Upload folder using huggingface_hub
Browse files- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/env.csv +0 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/env_sv.csv +0 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/eval.csv +31 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/eval_sv.csv +31 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/flags.json +1 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/offline_agent.csv +201 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/offline_agent_sv.csv +201 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/online_agent.csv +101 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/online_agent_sv.csv +101 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_100000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1000000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1050000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1100000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1150000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1200000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1250000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1300000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1350000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1400000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1450000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_150000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1500000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_200000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_250000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_300000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_350000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_400000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_450000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_50000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_500000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_550000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_600000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_650000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_700000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_750000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_800000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_850000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_900000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_950000.pkl +3 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/progress.tk +1 -0
- pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/token.tk +1 -0
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/env.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/env_sv.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/eval.csv
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
avg_gripper_contact_length,num_gripper_contacts,prev_button_states,button_states,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
|
| 2 |
+
0.0,0.0,0.4488888888888889,0.4488888888888889,-0.20680416172200317,0.01547550125844133,-0.20722964420338036,-0.012948341011234172,29.558048089491862,25.24999999999688,0.0,12750.0,-4.96,-2501.72,500.0,2.002183966636658,50000
|
| 3 |
+
0.0,0.0,0.7266666666666667,0.74,-0.1854476121177269,-0.01335119137984624,-0.1861146343546096,-0.006979354672037157,28.732932887996117,25.16099999999693,0.04,38661.04,-2.34,-1661.5,498.22,2.042941493988037,100000
|
| 4 |
+
0.0,0.0,0.7422222222222222,0.7444444444444445,-0.18348460672044434,0.0012451527630795403,-0.18069521212259923,0.034461910602042185,30.516045327179313,25.24999999999688,0.0,64661.0,-2.3,-1702.3,500.0,2.062965712547302,150000
|
| 5 |
+
0.0,0.0,0.6533333333333333,0.6666666666666666,-0.19964201245279992,-0.007760532254531665,-0.1990004763390213,0.016627940463982027,31.964068314275824,25.19599999999691,0.02,90657.76,-3.0,-1860.68,498.92,2.1877321720123293,200000
|
| 6 |
+
0.0,0.0,0.6933333333333334,0.6933333333333334,-0.17685440892730178,0.05975606803258132,-0.17344016040318241,0.04926630500524546,29.821150247595963,25.24999999999688,0.0,116607.0,-2.76,-1953.06,500.0,2.28888795375824,250000
|
| 7 |
+
0.0,0.0,0.7355555555555555,0.7577777777777778,-0.18135235756919943,0.008851659072488824,-0.18074901685330147,0.007437717748463166,32.94565076193694,25.039999999996997,0.06,142478.2,-2.18,-1542.5,495.8,1.951694016456604,300000
|
| 8 |
+
0.0,0.0,0.8044444444444444,0.8111111111111111,-0.17896617352833882,0.05886189379135026,-0.1762117698136557,0.0355998712497451,33.162710036881506,25.147999999996937,0.02,168335.8,-1.7,-1416.58,497.96,2.026948881149292,350000
|
| 9 |
+
0.0,0.0,0.7466666666666667,0.7977777777777778,-0.17932047936805479,0.045840292108437215,-0.17690242781087562,0.019894232641960916,31.21540443410542,24.377999999997318,0.12,193880.02,-1.82,-1462.32,482.56,1.9685649013519286,400000
|
| 10 |
+
0.0,0.0,0.6177777777777778,0.6688888888888889,-0.17751183693960446,-0.007863775691305098,-0.17845011569847202,-0.021185367628569686,33.73249375968149,24.711999999997115,0.12,219145.22,-2.98,-1644.52,489.24,1.9599166679382325,450000
|
| 11 |
+
0.0,0.0,0.72,0.7577777777777778,-0.17158279193632175,0.04749619776347568,-0.16915655971789675,0.03844587760577912,32.779324507792914,25.065999999996983,0.08,244676.1,-2.18,-1477.5,496.32,2.0157172107696533,500000
|
| 12 |
+
0.0,0.0,0.6,0.8,-0.17555322885784508,0.02373651390677701,-0.17572012235363965,-0.005045039120291159,31.90714535748212,23.220999999997908,0.46,269621.84,-1.8,-1715.66,459.42,1.846357021331787,550000
|
| 13 |
+
0.0,0.0,0.6422222222222222,0.7444444444444445,-0.18061584086094765,0.005812422361398958,-0.17985785390275943,0.02778930445563429,32.7520054206505,24.016999999997534,0.32,294150.54,-2.3,-1609.9,475.34,1.9044554424285889,600000
|
| 14 |
+
0.0,0.0,0.6733333333333333,0.7666666666666667,-0.17605478516074313,-0.000746491285394985,-0.17622982072354282,-0.016698952300278905,32.19687751908793,24.377999999997364,0.22,318556.1,-2.1,-1644.36,482.56,1.9115493392944336,650000
|
| 15 |
+
0.0,0.0,0.5822222222222222,0.7222222222222222,-0.18718479495817233,-0.0010322814913027122,-0.1890239056661064,-0.037866318590239104,32.0626335230043,23.988999999997578,0.38,343645.02,-2.5,-1909.44,474.78,1.8747428512573243,700000
|
| 16 |
+
0.0,0.0,0.6444444444444445,0.7533333333333333,-0.18371414208168235,0.007896796526313175,-0.1840803076262562,-0.02605506658813193,31.96479186237324,24.501999999997295,0.26,368540.76,-2.22,-1736.3,485.04,1.9377984189987183,750000
|
| 17 |
+
0.0,0.0,0.5222222222222223,0.6288888888888889,-0.18257101054331618,-0.014768960348056815,-0.1835998611766779,-0.021854857496055227,33.290093039656284,23.863999999997603,0.24,393583.82,-3.34,-1993.12,472.28,1.8545687437057494,800000
|
| 18 |
+
0.0,0.0,0.5088888888888888,0.6266666666666667,-0.18891999229925704,-0.0006039382962920346,-0.1901337485852135,-0.022857406912811674,33.600021602182835,24.00399999999757,0.26,417923.06,-3.36,-2049.92,475.08,1.8721244478225707,850000
|
| 19 |
+
0.0,0.0,0.5555555555555556,0.6911111111111111,-0.18638468886697948,0.03956649927557618,-0.18617571952672451,-0.007543856227743689,32.6656717391095,24.135999999997498,0.3,442973.14,-2.78,-1955.34,477.72,1.8773225355148315,900000
|
| 20 |
+
0.0,0.0,0.5044444444444445,0.6044444444444445,-0.18208563081115278,0.012150630768111174,-0.18185181343257564,0.00045336562550222923,33.58538418833902,24.78099999999714,0.18,467951.8,-3.56,-1953.98,490.62,1.936088147163391,950000
|
| 21 |
+
0.0,0.0,0.7311111111111112,0.7311111111111112,-0.1790296041472884,0.11698441233387845,-0.17881220487300814,0.0025451911064586566,32.40688893934606,25.24999999999688,0.0,493852.0,-2.42,-1684.82,500.0,1.958337836265564,1000000
|
| 22 |
+
0.0,0.0,0.5488888888888889,0.5955555555555555,-0.19644438341152412,0.03599218157830041,-0.1961085097014952,0.0003127847066936155,25.914846435676807,24.609999999997235,0.14,519350.96,-3.64,-2289.52,487.2,1.887710075378418,1050000
|
| 23 |
+
0.0,0.0,0.6511111111111111,0.9044444444444445,-0.1847367834506517,0.0075577816477464576,-0.185250337570047,-0.009764469791546338,29.266492449406936,18.410999999999614,0.76,542097.6,-0.86,-1451.74,363.22,1.5121442413330077,1100000
|
| 24 |
+
0.0,0.0,0.6577777777777778,1.0,-0.17535067673927832,-0.002102829075216248,-0.17737521237073822,-0.03791050271346351,31.5890802615749,13.068000000000762,1.0,558059.82,0.0,-1061.68,256.36,1.0563156366348267,1150000
|
| 25 |
+
0.0,0.0,0.6,1.0,-0.18963852885101065,0.00557962420047441,-0.18887406578679816,0.0421994070715676,30.268161539419328,10.534000000000203,1.0,569858.02,0.0,-822.32,205.68,0.8623985576629639,1200000
|
| 26 |
+
0.0,0.0,0.66,1.0,-0.19319863287748307,-0.022005106380143146,-0.19162248587870234,0.023028476586887378,33.32760642657459,8.729999999999814,1.0,579592.74,0.0,-668.66,169.6,0.7041564130783081,1250000
|
| 27 |
+
0.0,0.0,0.66,1.0,-0.1914633658545561,0.0006994413795694637,-0.18754575250845545,0.09832359175810695,34.497919482854705,8.604999999999812,1.0,588162.7,0.0,-604.3,167.1,0.695389051437378,1300000
|
| 28 |
+
0.0,0.0,0.6644444444444444,1.0,-0.19716072825579847,0.050689500856952785,-0.19598643654600947,0.048289978692907055,30.139667619474537,8.544999999999785,1.0,597051.26,0.0,-622.36,165.9,0.7005558204650879,1350000
|
| 29 |
+
0.0,0.0,0.6577777777777778,1.0,-0.18616383951048024,-0.028508548913920285,-0.18353344862649473,0.09603898406126393,33.162903286987486,9.522999999999945,1.0,606123.7,0.0,-675.4,185.46,0.7745941209793091,1400000
|
| 30 |
+
0.0,0.0,0.6622222222222223,1.0,-0.18204957063383034,-0.01657683839756466,-0.17890406935607805,0.07769659973777387,32.306357817118844,7.925999999999642,1.0,614986.88,0.0,-545.84,153.52,0.656562728881836,1450000
|
| 31 |
+
0.0,0.0,0.6488888888888888,1.0,-0.18598785910967924,0.030041496659288666,-0.18000599368569284,0.11475903166315826,33.73766761608772,8.362999999999742,1.0,623367.1,0.0,-626.18,162.26,0.686245265007019,1500000
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/eval_sv.csv
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
avg_gripper_contact_length,num_gripper_contacts,prev_button_states,button_states,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
|
| 2 |
+
0.0,0.0,0.4488888888888889,0.4488888888888889,-0.20680416172200317,0.01547550125844133,-0.20722964420338036,-0.012948341011234172,29.558048089491862,25.24999999999688,0.0,12750.0,-4.96,-2501.72,500.0,2.002183966636658,50000
|
| 3 |
+
0.0,0.0,0.7266666666666667,0.74,-0.1854476121177269,-0.01335119137984624,-0.1861146343546096,-0.006979354672037157,28.732932887996117,25.16099999999693,0.04,38661.04,-2.34,-1661.5,498.22,2.042941493988037,100000
|
| 4 |
+
