Tiredsheep commited on
Commit
f37a88f
·
verified ·
1 Parent(s): 5971741

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +10 -0
  2. O2O-w-diff-ckpts/cgql/20260318_034410/env.csv +0 -0
  3. O2O-w-diff-ckpts/cgql/20260318_034410/env_sv.csv +0 -0
  4. O2O-w-diff-ckpts/cgql/20260318_034410/eval.csv +11 -0
  5. O2O-w-diff-ckpts/cgql/20260318_034410/eval_sv.csv +11 -0
  6. O2O-w-diff-ckpts/cgql/20260318_034410/online_agent.csv +101 -0
  7. O2O-w-diff-ckpts/cgql/20260318_034410/online_agent_sv.csv +101 -0
  8. O2O-w-diff-ckpts/cgql/20260318_034410/params_1000000.pkl +3 -0
  9. O2O-w-diff-ckpts/cgql/20260318_034410/params_1050000.pkl +3 -0
  10. O2O-w-diff-ckpts/cgql/20260318_034410/params_1100000.pkl +3 -0
  11. O2O-w-diff-ckpts/cgql/20260318_034410/params_1150000.pkl +3 -0
  12. O2O-w-diff-ckpts/cgql/20260318_034410/params_1200000.pkl +3 -0
  13. O2O-w-diff-ckpts/cgql/20260318_034410/params_1250000.pkl +3 -0
  14. O2O-w-diff-ckpts/cgql/20260318_034410/params_1300000.pkl +3 -0
  15. O2O-w-diff-ckpts/cgql/20260318_034410/params_1350000.pkl +3 -0
  16. O2O-w-diff-ckpts/cgql/20260318_034410/params_1400000.pkl +3 -0
  17. O2O-w-diff-ckpts/cgql/20260318_034410/params_950000.pkl +3 -0
  18. O2O-w-diff-ckpts/cgql/20260318_034410/progress.tk +1 -0
  19. O2O-w-diff-ckpts/cgql/20260318_034410/token.tk +1 -0
  20. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1000000.png +3 -0
  21. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1050000.png +3 -0
  22. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1100000.png +3 -0
  23. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1150000.png +3 -0
  24. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1200000.png +3 -0
  25. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1250000.png +3 -0
  26. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1300000.png +3 -0
  27. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1350000.png +3 -0
  28. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1400000.png +3 -0
  29. O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_950000.png +3 -0
.gitattributes CHANGED
@@ -563,3 +563,13 @@ O2O-w-diff-ckpts/dsrl/20260317_104808/visited_states_800000.png filter=lfs diff=
563
  O2O-w-diff-ckpts/dsrl/20260317_104808/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
564
  O2O-w-diff-ckpts/dsrl/20260317_104808/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
565
  O2O-w-diff-ckpts/dsrl/20260317_104808/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
563
  O2O-w-diff-ckpts/dsrl/20260317_104808/visited_states_850000.png filter=lfs diff=lfs merge=lfs -text
564
  O2O-w-diff-ckpts/dsrl/20260317_104808/visited_states_900000.png filter=lfs diff=lfs merge=lfs -text
565
  O2O-w-diff-ckpts/dsrl/20260317_104808/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
566
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1000000.png filter=lfs diff=lfs merge=lfs -text
567
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1050000.png filter=lfs diff=lfs merge=lfs -text
568
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1100000.png filter=lfs diff=lfs merge=lfs -text
569
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1150000.png filter=lfs diff=lfs merge=lfs -text
570
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1200000.png filter=lfs diff=lfs merge=lfs -text
571
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1250000.png filter=lfs diff=lfs merge=lfs -text
572
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1300000.png filter=lfs diff=lfs merge=lfs -text
573
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1350000.png filter=lfs diff=lfs merge=lfs -text
574
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1400000.png filter=lfs diff=lfs merge=lfs -text
575
+ O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_950000.png filter=lfs diff=lfs merge=lfs -text
O2O-w-diff-ckpts/cgql/20260318_034410/env.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/cgql/20260318_034410/env_sv.csv ADDED
The diff for this file is too large to render. See raw diff
 
