7038842,-176.34155,-217.1039,1.7257469,6.003276,-11.860834,98.0921,1080000
38
+ 0.6506604,186.0116,0.002336332,-0.0002748907,-4.117659,0.30434188,-186.00197,186.31566,1.3902026,2.223037,-7.5813756,-186.46422,-232.31345,3.6132398,9.594994,-8.594264,146.37076,1085000
39
+ 0.652061,183.2174,0.0023334573,-0.001554958,-4.666375,0.29976183,-183.20651,183.51561,0.7915159,4.4025683,-48.24972,-183.38266,-245.62697,5.194084,16.519905,-36.865257,285.03165,1090000
40
+ 0.6567608,186.47813,0.0023156593,0.0013362423,-3.4229538,0.31650367,-186.47021,186.79597,0.7491216,1.2969416,0.323345,-186.18817,-211.55882,2.0460632,6.2805576,-7.159275,94.24598,1095000
41
+ 0.6436409,182.1963,0.0022645986,-0.00074935285,-4.330899,0.3053896,-182.1865,182.50095,0.66368645,0.7930439,4.2188425,-182.42897,-221.49084,1.4567304,4.5064898,-6.8867426,84.16779,1100000
42
+ 0.655128,182.07822,0.0021947452,-0.0003744192,-4.170598,0.34229472,-182.06906,182.42014,0.6151415,0.67463297,-8.587779,-182.21861,-216.79861,1.2897744,3.907357,-13.458316,77.543785,1105000
43
+ 0.6652458,187.41064,0.0022122331,0.0003859376,-3.8255439,0.27877766,-187.40218,187.6898,0.30980536,0.52310896,-38.40468,-187.49355,-249.47319,0.83291435,4.0658436,-2.0563478,38.74371,1110000
44
+ 0.6575564,187.17654,0.0021328754,0.00070915866,-3.6675105,0.23865625,-187.16872,187.41591,0.7333812,0.79869324,1.410733,-187.1395,-217.79248,1.5320745,5.9407444,-21.820446,114.63686,1115000
45
+ 0.6676979,187.98389,0.0020810836,0.001414541,-3.3202863,0.29076773,-187.97699,188.27608,0.3966453,0.76981974,0.6973159,-187.96904,-229.99965,1.166465,2.8445241,-1.8834102,49.761215,1120000
46
+ 0.66437435,185.94025,0.0019960946,0.0011225481,-3.4376278,0.30806768,-185.93338,186.24945,1.2258366,1.1876472,1.7314005,-186.147,-213.1374,2.4134839,4.9485245,-3.7659798,73.601074,1125000
47
+ 0.66271317,187.0163,0.0021663825,-0.0018907213,-4.872755,0.30348355,-187.00574,187.31789,0.9031753,2.2473264,-36.184795,-187.18187,-260.57977,3.1505017,20.14508,-12.116455,156.49402,1130000
48
+ 0.66359174,187.67207,0.0018972148,0.0014071722,-3.2582958,0.29552713,-187.66588,187.96901,0.31484076,0.594236,-0.38659585,-187.84175,-245.0254,0.9090768,2.4164066,-1.278304,37.667725,1135000
49
+ 0.6635903,188.55565,0.0020219828,-0.00046983734,-4.2323647,0.28295422,-188.54709,188.83813,0.6003941,0.68671215,-57.1251,-188.69202,-213.08112,1.2871063,5.735427,-9.153477,72.11002,1140000
50
+ 0.65965366,187.42276,0.0019339497,-0.000655934,-4.339168,0.3020659,-187.41437,187.72417,0.3606383,0.98102057,-3.9209325,-187.51787,-280.9202,1.3416588,5.4048357,-7.31367,74.38152,1145000
51
+ 0.6651617,186.78256,0.0019910857,-0.00022401936,-4.112511,0.26183033,-186.77437,187.04416,1.5413059,4.9389343,-8.242328,-186.82028,-212.7199,6.4802403,15.669991,-30.480188,270.63315,1150000
52
+ 0.6412491,183.8808,0.0019808733,-0.0025341476,-5.2793083,0.35885623,-183.87033,184.23712,1.6459633,1.4377335,-6.3845572,-184.02109,-226.51802,3.0836968,17.45944,-25.389326,200.579,1155000
53
+ 0.6625606,185.1886,0.0018586724,-0.0005678112,-4.305493,0.29028505,-185.1806,185.47832,0.749879,1.1323298,-0.35623384,-185.29268,-237.60846,1.8822088,6.9356008,-10.002862,96.60294,1160000
54
+ 0.684578,189.9986,0.0018355735,0.00053188123,-3.710237,0.29534695,-189.99176,190.29448,0.35125598,0.96093637,-47.67652,-190.22746,-240.8643,1.3121923,9.135215,-10.291422,80.63627,1165000
55
+ 0.66897213,187.25061,0.0017760245,0.001033352,-3.4181657,0.29828075,-187.24454,187.54993,0.39274785,0.76781255,-18.745111,-187.33206,-214.44073,1.1605604,3.9177527,-2.7622867,47.753395,1170000