0.0,0.0,0.7422222222222222,0.7444444444444445,-0.18348460672044434,0.0012451527630795403,-0.18069521212259923,0.034461910602042185,30.516045327179313,25.24999999999688,0.0,64661.0,-2.3,-1702.3,500.0,2.062965712547302,150000
|
| 5 |
+
0.0,0.0,0.6533333333333333,0.6666666666666666,-0.19964201245279992,-0.007760532254531665,-0.1990004763390213,0.016627940463982027,31.964068314275824,25.19599999999691,0.02,90657.76,-3.0,-1860.68,498.92,2.1877321720123293,200000
|
| 6 |
+
0.0,0.0,0.6933333333333334,0.6933333333333334,-0.17685440892730178,0.05975606803258132,-0.17344016040318241,0.04926630500524546,29.821150247595963,25.24999999999688,0.0,116607.0,-2.76,-1953.06,500.0,2.28888795375824,250000
|
| 7 |
+
0.0,0.0,0.7355555555555555,0.7577777777777778,-0.18135235756919943,0.008851659072488824,-0.18074901685330147,0.007437717748463166,32.94565076193694,25.039999999996997,0.06,142478.2,-2.18,-1542.5,495.8,1.951694016456604,300000
|
| 8 |
+
0.0,0.0,0.8044444444444444,0.8111111111111111,-0.17896617352833882,0.05886189379135026,-0.1762117698136557,0.0355998712497451,33.162710036881506,25.147999999996937,0.02,168335.8,-1.7,-1416.58,497.96,2.026948881149292,350000
|
| 9 |
+
0.0,0.0,0.7466666666666667,0.7977777777777778,-0.17932047936805479,0.045840292108437215,-0.17690242781087562,0.019894232641960916,31.21540443410542,24.377999999997318,0.12,193880.02,-1.82,-1462.32,482.56,1.9685649013519286,400000
|
| 10 |
+
0.0,0.0,0.6177777777777778,0.6688888888888889,-0.17751183693960446,-0.007863775691305098,-0.17845011569847202,-0.021185367628569686,33.73249375968149,24.711999999997115,0.12,219145.22,-2.98,-1644.52,489.24,1.9599166679382325,450000
|
| 11 |
+
0.0,0.0,0.72,0.7577777777777778,-0.17158279193632175,0.04749619776347568,-0.16915655971789675,0.03844587760577912,32.779324507792914,25.065999999996983,0.08,244676.1,-2.18,-1477.5,496.32,2.0157172107696533,500000
|
| 12 |
+
0.0,0.0,0.6,0.8,-0.17555322885784508,0.02373651390677701,-0.17572012235363965,-0.005045039120291159,31.90714535748212,23.220999999997908,0.46,269621.84,-1.8,-1715.66,459.42,1.846357021331787,550000
|
| 13 |
+
0.0,0.0,0.6422222222222222,0.7444444444444445,-0.18061584086094765,0.005812422361398958,-0.17985785390275943,0.02778930445563429,32.7520054206505,24.016999999997534,0.32,294150.54,-2.3,-1609.9,475.34,1.9044554424285889,600000
|
| 14 |
+
0.0,0.0,0.6733333333333333,0.7666666666666667,-0.17605478516074313,-0.000746491285394985,-0.17622982072354282,-0.016698952300278905,32.19687751908793,24.377999999997364,0.22,318556.1,-2.1,-1644.36,482.56,1.9115493392944336,650000
|
| 15 |
+
0.0,0.0,0.5822222222222222,0.7222222222222222,-0.18718479495817233,-0.0010322814913027122,-0.1890239056661064,-0.037866318590239104,32.0626335230043,23.988999999997578,0.38,343645.02,-2.5,-1909.44,474.78,1.8747428512573243,700000
|
| 16 |
+
0.0,0.0,0.6444444444444445,0.7533333333333333,-0.18371414208168235,0.007896796526313175,-0.1840803076262562,-0.02605506658813193,31.96479186237324,24.501999999997295,0.26,368540.76,-2.22,-1736.3,485.04,1.9377984189987183,750000
|
| 17 |
+
0.0,0.0,0.5222222222222223,0.6288888888888889,-0.18257101054331618,-0.014768960348056815,-0.1835998611766779,-0.021854857496055227,33.290093039656284,23.863999999997603,0.24,393583.82,-3.34,-1993.12,472.28,1.8545687437057494,800000
|
| 18 |
+
0.0,0.0,0.5088888888888888,0.6266666666666667,-0.18891999229925704,-0.0006039382962920346,-0.1901337485852135,-0.022857406912811674,33.600021602182835,24.00399999999757,0.26,417923.06,-3.36,-2049.92,475.08,1.8721244478225707,850000
|
| 19 |
+
0.0,0.0,0.5555555555555556,0.6911111111111111,-0.18638468886697948,0.03956649927557618,-0.18617571952672451,-0.007543856227743689,32.6656717391095,24.135999999997498,0.3,442973.14,-2.78,-1955.34,477.72,1.8773225355148315,900000
|
| 20 |
+
0.0,0.0,0.5044444444444445,0.6044444444444445,-0.18208563081115278,0.012150630768111174,-0.18185181343257564,0.00045336562550222923,33.58538418833902,24.78099999999714,0.18,467951.8,-3.56,-1953.98,490.62,1.936088147163391,950000
|
| 21 |
+
0.0,0.0,0.7311111111111112,0.7311111111111112,-0.1790296041472884,0.11698441233387845,-0.17881220487300814,0.0025451911064586566,32.40688893934606,25.24999999999688,0.0,493852.0,-2.42,-1684.82,500.0,1.958337836265564,1000000
|
| 22 |
+
0.0,0.0,0.5488888888888889,0.5955555555555555,-0.19644438341152412,0.03599218157830041,-0.1961085097014952,0.0003127847066936155,25.914846435676807,24.609999999997235,0.14,519350.96,-3.64,-2289.52,487.2,1.887710075378418,1050000
|
| 23 |
+
0.0,0.0,0.6511111111111111,0.9044444444444445,-0.1847367834506517,0.0075577816477464576,-0.185250337570047,-0.009764469791546338,29.266492449406936,18.410999999999614,0.76,542097.6,-0.86,-1451.74,363.22,1.5121442413330077,1100000
|
| 24 |
+
0.0,0.0,0.6577777777777778,1.0,-0.17535067673927832,-0.002102829075216248,-0.17737521237073822,-0.03791050271346351,31.5890802615749,13.068000000000762,1.0,558059.82,0.0,-1061.68,256.36,1.0563156366348267,1150000
|
| 25 |
+
0.0,0.0,0.6,1.0,-0.18963852885101065,0.00557962420047441,-0.18887406578679816,0.0421994070715676,30.268161539419328,10.534000000000203,1.0,569858.02,0.0,-822.32,205.68,0.8623985576629639,1200000
|
| 26 |
+
0.0,0.0,0.66,1.0,-0.19319863287748307,-0.022005106380143146,-0.19162248587870234,0.023028476586887378,33.32760642657459,8.729999999999814,1.0,579592.74,0.0,-668.66,169.6,0.7041564130783081,1250000
|
| 27 |
+
0.0,0.0,0.66,1.0,-0.1914633658545561,0.0006994413795694637,-0.18754575250845545,0.09832359175810695,34.497919482854705,8.604999999999812,1.0,588162.7,0.0,-604.3,167.1,0.695389051437378,1300000
|
| 28 |
+
0.0,0.0,0.6644444444444444,1.0,-0.19716072825579847,0.050689500856952785,-0.19598643654600947,0.048289978692907055,30.139667619474537,8.544999999999785,1.0,597051.26,0.0,-622.36,165.9,0.7005558204650879,1350000
|
| 29 |
+
0.0,0.0,0.6577777777777778,1.0,-0.18616383951048024,-0.028508548913920285,-0.18353344862649473,0.09603898406126393,33.162903286987486,9.522999999999945,1.0,606123.7,0.0,-675.4,185.46,0.7745941209793091,1400000
|
| 30 |
+
0.0,0.0,0.6622222222222223,1.0,-0.18204957063383034,-0.01657683839756466,-0.17890406935607805,0.07769659973777387,32.306357817118844,7.925999999999642,1.0,614986.88,0.0,-545.84,153.52,0.656562728881836,1450000
|
| 31 |
+
0.0,0.0,0.6488888888888888,1.0,-0.18598785910967924,0.030041496659288666,-0.18000599368569284,0.11475903166315826,33.73766761608772,8.362999999999742,1.0,623367.1,0.0,-626.18,162.26,0.686245265007019,1500000
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"logtostderr": false, "alsologtostderr": false, "log_dir": "", "v": 0, "verbosity": 0, "logger_levels": {}, "stderrthreshold": "fatal", "showprefixforinfo": true, "run_with_pdb": false, "pdb_post_mortem": false, "pdb": false, "run_with_profiling": false, "profile_file": null, "use_cprofile_for_profiling": true, "only_check_args": false, "pymjcf_debug": false, "pymjcf_debug_full_dump_dir": "", "pymjcf_log_xml": false, "timeout": true, "chex_n_cpu_devices": 1, "chex_assert_multiple_cpu_devices": false, "test_srcdir": "", "test_tmpdir": "/tmp/absl_testing", "test_random_seed": 301, "test_randomize_ordering_seed": "", "xml_output_file": "", "chex_skip_pmap_variant_if_single_device": true, "run_group": "main-experiments", "tags": "CGQL", "seed": 10001, "env_name": "puzzle-3x3-play-singletask-task4-v0", "save_dir": "exp/qam-reproduce/main-experiments/puzzle-3x3-play-singletask-task4-v0/20260308_015226", "offline_steps": 1000000, "online_steps": 500000, "buffer_size": 1000000, "log_interval": 5000, "eval_interval": 50000, "save_interval": 50000, "start_training": 5000, "utd_ratio": 1, "eval_episodes": 50, "video_episodes": 2, "video_frame_skip": 3, "agent": {"action_chunking": true, "action_dim": 5, "actor_hidden_dims": [512, 512, 512, 512], "actor_layer_norm": false, "agent_name": "cgql", "batch_size": 256, "best_of_n": 1, "discount": 0.99, "flow_steps": 10, "guidance_coef": 0.1, "horizon_length": 5, "inv_temp": 10.0, "isd_clip": 5.0, "lr": 0.0003, "mode": "simple", "noisy_coef": 0.001, "num_qs": 10, "ob_dims": [55], "rho": 0.5, "separate": false, "target_guidance": true, "tau": 0.005, "value_hidden_dims": [512, 512, 512, 512], "value_layer_norm": true}, "dataset_proportion": 1.0, "dataset_replace_interval": 1000, "ogbench_dataset_dir": null, "horizon_length": 5, "sparse": true, "save_all_online_states": false, "save_last_checkpoint": false, "save_replay_buffer": false, "balanced_sampling": false, "?": false, "help": false, "helpshort": false, "helpfull": false, "helpxml": false}
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/offline_agent.csv
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.2572963,2.8757513,-6.884718,-47.457375,-54.27165,0.21008998,-0.17022747,16.587677,5000
|
| 3 |
+
0.22032467,1.7587227,-22.457716,-66.15852,-71.69979,0.10479148,-0.042718813,8.374995,10000
|
| 4 |
+
0.20516817,2.693316,-52.942493,-75.89294,-80.661026,0.1093789,-0.123407885,12.331238,15000
|
| 5 |
+
0.2198817,13.278651,0.06988962,-73.76223,-83.32882,0.16126485,-0.15315206,18.607115,20000
|
| 6 |
+
0.19808263,3.2442753,-0.02055154,-77.21038,-85.26574,0.06425947,-0.16669066,12.199322,25000
|
| 7 |
+
0.22699443,3.1142654,-45.800617,-78.19172,-85.19057,0.15968089,-0.062066477,13.566454,30000
|
| 8 |
+
0.187579,4.3099933,-0.27504468,-78.3735,-85.83786,0.11708765,-0.2936991,16.922785,35000
|
| 9 |
+
0.19481528,5.5027027,-40.190754,-81.31798,-86.838486,0.08946003,-0.15038222,11.422528,40000
|
| 10 |
+
0.18673019,2.3173273,-48.156063,-83.193214,-90.18087,0.09581773,-0.06091846,9.2374115,45000
|
| 11 |
+
0.20928177,1.83853,0.1591253,-83.689514,-90.435616,0.04445765,-0.097805046,7.4046497,50000
|
| 12 |
+
0.2056104,4.6894584,-52.88556,-86.91802,-92.65937,0.09625972,-0.13189311,11.793656,55000
|
| 13 |
+
0.18138832,2.0303402,0.31331873,-86.26133,-93.29196,0.097647876,-0.037843715,6.563656,60000
|
| 14 |
+
0.2048267,6.8799715,-53.033016,-89.117485,-94.72957,0.24241063,-0.070460305,13.402856,65000
|
| 15 |
+
0.2189494,2.3664708,0.17540592,-87.344154,-95.00766,0.07620191,-0.1330857,9.002398,70000
|
| 16 |
+
0.18829924,1.6644677,-44.751225,-89.565636,-95.59585,0.051102158,-0.1050974,6.5506425,75000
|
| 17 |
+
0.16236562,1.4387068,-63.39566,-90.79964,-95.99232,0.039105915,-0.061701093,6.394159,80000
|
| 18 |
+
0.214394,2.000639,-48.05386,-90.96615,-96.91785,0.06602095,-0.11765638,8.21324,85000
|
| 19 |
+
0.19452995,5.546045,-59.003662,-84.16066,-90.55542,0.069388226,-0.18941772,11.795287,90000
|
| 20 |
+
0.17297727,14.47966,-45.451138,-79.462555,-87.15001,0.18066831,-0.16397771,18.643894,95000
|
| 21 |
+
0.1991788,7.500141,-0.053330444,-73.92818,-81.95545,0.10799493,-0.39273918,18.594067,100000
|
| 22 |
+
0.18198419,7.459452,-28.67862,-68.88222,-77.878784,0.50970215,-0.56838024,25.150383,105000
|
| 23 |
+
0.1998119,10.150368,-33.04542,-64.10658,-74.7097,0.29348722,-0.46333775,27.715359,110000
|
| 24 |
+