O2O-w-diff-ckpts/cgql/20260318_034410/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
+ 0.0,0.0,34.883863828879704,4.691279542658835,0.06330855280775169,4.697166693270205,0.013688452402429791,0.38,24516.64,-0.62,-958.94,959.32,3.6378892946243284,950000
3
+ 0.0,0.0,40.468745998293855,5.483630411084731,0.05975888251915726,5.492773287674696,0.11613871922358324,0.86,71421.04,-0.14,-831.18,832.04,3.1441927576065063,1000000
4
+ 0.0,0.0,40.490853489106755,5.499662858884623,0.08184368451414822,5.5098038655126995,0.10178503762229106,0.84,114623.6,-0.16,-859.7,860.54,3.243417959213257,1050000
5
+ 0.0,0.0,38.38282311361394,5.198349268934774,-0.0023854694830528597,5.198740105781581,0.05474013231193666,0.76,159268.74,-0.24,-839.44,840.2,3.165546193122864,1100000
6
+ 0.0,0.0,38.81473941813229,5.279485996953453,0.14066309965482138,5.290481349928139,0.13651044727759937,0.84,202227.14,-0.16,-820.44,821.28,3.0977723455429076,1150000
7
+ 0.0,0.0,39.97667938253428,5.443289372944471,0.136851239183023,5.453953544100248,0.07338174585573864,0.9,244717.42,-0.1,-808.1,809.0,3.07224401473999,1200000
8
+ 0.0,0.0,39.56200262799303,5.373180701690149,0.13248497160886327,5.38538455863648,0.09184925281205363,0.86,286029.74,-0.14,-785.82,786.68,2.963534045219421,1250000
9
+ 0.0,0.0,38.43260482549906,5.2203297004773,0.11172357401186052,5.229595880727427,0.09032957643504053,0.84,327354.38,-0.16,-796.42,797.26,3.0202660751342774,1300000
10
+ 0.0,0.0,39.11345725943194,5.3085461550820945,0.10881776492417014,5.318839557590414,0.09736666146846025,0.88,368753.26,-0.12,-789.24,790.12,2.993873839378357,1350000
11
+ 0.0,0.0,39.09147473562961,5.30414796111516,0.12266216030059737,5.315361499617854,0.06042019375253688,0.86,409049.06,-0.14,-778.7,779.56,2.9118967866897583,1400000
O2O-w-diff-ckpts/cgql/20260318_034410/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
+ 0.0,0.0,34.883863828879704,4.691279542658835,0.06330855280775169,4.697166693270205,0.013688452402429791,0.38,24516.64,-0.62,-958.94,959.32,3.6378892946243284,950000
3
+ 0.0,0.0,40.468745998293855,5.483630411084731,0.05975888251915726,5.492773287674696,0.11613871922358324,0.86,71421.04,-0.14,-831.18,832.04,3.1441927576065063,1000000
4
+ 0.0,0.0,40.490853489106755,5.499662858884623,0.08184368451414822,5.5098038655126995,0.10178503762229106,0.84,114623.6,-0.16,-859.7,860.54,3.243417959213257,1050000
5
+ 0.0,0.0,38.38282311361394,5.198349268934774,-0.0023854694830528597,5.198740105781581,0.05474013231193666,0.76,159268.74,-0.24,-839.44,840.2,3.165546193122864,1100000
6
+ 0.0,0.0,38.81473941813229,5.279485996953453,0.14066309965482138,5.290481349928139,0.13651044727759937,0.84,202227.14,-0.16,-820.44,821.28,3.0977723455429076,1150000
7
+ 0.0,0.0,39.97667938253428,5.443289372944471,0.136851239183023,5.453953544100248,0.07338174585573864,0.9,244717.42,-0.1,-808.1,809.0,3.07224401473999,1200000
8
+ 0.0,0.0,39.56200262799303,5.373180701690149,0.13248497160886327,5.38538455863648,0.09184925281205363,0.86,286029.74,-0.14,-785.82,786.68,2.963534045219421,1250000
9
+ 0.0,0.0,38.43260482549906,5.2203297004773,0.11172357401186052,5.229595880727427,0.09032957643504053,0.84,327354.38,-0.16,-796.42,797.26,3.0202660751342774,1300000
10
+ 0.0,0.0,39.11345725943194,5.3085461550820945,0.10881776492417014,5.318839557590414,0.09736666146846025,0.88,368753.26,-0.12,-789.24,790.12,2.993873839378357,1350000
11
+ 0.0,0.0,39.09147473562961,5.30414796111516,0.12266216030059737,5.315361499617854,0.06042019375253688,0.86,409049.06,-0.14,-778.7,779.56,2.9118967866897583,1400000
O2O-w-diff-ckpts/cgql/20260318_034410/online_agent.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 0.34999406,0.19663358,-6.8893948,-164.74182,-207.9134,0.8975188,-1.0270395,12.78805,905000
3
+ 0.3058906,0.26259756,-9.4874525,-161.82701,-207.23886,0.6175883,-1.2479126,13.301623,910000
4
+ 0.36616966,0.20064068,-5.4069853,-168.0879,-208.55345,0.7783566,-1.5626444,17.087374,915000
5
+ 0.31237015,0.27005962,-15.848886,-167.34488,-211.07239,3.1994972,-1.6521376,31.157158,920000
6
+ 0.30418694,0.27922267,0.51072747,-163.72238,-207.40088,1.2206324,-2.4659173,23.825125,925000
7
+ 0.26731175,0.23099624,0.43121347,-164.88004,-207.26733,0.5421911,-1.0211483,9.736192,930000