56
+ 0.680139,186.06433,0.0018642617,0.0012665811,-3.320599,0.24527708,-186.05814,186.31087,0.6147364,0.66490066,-30.592094,-186.07072,-230.59204,1.2796371,6.7922378,-7.491382,78.51149,1175000
57
+ 0.6696539,188.01462,0.0017443235,0.00086263317,-3.5054626,0.33126038,-188.0085,188.34674,0.6247472,0.55617696,-0.4407962,-188.03061,-229.30049,1.1809242,29.061659,-18.670643,148.81482,1180000
58
+ 0.644456,185.49583,0.0017406752,-0.0031835015,-5.828889,0.3024999,-185.48569,185.79515,2.0113702,1.2702777,-0.8049642,-185.62553,-236.13219,3.281648,20.689247,-16.937656,143.2643,1185000
59
+ 0.66383713,191.40607,0.0017571715,1.2315648e-05,-3.9929912,0.2840946,-191.39906,191.69017,0.22074628,0.3342249,-22.662098,-191.73994,-235.87083,0.5549712,1.4654535,-1.606861,36.17539,1190000
60
+ 0.66767955,185.06189,0.0017427141,0.00058739254,-3.6629438,0.29949197,-185.0555,185.36197,0.7817203,1.0410947,0.8614138,-185.13731,-223.08038,1.822815,6.9324923,-9.057613,93.56229,1195000
61
+ 0.66876,189.94522,0.001729595,0.0006419854,-3.6288233,0.27812645,-189.93895,190.22398,0.58780986,0.81608737,-65.83135,-190.13255,-255.14702,1.4038973,4.2788177,-3.6268425,74.738464,1200000
62
+ 0.6558011,190.2015,0.0015415895,-0.0009019255,-4.585062,0.27192885,-190.19446,190.47253,1.2333082,1.212839,-19.169046,-190.19174,-218.19025,2.4461472,9.163995,-21.323908,141.52603,1205000
63
+ 0.6711917,189.36993,0.0015630581,0.00041140517,-3.7367947,0.28113383,-189.36409,189.65147,2.2042122,2.281865,-47.717094,-189.37433,-218.41667,4.4860773,18.297009,-35.996246,247.66118,1210000
64
+ 0.65276635,186.03577,0.0016190315,-0.00052695157,-4.3254733,0.31283137,-186.02878,186.34807,0.59829426,0.9340796,0.106386065,-186.27869,-215.31453,1.5323739,6.733148,-6.636025,84.21106,1215000
65
+ 0.65899605,189.50648,0.0015477265,-0.00019628354,-4.1268206,0.32201314,-189.50009,189.8283,0.5395903,0.80041903,0.2826603,-189.7017,-225.51933,1.3400093,4.8356028,-7.152608,84.37147,1220000
66
+ 0.6603303,184.99875,0.0016244717,-0.00056068256,-4.3451476,0.33500856,-184.9917,185.33319,1.1913587,1.8695863,1.61325,-185.26549,-251.88588,3.060945,7.614193,-7.7456226,124.9681,1225000
67
+ 0.6634073,188.66718,0.0015307033,-0.0009460681,-4.618061,0.27876443,-188.6601,188.94499,1.0020288,1.4237286,-8.167051,-188.89143,-213.05287,2.4257574,7.538858,-15.709928,151.12758,1230000
68
+ 0.6478219,189.18188,0.0015219718,-0.0012715955,-4.835492,0.29118016,-189.17451,189.4718,0.4577872,1.0503892,-26.699345,-189.20609,-216.46574,1.5081763,5.5687094,-8.489463,76.80682,1235000
69
+ 0.67438126,189.64641,0.0014525312,0.0012371046,-3.1483111,0.3233869,-189.64182,189.97102,0.84964335,0.6814948,-7.4888473,-189.87157,-223.38509,1.5311382,6.752016,-11.91947,114.96374,1240000
70
+ 0.6636891,189.64005,0.0014129002,-0.00032577757,-4.2305737,0.29718095,-189.63406,189.9369,0.32748538,0.74015343,-33.90202,-189.8833,-253.56633,1.0676389,11.806709,-5.2704186,73.08186,1245000
71
+ 0.6676886,191.59473,0.0014261608,0.00014190869,-3.900496,0.32033437,-191.58917,191.91519,0.45286036,2.1346624,0.258246,-191.72298,-214.11177,2.5875227,19.192015,-43.500847,267.83157,1250000
72
+ 0.6589515,188.48468,0.001334333,-0.0007590996,-4.568898,0.30203694,-188.47858,188.78595,0.7608811,1.1714209,-0.16646016,-188.5987,-247.2255,1.932302,7.5328364,-11.227447,102.84806,1255000
73
+ 0.67489004,192.39638,0.0014136912,0.0006339777,-3.5515444,0.27905744,-192.39136,192.67607,0.7575829,1.1946213,-32.268173,-192.7069,-244.6381,1.9522042,9.652484,-7.703369,125.14337,1260000