0.16973805,5.2010193,-2.0987587,-68.914055,-75.86958,0.10484245,-0.0758149,7.42672,115000
|
| 25 |
+
0.19587372,8.223113,0.31897303,-62.308083,-71.21974,0.20417789,-0.10297102,10.218219,120000
|
| 26 |
+
0.16178355,2.842429,0.1961015,-68.79577,-74.66943,0.055767756,-0.09289457,5.06077,125000
|
| 27 |
+
0.18170504,3.4758568,1.4748884,-69.28972,-76.03322,0.08895397,-0.046542875,5.8783655,130000
|
| 28 |
+
0.18178825,5.520847,0.20378794,-72.503235,-80.790596,0.09336635,-0.19283757,11.881831,135000
|
| 29 |
+
0.17216119,1.3690087,0.06403466,-66.75832,-72.47558,0.07390837,-0.026367968,3.6040146,140000
|
| 30 |
+
0.19881429,3.57312,0.14224197,-73.26216,-79.6412,0.088621005,-0.098922476,8.459568,145000
|
| 31 |
+
0.16488926,2.9589696,-2.7193131,-73.29172,-82.62737,0.069251165,-0.05452293,5.5363417,150000
|
| 32 |
+
0.17575201,6.4313216,-2.4178462,-62.613068,-71.0884,0.23054907,-0.08137993,12.168918,155000
|
| 33 |
+
0.16816649,9.586767,-38.221443,-60.803432,-74.25905,0.111030996,-0.07247004,7.352281,160000
|
| 34 |
+
0.18632457,11.737292,-31.344578,-69.86383,-82.27743,0.4292372,-0.12294637,17.048931,165000
|
| 35 |
+
0.20565213,3.788887,-42.136654,-66.13323,-74.87475,0.055728465,-0.16898131,9.196728,170000
|
| 36 |
+
0.20571421,5.174135,-44.722878,-74.43151,-80.40684,0.08530452,-0.16087487,9.625588,175000
|
| 37 |
+
0.18088534,8.0158205,-34.96553,-77.23165,-84.819435,0.15029156,-0.13998443,9.710448,180000
|
| 38 |
+
0.19679624,2.6585999,-47.114395,-75.085,-82.204636,0.046296977,-0.13778594,7.1520686,185000
|
| 39 |
+
0.18229145,12.444697,-45.182053,-71.424446,-80.460236,0.1591757,-0.094589025,12.106635,190000
|
| 40 |
+
0.18066782,4.8873,-0.55365384,-77.70424,-84.93314,0.15417162,-0.09138273,8.301131,195000
|
| 41 |
+
0.19121677,7.4262085,-48.402378,-74.30436,-82.93687,0.31251672,-0.092816934,14.603978,200000
|
| 42 |
+
0.14713211,4.726383,0.21384452,-71.197014,-77.68874,0.12568982,-0.13313186,6.6054134,205000
|
| 43 |
+
0.19748282,6.383526,0.2916274,-73.18861,-81.29828,0.077428,-0.12814282,7.271771,210000
|
| 44 |
+
0.15624604,2.8339427,-47.94678,-81.596,-86.720146,0.14216934,-0.24450873,12.059544,215000
|
| 45 |
+
0.16416731,3.4598184,-46.90138,-76.674065,-83.44083,0.056935538,-0.12927964,7.7018466,220000
|
| 46 |
+
0.17891273,2.1092885,-3.1742644,-85.57961,-91.3187,0.062558636,-0.23078477,7.645746,225000
|
| 47 |
+
0.18369085,10.956664,-44.13418,-79.12253,-87.94235,0.22254628,-0.095978424,12.801839,230000
|
| 48 |
+
0.1574542,4.3759747,0.15361,-78.28094,-86.90449,0.10044719,-0.07994616,6.6798096,235000
|
| 49 |
+
0.16072465,2.4716718,-43.185875,-73.75741,-81.703636,0.19161111,-0.052231155,7.919861,240000
|
| 50 |
+
0.22595093,2.012357,0.4941942,-76.17387,-89.160645,0.05496559,-0.058613706,4.2350397,245000
|
| 51 |
+
0.16564709,9.241527,0.30581868,-70.8988,-78.52652,0.26122546,-0.15837139,11.78088,250000
|
| 52 |
+
0.17491597,7.960424,-1.948431,-68.86358,-78.4969,0.29017553,-0.14889431,12.846415,255000
|
| 53 |
+
0.18059155,2.0475662,0.10874809,-79.66894,-85.57317,0.07177102,-0.056531984,4.6582165,260000
|
| 54 |
+
0.17094405,3.2575417,-46.656986,-86.74264,-93.06087,0.08433035,-0.28854036,12.61969,265000
|
| 55 |
+
0.18359053,6.818828,-44.41537,-85.44787,-93.37147,0.22091387,-0.091636196,9.225166,270000
|
| 56 |
+
0.15665802,1.500351,-0.026100636,-87.38299,-93.64092,0.15631667,-0.056738757,6.1437364,275000
|
| 57 |
+
0.173991,2.82946,-0.39647007,-88.97873,-96.172005,0.25666237,-0.084384926,11.835951,280000
|
| 58 |
+
0.17418075,2.5689502,-64.72041,-88.45193,-95.541504,0.2616659,-0.078560136,9.629518,285000
|
| 59 |
+
0.16338994,1.5565556,-54.848747,-88.42059,-94.87744,0.054752015,-0.040324934,3.9841862,290000
|
| 60 |
+
0.17160243,1.8637087,-61.089405,-89.389915,-95.179016,0.054462533,-0.09820488,4.703696,295000
|
| 61 |
+
0.1483278,2.1624653,-1.457453,-87.755165,-95.09203,0.058320887,-0.058622032,4.751169,300000
|
| 62 |
+
0.17464146,2.5043724,-55.78133,-84.63003,-90.79055,0.049829733,-0.14489886,6.4337983,305000
|
| 63 |
+
0.15535185,2.1301763,-50.488316,-84.34457,-91.47643,0.07812295,-0.057269406,4.7983313,310000
|
| 64 |
+
0.1520545,1.7595524,-59.004547,-84.67006,-90.02232,0.05170137,-0.118544,6.476858,315000
|
| 65 |
+
0.18118146,2.1447988,-48.19687,-81.97771,-89.85942,0.1286551,-0.057283536,6.558062,320000
|
| 66 |
+
0.14364162,2.029923,-2.466668,-83.96323,-90.00855,0.029013982,-0.058424845,3.9153438,325000
|
| 67 |
+
0.17935982,1.530317,-52.846523,-84.20581,-90.38179,0.078774735,-0.046928484,4.2008476,330000
|
| 68 |
+
0.1969758,4.190722,-50.83039,-80.403755,-88.24771,0.07778803,-0.09158732,5.873816,335000
|
| 69 |
+
0.19454469,12.062816,-38.882442,-77.666824,-87.85914,0.13574497,-0.3858543,18.13717,340000
|
| 70 |
+
0.18592843,6.228112,-39.33877,-78.39908,-86.48709,0.067129105,-0.25693306,9.718432,345000
|
| 71 |
+
0.18274838,3.7947018,-1.4324914,-80.67717,-88.85705,0.13894638,-0.062955156,6.2857914,350000
|
| 72 |
+
0.17364532,2.4773405,0.1514796,-84.26049,-90.587,0.093508385,-0.048877914,4.8645115,355000
|
| 73 |
+
0.17542326,1.948296,0.2094003,-85.08567,-92.410286,0.03665927,-0.11686966,4.685695,360000
|
| 74 |
+
0.18152358,2.904509,-49.835716,-85.10571,-91.644966,0.2794429,-0.08719352,9.88364,365000
|
| 75 |
+
0.17305782,2.040823,-58.316963,-87.57882,-94.39644,0.05563179,-0.1247595,4.736765,370000
|
| 76 |
+
0.18957883,7.6660438,0.20794082,-86.23679,-93.32169,0.07930765,-0.3319505,11.033183,375000
|
| 77 |
+
0.15184093,6.337664,0.12596776,-86.1701,-92.25916,0.32313693,-0.081276216,12.876635,380000
|
| 78 |
+
0.17275347,1.4936373,0.103296965,-83.57162,-90.30167,0.03353585,-0.0764318,4.428326,385000
|
| 79 |
+
0.16982418,1.0066189,0.25396663,-84.960045,-91.793076,0.04183414,-0.13405813,4.0450087,390000
|
| 80 |
+
0.14575744,2.0360818,-51.511875,-82.89551,-88.858635,0.034792453,-0.12081907,4.887505,395000
|
| 81 |
+
0.17419304,2.4270234,-53.57397,-85.68333,-92.26367,0.047190957,-0.12240348,5.685435,400000
|
| 82 |
+
0.19448379,2.9125607,0.547173,-85.89473,-91.818375,0.0744646,-0.07087349,4.5730443,405000
|
| 83 |
+
0.16962893,3.4269874,-59.63319,-88.85558,-95.096634,0.13959908,-0.11847384,6.714976,410000
|
| 84 |
+
0.17519955,1.8053694,-48.32858,-87.34418,-94.48925,0.089061916,-0.046870075,4.165262,415000
|
| 85 |
+
0.17579374,7.6360984,0.15147714,-84.52576,-91.631805,0.13448933,-0.23196834,10.3734665,420000
|
| 86 |
+
0.17266396,7.076782,-48.570267,-82.25295,-89.71968,0.13097191,-0.13808702,7.544936,425000
|
| 87 |
+
0.19258446,2.0736244,0.080171525,-83.49354,-90.502686,0.22771728,-0.072991736,7.112708,430000
|
| 88 |
+
0.1751588,2.1744707,-55.140625,-85.10699,-91.06276,0.08877929,-0.05608412,4.010222,435000
|
| 89 |
+
0.15807246,2.962835,-45.476055,-85.6148,-92.59859,0.09235321,-0.058545224,4.963947,440000
|
| 90 |
+
0.17034027,2.1440928,-60.525654,-82.23673,-88.99567,0.32548553,-0.09169972,8.70948,445000
|
| 91 |
+
0.19760998,1.3073338,0.2829643,-83.36091,-89.26978,0.08341801,-0.03775637,4.0676723,450000
|
| 92 |
+
0.16943488,2.1516755,-1.9523083,-87.41828,-92.577965,0.13221264,-0.041973338,4.8879237,455000
|
| 93 |
+
0.18314615,2.5061855,0.26451772,-83.66064,-89.97127,0.0514826,-0.055928975,3.595716,460000
|
| 94 |
+
0.17109749,3.2862968,0.7653688,-80.87065,-90.88009,0.15101096,-0.07996436,5.255858,465000
|
| 95 |
+
0.17486401,1.8330605,-58.87331,-86.15734,-92.06369,0.23182401,-0.07710223,6.1823187,470000
|
| 96 |
+
0.18878421,6.8366923,-42.76834,-83.118286,-90.34588,0.6224099,-0.23372781,20.860987,475000
|
| 97 |
+
0.16974846,1.5026636,0.16770345,-85.35663,-91.121864,0.04776113,-0.051660586,3.248783,480000
|
| 98 |
+
0.17718437,6.073461,-52.81311,-87.31437,-93.572754,0.1798568,-0.30054545,11.304109,485000
|
| 99 |
+
0.1716834,8.178763,-41.838573,-88.61199,-95.28473,0.26610738,-0.08534043,10.705814,490000
|
| 100 |
+
0.20580983,1.3871874,0.14666378,-86.33766,-92.88357,0.07809347,-0.0367968,4.976552,495000
|
| 101 |
+
0.20432553,3.2044308,-1.3847033,-86.72691,-92.9082,0.1626674,-0.14102788,6.5830717,500000
|
| 102 |
+
0.17787777,1.579673,0.062957,-86.74449,-93.25625,0.049588814,-0.073520884,3.7727475,505000
|
| 103 |
+
0.16647692,5.3306365,-41.35892,-85.0953,-96.0411,0.13841283,-0.12640569,7.8876314,510000
|
| 104 |
+
0.18855122,5.2063403,0.31108505,-67.220375,-78.60237,0.08330884,-0.105306685,7.8057528,515000
|
| 105 |
+
0.15842299,1.8295218,-0.65082455,-80.761665,-88.27328,0.046475295,-0.11425474,4.847315,520000
|
| 106 |
+
0.17902955,8.1822,-48.75557,-86.016655,-97.23179,0.24717608,-0.17990029,10.464842,525000
|
| 107 |
+
0.19574605,1.8086265,-3.523472,-89.30532,-99.01479,0.18415713,-0.062007796,6.9550447,530000
|
| 108 |
+
0.1665675,3.6191108,-56.07593,-91.01959,-96.61459,0.13969307,-0.42095733,9.6669,535000
|
| 109 |
+
0.1974013,1.6584812,0.15338892,-91.28923,-96.64004,0.1761198,-0.13468188,6.718706,540000
|
| 110 |
+
0.19353244,3.6213658,-52.886307,-89.53361,-95.801735,0.10191037,-0.28714514,6.0031123,545000
|
| 111 |
+
0.1800055,1.5889755,0.25019038,-90.52693,-99.289185,0.14949974,-0.06956374,4.310659,550000
|
| 112 |
+
0.1641391,4.3210096,0.19214371,-88.0754,-95.5824,0.33024117,-0.11091738,10.622002,555000
|
| 113 |
+
0.18438941,1.3567135,0.107595205,-89.82818,-95.70195,0.09984036,-0.05988896,3.7351973,560000
|
| 114 |
+
0.18360071,1.1385726,-57.196693,-91.124916,-96.109116,0.06816056,-0.038281754,2.8217592,565000
|
| 115 |
+
0.17819399,1.7357944,-53.93353,-89.951706,-96.02977,0.24302542,-0.08313479,8.062514,570000
|
| 116 |
+
0.15571612,2.2483795,0.15390505,-88.05599,-94.72004,0.0584489,-0.13877666,6.156764,575000
|
| 117 |
+
0.15753253,1.9414628,0.050977767,-89.36062,-95.74177,0.049651995,-0.091022044,3.4566584,580000
|
| 118 |
+
0.1509322,2.2365098,-53.69936,-87.89788,-94.89,0.07409463,-0.058728136,3.9389224,585000
|
| 119 |
+
0.14418253,1.3058451,0.1272309,-89.55508,-99.74093,0.034531243,-0.10957846,3.3958306,590000
|
| 120 |
+
0.15977249,1.5562865,-57.352013,-90.92139,-96.72982,0.0845426,-0.033310894,3.903314,595000
|
| 121 |
+
0.17314948,1.8810433,-53.44774,-90.37095,-96.84034,0.07218593,-0.05856144,4.091344,600000
|
| 122 |
+
0.17220366,1.706828,-50.883297,-88.46276,-94.63985,0.14560512,-0.05161989,4.983767,605000
|
| 123 |
+
0.15778181,2.812156,0.29818618,-88.28165,-95.50831,0.06985769,-0.17413111,5.55726,610000
|
| 124 |
+
0.14800104,2.040551,0.18628992,-89.71972,-95.968544,0.06058959,-0.15252802,5.097691,615000
|
| 125 |
+
0.15856081,4.03224,-46.865395,-87.44813,-94.654396,0.27798438,-0.09224279,10.443016,620000
|
| 126 |
+
0.20492706,1.5607985,-59.227974,-88.56532,-94.20476,0.16839328,-0.0560684,5.408322,625000
|
| 127 |
+
0.19597971,1.761536,-55.001312,-88.4284,-94.74196,0.08182536,-0.045896873,3.4074686,630000
|
| 128 |
+
0.15783447,2.2108681,-0.739065,-87.80731,-93.96007,0.16148436,-0.055070493,5.264937,635000
|
| 129 |
+
