1
0
mirror of https://github.com/gryf/coach.git synced 2026-03-16 22:53:37 +01:00

trace tests update

This commit is contained in:
Shadi Endrawis
2018-10-02 17:55:16 +03:00
parent 51726a5b80
commit f7990d4003
79 changed files with 10105 additions and 9539 deletions

View File

@@ -1,6 +1,6 @@
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,Discounted Return/Mean,Discounted Return/Stdev,Discounted Return/Max,Discounted Return/Min,Q/Mean,Q/Stdev,Q/Max,Q/Min
1,0.0,1.0,1117.0,1117.0,1117.0,1117.0,1.0,,,0.0,,,,,,,,,,,,,,,,-1.5180229894995567,0.6998808293377133,-0.08930329112720292,-3.148474706421977,,,,
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9992620000000244,-21.0,-21.0,0.0,,,,0.010741595556704321,0.012929108810701093,0.059776991605758674,1.955357765837107e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.06700998,0.05211416,0.28223783,0.010616378999999999,-2.3361342922088504,0.784322378590693,-0.38878391807422696,-3.369599601005491,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9985141000000488,-21.0,-21.0,0.0,,,,0.011494234373143487,0.013620432539034891,0.08901263028383255,7.457365427399054e-05,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.049767,0.03138836,0.17539442,0.011668723999999998,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,0.025700996,0.008655511,0.0347657,0.008379098
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9976006000000791,-20.0,-20.0,0.0,,,,0.011251820331667623,0.01194864814747996,0.04630041867494583,9.452360245632008e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.046036932999999995,0.02848018,0.14712586,0.010549873999999999,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,0.014692268999999999,0.00800893,0.026871104,-0.00019203185000000002
5,954.0,0.0,4934.0,4934.0,1151.0,4934.0,0.9965647000001132,-18.0,-18.0,0.0,,,,0.010213364634658,0.011762000707730695,0.06160044670104981,0.00010682888387236744,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.041461904,0.025549995,0.14279638,0.012242042,-1.491249294691959,1.0312726923259208,0.5895735538220139,-3.345591480809256,0.021241617999999997,0.008987491,0.036087215,-0.0034641959999999997
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9992620000000244,-21.0,-21.0,0.0,,,,0.011032734143000421,0.013050631943252157,0.06188610941171646,5.788924681837671e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.09481886,0.06547235,0.4128104,0.014912024,-2.3361342922088504,0.784322378590693,-0.38878391807422696,-3.369599601005491,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9985141000000488,-21.0,-21.0,0.0,,,,0.011714245055950064,0.013615523545387836,0.08608928322792052,4.0108770917868235e-05,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.078761965,0.042246383,0.2695421,0.010716428,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,0.13584568,0.011556746000000001,0.14892316,0.11885095400000001
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9976006000000791,-20.0,-20.0,0.0,,,,0.011432893811852264,0.012069273288368423,0.050671517848968506,6.866654439363629e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.06967258,0.03742053,0.20260468,0.011122073,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,0.12361515,0.012860634,0.14413264,0.10136055
5,947.0,0.0,4906.0,4906.0,1123.0,4906.0,0.9965899000001124,-18.0,-18.0,0.0,,,,0.010396778351917291,0.011949964558787713,0.06747313588857651,4.6792134526185685e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.062268693,0.038279983999999996,0.35579062,0.008977733,-1.5284306594746384,1.0386188434297503,0.5895609917959839,-3.3469363938389924,0.10764929999999999,0.011775569,0.123398446,0.085828155
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 Discounted Return/Mean Discounted Return/Stdev Discounted Return/Max Discounted Return/Min Q/Mean Q/Stdev Q/Max Q/Min
2 1 0.0 1.0 1117.0 1117.0 1117.0 1117.0 1.0 0.0 -1.5180229894995567 0.6998808293377133 -0.08930329112720292 -3.148474706421977
3 2 205.0 0.0 1937.0 1937.0 820.0 1937.0 0.9992620000000244 -21.0 -21.0 0.0 0.010741595556704321 0.011032734143000421 0.012929108810701093 0.013050631943252157 0.059776991605758674 0.06188610941171646 1.955357765837107e-05 5.788924681837671e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.06700998 0.09481886 0.05211416 0.06547235 0.28223783 0.4128104 0.010616378999999999 0.014912024 -2.3361342922088504 0.784322378590693 -0.38878391807422696 -3.369599601005491
4 3 413.0 0.0 2768.0 2768.0 831.0 2768.0 0.9985141000000488 -21.0 -21.0 0.0 0.011494234373143487 0.011714245055950064 0.013620432539034891 0.013615523545387836 0.08901263028383255 0.08608928322792052 7.457365427399054e-05 4.0108770917868235e-05 0.00010000000000000003 2.7105054312137605e-20 0.0001 0.0001 0.049767 0.078761965 0.03138836 0.042246383 0.17539442 0.2695421 0.011668723999999998 0.010716428 -2.320394201181889 0.6047235028955231 -0.7105532272722921 -3.350537576335216 0.025700996 0.13584568 0.008655511 0.011556746000000001 0.0347657 0.14892316 0.008379098 0.11885095400000001
5 4 667.0 0.0 3783.0 3783.0 1015.0 3783.0 0.9976006000000791 -20.0 -20.0 0.0 0.011251820331667623 0.011432893811852264 0.01194864814747996 0.012069273288368423 0.04630041867494583 0.050671517848968506 9.452360245632008e-05 6.866654439363629e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.046036932999999995 0.06967258 0.02848018 0.03742053 0.14712586 0.20260468 0.010549873999999999 0.011122073 -1.7531357837449677 0.7448577440634202 -0.1288331810939122 -3.2971074888190803 0.014692268999999999 0.12361515 0.00800893 0.012860634 0.026871104 0.14413264 -0.00019203185000000002 0.10136055
6 5 954.0 947.0 0.0 4934.0 4906.0 4934.0 4906.0 1151.0 1123.0 4934.0 4906.0 0.9965647000001132 0.9965899000001124 -18.0 -18.0 0.0 0.010213364634658 0.010396778351917291 0.011762000707730695 0.011949964558787713 0.06160044670104981 0.06747313588857651 0.00010682888387236744 4.6792134526185685e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.041461904 0.062268693 0.025549995 0.038279983999999996 0.14279638 0.35579062 0.012242042 0.008977733 -1.491249294691959 -1.5284306594746384 1.0312726923259208 1.0386188434297503 0.5895735538220139 0.5895609917959839 -3.345591480809256 -3.3469363938389924 0.021241617999999997 0.10764929999999999 0.008987491 0.011775569 0.036087215 0.123398446 -0.0034641959999999997 0.085828155