74
+ 0.6729989,189.85245,0.0013004862,3.1992928e-05,-3.9753993,0.30166274,-189.84727,190.15414,0.4210177,1.1057855,1.472721,-189.94926,-236.23665,1.5268033,7.574065,-8.694388,71.572754,1265000
75
+ 0.65882593,189.55894,0.0012825095,-0.00029658558,-4.231254,0.25696045,-189.55351,189.81561,0.46703932,1.1755527,0.62234765,-189.71507,-213.04564,1.6425921,14.317837,-11.414072,106.28622,1270000
76
+ 0.68319213,190.5317,0.0013732393,0.0007882569,-3.4259872,0.2977566,-190.527,190.83025,0.5956725,2.1003444,0.34344178,-190.31625,-217.31012,2.6960168,12.811114,-28.88376,234.6852,1275000
77
+ 0.667497,189.89783,0.0012949534,-0.00019632342,-4.1516066,0.32844105,-189.89246,190.22607,0.5517094,1.0260916,-8.570631,-189.91032,-209.59491,1.577801,23.346142,-8.224873,122.62017,1280000
78
+ 0.6478355,189.3947,0.0012660892,-0.0019161766,-5.513461,0.31495532,-189.38773,189.70773,0.46424732,0.94187415,-19.431961,-189.58865,-229.73236,1.4061215,9.99692,-6.4547997,112.19078,1285000
79
+ 0.66811085,189.8552,0.0013130505,-0.00033728676,-4.2568727,0.30200303,-189.84961,190.15686,0.5318803,0.9720645,-1.7684671,-189.91533,-214.95042,1.5039449,9.5580435,-14.919923,97.965004,1290000
80
+ 0.6897229,193.9361,0.0012794408,0.0006059833,-3.5263686,0.30013862,-193.9316,194.23685,0.6155899,2.0100822,-56.650864,-194.24533,-230.51218,2.625672,9.039595,-13.824524,112.125916,1295000
81
+ 0.67239165,188.8928,0.0011562572,-0.000650978,-4.5630045,0.3134975,-188.88753,189.20564,1.7178701,3.8759668,-1.884011,-189.18369,-212.17557,5.593837,28.898293,-15.649969,281.90503,1300000
82
+ 0.6707265,189.641,0.0012659129,0.00023426262,-3.8149457,0.25783128,-189.63618,189.89906,0.9185651,1.3036112,-1.7179902,-189.78883,-223.6208,2.2221763,11.156598,-18.614403,128.08795,1305000
83
+ 0.6521983,190.77173,0.0011331359,-0.0007401456,-4.6531835,0.2820726,-190.76645,191.05305,0.51388365,1.9059056,-13.504359,-190.91954,-221.67256,2.4197893,25.948671,-67.03914,232.94257,1310000
84
+ 0.6788319,192.28644,0.001145226,0.0016204854,-2.5850081,0.29923537,-192.28346,192.5873,1.4801296,1.139309,-5.9369617,-192.29178,-226.2393,2.6194386,25.453903,-25.491425,159.44028,1315000
85
+ 0.6576946,189.32326,0.0011645893,-0.0017518986,-5.504306,0.29428604,-189.31686,189.61578,1.2485723,3.038218,2.6920884,-189.47063,-228.53975,4.2867904,29.616684,-59.355618,415.6256,1320000
86
+ 0.6766582,191.10506,0.0011396552,0.00076544884,-3.3283505,0.27516,-191.10126,191.38098,0.71745574,0.84171194,-19.883501,-191.25041,-245.19237,1.5591676,4.431915,-11.5639105,120.916115,1325000
87
+ 0.6755313,192.24911,0.0011133921,0.0003637327,-3.6733112,0.29380512,-192.24501,192.54329,0.6779932,1.9399832,-33.367584,-192.49596,-215.49455,2.6179764,16.188494,-45.45846,290.20746,1330000
88
+ 0.66944575,190.62897,0.0011105358,0.0004956512,-3.5536828,0.29074013,-190.625,190.9202,0.59080523,1.1538883,-27.686056,-190.63925,-206.60405,1.7446935,19.182175,-9.34041,126.958786,1335000
89
+ 0.6746665,191.68367,0.0011612128,0.00043918347,-3.621789,0.32288614,-191.67947,192.007,0.9456024,0.9943952,0.9420806,-191.66913,-214.68863,1.9399977,10.580227,-10.945002,103.724594,1340000
90
+ 0.6648619,190.11557,0.0011793822,-5.804648e-05,-4.0492177,0.27021506,-190.11081,190.38573,0.5894999,1.8403851,-1.0759437,-190.04137,-240.6017,2.429885,16.774399,-22.063086,175.72401,1345000
91
+ 0.66499615,188.07614,0.0011318453,-0.0002976235,-4.262954,0.27908766,-188.07132,188.35492,1.5095762,1.720603,-2.3393497,-188.14012,-211.24829,3.2301793,46.521484,-14.648386,225.22865,1350000