0.17757615,2.177531,0.13076366,-89.33156,-95.942024,0.108881466,-0.30380395,7.5740423,640000
|
| 130 |
+
0.19274479,2.3278275,-59.95301,-90.758446,-96.47719,0.03918398,-0.11847336,3.977826,645000
|
| 131 |
+
0.15427217,0.92520183,-50.629498,-91.84579,-97.368355,0.124595195,-0.040870473,3.5469174,650000
|
| 132 |
+
0.17455535,1.4578685,0.12324707,-91.113304,-97.81644,0.08427857,-0.039141472,3.1349487,655000
|
| 133 |
+
0.1601198,1.3781966,-62.80423,-92.14003,-97.986595,0.20087302,-0.07280414,5.0021844,660000
|
| 134 |
+
0.21596768,2.0849648,0.060468048,-92.29362,-97.97848,0.22044659,-0.5993423,10.933109,665000
|
| 135 |
+
0.17855284,2.8853557,-60.850277,-92.56803,-97.716576,0.11801767,-0.31993368,5.4909368,670000
|
| 136 |
+
0.17509887,0.9778639,-61.829285,-91.525375,-96.93158,0.18131651,-0.06570783,4.443909,675000
|
| 137 |
+
0.14906655,0.87957555,-59.267303,-91.921265,-96.786415,0.14485475,-0.046387404,3.8251944,680000
|
| 138 |
+
0.17406215,1.496503,-66.997345,-92.850975,-97.952774,0.07328141,-0.20060952,4.812868,685000
|
| 139 |
+
0.17359367,3.3340676,-64.21688,-92.35364,-97.40136,0.0426336,-0.07807331,5.1552677,690000
|
| 140 |
+
0.18304768,0.80914557,-62.70612,-93.211136,-97.96013,0.14332652,-0.045911796,3.9331114,695000
|
| 141 |
+
0.18053241,2.1517413,0.15604642,-92.109406,-100.43147,0.093992986,-0.09718458,4.4981785,700000
|
| 142 |
+
0.1848199,0.7879347,0.32469437,-92.63952,-98.23076,0.100522295,-0.034553807,2.598812,705000
|
| 143 |
+
0.15170994,0.91385174,0.2179083,-93.50895,-98.82955,0.09055549,-0.24491033,5.0108027,710000
|
| 144 |
+
0.17422107,6.331247,0.110954404,-92.46316,-97.97784,0.35330623,-0.1325548,7.52773,715000
|
| 145 |
+
0.19752811,0.8219658,-58.63016,-91.648186,-96.806046,0.06263126,-0.0568008,2.9346547,720000
|
| 146 |
+
0.15826803,2.4619825,-62.500652,-92.65542,-97.55487,0.28359175,-0.10430444,5.368049,725000
|
| 147 |
+
0.20204127,1.6019169,-65.269875,-94.14889,-98.344894,0.084848136,-0.058791183,3.482994,730000
|
| 148 |
+
0.19116108,2.8192399,0.10933399,-92.12604,-98.00004,0.09134876,-0.24894425,6.39962,735000
|
| 149 |
+
0.16472131,3.7088437,0.27420968,-91.906235,-97.51674,0.1244892,-0.3369847,9.486282,740000
|
| 150 |
+
0.18711653,1.3302039,0.30137897,-92.65961,-97.343414,0.11401688,-0.07413992,4.1237674,745000
|
| 151 |
+
0.14541158,1.0957421,-50.97568,-92.97722,-97.73727,0.097112514,-0.068017654,3.089244,750000
|
| 152 |
+
0.17192182,0.97078717,0.11341825,-93.05471,-98.13086,0.054624025,-0.045523707,2.9833598,755000
|
| 153 |
+
0.20266347,1.4758996,0.058245182,-92.95011,-98.04161,0.038352273,-0.06858465,2.4093502,760000
|
| 154 |
+
0.16832139,1.2663355,-58.927147,-93.054665,-97.566795,0.034905426,-0.08221901,3.297619,765000
|
| 155 |
+
0.16920465,0.84650785,-67.91886,-94.08958,-98.43724,0.066067964,-0.12392876,3.6940122,770000
|
| 156 |
+
0.16414143,1.0032858,0.23476243,-93.70269,-98.30491,0.4703236,-0.17187431,9.578885,775000
|
| 157 |
+
0.19269894,0.862846,0.30633777,-92.792046,-98.243614,0.03473298,-0.10981062,3.0821176,780000
|
| 158 |
+
0.17587699,1.0220425,0.22734493,-91.63894,-96.77523,0.05577966,-0.17115648,4.063451,785000
|
| 159 |
+
0.16667823,3.437959,-54.55468,-94.26869,-98.218544,0.19592625,-0.114406005,4.744309,790000
|
| 160 |
+
0.15531762,1.1733404,0.3280328,-95.13991,-100.24602,0.065005094,-0.09733345,3.4124155,795000
|
| 161 |
+
0.21223885,0.6390519,-65.64075,-95.98061,-99.35446,0.04765972,-0.10993517,3.093162,800000
|
| 162 |
+
0.17432666,1.6103646,-66.18879,-95.49217,-99.9056,0.033883005,-0.083071046,3.4015846,805000
|
| 163 |
+
0.19350114,7.134253,-1.2376552,-95.43891,-99.28911,0.12951079,-0.25154397,9.963772,810000
|
| 164 |
+
0.1633431,4.647776,-0.8953617,-94.77975,-98.94503,0.05422651,-0.191651,7.141258,815000
|
| 165 |
+
0.15249088,1.2674106,-55.386242,-94.48676,-98.92588,0.3303269,-0.12348691,6.9757156,820000
|
| 166 |
+
0.1704573,2.68149,0.1369867,-92.15411,-97.40384,0.43686846,-0.16264704,11.1231,825000
|
| 167 |
+
0.17126867,1.007101,-63.41924,-93.69732,-98.03873,0.05368818,-0.058954865,2.91303,830000
|
| 168 |
+
0.1852395,1.8646601,-69.85397,-94.31858,-98.4622,0.19556074,-0.1401055,7.4939966,835000
|
| 169 |
+
0.15718403,0.88632435,0.13383156,-94.513,-99.19408,0.09545756,-0.028931813,3.1450248,840000
|
| 170 |
+
0.1877352,1.0453237,-70.802795,-94.93805,-99.032036,0.21357438,-0.073101275,4.879979,845000
|
| 171 |
+
0.16864385,2.2775578,-57.045105,-94.08561,-99.25093,0.11863408,-0.057911858,4.207651,850000
|
| 172 |
+
0.18609428,1.0753447,-3.086278,-94.2458,-99.19478,0.032031663,-0.04262338,2.472638,855000
|
| 173 |
+
0.17291103,0.88192827,-65.46063,-94.368835,-98.967384,0.109514296,-0.04653715,3.1140316,860000
|
| 174 |
+
0.17181787,1.926474,0.2219496,-93.46555,-99.86908,0.16828518,-0.055484917,5.026231,865000
|
| 175 |
+
0.14170346,2.0287657,-59.632767,-92.07702,-99.16361,0.110188566,-0.035346735,4.924605,870000
|
| 176 |
+
0.17958584,1.4355626,-58.486973,-91.504456,-96.259674,0.061938424,-0.13058992,3.7401693,875000
|
| 177 |
+
0.15887973,1.0964136,-64.56659,-93.18766,-97.51375,0.16467564,-0.06145933,3.918549,880000
|
| 178 |
+
0.18415911,2.336114,-70.30277,-93.22021,-98.37505,0.14093143,-0.05035953,3.989604,885000
|
| 179 |
+
0.16598071,1.385315,-66.03086,-93.27149,-97.61277,0.043030173,-0.09824516,3.938942,890000
|
| 180 |
+
0.15662202,6.2655025,-64.95663,-93.9987,-98.42647,0.10488283,-0.30645245,9.667374,895000
|
| 181 |
+
0.1750071,1.3424306,-63.45947,-95.01666,-98.94954,0.06121685,-0.16170666,3.8803093,900000
|
| 182 |
+
0.16102879,1.5063243,0.14499125,-94.19059,-98.63906,0.29611897,-0.10780943,6.697485,905000
|
| 183 |
+
0.17602937,2.673697,-52.27843,-92.2174,-97.54566,0.108000904,-0.1340013,4.278904,910000
|
| 184 |
+
0.17555167,0.5353095,0.16832447,-93.77151,-98.88167,0.04661865,-0.109302446,2.217169,915000
|
| 185 |
+
0.17915523,1.1235574,-59.257305,-94.62313,-98.69597,0.15297207,-0.056356736,3.73302,920000
|
| 186 |
+
0.17067078,1.1883043,-77.401695,-94.825935,-98.34538,0.042714547,-0.09018546,2.7792928,925000
|
| 187 |
+
0.17647657,1.0134457,-60.40226,-95.20718,-98.95687,0.06134288,-0.15938687,2.9626076,930000
|
| 188 |
+
0.16388866,1.3343816,-68.64692,-94.6733,-98.85915,0.35570508,-0.13560641,6.5593853,935000
|
| 189 |
+
0.17452843,2.6133265,0.016470075,-94.731384,-99.23486,0.14917542,-0.39524156,6.7133665,940000
|
| 190 |
+
0.17338078,1.3209505,0.2232022,-94.38656,-99.42385,0.2327805,-0.3295098,4.3951063,945000
|
| 191 |
+
0.16115522,1.6880726,-2.8768203,-94.439545,-98.84498,0.2777391,-0.31908077,6.074794,950000
|
| 192 |
+
0.158196,2.095609,0.1269663,-93.46073,-98.25763,0.10999935,-0.06473131,3.51804,955000
|
| 193 |
+
0.19228348,5.29199,-60.46291,-94.00502,-98.260895,0.11249266,-0.3248689,8.279984,960000
|
| 194 |
+
0.17637597,1.6848849,-65.597305,-95.35052,-98.74384,0.048550837,-0.14268407,3.8999355,965000
|
| 195 |
+
0.16515759,4.2124066,-2.7778509,-94.295265,-98.47645,0.09797472,-0.06866383,4.186471,970000
|
| 196 |
+
0.16301264,2.62299,0.14825472,-93.66481,-98.75928,0.0959222,-0.053659506,3.7161117,975000
|
| 197 |
+
0.18159676,3.4013722,-66.71496,-94.37035,-98.617386,0.09877542,-0.2586238,6.7011385,980000
|
| 198 |
+
0.18150829,1.5491437,-63.085304,-95.536736,-98.94107,0.12887965,-0.37341434,7.311356,985000
|
| 199 |
+
0.1648148,8.400957,-55.505077,-94.96444,-98.798775,0.38127014,-0.14186604,9.115551,990000
|
| 200 |
+
0.18878883,0.685028,-72.211044,-95.56591,-99.00624,0.06008085,-0.036493536,2.3671694,995000
|
| 201 |
+
0.13926311,16.34309,-0.09311023,-88.204155,-96.001884,0.22129321,-0.13321891,8.935838,1000000
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/offline_agent_sv.csv
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.2572963,2.8757513,-6.884718,-47.457375,-54.27165,0.21008998,-0.17022747,16.587677,5000
|
| 3 |
+
0.22032467,1.7587227,-22.457716,-66.15852,-71.69979,0.10479148,-0.042718813,8.374995,10000
|
| 4 |
+
0.20516817,2.693316,-52.942493,-75.89294,-80.661026,0.1093789,-0.123407885,12.331238,15000
|
| 5 |
+
0.2198817,13.278651,0.06988962,-73.76223,-83.32882,0.16126485,-0.15315206,18.607115,20000
|
| 6 |
+
0.19808263,3.2442753,-0.02055154,-77.21038,-85.26574,0.06425947,-0.16669066,12.199322,25000
|
| 7 |
+
0.22699443,3.1142654,-45.800617,-78.19172,-85.19057,0.15968089,-0.062066477,13.566454,30000
|
| 8 |
+
0.187579,4.3099933,-0.27504468,-78.3735,-85.83786,0.11708765,-0.2936991,16.922785,35000
|
| 9 |
+
0.19481528,5.5027027,-40.190754,-81.31798,-86.838486,0.08946003,-0.15038222,11.422528,40000
|
| 10 |
+
0.18673019,2.3173273,-48.156063,-83.193214,-90.18087,0.09581773,-0.06091846,9.2374115,45000
|
| 11 |
+
0.20928177,1.83853,0.1591253,-83.689514,-90.435616,0.04445765,-0.097805046,7.4046497,50000
|
| 12 |
+
0.2056104,4.6894584,-52.88556,-86.91802,-92.65937,0.09625972,-0.13189311,11.793656,55000
|
| 13 |
+
0.18138832,2.0303402,0.31331873,-86.26133,-93.29196,0.097647876,-0.037843715,6.563656,60000
|
| 14 |
+
0.2048267,6.8799715,-53.033016,-89.117485,-94.72957,0.24241063,-0.070460305,13.402856,65000
|
| 15 |
+
0.2189494,2.3664708,0.17540592,-87.344154,-95.00766,0.07620191,-0.1330857,9.002398,70000
|
| 16 |
+
0.18829924,1.6644677,-44.751225,-89.565636,-95.59585,0.051102158,-0.1050974,6.5506425,75000
|
| 17 |
+
0.16236562,1.4387068,-63.39566,-90.79964,-95.99232,0.039105915,-0.061701093,6.394159,80000
|
| 18 |
+
0.214394,2.000639,-48.05386,-90.96615,-96.91785,0.06602095,-0.11765638,8.21324,85000
|
| 19 |
+
0.19452995,5.546045,-59.003662,-84.16066,-90.55542,0.069388226,-0.18941772,11.795287,90000
|
| 20 |
+
0.17297727,14.47966,-45.451138,-79.462555,-87.15001,0.18066831,-0.16397771,18.643894,95000
|
| 21 |
+
0.1991788,7.500141,-0.053330444,-73.92818,-81.95545,0.10799493,-0.39273918,18.594067,100000
|
| 22 |
+
0.18198419,7.459452,-28.67862,-68.88222,-77.878784,0.50970215,-0.56838024,25.150383,105000
|
| 23 |
+
0.1998119,10.150368,-33.04542,-64.10658,-74.7097,0.29348722,-0.46333775,27.715359,110000
|
| 24 |
+
0.16973805,5.2010193,-2.0987587,-68.914055,-75.86958,0.10484245,-0.0758149,7.42672,115000
|
| 25 |
+
0.19587372,8.223113,0.31897303,-62.308083,-71.21974,0.20417789,-0.10297102,10.218219,120000
|
| 26 |
+
0.16178355,2.842429,0.1961015,-68.79577,-74.66943,0.055767756,-0.09289457,5.06077,125000
|
| 27 |
+
0.18170504,3.4758568,1.4748884,-69.28972,-76.03322,0.08895397,-0.046542875,5.8783655,130000
|
| 28 |
+
0.18178825,5.520847,0.20378794,-72.503235,-80.790596,0.09336635,-0.19283757,11.881831,135000
|
| 29 |
+
0.17216119,1.3690087,0.06403466,-66.75832,-72.47558,0.07390837,-0.026367968,3.6040146,140000
|
| 30 |
+
0.19881429,3.57312,0.14224197,-73.26216,-79.6412,0.088621005,-0.098922476,8.459568,145000
|
| 31 |
+
0.16488926,2.9589696,-2.7193131,-73.29172,-82.62737,0.069251165,-0.05452293,5.5363417,150000
|
| 32 |
+
0.17575201,6.4313216,-2.4178462,-62.613068,-71.0884,0.23054907,-0.08137993,12.168918,155000
