gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-02-23 18:45:50 +01:00
Code Issues Projects Releases Wiki Activity

Trace tests update

Browse Source
This commit is contained in:
Shadi Endrawis
2018-08-20 13:01:17 +03:00
parent c1f428666e
commit 3abb6cd415
99 changed files with 12876 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
rl_coach/traces/Atari_NStepQ_space_invaders/trace.csv Normal file
View File

@@ -0,0 +1,21 @@
Episode #,Training Iter,In Heatup,ER #Transitions,ER #Episodes,Episode Length,Total steps,Epsilon,Shaped Training Reward,Training Reward,Update Target Network,Evaluation Reward,Shaped Evaluation Reward,Success Rate,Loss/Mean,Loss/Stdev,Loss/Max,Loss/Min,Learning Rate/Mean,Learning Rate/Stdev,Learning Rate/Max,Learning Rate/Min,Grads (unclipped)/Mean,Grads (unclipped)/Stdev,Grads (unclipped)/Max,Grads (unclipped)/Min,Entropy/Mean,Entropy/Stdev,Entropy/Max,Entropy/Min,Q/Mean,Q/Stdev,Q/Max,Q/Min,Q Values/Mean,Q Values/Stdev,Q Values/Max,Q Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min
1,0.0,1.0,486.0,1.0,486.0,486.0,0.5,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,87.0,1.0,87.0,573.0,0.5,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
3,0.0,1.0,149.0,1.0,149.0,722.0,0.5,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
4,0.0,1.0,335.0,1.0,335.0,1057.0,0.5,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
5,36.0,0.0,180.0,1.0,180.0,1237.0,0.4982359999999992,3.0,30.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.0709828,0.02884768,0.14847249,-0.025073245,0.15536511,0.67742556,4.0763674,0.00025629386
6,51.0,0.0,74.0,1.0,74.0,1311.0,0.4975107999999989,2.0,15.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.09154996,0.034854878,0.17196007,0.029762035,0.06300321,0.1426023,0.49494484,0.0034788419
7,77.0,0.0,131.0,1.0,131.0,1442.0,0.4962269999999984,2.0,35.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.07617202,0.023897866,0.14918622,0.035134307999999996,0.016550515,0.04922439,0.18912512,0.00011201962
8,118.0,0.0,204.0,1.0,204.0,1646.0,0.4942277999999975,2.0,15.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.059103607999999995,0.020852849,0.11587171,0.006847885400000001,0.03776522,0.16741602,0.9484094999999999,7.4577442e-06
9,137.0,0.0,92.0,1.0,92.0,1738.0,0.4933261999999971,1.0,5.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.07352363,0.034035592999999996,0.15143472,0.0044105817,0.05140639,0.20671843,0.9284075999999999,0.00020915868000000003
10,201.0,0.0,321.0,1.0,321.0,2059.0,0.4901803999999957,10.0,115.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.08682183,0.04259716,0.30125758,0.0020528187,0.08377568,0.18461238,0.6967797,0.00044282363
11,265.0,0.0,317.0,1.0,317.0,2376.0,0.4870737999999944,8.0,130.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.107165605,0.036707986,0.23180877,0.01380832,0.09232898,0.22525571,0.87342286,0.0018040526999999998
12,310.0,0.0,224.0,1.0,224.0,2600.0,0.4848785999999934,3.0,20.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.086089715,0.027629882,0.19709364,0.025783142000000002,0.025214866000000002,0.08048548,0.39741653,9.443184499999999e-05
13,338.0,0.0,138.0,1.0,138.0,2738.0,0.4835261999999929,1.0,10.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.056624517,0.014742057,0.09184578,0.023095844,0.013557022,0.06671045,0.36011392,7.6326745e-05
14,378.0,0.0,200.0,1.0,200.0,2938.0,0.481566199999992,1.0,5.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.069043785,0.030751564,0.16467288,0.0038135927,0.01971127,0.1051151,0.6758529999999999,4.7275649999999995e-05
15,422.0,0.0,221.0,1.0,221.0,3159.0,0.4794003999999911,3.0,30.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.06917530000000001,0.027813602000000003,0.13201289,0.016976256000000002,0.04862738,0.18498637,1.0439113000000002,6.747579e-05
16,460.0,0.0,190.0,1.0,190.0,3349.0,0.4775383999999903,2.0,45.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.056344293,0.023635779,0.10303167,-0.009649781,0.032846852999999995,0.14394106,0.83443564,0.00015374989
17,511.0,0.0,255.0,1.0,255.0,3604.0,0.4750393999999892,6.0,75.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.07982238,0.03705571,0.15894309,-0.003064227,0.07116045,0.20118825,0.8639594999999999,0.00021242326000000001
