1
0
mirror of https://github.com/gryf/coach.git synced 2026-04-07 13:43:32 +02:00

Trace tests update

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

View File

@@ -0,0 +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,Entropy/Mean,Entropy/Stdev,Entropy/Max,Entropy/Min,Advantages/Mean,Advantages/Stdev,Advantages/Max,Advantages/Min,Values/Mean,Values/Stdev,Values/Max,Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min,Policy Loss/Mean,Policy Loss/Stdev,Policy Loss/Max,Policy Loss/Min
1,0.0,1.0,772.0,1.0,772.0,772.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,821.0,1.0,821.0,1593.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
3,40.0,0.0,798.0,1.0,798.0,2391.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.6925433,1.56166,5.4782605,0.011157283,1.7178073,0.09590818,1.7916279,1.4786046,-1.1788440822140267,1.255206542380211,1.0642428398132324,-3.2777271270751958,-1.3811463,1.9222080000000001,-0.023936661,-5.8730206,0.34145027,0.439121,2.7880993,0.00036954717000000004,-0.13185489,0.9237273000000001,0.9732863000000002,-4.1131425
4,78.0,0.0,755.0,1.0,755.0,3146.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,2.4706511000000004,4.6726856,30.583601,0.67071736,1.5111907,0.024124695,1.5492108999999998,1.439797,0.24763718664174345,0.8147690823204996,4.918219566345215,-0.9567646980285645,-4.656093599999999,0.40140057,-2.9237971000000003,-5.8753314,0.443355,1.7042981,10.802688999999999,0.08576387,0.41162340000000003,1.3014139999999998,7.6323996,-0.8151264
5,116.0,0.0,756.0,1.0,756.0,3902.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.850646,2.4202513999999997,16.295288,0.4290005,1.3224964,0.050945385999999995,1.4303273,1.2031558,0.14155570039685988,0.5814409942921325,3.3915529251098637,-0.8861622810363771,-3.0170727000000004,0.6280401999999999,-2.1003609,-4.3324237,0.22347862,0.839418,5.326185,0.05343006,0.22746566,0.82214487,4.685924,-0.7187973000000001
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 Advantages/Mean Advantages/Stdev Advantages/Max Advantages/Min Values/Mean Values/Stdev Values/Max Values/Min Value Loss/Mean Value Loss/Stdev Value Loss/Max Value Loss/Min Policy Loss/Mean Policy Loss/Stdev Policy Loss/Max Policy Loss/Min
2 1 0.0 1.0 772.0 1.0 772.0 772.0 0.0 0.0
3 2 0.0 1.0 821.0 1.0 821.0 1593.0 0.0 0.0
4 3 40.0 0.0 798.0 1.0 798.0 2391.0 0.0 -21.0 -21.0 0.0 1.6925433 1.56166 5.4782605 0.011157283 1.7178073 0.09590818 1.7916279 1.4786046 -1.1788440822140267 1.255206542380211 1.0642428398132324 -3.2777271270751958 -1.3811463 1.9222080000000001 -0.023936661 -5.8730206 0.34145027 0.439121 2.7880993 0.00036954717000000004 -0.13185489 0.9237273000000001 0.9732863000000002 -4.1131425
5 4 78.0 0.0 755.0 1.0 755.0 3146.0 0.0 -21.0 -21.0 0.0 2.4706511000000004 4.6726856 30.583601 0.67071736 1.5111907 0.024124695 1.5492108999999998 1.439797 0.24763718664174345 0.8147690823204996 4.918219566345215 -0.9567646980285645 -4.656093599999999 0.40140057 -2.9237971000000003 -5.8753314 0.443355 1.7042981 10.802688999999999 0.08576387 0.41162340000000003 1.3014139999999998 7.6323996 -0.8151264
6 5 116.0 0.0 756.0 1.0 756.0 3902.0 0.0 -21.0 -21.0 0.0 1.850646 2.4202513999999997 16.295288 0.4290005 1.3224964 0.050945385999999995 1.4303273 1.2031558 0.14155570039685988 0.5814409942921325 3.3915529251098637 -0.8861622810363771 -3.0170727000000004 0.6280401999999999 -2.1003609 -4.3324237 0.22347862 0.839418 5.326185 0.05343006 0.22746566 0.82214487 4.685924 -0.7187973000000001