|
| 33 |
+
0.16816649,9.586767,-38.221443,-60.803432,-74.25905,0.111030996,-0.07247004,7.352281,160000
|
| 34 |
+
0.18632457,11.737292,-31.344578,-69.86383,-82.27743,0.4292372,-0.12294637,17.048931,165000
|
| 35 |
+
0.20565213,3.788887,-42.136654,-66.13323,-74.87475,0.055728465,-0.16898131,9.196728,170000
|
| 36 |
+
0.20571421,5.174135,-44.722878,-74.43151,-80.40684,0.08530452,-0.16087487,9.625588,175000
|
| 37 |
+
0.18088534,8.0158205,-34.96553,-77.23165,-84.819435,0.15029156,-0.13998443,9.710448,180000
|
| 38 |
+
0.19679624,2.6585999,-47.114395,-75.085,-82.204636,0.046296977,-0.13778594,7.1520686,185000
|
| 39 |
+
0.18229145,12.444697,-45.182053,-71.424446,-80.460236,0.1591757,-0.094589025,12.106635,190000
|
| 40 |
+
0.18066782,4.8873,-0.55365384,-77.70424,-84.93314,0.15417162,-0.09138273,8.301131,195000
|
| 41 |
+
0.19121677,7.4262085,-48.402378,-74.30436,-82.93687,0.31251672,-0.092816934,14.603978,200000
|
| 42 |
+
0.14713211,4.726383,0.21384452,-71.197014,-77.68874,0.12568982,-0.13313186,6.6054134,205000
|
| 43 |
+
0.19748282,6.383526,0.2916274,-73.18861,-81.29828,0.077428,-0.12814282,7.271771,210000
|
| 44 |
+
0.15624604,2.8339427,-47.94678,-81.596,-86.720146,0.14216934,-0.24450873,12.059544,215000
|
| 45 |
+
0.16416731,3.4598184,-46.90138,-76.674065,-83.44083,0.056935538,-0.12927964,7.7018466,220000
|
| 46 |
+
0.17891273,2.1092885,-3.1742644,-85.57961,-91.3187,0.062558636,-0.23078477,7.645746,225000
|
| 47 |
+
0.18369085,10.956664,-44.13418,-79.12253,-87.94235,0.22254628,-0.095978424,12.801839,230000
|
| 48 |
+
0.1574542,4.3759747,0.15361,-78.28094,-86.90449,0.10044719,-0.07994616,6.6798096,235000
|
| 49 |
+
0.16072465,2.4716718,-43.185875,-73.75741,-81.703636,0.19161111,-0.052231155,7.919861,240000
|
| 50 |
+
0.22595093,2.012357,0.4941942,-76.17387,-89.160645,0.05496559,-0.058613706,4.2350397,245000
|
| 51 |
+
0.16564709,9.241527,0.30581868,-70.8988,-78.52652,0.26122546,-0.15837139,11.78088,250000
|
| 52 |
+
0.17491597,7.960424,-1.948431,-68.86358,-78.4969,0.29017553,-0.14889431,12.846415,255000
|
| 53 |
+
0.18059155,2.0475662,0.10874809,-79.66894,-85.57317,0.07177102,-0.056531984,4.6582165,260000
|
| 54 |
+
0.17094405,3.2575417,-46.656986,-86.74264,-93.06087,0.08433035,-0.28854036,12.61969,265000
|
| 55 |
+
0.18359053,6.818828,-44.41537,-85.44787,-93.37147,0.22091387,-0.091636196,9.225166,270000
|
| 56 |
+
0.15665802,1.500351,-0.026100636,-87.38299,-93.64092,0.15631667,-0.056738757,6.1437364,275000
|
| 57 |
+
0.173991,2.82946,-0.39647007,-88.97873,-96.172005,0.25666237,-0.084384926,11.835951,280000
|
| 58 |
+
0.17418075,2.5689502,-64.72041,-88.45193,-95.541504,0.2616659,-0.078560136,9.629518,285000
|
| 59 |
+
0.16338994,1.5565556,-54.848747,-88.42059,-94.87744,0.054752015,-0.040324934,3.9841862,290000
|
| 60 |
+
0.17160243,1.8637087,-61.089405,-89.389915,-95.179016,0.054462533,-0.09820488,4.703696,295000
|
| 61 |
+
0.1483278,2.1624653,-1.457453,-87.755165,-95.09203,0.058320887,-0.058622032,4.751169,300000
|
| 62 |
+
0.17464146,2.5043724,-55.78133,-84.63003,-90.79055,0.049829733,-0.14489886,6.4337983,305000
|
| 63 |
+
0.15535185,2.1301763,-50.488316,-84.34457,-91.47643,0.07812295,-0.057269406,4.7983313,310000
|
| 64 |
+
0.1520545,1.7595524,-59.004547,-84.67006,-90.02232,0.05170137,-0.118544,6.476858,315000
|
| 65 |
+
0.18118146,2.1447988,-48.19687,-81.97771,-89.85942,0.1286551,-0.057283536,6.558062,320000
|
| 66 |
+
0.14364162,2.029923,-2.466668,-83.96323,-90.00855,0.029013982,-0.058424845,3.9153438,325000
|
| 67 |
+
0.17935982,1.530317,-52.846523,-84.20581,-90.38179,0.078774735,-0.046928484,4.2008476,330000
|
| 68 |
+
0.1969758,4.190722,-50.83039,-80.403755,-88.24771,0.07778803,-0.09158732,5.873816,335000
|
| 69 |
+
0.19454469,12.062816,-38.882442,-77.666824,-87.85914,0.13574497,-0.3858543,18.13717,340000
|
| 70 |
+
0.18592843,6.228112,-39.33877,-78.39908,-86.48709,0.067129105,-0.25693306,9.718432,345000
|
| 71 |
+
0.18274838,3.7947018,-1.4324914,-80.67717,-88.85705,0.13894638,-0.062955156,6.2857914,350000
|
| 72 |
+
0.17364532,2.4773405,0.1514796,-84.26049,-90.587,0.093508385,-0.048877914,4.8645115,355000
|
| 73 |
+
0.17542326,1.948296,0.2094003,-85.08567,-92.410286,0.03665927,-0.11686966,4.685695,360000
|
| 74 |
+
0.18152358,2.904509,-49.835716,-85.10571,-91.644966,0.2794429,-0.08719352,9.88364,365000
|
| 75 |
+
0.17305782,2.040823,-58.316963,-87.57882,-94.39644,0.05563179,-0.1247595,4.736765,370000
|
| 76 |
+
0.18957883,7.6660438,0.20794082,-86.23679,-93.32169,0.07930765,-0.3319505,11.033183,375000
|
| 77 |
+
0.15184093,6.337664,0.12596776,-86.1701,-92.25916,0.32313693,-0.081276216,12.876635,380000
|
| 78 |
+
0.17275347,1.4936373,0.103296965,-83.57162,-90.30167,0.03353585,-0.0764318,4.428326,385000
|
| 79 |
+
0.16982418,1.0066189,0.25396663,-84.960045,-91.793076,0.04183414,-0.13405813,4.0450087,390000
|
| 80 |
+
0.14575744,2.0360818,-51.511875,-82.89551,-88.858635,0.034792453,-0.12081907,4.887505,395000
|
| 81 |
+
0.17419304,2.4270234,-53.57397,-85.68333,-92.26367,0.047190957,-0.12240348,5.685435,400000
|
| 82 |
+
0.19448379,2.9125607,0.547173,-85.89473,-91.818375,0.0744646,-0.07087349,4.5730443,405000
|
| 83 |
+
0.16962893,3.4269874,-59.63319,-88.85558,-95.096634,0.13959908,-0.11847384,6.714976,410000
|
| 84 |
+
0.17519955,1.8053694,-48.32858,-87.34418,-94.48925,0.089061916,-0.046870075,4.165262,415000
|
| 85 |
+
0.17579374,7.6360984,0.15147714,-84.52576,-91.631805,0.13448933,-0.23196834,10.3734665,420000
|
| 86 |
+
0.17266396,7.076782,-48.570267,-82.25295,-89.71968,0.13097191,-0.13808702,7.544936,425000
|
| 87 |
+
0.19258446,2.0736244,0.080171525,-83.49354,-90.502686,0.22771728,-0.072991736,7.112708,430000
|
| 88 |
+
0.1751588,2.1744707,-55.140625,-85.10699,-91.06276,0.08877929,-0.05608412,4.010222,435000
|
| 89 |
+
0.15807246,2.962835,-45.476055,-85.6148,-92.59859,0.09235321,-0.058545224,4.963947,440000
|
| 90 |
+
0.17034027,2.1440928,-60.525654,-82.23673,-88.99567,0.32548553,-0.09169972,8.70948,445000
|
| 91 |
+
0.19760998,1.3073338,0.2829643,-83.36091,-89.26978,0.08341801,-0.03775637,4.0676723,450000
|
| 92 |
+
0.16943488,2.1516755,-1.9523083,-87.41828,-92.577965,0.13221264,-0.041973338,4.8879237,455000
|
| 93 |
+
0.18314615,2.5061855,0.26451772,-83.66064,-89.97127,0.0514826,-0.055928975,3.595716,460000
|
| 94 |
+
0.17109749,3.2862968,0.7653688,-80.87065,-90.88009,0.15101096,-0.07996436,5.255858,465000
|
| 95 |
+
0.17486401,1.8330605,-58.87331,-86.15734,-92.06369,0.23182401,-0.07710223,6.1823187,470000
|
| 96 |
+
0.18878421,6.8366923,-42.76834,-83.118286,-90.34588,0.6224099,-0.23372781,20.860987,475000
|
| 97 |
+
0.16974846,1.5026636,0.16770345,-85.35663,-91.121864,0.04776113,-0.051660586,3.248783,480000
|
| 98 |
+
0.17718437,6.073461,-52.81311,-87.31437,-93.572754,0.1798568,-0.30054545,11.304109,485000
|
| 99 |
+
0.1716834,8.178763,-41.838573,-88.61199,-95.28473,0.26610738,-0.08534043,10.705814,490000
|
| 100 |
+
0.20580983,1.3871874,0.14666378,-86.33766,-92.88357,0.07809347,-0.0367968,4.976552,495000
|
| 101 |
+
0.20432553,3.2044308,-1.3847033,-86.72691,-92.9082,0.1626674,-0.14102788,6.5830717,500000
|
| 102 |
+
0.17787777,1.579673,0.062957,-86.74449,-93.25625,0.049588814,-0.073520884,3.7727475,505000
|
| 103 |
+
0.16647692,5.3306365,-41.35892,-85.0953,-96.0411,0.13841283,-0.12640569,7.8876314,510000
|
| 104 |
+
0.18855122,5.2063403,0.31108505,-67.220375,-78.60237,0.08330884,-0.105306685,7.8057528,515000
|
| 105 |
+
0.15842299,1.8295218,-0.65082455,-80.761665,-88.27328,0.046475295,-0.11425474,4.847315,520000
|
| 106 |
+
0.17902955,8.1822,-48.75557,-86.016655,-97.23179,0.24717608,-0.17990029,10.464842,525000
|
| 107 |
+
0.19574605,1.8086265,-3.523472,-89.30532,-99.01479,0.18415713,-0.062007796,6.9550447,530000
|
| 108 |
+
0.1665675,3.6191108,-56.07593,-91.01959,-96.61459,0.13969307,-0.42095733,9.6669,535000
|
| 109 |
+
0.1974013,1.6584812,0.15338892,-91.28923,-96.64004,0.1761198,-0.13468188,6.718706,540000
|
| 110 |
+
0.19353244,3.6213658,-52.886307,-89.53361,-95.801735,0.10191037,-0.28714514,6.0031123,545000
|
| 111 |
+
0.1800055,1.5889755,0.25019038,-90.52693,-99.289185,0.14949974,-0.06956374,4.310659,550000
|
| 112 |
+
0.1641391,4.3210096,0.19214371,-88.0754,-95.5824,0.33024117,-0.11091738,10.622002,555000
|
| 113 |
+
0.18438941,1.3567135,0.107595205,-89.82818,-95.70195,0.09984036,-0.05988896,3.7351973,560000
|
| 114 |
+
0.18360071,1.1385726,-57.196693,-91.124916,-96.109116,0.06816056,-0.038281754,2.8217592,565000
|
| 115 |
+
0.17819399,1.7357944,-53.93353,-89.951706,-96.02977,0.24302542,-0.08313479,8.062514,570000
|
| 116 |
+
0.15571612,2.2483795,0.15390505,-88.05599,-94.72004,0.0584489,-0.13877666,6.156764,575000
|
| 117 |
+
0.15753253,1.9414628,0.050977767,-89.36062,-95.74177,0.049651995,-0.091022044,3.4566584,580000
|
| 118 |
+
0.1509322,2.2365098,-53.69936,-87.89788,-94.89,0.07409463,-0.058728136,3.9389224,585000
|
| 119 |
+
0.14418253,1.3058451,0.1272309,-89.55508,-99.74093,0.034531243,-0.10957846,3.3958306,590000
|
| 120 |
+
0.15977249,1.5562865,-57.352013,-90.92139,-96.72982,0.0845426,-0.033310894,3.903314,595000
|
| 121 |
+
0.17314948,1.8810433,-53.44774,-90.37095,-96.84034,0.07218593,-0.05856144,4.091344,600000
|
| 122 |
+
0.17220366,1.706828,-50.883297,-88.46276,-94.63985,0.14560512,-0.05161989,4.983767,605000
|
| 123 |
+
0.15778181,2.812156,0.29818618,-88.28165,-95.50831,0.06985769,-0.17413111,5.55726,610000
|
| 124 |
+
0.14800104,2.040551,0.18628992,-89.71972,-95.968544,0.06058959,-0.15252802,5.097691,615000
|
| 125 |
+
0.15856081,4.03224,-46.865395,-87.44813,-94.654396,0.27798438,-0.09224279,10.443016,620000
|
| 126 |
+
0.20492706,1.5607985,-59.227974,-88.56532,-94.20476,0.16839328,-0.0560684,5.408322,625000
|
| 127 |
+
0.19597971,1.761536,-55.001312,-88.4284,-94.74196,0.08182536,-0.045896873,3.4074686,630000
|
| 128 |
+
0.15783447,2.2108681,-0.739065,-87.80731,-93.96007,0.16148436,-0.055070493,5.264937,635000
|
| 129 |
+
0.17757615,2.177531,0.13076366,-89.33156,-95.942024,0.108881466,-0.30380395,7.5740423,640000
|
| 130 |
+
0.19274479,2.3278275,-59.95301,-90.758446,-96.47719,0.03918398,-0.11847336,3.977826,645000
|
| 131 |
+
0.15427217,0.92520183,-50.629498,-91.84579,-97.368355,0.124595195,-0.040870473,3.5469174,650000
|
| 132 |
+
0.17455535,1.4578685,0.12324707,-91.113304,-97.81644,0.08427857,-0.039141472,3.1349487,655000
|
| 133 |
+
0.1601198,1.3781966,-62.80423,-92.14003,-97.986595,0.20087302,-0.07280414,5.0021844,660000
|
| 134 |
+
0.21596768,2.0849648,0.060468048,-92.29362,-97.97848,0.22044659,-0.5993423,10.933109,665000
|
| 135 |
+
0.17855284,2.8853557,-60.850277,-92.56803,-97.716576,0.11801767,-0.31993368,5.4909368,670000
|
| 136 |
+
0.17509887,0.9778639,-61.829285,-91.525375,-96.93158,0.18131651,-0.06570783,4.443909,675000
|
| 137 |
+