8
+ 0.3157612,0.32124612,0.48955643,-165.25542,-210.66354,1.552668,-2.11375,22.188442,935000
9
+ 0.3663082,0.27067038,-5.5725026,-165.5449,-208.6755,2.1495261,-1.0485483,20.63409,940000
10
+ 0.3151824,0.15882477,-11.309356,-169.01642,-209.95709,1.6527803,-0.98696005,14.040943,945000
11
+ 0.34764445,0.27135497,0.70782995,-167.40837,-209.80342,0.9988602,-1.5500162,17.535385,950000
12
+ 0.3081379,0.25611916,0.68679875,-165.60509,-207.98853,1.4436535,-1.8555876,22.911993,955000
13
+ 0.31272966,0.21315642,-34.446667,-168.96962,-211.3151,2.2280667,-1.1499774,18.23496,960000
14
+ 0.3303939,0.2744611,-16.65117,-171.27963,-208.59439,0.9944999,-1.3676337,19.002035,965000
15
+ 0.30543372,2.0478075,-15.499145,-171.27684,-206.89578,5.8652496,-4.433834,57.704796,970000
16
+ 0.27878428,0.22731176,0.66744834,-172.43916,-209.4323,1.3592099,-0.875193,16.06445,975000
17
+ 0.3036401,0.25271758,-10.593065,-171.5561,-208.3717,1.3069928,-0.52467614,12.695478,980000
18
+ 0.30459803,0.19326022,-1.7720408,-172.85466,-209.17311,0.8219647,-1.2127271,15.416442,985000
19
+ 0.3584556,0.35788327,-7.440972,-169.04349,-210.73865,2.1637914,-3.7281702,27.296661,990000
20
+ 0.3447119,0.7991619,0.26738003,-167.53491,-207.77626,10.693879,-3.3921745,66.85978,995000
21
+ 0.25757426,0.29862905,-4.6136465,-168.4984,-208.01857,2.4301155,-3.380428,26.489557,1000000
22
+ 0.2932371,0.19759057,-18.563961,-173.24059,-209.31993,1.4686325,-1.0261012,16.589256,1005000
23
+ 0.25502485,0.24292408,-1.0589055,-169.07039,-206.5673,2.4665747,-6.207915,28.896147,1010000
24
+ 0.35261935,0.24506374,-13.254392,-177.05363,-214.67079,1.4736786,-1.1508954,18.183813,1015000
25
+ 0.3059777,0.22541189,-20.385845,-176.81345,-211.35594,1.5662873,-2.674615,21.514181,1020000
26
+ 0.30998975,0.21290202,-29.594275,-174.67674,-207.9514,1.1506214,-1.8958261,20.535782,1025000
27
+ 0.31481403,0.32012597,-15.453416,-174.65108,-209.23378,3.129886,-1.7207837,32.43733,1030000
28
+ 0.34351644,0.2653307,-0.46204758,-174.71115,-210.85127,0.63813555,-1.1274893,14.660831,1035000
29
+ 0.25504956,0.69539183,-10.6238575,-176.94084,-214.01878,2.6072373,-5.1779385,45.430023,1040000
30
+ 0.31769562,0.31793854,-16.557919,-172.70926,-207.32724,1.1947296,-0.7773669,15.738928,1045000
31
+ 0.31635818,0.21018969,-3.978415,-175.6591,-208.37856,1.7113433,-2.4068122,21.594952,1050000
32
+ 0.30258983,0.2234724,-17.784554,-175.68416,-208.23979,4.849537,-1.7291706,26.740843,1055000
33
+ 0.31277695,0.31637463,-0.5600928,-173.02664,-208.45769,1.7052317,-2.7730677,22.69692,1060000
34
+ 0.31068054,0.2736961,-0.17135108,-175.0616,-212.00092,2.6385086,-2.7193182,26.689806,1065000
35
+ 0.34224117,0.4468855,-9.669807,-172.97632,-206.23944,1.9840267,-4.3112683,31.75994,1070000
36
+ 0.31038487,0.31072313,-17.439322,-176.76157,-207.40732,3.0705488,-1.4376105,23.081575,1075000
37
+ 0.32969755,0.7234192,-2.9551792,-167.33682,-210.25339,9.699915,-3.6171799,81.59502,1080000
38
+ 0.34235415,0.40629587,-9.128574,-176.32579,-212.93178,2.0683787,-8.131725,40.193943,1085000
39
+ 0.3233912,0.49841094,-2.6676724,-172.0129,-226.38666,5.9337573,-3.7222009,58.009552,1090000
40
+ 0.3169699,0.38687202,0.27510324,-172.94933,-207.75513,4.016484,-5.1648355,50.440594,1095000
41
+ 0.33440515,0.30220017,-1.0768541,-173.7058,-215.85904,5.573942,-4.431129,40.19028,1100000
42
+ 0.3588432,0.24380493,-0.06151268,-173.4376,-208.86134,1.3899939,-2.2800949,26.159428,1105000
43
+ 0.29160267,0.46402046,-2.165909,-175.18784,-217.32729,2.206079,-1.9684633,26.46106,1110000
44
+ 0.27102798,0.21435395,0.79099834,-175.7447,-214.77286,1.7759356,-1.0748321,18.138195,1115000
45
+ 0.2923872,0.3570268,-0.16040736,-174.37134,-209.11523,3.1025774,-4.273025,30.002014,1120000
46
+ 0.35590488,0.23671933,0.6471641,-173.32684,-208.75061,1.8981509,-2.8795204,27.892197,1125000
47
+ 0.30866987,0.90600616,-29.515326,-176.36234,-210.1144,2.1397629,-4.5197673,36.69259,1130000
48
+ 0.33116376,0.17193614,0.37078762,-173.63524,-207.96436,1.4448569,-2.642943,20.232464,1135000
49
+ 0.29535577,0.23883191,-12.939276,-177.04381,-218.70032,0.725528,-1.1595536,13.777972,1140000
50
+ 0.33760306,0.3932365,-4.5789914,-172.52573,-210.03862,3.470097,-4.4070954,30.859137,1145000