92
+ 0.6673101,186.82529,0.001099571,-0.00041705274,-4.379287,0.29642433,-186.82047,187.12129,0.7570882,1.458845,0.6311318,-187.18268,-208.62889,2.2159333,11.037621,-7.0275216,122.084015,1355000
93
+ 0.6628126,187.78026,0.0010589059,-0.00085754046,-4.8098364,0.27903196,-187.77516,188.05844,0.67444676,1.1782779,-7.7790756,-187.77623,-244.33675,1.8527246,10.777802,-19.4964,161.95267,1360000
94
+ 0.6651502,190.53473,0.0011664344,-0.00083391176,-4.714924,0.28134057,-190.52924,190.81523,0.43593,0.44178638,-33.873573,-190.65344,-208.68993,0.8777164,3.0523822,-2.2588813,43.05083,1365000
95
+ 0.65933543,189.21286,0.0010925618,-0.00056457124,-4.516741,0.29277897,-189.20792,189.50508,0.7423549,0.94796723,-30.778757,-189.34367,-208.29475,1.6903222,25.019537,-10.591511,116.96028,1370000
96
+ 0.6560611,189.20663,0.0011332964,-0.0018990617,-5.6756973,0.30328926,-189.20021,189.50803,0.54705566,1.1886309,-3.2238007,-189.31395,-253.3823,1.7356865,4.636482,-13.878847,100.28694,1375000
97
+ 0.6577573,190.05699,0.0010596467,-0.00053258473,-4.502606,0.26018685,-190.05222,190.31665,0.4905034,0.6707069,-0.58878696,-190.19266,-253.94662,1.1612103,11.340082,-4.046285,69.14705,1380000
98
+ 0.6762712,192.89609,0.0011564452,0.0008689783,-3.248578,0.24934614,-192.8923,193.1463,0.51565176,1.1313419,-33.38729,-193.10847,-288.62622,1.6469936,23.770477,-12.508214,135.57913,1385000
99
+ 0.6811887,190.10342,0.0010931684,0.00077544065,-3.2906485,0.23569907,-190.09984,190.3399,0.6655709,1.3018726,-4.550262,-190.32463,-210.89786,1.9674435,22.244179,-17.581743,143.3633,1390000
100
+ 0.674438,191.76791,0.001088434,0.0011208932,-2.9701781,0.2547149,-191.76468,192.02374,0.384879,0.93062776,-13.582942,-192.01184,-217.71571,1.3155067,17.247381,-7.557503,144.55774,1395000
101
+ 0.6831577,193.14474,0.0010726207,0.0013227422,-2.7668128,0.27333897,-193.14178,193.41942,0.35746703,0.52970934,-31.720692,-193.33586,-207.13063,0.8871764,6.3352184,-4.335554,59.85502,1400000
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c131dca0e5c110e915adcc33377cc74f01c794b1a757c771f99fbad92baaad
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a86eccfe8018decabd001f053d54cb90ce18cf98cbae40fb2e56e8154ea104
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b1be3e7952799a9d7fc3a6794460ef45106b248f32290944a7a3fcc7792e84
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64bbef95a3508b11b651c15cbfb5547007b00eeafa87dcdc370d81fc2aacdc3b
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22d9726d9a72fc985ed5bf681a646aa9dd1293bb5d2af9f1dee90faf083d1e3f
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d13d06a29591932223b8685b274fb6ad2221fa6079d1fbbe79046ee95022122
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08eab1ad202067103b7f7482501436af6ede144135867738bc8879da2b18d14b
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063356a101522d3db47f75252d12ecc0bd5089807d4016cb5b3a5f7f2194be3e
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_1400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9520fdc0b4dbbcd46c92c791ed8803d28b3db7f55d5e9a79fba2c9974a340e7
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e46f4528ec2008a0b880db8af13474ae32b8b2b4628d838fff74d6cc552619c
3
+ size 321574838
O2O-w-diff-ckpts/dsrl/20260318_021110/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/dsrl/20260318_021110/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/6wfbfzr2
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1000000.png ADDED