0.14906655,0.87957555,-59.267303,-91.921265,-96.786415,0.14485475,-0.046387404,3.8251944,680000
|
| 138 |
+
0.17406215,1.496503,-66.997345,-92.850975,-97.952774,0.07328141,-0.20060952,4.812868,685000
|
| 139 |
+
0.17359367,3.3340676,-64.21688,-92.35364,-97.40136,0.0426336,-0.07807331,5.1552677,690000
|
| 140 |
+
0.18304768,0.80914557,-62.70612,-93.211136,-97.96013,0.14332652,-0.045911796,3.9331114,695000
|
| 141 |
+
0.18053241,2.1517413,0.15604642,-92.109406,-100.43147,0.093992986,-0.09718458,4.4981785,700000
|
| 142 |
+
0.1848199,0.7879347,0.32469437,-92.63952,-98.23076,0.100522295,-0.034553807,2.598812,705000
|
| 143 |
+
0.15170994,0.91385174,0.2179083,-93.50895,-98.82955,0.09055549,-0.24491033,5.0108027,710000
|
| 144 |
+
0.17422107,6.331247,0.110954404,-92.46316,-97.97784,0.35330623,-0.1325548,7.52773,715000
|
| 145 |
+
0.19752811,0.8219658,-58.63016,-91.648186,-96.806046,0.06263126,-0.0568008,2.9346547,720000
|
| 146 |
+
0.15826803,2.4619825,-62.500652,-92.65542,-97.55487,0.28359175,-0.10430444,5.368049,725000
|
| 147 |
+
0.20204127,1.6019169,-65.269875,-94.14889,-98.344894,0.084848136,-0.058791183,3.482994,730000
|
| 148 |
+
0.19116108,2.8192399,0.10933399,-92.12604,-98.00004,0.09134876,-0.24894425,6.39962,735000
|
| 149 |
+
0.16472131,3.7088437,0.27420968,-91.906235,-97.51674,0.1244892,-0.3369847,9.486282,740000
|
| 150 |
+
0.18711653,1.3302039,0.30137897,-92.65961,-97.343414,0.11401688,-0.07413992,4.1237674,745000
|
| 151 |
+
0.14541158,1.0957421,-50.97568,-92.97722,-97.73727,0.097112514,-0.068017654,3.089244,750000
|
| 152 |
+
0.17192182,0.97078717,0.11341825,-93.05471,-98.13086,0.054624025,-0.045523707,2.9833598,755000
|
| 153 |
+
0.20266347,1.4758996,0.058245182,-92.95011,-98.04161,0.038352273,-0.06858465,2.4093502,760000
|
| 154 |
+
0.16832139,1.2663355,-58.927147,-93.054665,-97.566795,0.034905426,-0.08221901,3.297619,765000
|
| 155 |
+
0.16920465,0.84650785,-67.91886,-94.08958,-98.43724,0.066067964,-0.12392876,3.6940122,770000
|
| 156 |
+
0.16414143,1.0032858,0.23476243,-93.70269,-98.30491,0.4703236,-0.17187431,9.578885,775000
|
| 157 |
+
0.19269894,0.862846,0.30633777,-92.792046,-98.243614,0.03473298,-0.10981062,3.0821176,780000
|
| 158 |
+
0.17587699,1.0220425,0.22734493,-91.63894,-96.77523,0.05577966,-0.17115648,4.063451,785000
|
| 159 |
+
0.16667823,3.437959,-54.55468,-94.26869,-98.218544,0.19592625,-0.114406005,4.744309,790000
|
| 160 |
+
0.15531762,1.1733404,0.3280328,-95.13991,-100.24602,0.065005094,-0.09733345,3.4124155,795000
|
| 161 |
+
0.21223885,0.6390519,-65.64075,-95.98061,-99.35446,0.04765972,-0.10993517,3.093162,800000
|
| 162 |
+
0.17432666,1.6103646,-66.18879,-95.49217,-99.9056,0.033883005,-0.083071046,3.4015846,805000
|
| 163 |
+
0.19350114,7.134253,-1.2376552,-95.43891,-99.28911,0.12951079,-0.25154397,9.963772,810000
|
| 164 |
+
0.1633431,4.647776,-0.8953617,-94.77975,-98.94503,0.05422651,-0.191651,7.141258,815000
|
| 165 |
+
0.15249088,1.2674106,-55.386242,-94.48676,-98.92588,0.3303269,-0.12348691,6.9757156,820000
|
| 166 |
+
0.1704573,2.68149,0.1369867,-92.15411,-97.40384,0.43686846,-0.16264704,11.1231,825000
|
| 167 |
+
0.17126867,1.007101,-63.41924,-93.69732,-98.03873,0.05368818,-0.058954865,2.91303,830000
|
| 168 |
+
0.1852395,1.8646601,-69.85397,-94.31858,-98.4622,0.19556074,-0.1401055,7.4939966,835000
|
| 169 |
+
0.15718403,0.88632435,0.13383156,-94.513,-99.19408,0.09545756,-0.028931813,3.1450248,840000
|
| 170 |
+
0.1877352,1.0453237,-70.802795,-94.93805,-99.032036,0.21357438,-0.073101275,4.879979,845000
|
| 171 |
+
0.16864385,2.2775578,-57.045105,-94.08561,-99.25093,0.11863408,-0.057911858,4.207651,850000
|
| 172 |
+
0.18609428,1.0753447,-3.086278,-94.2458,-99.19478,0.032031663,-0.04262338,2.472638,855000
|
| 173 |
+
0.17291103,0.88192827,-65.46063,-94.368835,-98.967384,0.109514296,-0.04653715,3.1140316,860000
|
| 174 |
+
0.17181787,1.926474,0.2219496,-93.46555,-99.86908,0.16828518,-0.055484917,5.026231,865000
|
| 175 |
+
0.14170346,2.0287657,-59.632767,-92.07702,-99.16361,0.110188566,-0.035346735,4.924605,870000
|
| 176 |
+
0.17958584,1.4355626,-58.486973,-91.504456,-96.259674,0.061938424,-0.13058992,3.7401693,875000
|
| 177 |
+
0.15887973,1.0964136,-64.56659,-93.18766,-97.51375,0.16467564,-0.06145933,3.918549,880000
|
| 178 |
+
0.18415911,2.336114,-70.30277,-93.22021,-98.37505,0.14093143,-0.05035953,3.989604,885000
|
| 179 |
+
0.16598071,1.385315,-66.03086,-93.27149,-97.61277,0.043030173,-0.09824516,3.938942,890000
|
| 180 |
+
0.15662202,6.2655025,-64.95663,-93.9987,-98.42647,0.10488283,-0.30645245,9.667374,895000
|
| 181 |
+
0.1750071,1.3424306,-63.45947,-95.01666,-98.94954,0.06121685,-0.16170666,3.8803093,900000
|
| 182 |
+
0.16102879,1.5063243,0.14499125,-94.19059,-98.63906,0.29611897,-0.10780943,6.697485,905000
|
| 183 |
+
0.17602937,2.673697,-52.27843,-92.2174,-97.54566,0.108000904,-0.1340013,4.278904,910000
|
| 184 |
+
0.17555167,0.5353095,0.16832447,-93.77151,-98.88167,0.04661865,-0.109302446,2.217169,915000
|
| 185 |
+
0.17915523,1.1235574,-59.257305,-94.62313,-98.69597,0.15297207,-0.056356736,3.73302,920000
|
| 186 |
+
0.17067078,1.1883043,-77.401695,-94.825935,-98.34538,0.042714547,-0.09018546,2.7792928,925000
|
| 187 |
+
0.17647657,1.0134457,-60.40226,-95.20718,-98.95687,0.06134288,-0.15938687,2.9626076,930000
|
| 188 |
+
0.16388866,1.3343816,-68.64692,-94.6733,-98.85915,0.35570508,-0.13560641,6.5593853,935000
|
| 189 |
+
0.17452843,2.6133265,0.016470075,-94.731384,-99.23486,0.14917542,-0.39524156,6.7133665,940000
|
| 190 |
+
0.17338078,1.3209505,0.2232022,-94.38656,-99.42385,0.2327805,-0.3295098,4.3951063,945000
|
| 191 |
+
0.16115522,1.6880726,-2.8768203,-94.439545,-98.84498,0.2777391,-0.31908077,6.074794,950000
|
| 192 |
+
0.158196,2.095609,0.1269663,-93.46073,-98.25763,0.10999935,-0.06473131,3.51804,955000
|
| 193 |
+
0.19228348,5.29199,-60.46291,-94.00502,-98.260895,0.11249266,-0.3248689,8.279984,960000
|
| 194 |
+
0.17637597,1.6848849,-65.597305,-95.35052,-98.74384,0.048550837,-0.14268407,3.8999355,965000
|
| 195 |
+
0.16515759,4.2124066,-2.7778509,-94.295265,-98.47645,0.09797472,-0.06866383,4.186471,970000
|
| 196 |
+
0.16301264,2.62299,0.14825472,-93.66481,-98.75928,0.0959222,-0.053659506,3.7161117,975000
|
| 197 |
+
0.18159676,3.4013722,-66.71496,-94.37035,-98.617386,0.09877542,-0.2586238,6.7011385,980000
|
| 198 |
+
0.18150829,1.5491437,-63.085304,-95.536736,-98.94107,0.12887965,-0.37341434,7.311356,985000
|
| 199 |
+
0.1648148,8.400957,-55.505077,-94.96444,-98.798775,0.38127014,-0.14186604,9.115551,990000
|
| 200 |
+
0.18878883,0.685028,-72.211044,-95.56591,-99.00624,0.06008085,-0.036493536,2.3671694,995000
|
| 201 |
+
0.13926311,16.34309,-0.09311023,-88.204155,-96.001884,0.22129321,-0.13321891,8.935838,1000000
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/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 |
+
0.16084367,9.575096,-21.822905,-88.13189,-96.14445,0.9452354,-0.3512268,33.737576,1005000
|
| 3 |
+
0.17947125,3.7338498,-1.7590287,-81.93506,-89.249565,0.13523623,-0.35951233,7.7677917,1010000
|
| 4 |
+
0.1627962,0.8653477,0.22971529,-89.49913,-95.31971,0.06066885,-0.16389063,3.2629325,1015000
|
| 5 |
+
0.20054117,0.87020016,-3.561875,-91.830055,-97.74863,0.08392087,-0.04051925,3.1170187,1020000
|
| 6 |
+
0.20334005,0.76561683,-61.307404,-93.875786,-98.91833,0.033206057,-0.072317615,2.3725932,1025000
|
| 7 |
+
0.18869703,1.4091405,-72.19238,-93.57729,-99.52034,0.28345418,-0.10737905,5.575432,1030000
|
| 8 |
+
0.2115793,0.66999245,-3.4971585,-93.67144,-100.242836,0.08326265,-0.03124506,2.9536471,1035000
|
| 9 |
+
0.13603976,1.1342505,-70.57792,-92.64378,-99.86783,0.056847155,-0.12286169,3.6456747,1040000
|
| 10 |
+
0.22719522,1.394094,0.04318601,-92.96671,-100.07741,0.11398257,-0.05803013,3.7319698,1045000
|
| 11 |
+
0.222113,11.731871,-63.547268,-92.54645,-99.80245,0.29858485,-0.20882884,8.422899,1050000
|
| 12 |
+
0.21716905,1.8870277,-52.746796,-91.36155,-99.7337,0.29003617,-0.111025006,5.6187935,1055000
|
| 13 |
+
0.22860456,0.9926214,0.15674576,-90.41507,-99.72084,0.35740876,-0.13620088,7.0737658,1060000
|
| 14 |
+
0.21030325,3.7423177,-26.85309,-85.1276,-99.68258,0.32423306,-0.11888274,11.341568,1065000
|
| 15 |
+
0.26235715,3.1119664,-12.663647,-74.26531,-91.30064,0.3635885,-0.13554749,10.269772,1070000
|
| 16 |
+
0.23513967,3.0365171,-15.799355,-77.22851,-92.53843,0.09044298,-0.23528913,7.6695623,1075000
|
| 17 |
+
0.26127687,3.2223454,-1.4822415,-79.567665,-95.844406,0.11712634,-0.17038794,7.7899,1080000
|
| 18 |
+
0.2379556,3.5466354,-34.40969,-77.67818,-95.17876,0.2685252,-0.09936219,8.889769,1085000
|
| 19 |
+
0.22171558,2.5681381,-25.732851,-75.915184,-93.76915,0.3596021,-0.13231754,9.513529,1090000
|
| 20 |
+
0.21703812,2.4394891,-35.25171,-76.677505,-95.350784,0.062408008,-0.14664738,5.740473,1095000
|
| 21 |
+
0.25325036,4.6876616,-28.22559,-76.89492,-95.40923,0.1515472,-0.40113837,12.469704,1100000
|
| 22 |
+
0.2365234,3.5425217,-2.6437624,-72.305,-95.22686,0.13669226,-0.3594594,11.064044,1105000
|
| 23 |
+
0.23797518,3.4938266,0.1555658,-72.19715,-92.21358,0.09269208,-0.09940697,5.9962993,1110000
|
| 24 |
+
0.20115009,3.0038526,-35.060616,-73.76748,-91.64848,0.19641404,-0.1007818,6.866116,1115000
|
| 25 |
+
0.25643808,3.9408944,-2.023408,-70.48583,-94.97717,0.22770515,-0.13803354,10.335558,1120000
|
| 26 |
+
0.26242062,3.1044643,-23.7452,-69.72378,-93.49275,0.11734769,-0.31234312,8.568487,1125000
|
| 27 |
+
0.27941814,2.7736146,0.22214109,-71.30729,-93.56707,0.08700342,-0.24716836,7.357201,1130000
|
| 28 |
+
0.29598105,5.668283,-28.673903,-69.71908,-93.19694,0.23008072,-0.15865305,12.443473,1135000
|
| 29 |
+
0.27388066,2.9366286,-24.117348,-69.28965,-91.02834,0.06563335,-0.13134009,6.4186754,1140000
|
| 30 |
+
0.28638658,2.5600371,0.25663713,-68.76285,-92.300835,0.109101996,-0.09432482,5.4128447,1145000
|
| 31 |
+
0.23860395,2.0291963,-30.916063,-68.78072,-92.0076,0.14367977,-0.09099172,5.9600377,1150000
|
| 32 |
+
0.25766385,2.0518868,0.23160978,-67.8211,-87.8516,0.25542566,-0.09040986,6.4984035,1155000
|
| 33 |
+
0.29943863,2.4853184,0.023178145,-68.796684,-89.61473,0.053570926,-0.16037732,5.7776413,1160000
|
| 34 |
+
0.32200947,2.8827353,-24.48955,-66.49139,-89.62327,0.2921234,-0.35584837,8.190651,1165000
|
| 35 |
+
0.22497472,1.9699306,-30.835812,-66.50915,-89.96553,0.25185913,-0.09473857,7.4563065,1170000
|
| 36 |
+
0.25924414,2.4851017,-0.8173568,-65.40513,-91.30807,0.20044082,-0.14555176,6.809092,1175000
|
| 37 |
+
0.3246436,2.3802178,-28.206207,-67.17901,-89.82486,0.11646056,-0.12909126,5.998129,1180000
|
| 38 |
+
0.2862863,2.3927562,0.26388216,-65.11758,-86.523155,0.08921548,-0.12950669,5.6245418,1185000
|
| 39 |
+
0.28530964,2.5240796,-31.181145,-65.461,-88.84335,0.07986237,-0.20250514,6.3848057,1190000
|
| 40 |
+
0.3015533,3.8072534,0.14737505,-64.027824,-88.33287,0.16834934,-0.13412985,7.008562,1195000