51
+ 0.3049608,0.18519863,-2.895953,-172.73827,-210.86618,1.5499613,-3.25203,21.847261,1150000
52
+ 0.3273303,0.35364455,-5.3481154,-172.43672,-213.62256,8.266376,-3.3255842,53.983673,1155000
53
+ 0.3575809,0.22203767,-2.0182018,-172.36455,-210.14317,2.6613505,-1.2747713,25.345898,1160000
54
+ 0.31756353,0.41230175,-16.350393,-174.30415,-216.34584,5.1201153,-2.5001602,36.458546,1165000
55
+ 0.3313924,0.21096058,-0.59130883,-172.27742,-211.2376,7.906563,-2.6823013,35.150227,1170000
56
+ 0.24698123,0.19414495,-25.99521,-174.15393,-215.33807,2.595295,-1.6932079,26.53888,1175000
57
+ 0.34843802,0.24661599,-27.573181,-174.13757,-211.82394,1.3702126,-1.6325705,20.278444,1180000
58
+ 0.2872371,0.3487758,-0.8443367,-171.16348,-208.79118,3.434669,-1.5139709,22.291023,1185000
59
+ 0.3121975,0.23908053,-20.091068,-179.25594,-216.21304,2.3943787,-2.2283432,19.206182,1190000
60
+ 0.32553732,0.4488821,0.15401524,-173.70758,-209.05971,4.7189946,-1.7773895,33.87199,1195000
61
+ 0.33535057,0.25018272,0.19473249,-170.25583,-209.97986,4.332939,-2.720126,26.295795,1200000
62
+ 0.31020135,0.19423883,-9.6098795,-178.50578,-212.58818,1.6688697,-2.72421,24.025898,1205000
63
+ 0.29578018,0.26704726,-14.725897,-176.59259,-210.44412,1.3622613,-1.9790215,23.003792,1210000
64
+ 0.34668756,0.21201546,-11.385111,-177.00085,-219.10379,1.2056446,-0.5120243,12.636908,1215000
65
+ 0.35204932,0.25795045,-2.3572676,-175.48222,-210.09201,1.7766262,-4.385661,28.207094,1220000
66
+ 0.34043556,0.25418326,-9.003413,-168.5662,-209.97456,1.7811917,-2.8603113,17.743351,1225000
67
+ 0.30425993,0.2614127,-5.7479854,-173.24327,-212.60335,3.9773543,-1.9443973,34.101532,1230000
68
+ 0.29985666,0.18194823,-7.046682,-175.27266,-211.42197,2.7708728,-1.4955988,20.75425,1235000
69
+ 0.36754695,0.40637818,-1.2025924,-172.71655,-210.63008,2.9495845,-4.1540947,39.916077,1240000
70
+ 0.29800388,0.24296264,-42.426678,-176.84933,-209.15933,2.4337451,-1.1597252,22.988194,1245000
71
+ 0.36272675,0.42909542,0.22093117,-175.47392,-214.3929,7.505039,-10.423239,74.595184,1250000
72
+ 0.31800765,0.28715822,-1.1764843,-173.49628,-214.60835,1.2362254,-2.8296785,25.913982,1255000
73
+ 0.2973084,0.19780543,-19.067562,-175.01372,-209.89967,0.90030307,-2.843083,15.251894,1260000
74
+ 0.33550438,0.30224413,0.9570138,-172.01949,-209.5187,4.141055,-7.6900706,46.821503,1265000
75
+ 0.2785343,0.25274777,1.1212224,-174.77983,-208.83836,1.1931213,-3.0754628,24.626953,1270000
76
+ 0.34992272,0.21056794,-0.6970258,-175.49632,-208.96242,0.98759604,-0.7674203,13.413205,1275000
77
+ 0.3122744,0.23091431,-1.5818354,-176.02423,-208.50056,2.4005876,-5.0732675,38.142998,1280000
78
+ 0.34195805,0.2717211,-20.12931,-173.6409,-211.42502,3.1680968,-1.6279061,23.755907,1285000
79
+ 0.32867074,0.27179012,-4.5306516,-171.22865,-210.95433,2.433219,-5.44945,28.400547,1290000
80
+ 0.3578117,0.30875692,-8.51349,-175.70619,-210.06453,2.2814848,-5.6207547,37.55512,1295000
81
+ 0.31331483,0.2924929,-0.035051525,-174.09274,-210.0595,3.8161042,-2.0089934,24.481152,1300000
82
+ 0.3166747,0.32972988,0.16278625,-171.02776,-209.80623,1.2504675,-4.3969564,25.043781,1305000
83
+ 0.31062678,0.35268328,1.0470086,-169.13213,-213.192,9.185708,-4.188615,58.699863,1310000
84
+ 0.30423003,0.21169798,0.62193644,-174.4039,-209.10634,1.2560433,-3.9188812,22.918959,1315000
85
+ 0.28229266,0.20620437,0.6372287,-175.59285,-210.49321,3.6689153,-1.893384,19.974754,1320000
86
+ 0.32237238,0.78032255,-3.2096553,-172.14514,-213.1761,6.461669,-3.114931,50.168537,1325000
87
+ 0.3366441,0.22243948,1.113615,-174.40952,-214.36923,6.249636,-2.8473625,36.650543,1330000
88
+ 0.33654916,0.23976927,-9.571063,-172.93443,-208.36832,1.4511602,-1.0950094,15.464103,1335000
89
+ 0.33035678,0.30445987,0.21324903,-175.92044,-211.76045,2.7865617,-6.8696003,40.305058,1340000
90
+ 0.30993402,0.36598873,1.0656261,-172.5009,-214.50749,4.990144,-1.995551,40.48791,1345000
91
+ 0.33470708,0.32870445,-1.8778676,-169.86778,-211.57164,2.593764,-7.7781463,46.18041,1350000
92
+ 0.36013138,0.3264738,-1.077136,-173.02489,-212.02313,3.602879,-8.025494,51.618217,1355000
93
+ 0.31899512,0.24962746,-15.067964,-172.90611,-210.4376,0.81174296,-1.6283232,16.921368,1360000
94