18,583.0,0.0,360.0,1.0,360.0,3964.0,0.4715113999999877,4.0,50.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.0702058,0.03336375,0.18290229,-0.0028483917,0.027493622000000002,0.12953442,1.0179706,4.404120299999999e-06
19,623.0,0.0,199.0,1.0,199.0,4163.0,0.4695611999999868,2.0,35.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.06575828,0.020313479,0.1296886,0.031751662,0.02896362,0.14715028,0.930523,9.032046999999998e-05
20,673.0,0.0,247.0,1.0,247.0,4410.0,0.4671405999999858,5.0,35.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.08191794,0.025515838,0.16764577,0.02347238,0.051037148,0.15077179999999998,0.6975503000000001,2.4204688e-05
1 Episode # Training Iter In Heatup ER #Transitions ER #Episodes Episode Length Total steps Epsilon Shaped Training Reward Training Reward Update Target Network Evaluation Reward Shaped Evaluation Reward Success Rate Loss/Mean Loss/Stdev Loss/Max Loss/Min Learning Rate/Mean Learning Rate/Stdev Learning Rate/Max Learning Rate/Min Grads (unclipped)/Mean Grads (unclipped)/Stdev Grads (unclipped)/Max Grads (unclipped)/Min Entropy/Mean Entropy/Stdev Entropy/Max Entropy/Min Q/Mean Q/Stdev Q/Max Q/Min Q Values/Mean Q Values/Stdev Q Values/Max Q Values/Min Value Loss/Mean Value Loss/Stdev Value Loss/Max Value Loss/Min
2 1 0.0 1.0 486.0 1.0 486.0 486.0 0.5 0.0
3 2 0.0 1.0 87.0 1.0 87.0 573.0 0.5 0.0
4 3 0.0 1.0 149.0 1.0 149.0 722.0 0.5 0.0
5 4 0.0 1.0 335.0 1.0 335.0 1057.0 0.5 0.0
6 5 36.0 0.0 180.0 1.0 180.0 1237.0 0.4982359999999992 3.0 30.0 0.0 0.0709828 0.02884768 0.14847249 -0.025073245 0.15536511 0.67742556 4.0763674 0.00025629386
7 6 51.0 0.0 74.0 1.0 74.0 1311.0 0.4975107999999989 2.0 15.0 0.0 0.09154996 0.034854878 0.17196007 0.029762035 0.06300321 0.1426023 0.49494484 0.0034788419
8 7 77.0 0.0 131.0 1.0 131.0 1442.0 0.4962269999999984 2.0 35.0 0.0 0.07617202 0.023897866 0.14918622 0.035134307999999996 0.016550515 0.04922439 0.18912512 0.00011201962
9 8 118.0 0.0 204.0 1.0 204.0 1646.0 0.4942277999999975 2.0 15.0 0.0 0.059103607999999995 0.020852849 0.11587171 0.006847885400000001 0.03776522 0.16741602 0.9484094999999999 7.4577442e-06
10 9 137.0 0.0 92.0 1.0 92.0 1738.0 0.4933261999999971 1.0 5.0 0.0 0.07352363 0.034035592999999996 0.15143472 0.0044105817 0.05140639 0.20671843 0.9284075999999999 0.00020915868000000003
11 10 201.0 0.0 321.0 1.0 321.0 2059.0 0.4901803999999957 10.0 115.0 0.0 0.08682183 0.04259716 0.30125758 0.0020528187 0.08377568 0.18461238 0.6967797 0.00044282363
12 11 265.0 0.0 317.0 1.0 317.0 2376.0 0.4870737999999944 8.0 130.0 0.0 0.107165605 0.036707986 0.23180877 0.01380832 0.09232898 0.22525571 0.87342286 0.0018040526999999998
13 12 310.0 0.0 224.0 1.0 224.0 2600.0 0.4848785999999934 3.0 20.0 0.0 0.086089715 0.027629882 0.19709364 0.025783142000000002 0.025214866000000002 0.08048548 0.39741653 9.443184499999999e-05
14 13 338.0 0.0 138.0 1.0 138.0 2738.0 0.4835261999999929 1.0 10.0 0.0 0.056624517 0.014742057 0.09184578 0.023095844 0.013557022 0.06671045 0.36011392 7.6326745e-05
15 14 378.0 0.0 200.0 1.0 200.0 2938.0 0.481566199999992 1.0 5.0 0.0 0.069043785 0.030751564 0.16467288 0.0038135927 0.01971127 0.1051151 0.6758529999999999 4.7275649999999995e-05
16 15 422.0 0.0 221.0 1.0 221.0 3159.0 0.4794003999999911 3.0 30.0 0.0 0.06917530000000001 0.027813602000000003 0.13201289 0.016976256000000002 0.04862738 0.18498637 1.0439113000000002 6.747579e-05
17 16 460.0 0.0 190.0 1.0 190.0 3349.0 0.4775383999999903 2.0 45.0 0.0 0.056344293 0.023635779 0.10303167 -0.009649781 0.032846852999999995 0.14394106 0.83443564 0.00015374989
18 17 511.0 0.0 255.0 1.0 255.0 3604.0 0.4750393999999892 6.0 75.0 0.0 0.07982238 0.03705571 0.15894309 -0.003064227 0.07116045 0.20118825 0.8639594999999999 0.00021242326000000001
19 18 583.0 0.0 360.0 1.0 360.0 3964.0 0.4715113999999877 4.0 50.0 0.0 0.0702058 0.03336375 0.18290229 -0.0028483917 0.027493622000000002 0.12953442 1.0179706 4.404120299999999e-06
20 19 623.0 0.0 199.0 1.0 199.0 4163.0 0.4695611999999868 2.0 35.0 0.0 0.06575828 0.020313479 0.1296886 0.031751662 0.02896362 0.14715028 0.930523 9.032046999999998e-05
21 20 673.0 0.0 247.0 1.0 247.0 4410.0 0.4671405999999858 5.0 35.0 0.0 0.08191794 0.025515838 0.16764577 0.02347238 0.051037148 0.15077179999999998 0.6975503000000001 2.4204688e-05