|
| 41 |
+
0.30554295,5.268529,-0.35862434,-61.45807,-87.48133,0.17009275,-0.08725572,9.212819,1200000
|
| 42 |
+
0.2573288,3.0126514,-24.084545,-63.15048,-86.36201,0.17421678,-0.06361489,7.588005,1205000
|
| 43 |
+
0.3115732,3.9208684,-8.247994,-62.476723,-86.78855,0.16873068,-0.13601926,6.5116787,1210000
|
| 44 |
+
0.3152727,3.0987,0.2641038,-60.460365,-83.19605,0.08475858,-0.21300772,7.235612,1215000
|
| 45 |
+
0.34176165,3.42725,-23.781984,-62.629925,-85.33286,0.09599193,-0.26741844,7.900793,1220000
|
| 46 |
+
0.34721234,3.215152,0.14247106,-64.09814,-82.80813,0.131109,-0.3668235,10.42333,1225000
|
| 47 |
+
0.3386051,4.2630534,-11.238298,-64.30384,-83.36028,0.17465258,-0.0696479,6.4402475,1230000
|
| 48 |
+
0.35315567,7.442858,-25.144848,-64.13323,-84.94342,0.17808208,-0.25167343,9.706675,1235000
|
| 49 |
+
0.26102847,3.4613438,0.29984948,-62.534863,-83.9004,0.22569454,-0.13138878,9.742595,1240000
|
| 50 |
+
0.32183754,2.4167173,-5.109396,-64.24133,-82.99023,0.16248426,-0.17995861,7.76478,1245000
|
| 51 |
+
0.33197004,2.6351528,-24.171616,-65.41605,-83.93782,0.15469696,-0.062378053,5.605343,1250000
|
| 52 |
+
0.30539095,1.7452011,-35.579792,-67.46694,-84.35835,0.19193831,-0.12951094,5.643739,1255000
|
| 53 |
+
0.3335951,3.4692712,-17.397657,-67.625015,-85.619934,0.13984431,-0.17546472,7.57337,1260000
|
| 54 |
+
0.30886692,2.1203337,-33.728577,-67.2767,-84.13962,0.2380584,-0.1991478,6.612579,1265000
|
| 55 |
+
0.33970347,2.725211,-20.488928,-67.34668,-85.37843,0.1029236,-0.15801567,8.21445,1270000
|
| 56 |
+
0.34691486,2.3660295,-32.77936,-66.097855,-86.011246,0.23494,-0.08284719,7.340578,1275000
|
| 57 |
+
0.37552884,4.5389457,-30.712492,-66.64126,-85.8063,0.1601192,-0.1943192,7.9218903,1280000
|
| 58 |
+
0.37445474,3.669979,-32.96991,-66.19552,-83.91085,0.12482998,-0.34435454,9.158147,1285000
|
| 59 |
+
0.34159213,5.009813,-40.617607,-69.33019,-91.73982,0.07050493,-0.13137606,6.847104,1290000
|
| 60 |
+
0.3479388,1.5929338,-18.227375,-70.88778,-87.017456,0.06542794,-0.06699151,3.6176748,1295000
|
| 61 |
+
0.3043188,2.6035135,0.3767551,-70.91786,-86.97844,0.31562382,-0.120214775,8.323084,1300000
|
| 62 |
+
0.3199113,1.6381238,0.14781404,-69.6599,-86.44105,0.15409042,-0.057349905,5.4344397,1305000
|
| 63 |
+
0.36274403,1.9187775,0.14761835,-68.919426,-86.697845,0.42262617,-0.15899713,10.200994,1310000
|
| 64 |
+
0.31335732,2.3573177,5.494179,-67.33492,-87.04612,0.5795053,-0.21798742,11.991345,1315000
|
| 65 |
+
0.36749658,4.260718,-4.2733397,-69.80277,-85.36596,0.11151378,-0.32551274,8.735874,1320000
|
| 66 |
+
0.3487035,14.070511,0.14212829,-67.73892,-85.46739,0.45644984,-0.31322867,11.6350155,1325000
|
| 67 |
+
0.36997837,9.297724,-38.38523,-69.55349,-87.031,0.19536808,-0.3932488,14.081216,1330000
|
| 68 |
+
0.3924844,8.529996,-0.67620665,-69.43581,-89.840225,0.10277253,-0.3713912,11.556158,1335000
|
| 69 |
+
0.38201958,4.495419,-40.207874,-69.4025,-85.62395,0.061743677,-0.23668936,9.011112,1340000
|
| 70 |
+
0.37825602,1.7239983,-36.44288,-69.94261,-84.89991,0.18101072,-0.061319336,5.8768144,1345000
|
| 71 |
+
0.39703056,2.4375126,-32.356728,-70.91211,-89.00602,0.12865606,-0.2379403,6.4848228,1350000
|
| 72 |
+
0.36110824,1.856458,-0.3686052,-70.83982,-88.41582,0.14056996,-0.099492505,5.7909,1355000
|
| 73 |
+
0.3719139,2.2101417,-44.005524,-71.31241,-86.77529,0.28508833,-0.106728904,7.830371,1360000
|
| 74 |
+
0.36272976,1.615786,-40.94519,-73.061134,-89.12707,0.46989942,-0.37402225,13.581576,1365000
|
| 75 |
+
0.40933305,3.3091118,4.2897725,-72.95342,-89.98497,0.65286505,-0.42948326,29.079573,1370000
|
| 76 |
+
0.40526477,2.8386967,-1.5343959,-73.08132,-88.22252,0.2634625,-0.18959358,8.746388,1375000
|
| 77 |
+
0.35213482,2.0324838,-40.408802,-71.91885,-88.31405,0.12825869,-0.16238691,6.9664955,1380000
|
| 78 |
+
0.3568496,4.856733,0.2917993,-72.068665,-87.82555,0.2093975,-0.18309483,10.116087,1385000
|
| 79 |
+
0.38250285,5.0261583,-3.3998075,-73.40017,-88.61018,0.34341022,-0.32632226,24.129007,1390000
|
| 80 |
+
0.36728317,2.4298666,-2.9278154,-72.190834,-90.72345,0.1736611,-0.07843729,4.6497464,1395000
|
| 81 |
+
0.3717967,7.8037186,-19.705576,-73.67324,-88.17704,0.18925384,-0.205077,9.427722,1400000
|
| 82 |
+
0.39682537,2.4497967,0.2806464,-72.388145,-93.12212,0.36928824,-0.14073445,9.623826,1405000
|
| 83 |
+
0.3546273,6.4444222,-26.266022,-73.92089,-88.21137,0.16192557,-0.2859206,11.853137,1410000
|
| 84 |
+
0.37429094,2.462179,-0.737865,-76.63706,-89.41226,0.2441035,-0.25128168,12.591532,1415000
|
| 85 |
+
0.36073518,4.682529,-0.63891464,-74.31471,-90.2527,0.21780562,-0.17416418,9.2064085,1420000
|
| 86 |
+
0.36884585,2.073633,-35.55877,-73.05088,-87.06206,0.87421376,-0.79681337,25.599617,1425000
|
| 87 |
+
0.3839017,6.392212,-43.111923,-73.17507,-86.90694,0.12848689,-0.34790528,8.784417,1430000
|
| 88 |
+
0.40413243,3.8404107,0.28101113,-70.82,-89.83005,0.25041196,-0.1061446,6.5976877,1435000
|
| 89 |
+
0.39739275,3.786618,-0.9610069,-69.11249,-85.84058,0.20259553,-0.48661566,14.518017,1440000
|
| 90 |
+
0.38250208,2.272793,-0.06600636,-71.37682,-89.78186,0.47464013,-0.3802075,22.376125,1445000
|
| 91 |
+
0.4058851,2.9280326,3.2864769,-72.86645,-87.49951,0.2838762,-0.40724295,16.661232,1450000
|
| 92 |
+
0.34424353,4.6464424,0.16964492,-72.51965,-91.73667,0.339288,-0.13549268,9.003332,1455000
|
| 93 |
+
0.37784547,16.91988,-43.506584,-72.68666,-86.838234,0.22806369,-0.44694385,10.548638,1460000
|
| 94 |
+
0.398295,3.1793506,0.48452756,-70.37343,-86.76585,0.11006744,-0.14390934,5.027549,1465000
|
| 95 |
+
0.38268244,1.8258187,-2.8150666,-71.54153,-89.88112,0.1419461,-0.22347555,7.035861,1470000
|
| 96 |
+
0.40742394,4.7282114,-39.97688,-71.1954,-87.90339,0.27179804,-0.30342278,11.037926,1475000
|
| 97 |
+
0.4194396,2.56842,-27.227345,-72.94338,-86.77057,0.283368,-0.39012647,12.722091,1480000
|
| 98 |
+
0.3639083,1.6978931,-34.975224,-72.59657,-91.83758,0.10673068,-0.30234668,6.5468106,1485000
|
| 99 |
+
0.40328333,4.177179,-42.21691,-73.49501,-93.21049,0.12138712,-0.18596464,11.150076,1490000
|
| 100 |
+
0.40715158,7.0427094,-48.65613,-74.4298,-91.39263,0.30958194,-0.31246892,14.93189,1495000
|
| 101 |
+
0.47719797,10.186979,-21.194233,-74.3796,-92.877686,0.17603016,-0.28611577,10.238736,1500000
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/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 |
+
0.16084367,9.575096,-21.822905,-88.13189,-96.14445,0.9452354,-0.3512268,33.737576,1005000
|
| 3 |
+
0.17947125,3.7338498,-1.7590287,-81.93506,-89.249565,0.13523623,-0.35951233,7.7677917,1010000
|
| 4 |
+
0.1627962,0.8653477,0.22971529,-89.49913,-95.31971,0.06066885,-0.16389063,3.2629325,1015000
|
| 5 |
+
0.20054117,0.87020016,-3.561875,-91.830055,-97.74863,0.08392087,-0.04051925,3.1170187,1020000
|
| 6 |
+
0.20334005,0.76561683,-61.307404,-93.875786,-98.91833,0.033206057,-0.072317615,2.3725932,1025000
|
| 7 |
+
0.18869703,1.4091405,-72.19238,-93.57729,-99.52034,0.28345418,-0.10737905,5.575432,1030000
|
| 8 |
+
0.2115793,0.66999245,-3.4971585,-93.67144,-100.242836,0.08326265,-0.03124506,2.9536471,1035000
|
| 9 |
+
0.13603976,1.1342505,-70.57792,-92.64378,-99.86783,0.056847155,-0.12286169,3.6456747,1040000
|
| 10 |
+
0.22719522,1.394094,0.04318601,-92.96671,-100.07741,0.11398257,-0.05803013,3.7319698,1045000
|
| 11 |
+
0.222113,11.731871,-63.547268,-92.54645,-99.80245,0.29858485,-0.20882884,8.422899,1050000
|
| 12 |
+
0.21716905,1.8870277,-52.746796,-91.36155,-99.7337,0.29003617,-0.111025006,5.6187935,1055000
|
| 13 |
+
0.22860456,0.9926214,0.15674576,-90.41507,-99.72084,0.35740876,-0.13620088,7.0737658,1060000
|
| 14 |
+
0.21030325,3.7423177,-26.85309,-85.1276,-99.68258,0.32423306,-0.11888274,11.341568,1065000
|
| 15 |
+
0.26235715,3.1119664,-12.663647,-74.26531,-91.30064,0.3635885,-0.13554749,10.269772,1070000
|
| 16 |
+
0.23513967,3.0365171,-15.799355,-77.22851,-92.53843,0.09044298,-0.23528913,7.6695623,1075000
|
| 17 |
+
0.26127687,3.2223454,-1.4822415,-79.567665,-95.844406,0.11712634,-0.17038794,7.7899,1080000
|
| 18 |
+
0.2379556,3.5466354,-34.40969,-77.67818,-95.17876,0.2685252,-0.09936219,8.889769,1085000
|
| 19 |
+
0.22171558,2.5681381,-25.732851,-75.915184,-93.76915,0.3596021,-0.13231754,9.513529,1090000
|
| 20 |
+
0.21703812,2.4394891,-35.25171,-76.677505,-95.350784,0.062408008,-0.14664738,5.740473,1095000
|
| 21 |
+
0.25325036,4.6876616,-28.22559,-76.89492,-95.40923,0.1515472,-0.40113837,12.469704,1100000
|
| 22 |
+
0.2365234,3.5425217,-2.6437624,-72.305,-95.22686,0.13669226,-0.3594594,11.064044,1105000
|
| 23 |
+
0.23797518,3.4938266,0.1555658,-72.19715,-92.21358,0.09269208,-0.09940697,5.9962993,1110000
|
| 24 |
+
0.20115009,3.0038526,-35.060616,-73.76748,-91.64848,0.19641404,-0.1007818,6.866116,1115000
|
| 25 |
+
0.25643808,3.9408944,-2.023408,-70.48583,-94.97717,0.22770515,-0.13803354,10.335558,1120000
|
| 26 |
+
0.26242062,3.1044643,-23.7452,-69.72378,-93.49275,0.11734769,-0.31234312,8.568487,1125000
|
| 27 |
+
0.27941814,2.7736146,0.22214109,-71.30729,-93.56707,0.08700342,-0.24716836,7.357201,1130000
|
| 28 |
+
0.29598105,5.668283,-28.673903,-69.71908,-93.19694,0.23008072,-0.15865305,12.443473,1135000
|
| 29 |
+
0.27388066,2.9366286,-24.117348,-69.28965,-91.02834,0.06563335,-0.13134009,6.4186754,1140000
|
| 30 |
+
0.28638658,2.5600371,0.25663713,-68.76285,-92.300835,0.109101996,-0.09432482,5.4128447,1145000
|
| 31 |
+
0.23860395,2.0291963,-30.916063,-68.78072,-92.0076,0.14367977,-0.09099172,5.9600377,1150000
|
| 32 |
+
0.25766385,2.0518868,0.23160978,-67.8211,-87.8516,0.25542566,-0.09040986,6.4984035,1155000
|
| 33 |
+
0.29943863,2.4853184,0.023178145,-68.796684,-89.61473,0.053570926,-0.16037732,5.7776413,1160000
|
| 34 |
+
0.32200947,2.8827353,-24.48955,-66.49139,-89.62327,0.2921234,-0.35584837,8.190651,1165000
|
| 35 |
+
0.22497472,1.9699306,-30.835812,-66.50915,-89.96553,0.25185913,-0.09473857,7.4563065,1170000
|
| 36 |
+
0.25924414,2.4851017,-0.8173568,-65.40513,-91.30807,0.20044082,-0.14555176,6.809092,1175000
|
| 37 |
+
0.3246436,2.3802178,-28.206207,-67.17901,-89.82486,0.11646056,-0.12909126,5.998129,1180000
|
| 38 |
+
0.2862863,2.3927562,0.26388216,-65.11758,-86.523155,0.08921548,-0.12950669,5.6245418,1185000
|
| 39 |
+
0.28530964,2.5240796,-31.181145,-65.461,-88.84335,0.07986237,-0.20250514,6.3848057,1190000
|
| 40 |
+
0.3015533,3.8072534,0.14737505,-64.027824,-88.33287,0.16834934,-0.13412985,7.008562,1195000
|
| 41 |
+
0.30554295,5.268529,-0.35862434,-61.45807,-87.48133,0.17009275,-0.08725572,9.212819,1200000
|
| 42 |
+
0.2573288,3.0126514,-24.084545,-63.15048,-86.36201,0.17421678,-0.06361489,7.588005,1205000
|
| 43 |
+
0.3115732,3.9208684,-8.247994,-62.476723,-86.78855,0.16873068,-0.13601926,6.5116787,1210000
|
| 44 |
+
0.3152727,3.0987,0.2641038,-60.460365,-83.19605,0.08475858,-0.21300772,7.235612,1215000