Git LFS Details

  • SHA256: db2aaa94ac035c6fd666c8d0db2e0310d381c05767bac92e75d8a79ca92a35b6
  • Pointer size: 131 Bytes
  • Size of remote file: 160 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1050000.png ADDED

Git LFS Details

  • SHA256: d68cbf6ca9df286fe16bfea89e97b1f91dfb7e5d554c743da068b5f1c4e9091d
  • Pointer size: 131 Bytes
  • Size of remote file: 190 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1100000.png ADDED

Git LFS Details

  • SHA256: a21b97e0c91b24b790a69be8c548526eeb08aec21e5fa962c2c37020140d6a95
  • Pointer size: 131 Bytes
  • Size of remote file: 200 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1150000.png ADDED

Git LFS Details

  • SHA256: 4149dc74e841ab26a58a9b965e874fd53fdb7ef29aa5d76e6c9225f78d3df363
  • Pointer size: 131 Bytes
  • Size of remote file: 203 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1200000.png ADDED

Git LFS Details

  • SHA256: 671c1972c236986975f459aca376b5c844123a4571245aad4d06ab359fafc805
  • Pointer size: 131 Bytes
  • Size of remote file: 211 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1250000.png ADDED

Git LFS Details

  • SHA256: f2d7077df1c962eed4431a323edeed474aa01b06358b4081ffcdea28214a19a5
  • Pointer size: 131 Bytes
  • Size of remote file: 187 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1300000.png ADDED

Git LFS Details

  • SHA256: db102dce39ab2d7e43fec175fe584c7cf00ae26fc614d8ff359a5f3a4f1a907e
  • Pointer size: 131 Bytes
  • Size of remote file: 197 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1350000.png ADDED

Git LFS Details

  • SHA256: 0dfee03871153139ba2558c99618f8e7cd8e857cc605aecb212354daa85e5460
  • Pointer size: 131 Bytes
  • Size of remote file: 204 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_1400000.png ADDED

Git LFS Details

  • SHA256: 2ce919d1c3b977b2ff4618a17ab7261614b2269494a6895072688e20d5e8c508
  • Pointer size: 131 Bytes
  • Size of remote file: 225 kB
O2O-w-diff-ckpts/dsrl/20260318_021110/visited_states_950000.png ADDED

Git LFS Details

  • SHA256: 35508ad72c0a1dd7eae98e5ff35568962cb342d977c8ad6825175018f8bc0daa
  • Pointer size: 131 Bytes
  • Size of remote file: 226 kB