+ 0.30280304,0.21083565,1.5317135,-173.57478,-211.2642,2.023129,-4.917066,28.74429,1365000
95
+ 0.31734645,0.25828207,-22.478802,-176.07896,-217.23512,2.4147475,-2.8054614,26.71988,1370000
96
+ 0.33075818,0.29108697,0.58967626,-172.49158,-210.57417,4.2985067,-5.0853567,37.18377,1375000
97
+ 0.29849657,0.26571175,-0.7729672,-166.56993,-207.62396,2.619543,-4.9118857,37.007416,1380000
98
+ 0.31538272,0.19046262,-10.275513,-171.41634,-214.54471,1.0139892,-0.63644004,13.722319,1385000
99
+ 0.27116057,0.18464947,-0.2510675,-174.94766,-209.48228,1.7899137,-1.6110406,16.077663,1390000
100
+ 0.28713134,0.29208785,-6.200351,-169.312,-212.24774,2.418765,-5.013042,30.366276,1395000
101
+ 0.32726696,0.3419394,-5.7824626,-172.42728,-208.72046,1.7336631,-3.151376,24.055445,1400000
O2O-w-diff-ckpts/cgql/20260318_034410/online_agent_sv.csv ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
2
+ 0.34999406,0.19663358,-6.8893948,-164.74182,-207.9134,0.8975188,-1.0270395,12.78805,905000
3
+ 0.3058906,0.26259756,-9.4874525,-161.82701,-207.23886,0.6175883,-1.2479126,13.301623,910000
4
+ 0.36616966,0.20064068,-5.4069853,-168.0879,-208.55345,0.7783566,-1.5626444,17.087374,915000
5
+ 0.31237015,0.27005962,-15.848886,-167.34488,-211.07239,3.1994972,-1.6521376,31.157158,920000
6
+ 0.30418694,0.27922267,0.51072747,-163.72238,-207.40088,1.2206324,-2.4659173,23.825125,925000
7
+ 0.26731175,0.23099624,0.43121347,-164.88004,-207.26733,0.5421911,-1.0211483,9.736192,930000
8
+ 0.3157612,0.32124612,0.48955643,-165.25542,-210.66354,1.552668,-2.11375,22.188442,935000
9
+ 0.3663082,0.27067038,-5.5725026,-165.5449,-208.6755,2.1495261,-1.0485483,20.63409,940000
10
+ 0.3151824,0.15882477,-11.309356,-169.01642,-209.95709,1.6527803,-0.98696005,14.040943,945000
11
+ 0.34764445,0.27135497,0.70782995,-167.40837,-209.80342,0.9988602,-1.5500162,17.535385,950000
12
+ 0.3081379,0.25611916,0.68679875,-165.60509,-207.98853,1.4436535,-1.8555876,22.911993,955000
13
+ 0.31272966,0.21315642,-34.446667,-168.96962,-211.3151,2.2280667,-1.1499774,18.23496,960000
14
+ 0.3303939,0.2744611,-16.65117,-171.27963,-208.59439,0.9944999,-1.3676337,19.002035,965000
15
+ 0.30543372,2.0478075,-15.499145,-171.27684,-206.89578,5.8652496,-4.433834,57.704796,970000
16
+ 0.27878428,0.22731176,0.66744834,-172.43916,-209.4323,1.3592099,-0.875193,16.06445,975000
17
+ 0.3036401,0.25271758,-10.593065,-171.5561,-208.3717,1.3069928,-0.52467614,12.695478,980000
18
+ 0.30459803,0.19326022,-1.7720408,-172.85466,-209.17311,0.8219647,-1.2127271,15.416442,985000
19
+ 0.3584556,0.35788327,-7.440972,-169.04349,-210.73865,2.1637914,-3.7281702,27.296661,990000
20
+ 0.3447119,0.7991619,0.26738003,-167.53491,-207.77626,10.693879,-3.3921745,66.85978,995000
21
+ 0.25757426,0.29862905,-4.6136465,-168.4984,-208.01857,2.4301155,-3.380428,26.489557,1000000
22
+ 0.2932371,0.19759057,-18.563961,-173.24059,-209.31993,1.4686325,-1.0261012,16.589256,1005000
23
+ 0.25502485,0.24292408,-1.0589055,-169.07039,-206.5673,2.4665747,-6.207915,28.896147,1010000
24
+ 0.35261935,0.24506374,-13.254392,-177.05363,-214.67079,1.4736786,-1.1508954,18.183813,1015000
25
+ 0.3059777,0.22541189,-20.385845,-176.81345,-211.35594,1.5662873,-2.674615,21.514181,1020000
26
+ 0.30998975,0.21290202,-29.594275,-174.67674,-207.9514,1.1506214,-1.8958261,20.535782,1025000
27
+ 0.31481403,0.32012597,-15.453416,-174.65108,-209.23378,3.129886,-1.7207837,32.43733,1030000
28
+ 0.34351644,0.2653307,-0.46204758,-174.71115,-210.85127,0.63813555,-1.1274893,14.660831,1035000
29
+ 0.25504956,0.69539183,-10.6238575,-176.94084,-214.01878,2.6072373,-5.1779385,45.430023,1040000
30
+ 0.31769562,0.31793854,-16.557919,-172.70926,-207.32724,1.1947296,-0.7773669,15.738928,1045000
31
+ 0.31635818,0.21018969,-3.978415,-175.6591,-208.37856,1.7113433,-2.4068122,21.594952,1050000
32
+ 0.30258983,0.2234724,-17.784554,-175.68416,-208.23979,4.849537,-1.7291706,26.740843,1055000
33
+ 0.31277695,0.31637463,-0.5600928,-173.02664,-208.45769,1.7052317,-2.7730677,22.69692,1060000
34
+ 0.31068054,0.2736961,-0.17135108,-175.0616,-212.00092,2.6385086,-2.7193182,26.689806,1065000
35
+ 0.34224117,0.4468855,-9.669807,-172.97632,-206.23944,1.9840267,-4.3112683,31.75994,1070000
36