|
| 45 |
+
0.34176165,3.42725,-23.781984,-62.629925,-85.33286,0.09599193,-0.26741844,7.900793,1220000
|
| 46 |
+
0.34721234,3.215152,0.14247106,-64.09814,-82.80813,0.131109,-0.3668235,10.42333,1225000
|
| 47 |
+
0.3386051,4.2630534,-11.238298,-64.30384,-83.36028,0.17465258,-0.0696479,6.4402475,1230000
|
| 48 |
+
0.35315567,7.442858,-25.144848,-64.13323,-84.94342,0.17808208,-0.25167343,9.706675,1235000
|
| 49 |
+
0.26102847,3.4613438,0.29984948,-62.534863,-83.9004,0.22569454,-0.13138878,9.742595,1240000
|
| 50 |
+
0.32183754,2.4167173,-5.109396,-64.24133,-82.99023,0.16248426,-0.17995861,7.76478,1245000
|
| 51 |
+
0.33197004,2.6351528,-24.171616,-65.41605,-83.93782,0.15469696,-0.062378053,5.605343,1250000
|
| 52 |
+
0.30539095,1.7452011,-35.579792,-67.46694,-84.35835,0.19193831,-0.12951094,5.643739,1255000
|
| 53 |
+
0.3335951,3.4692712,-17.397657,-67.625015,-85.619934,0.13984431,-0.17546472,7.57337,1260000
|
| 54 |
+
0.30886692,2.1203337,-33.728577,-67.2767,-84.13962,0.2380584,-0.1991478,6.612579,1265000
|
| 55 |
+
0.33970347,2.725211,-20.488928,-67.34668,-85.37843,0.1029236,-0.15801567,8.21445,1270000
|
| 56 |
+
0.34691486,2.3660295,-32.77936,-66.097855,-86.011246,0.23494,-0.08284719,7.340578,1275000
|
| 57 |
+
0.37552884,4.5389457,-30.712492,-66.64126,-85.8063,0.1601192,-0.1943192,7.9218903,1280000
|
| 58 |
+
0.37445474,3.669979,-32.96991,-66.19552,-83.91085,0.12482998,-0.34435454,9.158147,1285000
|
| 59 |
+
0.34159213,5.009813,-40.617607,-69.33019,-91.73982,0.07050493,-0.13137606,6.847104,1290000
|
| 60 |
+
0.3479388,1.5929338,-18.227375,-70.88778,-87.017456,0.06542794,-0.06699151,3.6176748,1295000
|
| 61 |
+
0.3043188,2.6035135,0.3767551,-70.91786,-86.97844,0.31562382,-0.120214775,8.323084,1300000
|
| 62 |
+
0.3199113,1.6381238,0.14781404,-69.6599,-86.44105,0.15409042,-0.057349905,5.4344397,1305000
|
| 63 |
+
0.36274403,1.9187775,0.14761835,-68.919426,-86.697845,0.42262617,-0.15899713,10.200994,1310000
|
| 64 |
+
0.31335732,2.3573177,5.494179,-67.33492,-87.04612,0.5795053,-0.21798742,11.991345,1315000
|
| 65 |
+
0.36749658,4.260718,-4.2733397,-69.80277,-85.36596,0.11151378,-0.32551274,8.735874,1320000
|
| 66 |
+
0.3487035,14.070511,0.14212829,-67.73892,-85.46739,0.45644984,-0.31322867,11.6350155,1325000
|
| 67 |
+
0.36997837,9.297724,-38.38523,-69.55349,-87.031,0.19536808,-0.3932488,14.081216,1330000
|
| 68 |
+
0.3924844,8.529996,-0.67620665,-69.43581,-89.840225,0.10277253,-0.3713912,11.556158,1335000
|
| 69 |
+
0.38201958,4.495419,-40.207874,-69.4025,-85.62395,0.061743677,-0.23668936,9.011112,1340000
|
| 70 |
+
0.37825602,1.7239983,-36.44288,-69.94261,-84.89991,0.18101072,-0.061319336,5.8768144,1345000
|
| 71 |
+
0.39703056,2.4375126,-32.356728,-70.91211,-89.00602,0.12865606,-0.2379403,6.4848228,1350000
|
| 72 |
+
0.36110824,1.856458,-0.3686052,-70.83982,-88.41582,0.14056996,-0.099492505,5.7909,1355000
|
| 73 |
+
0.3719139,2.2101417,-44.005524,-71.31241,-86.77529,0.28508833,-0.106728904,7.830371,1360000
|
| 74 |
+
0.36272976,1.615786,-40.94519,-73.061134,-89.12707,0.46989942,-0.37402225,13.581576,1365000
|
| 75 |
+
0.40933305,3.3091118,4.2897725,-72.95342,-89.98497,0.65286505,-0.42948326,29.079573,1370000
|
| 76 |
+
0.40526477,2.8386967,-1.5343959,-73.08132,-88.22252,0.2634625,-0.18959358,8.746388,1375000
|
| 77 |
+
0.35213482,2.0324838,-40.408802,-71.91885,-88.31405,0.12825869,-0.16238691,6.9664955,1380000
|
| 78 |
+
0.3568496,4.856733,0.2917993,-72.068665,-87.82555,0.2093975,-0.18309483,10.116087,1385000
|
| 79 |
+
0.38250285,5.0261583,-3.3998075,-73.40017,-88.61018,0.34341022,-0.32632226,24.129007,1390000
|
| 80 |
+
0.36728317,2.4298666,-2.9278154,-72.190834,-90.72345,0.1736611,-0.07843729,4.6497464,1395000
|
| 81 |
+
0.3717967,7.8037186,-19.705576,-73.67324,-88.17704,0.18925384,-0.205077,9.427722,1400000
|
| 82 |
+
0.39682537,2.4497967,0.2806464,-72.388145,-93.12212,0.36928824,-0.14073445,9.623826,1405000
|
| 83 |
+
0.3546273,6.4444222,-26.266022,-73.92089,-88.21137,0.16192557,-0.2859206,11.853137,1410000
|
| 84 |
+
0.37429094,2.462179,-0.737865,-76.63706,-89.41226,0.2441035,-0.25128168,12.591532,1415000
|
| 85 |
+
0.36073518,4.682529,-0.63891464,-74.31471,-90.2527,0.21780562,-0.17416418,9.2064085,1420000
|
| 86 |
+
0.36884585,2.073633,-35.55877,-73.05088,-87.06206,0.87421376,-0.79681337,25.599617,1425000
|
| 87 |
+
0.3839017,6.392212,-43.111923,-73.17507,-86.90694,0.12848689,-0.34790528,8.784417,1430000
|
| 88 |
+
0.40413243,3.8404107,0.28101113,-70.82,-89.83005,0.25041196,-0.1061446,6.5976877,1435000
|
| 89 |
+
0.39739275,3.786618,-0.9610069,-69.11249,-85.84058,0.20259553,-0.48661566,14.518017,1440000
|
| 90 |
+
0.38250208,2.272793,-0.06600636,-71.37682,-89.78186,0.47464013,-0.3802075,22.376125,1445000
|
| 91 |
+
0.4058851,2.9280326,3.2864769,-72.86645,-87.49951,0.2838762,-0.40724295,16.661232,1450000
|
| 92 |
+
0.34424353,4.6464424,0.16964492,-72.51965,-91.73667,0.339288,-0.13549268,9.003332,1455000
|
| 93 |
+
0.37784547,16.91988,-43.506584,-72.68666,-86.838234,0.22806369,-0.44694385,10.548638,1460000
|
| 94 |
+
0.398295,3.1793506,0.48452756,-70.37343,-86.76585,0.11006744,-0.14390934,5.027549,1465000
|
| 95 |
+
0.38268244,1.8258187,-2.8150666,-71.54153,-89.88112,0.1419461,-0.22347555,7.035861,1470000
|
| 96 |
+
0.40742394,4.7282114,-39.97688,-71.1954,-87.90339,0.27179804,-0.30342278,11.037926,1475000
|
| 97 |
+
0.4194396,2.56842,-27.227345,-72.94338,-86.77057,0.283368,-0.39012647,12.722091,1480000
|
| 98 |
+
0.3639083,1.6978931,-34.975224,-72.59657,-91.83758,0.10673068,-0.30234668,6.5468106,1485000
|
| 99 |
+
0.40328333,4.177179,-42.21691,-73.49501,-93.21049,0.12138712,-0.18596464,11.150076,1490000
|
| 100 |
+
0.40715158,7.0427094,-48.65613,-74.4298,-91.39263,0.30958194,-0.31246892,14.93189,1495000
|
| 101 |
+
0.47719797,10.186979,-21.194233,-74.3796,-92.877686,0.17603016,-0.28611577,10.238736,1500000
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_100000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e52ec31805878d268c2b3e71536f2fc94fe02bc3fb3f3891d03621ba3c5b404
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1000000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e8e41356bdaf3d237f6838596d19f3363636bc11d8406e1ddb10c7f9e0b56f6
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1050000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abe549e798dd5e0b3f81fb642b06d21dab3cd3569d042d187112bda779116d98
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1100000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:227132f7c9c2bc739d47cc38104cf252fe00b08506e57f1dfc05e8bbfbe2134d
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1150000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d14cc1e712859c408db287eab0c972d391bc7af1df4e39720888d8aa50752a49
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1200000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa4348c7d302e1bcba8f66f140b3ac2cc529ab1a5b2a356567eedcbdfa46f557
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1250000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f0b042ee40e551b6209224f6d13ac99b4e8707843322ef3f2dc9d89634ba124
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1300000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71cbfb726a6d90d2c39e98556c882a2a7e1882829dafbf971ef160d595586452
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:447d3ed52dd6aea17bc7031fad3786514f422e05db493a197747913d3861b285
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d061234fbd05180a192a55d73aa99b6ae1f10ae3d904a0701aed2f15a964ebce
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d544d0a6ecefe17e5adf47e70f7808a958e296ddfe60adddae073671a115fce3
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_150000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96162b197e6695560681d3981248f75e288a87dc0b8187f2c8f07dfacb9d67d1
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_1500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36646aa2d05b9f45b279416af85c68885a63e4e6eef0eecef1d2c896b7a38613
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_200000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15486df8684b45c9ec8b19756bda64a87e1d39a1349314cc1237dbd53c7bdc22
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_250000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7d6b07cd4baa66a568ad6717e6a6b99e88f768242a9eb2bf663055dbc05f741
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_300000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9205d98445dc50926f3e65946c13656197be8028636a869fb499da0fb75e8d0b
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:825a947621391f08da79231ebdc7ff4e8ea6a168b6c5c063b040e9f38703e3eb
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:495e78b41f10e0a0568775e331be9968ea0b01288724f772fab47afbf5ccd3e2
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35b3349dcae8f3d2398cfd8236b940ef51225ac9341e7c7972ec7b4aa14ef67f
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_50000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cac9985272492ff78a340157a3679e940ca90193b9290dd3e858ad6ffbf38706
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61486d06e9d62d277907586e2a99a4da2b92455112e3112f614d5b3293d9d870
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fa1bb74dcc1b0b5dd41c38f566d990d072ba729e9e0a76d0567ef6375c97a65
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efd17bce9c7fc8afd95dfdb6adf92c040485c9ce0f63ea829635de4a2977e504
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9e6a6900b314f81920791b6468d362a4e7a2e2263b8008a3b3f728b48f91e30
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9289703ee70b1ff176710722ca5f7f417c213415ce78a651ca8b37c1e6bfcd03
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_750000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e65f05121cfddf0e6a22ab0194e06d9eb5777a394458ca040ce71a53bfb3ceed
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_800000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d43d84515e8ac520634fb54036bd848beea89469bc4d021b411cb784385d6e2
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_850000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa3a1c4c8de690bae8094e703359c112e0f9ebdb9f09e207393035fa916a41ed
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_900000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1efa08d14f2e02174c98d43b64d2129dd24a51d281bdeaf11efb9cfa7c8b68d
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/params_950000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4382d4b5ee7ff4b4da07515e1391e594b8d2f19cfd1b4fc64832d63554c4ae25
|
| 3 |
+
size 220531328
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
pretrained_models/puzzle-3x3-play-singletask-task4-v0/20260308_015226/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-reproduce/runs/pz3bgbue
|