gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-04-20 23:41:24 +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
rl_coach/traces/Atari_UCB_with_Q_Ensembles_pong/trace.csv
+6
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,Q/Mean,Q/Stdev,Q/Max,Q/Min
1,0.0,1.0,909.0,909.0,909.0,909.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,1849.0,1849.0,940.0,1849.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,
3,185.0,0.0,2589.0,2589.0,740.0,2589.0,0.0,-21.0,-21.0,0.0,,,,0.01237654753620862,0.012107382206937413,0.047442745417356484,0.0005760944331996143,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.012748566999999999,0.0052782227,0.03766812,0.005078032,,,,
4,442.0,0.0,3618.0,3618.0,1029.0,3618.0,0.036310166120529175,-20.0,-20.0,0.0,,,,0.012453011741702252,0.013498447785635284,0.0759262964129448,0.000425029982579872,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.011709151000000001,0.0046144870000000004,0.027468227,0.0041608843,-0.0377305,0.005958211,-0.028756577999999998,-0.046951957
5,708.0,0.0,4679.0,4679.0,1061.0,4679.0,0.018979299813508987,-20.0,-20.0,0.0,,,,0.012743571282345172,0.013893963491457096,0.08593739569187164,0.0005298212054185568,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.010713641999999999,0.0042998786,0.04166126,0.005018155,-0.01665635,0.0030537121999999997,-0.0120764775,-0.02167279
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 Q/Mean Q/Stdev Q/Max Q/Min
2 1 0.0 1.0 909.0 909.0 909.0 909.0 0.0 0.0
3 2 0.0 1.0 1849.0 1849.0 940.0 1849.0 0.0 0.0
4 3 185.0 0.0 2589.0 2589.0 740.0 2589.0 0.0 -21.0 -21.0 0.0 0.01237654753620862 0.012107382206937413 0.047442745417356484 0.0005760944331996143 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.012748566999999999 0.0052782227 0.03766812 0.005078032
5 4 442.0 0.0 3618.0 3618.0 1029.0 3618.0 0.036310166120529175 -20.0 -20.0 0.0 0.012453011741702252 0.013498447785635284 0.0759262964129448 0.000425029982579872 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.011709151000000001 0.0046144870000000004 0.027468227 0.0041608843 -0.0377305 0.005958211 -0.028756577999999998 -0.046951957
6 5 708.0 0.0 4679.0 4679.0 1061.0 4679.0 0.018979299813508987 -20.0 -20.0 0.0 0.012743571282345172 0.013893963491457096 0.08593739569187164 0.0005298212054185568 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.010713641999999999 0.0042998786 0.04166126 0.005018155 -0.01665635 0.0030537121999999997 -0.0120764775 -0.02167279