+ 0.31038487,0.31072313,-17.439322,-176.76157,-207.40732,3.0705488,-1.4376105,23.081575,1075000
37
+ 0.32969755,0.7234192,-2.9551792,-167.33682,-210.25339,9.699915,-3.6171799,81.59502,1080000
38
+ 0.34235415,0.40629587,-9.128574,-176.32579,-212.93178,2.0683787,-8.131725,40.193943,1085000
39
+ 0.3233912,0.49841094,-2.6676724,-172.0129,-226.38666,5.9337573,-3.7222009,58.009552,1090000
40
+ 0.3169699,0.38687202,0.27510324,-172.94933,-207.75513,4.016484,-5.1648355,50.440594,1095000
41
+ 0.33440515,0.30220017,-1.0768541,-173.7058,-215.85904,5.573942,-4.431129,40.19028,1100000
42
+ 0.3588432,0.24380493,-0.06151268,-173.4376,-208.86134,1.3899939,-2.2800949,26.159428,1105000
43
+ 0.29160267,0.46402046,-2.165909,-175.18784,-217.32729,2.206079,-1.9684633,26.46106,1110000
44
+ 0.27102798,0.21435395,0.79099834,-175.7447,-214.77286,1.7759356,-1.0748321,18.138195,1115000
45
+ 0.2923872,0.3570268,-0.16040736,-174.37134,-209.11523,3.1025774,-4.273025,30.002014,1120000
46
+ 0.35590488,0.23671933,0.6471641,-173.32684,-208.75061,1.8981509,-2.8795204,27.892197,1125000
47
+ 0.30866987,0.90600616,-29.515326,-176.36234,-210.1144,2.1397629,-4.5197673,36.69259,1130000
48
+ 0.33116376,0.17193614,0.37078762,-173.63524,-207.96436,1.4448569,-2.642943,20.232464,1135000
49
+ 0.29535577,0.23883191,-12.939276,-177.04381,-218.70032,0.725528,-1.1595536,13.777972,1140000
50
+ 0.33760306,0.3932365,-4.5789914,-172.52573,-210.03862,3.470097,-4.4070954,30.859137,1145000
51
+ 0.3049608,0.18519863,-2.895953,-172.73827,-210.86618,1.5499613,-3.25203,21.847261,1150000
52
+ 0.3273303,0.35364455,-5.3481154,-172.43672,-213.62256,8.266376,-3.3255842,53.983673,1155000
53
+ 0.3575809,0.22203767,-2.0182018,-172.36455,-210.14317,2.6613505,-1.2747713,25.345898,1160000
54
+ 0.31756353,0.41230175,-16.350393,-174.30415,-216.34584,5.1201153,-2.5001602,36.458546,1165000
55
+ 0.3313924,0.21096058,-0.59130883,-172.27742,-211.2376,7.906563,-2.6823013,35.150227,1170000
56
+ 0.24698123,0.19414495,-25.99521,-174.15393,-215.33807,2.595295,-1.6932079,26.53888,1175000
57
+ 0.34843802,0.24661599,-27.573181,-174.13757,-211.82394,1.3702126,-1.6325705,20.278444,1180000
58
+ 0.2872371,0.3487758,-0.8443367,-171.16348,-208.79118,3.434669,-1.5139709,22.291023,1185000
59
+ 0.3121975,0.23908053,-20.091068,-179.25594,-216.21304,2.3943787,-2.2283432,19.206182,1190000
60
+ 0.32553732,0.4488821,0.15401524,-173.70758,-209.05971,4.7189946,-1.7773895,33.87199,1195000
61
+ 0.33535057,0.25018272,0.19473249,-170.25583,-209.97986,4.332939,-2.720126,26.295795,1200000
62
+ 0.31020135,0.19423883,-9.6098795,-178.50578,-212.58818,1.6688697,-2.72421,24.025898,1205000
63
+ 0.29578018,0.26704726,-14.725897,-176.59259,-210.44412,1.3622613,-1.9790215,23.003792,1210000
64
+ 0.34668756,0.21201546,-11.385111,-177.00085,-219.10379,1.2056446,-0.5120243,12.636908,1215000
65
+ 0.35204932,0.25795045,-2.3572676,-175.48222,-210.09201,1.7766262,-4.385661,28.207094,1220000
66
+ 0.34043556,0.25418326,-9.003413,-168.5662,-209.97456,1.7811917,-2.8603113,17.743351,1225000
67
+ 0.30425993,0.2614127,-5.7479854,-173.24327,-212.60335,3.9773543,-1.9443973,34.101532,1230000
68
+ 0.29985666,0.18194823,-7.046682,-175.27266,-211.42197,2.7708728,-1.4955988,20.75425,1235000
69
+ 0.36754695,0.40637818,-1.2025924,-172.71655,-210.63008,2.9495845,-4.1540947,39.916077,1240000
70
+ 0.29800388,0.24296264,-42.426678,-176.84933,-209.15933,2.4337451,-1.1597252,22.988194,1245000
71
+ 0.36272675,0.42909542,0.22093117,-175.47392,-214.3929,7.505039,-10.423239,74.595184,1250000
72
+ 0.31800765,0.28715822,-1.1764843,-173.49628,-214.60835,1.2362254,-2.8296785,25.913982,1255000
73
+ 0.2973084,0.19780543,-19.067562,-175.01372,-209.89967,0.90030307,-2.843083,15.251894,1260000
74
+ 0.33550438,0.30224413,0.9570138,-172.01949,-209.5187,4.141055,-7.6900706,46.821503,1265000
75
+ 0.2785343,0.25274777,1.1212224,-174.77983,-208.83836,1.1931213,-3.0754628,24.626953,1270000
76
+ 0.34992272,0.21056794,-0.6970258,-175.49632,-208.96242,0.98759604,-0.7674203,13.413205,1275000
77
+ 0.3122744,0.23091431,-1.5818354,-176.02423,-208.50056,2.4005876,-5.0732675,38.142998,1280000
78
+ 0.34195805,0.2717211,-20.12931,-173.6409,-211.42502,3.1680968,-1.6279061,23.755907,1285000
79
