gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-03-05 00:15:50 +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

6
rl_coach/traces/ControlSuite_DDPG_hopper_hop/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,Q/Mean,Q/Stdev,Q/Max,Q/Min,TD targets/Mean,TD targets/Stdev,TD targets/Max,TD targets/Min,actions/Mean,actions/Stdev,actions/Max,actions/Min
1,0.0,1.0,1000.0,1.0,1000.0,1000.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,2000.0,2.0,1000.0,2000.0,0.0,,,1.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
3,999.0,0.0,3000.0,3.0,1000.0,3000.0,-0.017666830179174003,0.0,0.0,1.0,,,,0.0038191572866389523,0.0037619606969040414,0.026500405743718147,0.0005351771251298487,0.00010000000000000003,4.0657581468206416e-20,0.0001,0.0001,0.14963633,0.12557492,1.0296046,0.022291046000000002,,,,,,,,,,,,,,,,,,,,,-0.06052997,0.07319117,0.09228404,-0.81788486,-0.2878782119320924,0.18290294876848567,0.15647711277008056,-1.5949552059173584,0.001995146476856135,0.7060122989726414,1.2513357156871705,-1.2238670209506697
4,1999.0,0.0,4000.0,4.0,1000.0,4000.0,-0.039999362478752916,0.0,0.0,1.0,,,,0.0005999824570681085,0.0005200396841794251,0.007392321713268756,0.0001155680656665936,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.035074446,0.023916507000000004,0.27376664,0.007415438000000001,,,,,,,,,,,,,,,,,,,,,-0.055866152,0.03557198,0.048398294,-0.20761846,-0.1228111611005996,0.10064295523824936,0.10938632614910604,-0.9385637390613556,0.3813050626909247,0.8586455988935526,1.9421025144380244,-1.2856749345811207
5,2999.0,0.0,5000.0,5.0,1000.0,5000.0,0.17145601483403705,0.0,0.0,0.0,,,,0.00016860231386453962,8.468335419663504e-05,0.0008860444650053977,4.115650153835304e-05,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.013316613,0.0064833634999999995,0.055022966,0.0038480079,,,,,,,,,,,,,,,,,,,,,-0.04638309,0.028830105,-0.0011850878,-0.36706513,-0.055944047987441965,0.061761207984293,0.16325088679790498,-0.6333049428462982,0.2629062319462116,0.7653580979608734,1.6618100999356682,-1.1699750612176198
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 Q/Mean Q/Stdev Q/Max Q/Min TD targets/Mean TD targets/Stdev TD targets/Max TD targets/Min actions/Mean actions/Stdev actions/Max actions/Min
2 1 0.0 1.0 1000.0 1.0 1000.0 1000.0 0.0 0.0
3 2 0.0 1.0 2000.0 2.0 1000.0 2000.0 0.0 1.0
4 3 999.0 0.0 3000.0 3.0 1000.0 3000.0 -0.017666830179174003 0.0 0.0 1.0 0.0038191572866389523 0.0037619606969040414 0.026500405743718147 0.0005351771251298487 0.00010000000000000003 4.0657581468206416e-20 0.0001 0.0001 0.14963633 0.12557492 1.0296046 0.022291046000000002 -0.06052997 0.07319117 0.09228404 -0.81788486 -0.2878782119320924 0.18290294876848567 0.15647711277008056 -1.5949552059173584 0.001995146476856135 0.7060122989726414 1.2513357156871705 -1.2238670209506697
5 4 1999.0 0.0 4000.0 4.0 1000.0 4000.0 -0.039999362478752916 0.0 0.0 1.0 0.0005999824570681085 0.0005200396841794251 0.007392321713268756 0.0001155680656665936 0.00010000000000000003 2.7105054312137605e-20 0.0001 0.0001 0.035074446 0.023916507000000004 0.27376664 0.007415438000000001 -0.055866152 0.03557198 0.048398294 -0.20761846 -0.1228111611005996 0.10064295523824936 0.10938632614910604 -0.9385637390613556 0.3813050626909247 0.8586455988935526 1.9421025144380244 -1.2856749345811207
6 5 2999.0 0.0 5000.0 5.0 1000.0 5000.0 0.17145601483403705 0.0 0.0 0.0 0.00016860231386453962 8.468335419663504e-05 0.0008860444650053977 4.115650153835304e-05 0.00010000000000000003 2.7105054312137605e-20 0.0001 0.0001 0.013316613 0.0064833634999999995 0.055022966 0.0038480079 -0.04638309 0.028830105 -0.0011850878 -0.36706513 -0.055944047987441965 0.061761207984293 0.16325088679790498 -0.6333049428462982 0.2629062319462116 0.7653580979608734 1.6618100999356682 -1.1699750612176198