1
0
mirror of https://github.com/gryf/coach.git synced 2026-04-28 11:34:10 +02:00

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
@@ -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,,,,
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,0.012080228037293859,0.012880618698819657,0.0570480152964592,6.0431495512602844e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.11952291400000001,0.07146234,0.36756375,0.010074032,-2.3361342922088504,0.784322378590693,-0.38878391807422696,-3.369599601005491,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9983655100000356,-21.0,-21.0,0.0,,,,0.01158361631276578,0.013744570346194931,0.08763836324214935,1.3804149602947293e-05,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.06339365,0.045202352,0.3223001,0.0032100508,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,-0.05946256,0.0071155433999999995,-0.048334688,-0.071884885
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,0.011621401665309342,0.011997949188739438,0.047944877296686166,1.704720125417225e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.061558142,0.038367815,0.19478188,0.0040269657,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,-0.06831099,0.009751156,-0.05039859,-0.08132484599999999
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,0.011371218297681479,0.01218400722584616,0.059932790696620934,1.6583624528720975e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.06680599999999999,0.04423054,0.21688205,0.0034790002000000004,-2.406465837413259,0.5636980823469648,-0.7105532272722921,-3.36383697254212,-0.048574314,0.009597616,-0.036119547,-0.06607885
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,0.013030857562661391,0.014064394699560966,0.06334743648767471,2.0799992853426374e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.14124954,0.15512846,0.9356431000000001,0.0037519853000000003,-2.3361342922088504,0.784322378590693,-0.38878391807422696,-3.369599601005491,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9983655100000356,-21.0,-21.0,0.0,,,,0.012065147789319152,0.014264555162560488,0.08900705724954605,3.336678491905332e-05,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.064539365,0.04878198,0.3403983,0.007120714,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,0.018258663,0.008410561,0.03039161,0.0031909812
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,0.013943941339460959,0.012418257338636593,0.05291028320789337,1.9593317119870335e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.11973736,0.119031124,0.8044271,0.0012378334,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,-0.02297779,0.0040406515,-0.01676904,-0.027261153
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,0.012252497132776626,0.013290761767708568,0.06478248536586761,3.438068233663216e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.06426661,0.056941237,0.30591047,0.005093545,-2.406465837413259,0.5636980823469648,-0.7105532272722921,-3.36383697254212,-0.0066491687,0.007894201,0.006075496,-0.020406375
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 0.9991882000000176 -21.0 -21.0 0.0 0.012080228037293859 0.013030857562661391 0.012880618698819657 0.014064394699560966 0.0570480152964592 0.06334743648767471 6.0431495512602844e-05 2.0799992853426374e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.11952291400000001 0.14124954 0.07146234 0.15512846 0.36756375 0.9356431000000001 0.010074032 0.0037519853000000003 -2.3361342922088504 0.784322378590693 -0.38878391807422696 -3.369599601005491
4 3 413.0 0.0 2768.0 2768.0 831.0 2768.0 0.9983655100000356 -21.0 -21.0 0.0 0.01158361631276578 0.012065147789319152 0.013744570346194931 0.014264555162560488 0.08763836324214935 0.08900705724954605 1.3804149602947293e-05 3.336678491905332e-05 0.00010000000000000003 2.7105054312137605e-20 0.0001 0.0001 0.06339365 0.064539365 0.045202352 0.04878198 0.3223001 0.3403983 0.0032100508 0.007120714 -2.320394201181889 0.6047235028955231 -0.7105532272722921 -3.350537576335216 -0.05946256 0.018258663 0.0071155433999999995 0.008410561 -0.048334688 0.03039161 -0.071884885 0.0031909812
5 4 667.0 0.0 3783.0 3783.0 1015.0 3783.0 0.9973606600000572 -20.0 -20.0 0.0 0.011621401665309342 0.013943941339460959 0.011997949188739438 0.012418257338636593 0.047944877296686166 0.05291028320789337 1.704720125417225e-05 1.9593317119870335e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.061558142 0.11973736 0.038367815 0.119031124 0.19478188 0.8044271 0.0040269657 0.0012378334 -1.7531357837449677 0.7448577440634202 -0.1288331810939122 -3.2971074888190803 -0.06831099 -0.02297779 0.009751156 0.0040406515 -0.05039859 -0.01676904 -0.08132484599999999 -0.027261153
6 5 867.0 0.0 4585.0 4585.0 802.0 4585.0 0.9965666800000744 -21.0 -21.0 0.0 0.011371218297681479 0.012252497132776626 0.01218400722584616 0.013290761767708568 0.059932790696620934 0.06478248536586761 1.6583624528720975e-05 3.438068233663216e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.06680599999999999 0.06426661 0.04423054 0.056941237 0.21688205 0.30591047 0.0034790002000000004 0.005093545 -2.406465837413259 0.5636980823469648 -0.7105532272722921 -3.36383697254212 -0.048574314 -0.0066491687 0.009597616 0.007894201 -0.036119547 0.006075496 -0.06607885 -0.020406375