+ 0.32867074,0.27179012,-4.5306516,-171.22865,-210.95433,2.433219,-5.44945,28.400547,1290000
80
+ 0.3578117,0.30875692,-8.51349,-175.70619,-210.06453,2.2814848,-5.6207547,37.55512,1295000
81
+ 0.31331483,0.2924929,-0.035051525,-174.09274,-210.0595,3.8161042,-2.0089934,24.481152,1300000
82
+ 0.3166747,0.32972988,0.16278625,-171.02776,-209.80623,1.2504675,-4.3969564,25.043781,1305000
83
+ 0.31062678,0.35268328,1.0470086,-169.13213,-213.192,9.185708,-4.188615,58.699863,1310000
84
+ 0.30423003,0.21169798,0.62193644,-174.4039,-209.10634,1.2560433,-3.9188812,22.918959,1315000
85
+ 0.28229266,0.20620437,0.6372287,-175.59285,-210.49321,3.6689153,-1.893384,19.974754,1320000
86
+ 0.32237238,0.78032255,-3.2096553,-172.14514,-213.1761,6.461669,-3.114931,50.168537,1325000
87
+ 0.3366441,0.22243948,1.113615,-174.40952,-214.36923,6.249636,-2.8473625,36.650543,1330000
88
+ 0.33654916,0.23976927,-9.571063,-172.93443,-208.36832,1.4511602,-1.0950094,15.464103,1335000
89
+ 0.33035678,0.30445987,0.21324903,-175.92044,-211.76045,2.7865617,-6.8696003,40.305058,1340000
90
+ 0.30993402,0.36598873,1.0656261,-172.5009,-214.50749,4.990144,-1.995551,40.48791,1345000
91
+ 0.33470708,0.32870445,-1.8778676,-169.86778,-211.57164,2.593764,-7.7781463,46.18041,1350000
92
+ 0.36013138,0.3264738,-1.077136,-173.02489,-212.02313,3.602879,-8.025494,51.618217,1355000
93
+ 0.31899512,0.24962746,-15.067964,-172.90611,-210.4376,0.81174296,-1.6283232,16.921368,1360000
94
+ 0.30280304,0.21083565,1.5317135,-173.57478,-211.2642,2.023129,-4.917066,28.74429,1365000
95
+ 0.31734645,0.25828207,-22.478802,-176.07896,-217.23512,2.4147475,-2.8054614,26.71988,1370000
96
+ 0.33075818,0.29108697,0.58967626,-172.49158,-210.57417,4.2985067,-5.0853567,37.18377,1375000
97
+ 0.29849657,0.26571175,-0.7729672,-166.56993,-207.62396,2.619543,-4.9118857,37.007416,1380000
98
+ 0.31538272,0.19046262,-10.275513,-171.41634,-214.54471,1.0139892,-0.63644004,13.722319,1385000
99
+ 0.27116057,0.18464947,-0.2510675,-174.94766,-209.48228,1.7899137,-1.6110406,16.077663,1390000
100
+ 0.28713134,0.29208785,-6.200351,-169.312,-212.24774,2.418765,-5.013042,30.366276,1395000
101
+ 0.32726696,0.3419394,-5.7824626,-172.42728,-208.72046,1.7336631,-3.151376,24.055445,1400000
O2O-w-diff-ckpts/cgql/20260318_034410/params_1000000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d83297e823d8b5c3aa3e1910c7ed00027bd2dd75a3889daf01a0a648003a9d
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_1050000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58ba0868f7a3f246a30666c18c8f121b8935184dd3a562fa2f34f8d1b5923d7
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_1100000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea2cac90a6acfa86f19120145b2260678121ac897a082ba6b93385f7063f035
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_1150000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec03c6c42f56d706ee2779631146d9dccbe7c02ef80c3bf5a8b44e8f0e4c827
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_1200000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5418819f041952d7e86919f0a7b6bb96564c89015f9f06840560fb31ce637915
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_1250000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c4da3883997cef9043e912b4e2557535143bb04babfb379ad1927a2c82ba17
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_1300000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4636bccc89963278283389812e7da25ae30bad8495f8e5528a92a798a5c6b7e6
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_1350000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe88faa7873d45c00f39ee9d5b4ec3efb665cefdfff31c62e04f74ff19c5a14
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_1400000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75fe4abf19f6b2f134cd95d312a4b3154d5cd96285b38455148261f53907f710
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/params_950000.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79dc68c71bbb9f1201de58bdc47909f854e6a0e570885a5ff14b15eacce02598
3
+ size 214509745
O2O-w-diff-ckpts/cgql/20260318_034410/progress.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ online,500000
O2O-w-diff-ckpts/cgql/20260318_034410/token.tk ADDED
@@ -0,0 +1 @@
 
