gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-03-31 00:53:32 +02:00
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

6
rl_coach/traces/Atari_A3C_pong/trace.csv Normal file
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
1,0.0,1.0,881.0,1.0,881.0,881.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,1043.0,1.0,1043.0,1924.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
3,40.0,0.0,800.0,1.0,800.0,2724.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.9787095000000001,1.6848618999999998,7.008404,0.010777535,1.6982583999999998,0.09253728,1.7866282,1.4752818,-1.1255737884236818,1.011838146554653,0.5801041126251221,-3.300693988800049,-0.599011,0.9902591000000001,0.05652909,-3.2763072999999996,0.15230414,0.30587232,1.9219400000000002,2.232377e-05,-0.35678893,0.77703935,0.5012678,-3.3208616
4,84.0,0.0,874.0,1.0,874.0,3598.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,2.7599952,4.4335379999999995,30.457005,0.31769055,1.6350366000000003,0.04428426,1.6724039000000002,1.4955306000000002,0.012454061887480996,0.5316342837334819,2.479757070541382,-0.97082257270813,-1.8976341,0.45726654,-1.5126665000000001,-3.3147082,0.14139508,0.42458066,2.8789976000000004,0.01374856,0.022890297999999996,0.7258614999999999,3.5482929,-1.1909457
5,133.0,0.0,962.0,1.0,962.0,4560.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,2.2067685,1.6116456000000001,8.973311,0.21847898,1.671777,0.014726803,1.6910971000000001,1.6381558,-0.005908215376385918,0.3910391646463375,1.0921021699905396,-0.9658074378967284,-1.8732144,0.11304277,-1.7097299,-2.2033259999999997,0.07926889,0.09812635,0.5330912,0.017862901,0.0026857766999999998,0.55807036,1.739695,-1.2937489
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 1.0 881.0 1.0 881.0 881.0 0.0 0.0
3 2 0.0 1.0 1043.0 1.0 1043.0 1924.0 0.0 0.0
4 3 40.0 0.0 800.0 1.0 800.0 2724.0 0.0 -21.0 -21.0 0.0 1.9787095000000001 1.6848618999999998 7.008404 0.010777535 1.6982583999999998 0.09253728 1.7866282 1.4752818 -1.1255737884236818 1.011838146554653 0.5801041126251221 -3.300693988800049 -0.599011 0.9902591000000001 0.05652909 -3.2763072999999996 0.15230414 0.30587232 1.9219400000000002 2.232377e-05 -0.35678893 0.77703935 0.5012678 -3.3208616
5 4 84.0 0.0 874.0 1.0 874.0 3598.0 0.0 -21.0 -21.0 0.0 2.7599952 4.4335379999999995 30.457005 0.31769055 1.6350366000000003 0.04428426 1.6724039000000002 1.4955306000000002 0.012454061887480996 0.5316342837334819 2.479757070541382 -0.97082257270813 -1.8976341 0.45726654 -1.5126665000000001 -3.3147082 0.14139508 0.42458066 2.8789976000000004 0.01374856 0.022890297999999996 0.7258614999999999 3.5482929 -1.1909457
6 5 133.0 0.0 962.0 1.0 962.0 4560.0 0.0 -21.0 -21.0 0.0 2.2067685 1.6116456000000001 8.973311 0.21847898 1.671777 0.014726803 1.6910971000000001 1.6381558 -0.005908215376385918 0.3910391646463375 1.0921021699905396 -0.9658074378967284 -1.8732144 0.11304277 -1.7097299 -2.2033259999999997 0.07926889 0.09812635 0.5330912 0.017862901 0.0026857766999999998 0.55807036 1.739695 -1.2937489