 
1
+ https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/h2gikz8n
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1000000.png ADDED

Git LFS Details

  • SHA256: a73e0d822e43a86137a362ea94347b7efa5bc644a5c227bfdb6a195d54bea14e
  • Pointer size: 131 Bytes
  • Size of remote file: 147 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1050000.png ADDED

Git LFS Details

  • SHA256: 46a6cfe4fd3612834899ef0debc6c3d51d6444de97fdfe60234ac06076a7c82e
  • Pointer size: 131 Bytes
  • Size of remote file: 188 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1100000.png ADDED

Git LFS Details

  • SHA256: 596a6f4b2e1f82ac0c1132679b6acd2c1c5cbb5af15524b1c58378b0a5cf2b53
  • Pointer size: 131 Bytes
  • Size of remote file: 169 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1150000.png ADDED

Git LFS Details

  • SHA256: 84386a7d8da4c0197331b5c9b926a9e3bd6e5b97bed66c05c967f9a682b0b0fe
  • Pointer size: 131 Bytes
  • Size of remote file: 143 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1200000.png ADDED

Git LFS Details

  • SHA256: 0a56eae5b84ab819a8f44f9ad49e334ceccf777779ca18a32872b2fa8b642227
  • Pointer size: 131 Bytes
  • Size of remote file: 150 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1250000.png ADDED

Git LFS Details

  • SHA256: a49a6e6641441a77fc019e18be0b5a59bc19a7b51d71c18ce7bbf275a504d707
  • Pointer size: 131 Bytes
  • Size of remote file: 148 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1300000.png ADDED

Git LFS Details

  • SHA256: c2267b6c3d29fd3f28d686b0c12b9462fb92f645076a2fd14647f3fe1c654459
  • Pointer size: 131 Bytes
  • Size of remote file: 141 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1350000.png ADDED

Git LFS Details

  • SHA256: 5d687cefe8b329c62d8dc75224170c92829c9ad95b0e5e9f4f44648d49e87ede
  • Pointer size: 131 Bytes
  • Size of remote file: 141 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_1400000.png ADDED

Git LFS Details

  • SHA256: cf3177b5fc1599a1b3719f0c10457bb5bfaec2131a61390fb3adacc8abc608f2
  • Pointer size: 131 Bytes
  • Size of remote file: 136 kB
O2O-w-diff-ckpts/cgql/20260318_034410/visited_states_950000.png ADDED

Git LFS Details

  • SHA256: 1305b52fa8b8ca61ca9357425c65feb6236536a67964b89e98b507c4cd2965a5
  • Pointer size: 131 Bytes
  • Size of remote file: 222 kB