gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-05-03 14:50:56 +02:00
Code Issues Projects Releases Wiki Activity

new traces

Browse Source
This commit is contained in:
itaicaspi-intel
2018-09-12 15:29:42 +03:00
parent 673911ff7f
commit fa4895f840
76 changed files with 12786 additions and 12606 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 -6
View File
@@ -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,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,,,,,,,,,,,,,,,,,,,
3,191.0,0.0,2612.0,2612.0,763.0,2612.0,0.0,-21.0,-21.0,0.0,,,,0.0130545203534384,0.01309133522881885,0.050950419157743454,0.0006263511604629457,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.013740225,0.005418419,0.03539303,0.0058373637,,,,
4,460.0,0.0,3688.0,3688.0,1076.0,3688.0,0.04093054309487343,-19.0,-19.0,0.0,,,,0.01353417751470193,0.013991631199855073,0.060094203799963,0.0007772938697598875,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.012196413,0.0043717,0.027787974,0.0044747777,-0.028111902999999997,0.007774155,-0.014797297,-0.03953904
5,679.0,0.0,4563.0,4563.0,875.0,4563.0,0.03276534005999565,-21.0,-21.0,0.0,,,,0.013156805880639923,0.01289872044109124,0.05886143445968627,0.0005613723187707366,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.012954918999999999,0.00410382,0.028127436000000002,0.0051577645,-0.006553585,0.009180349,0.011637015,-0.020697306999999998
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
1,0.0,1.0,909.0,909.0,909.0,909.0,0.0,,,0.0,,,,,,,,,,,,,,,,-1.9655950472199328,0.7232623981585671,-0.33416993016801505,-3.2856761435887236,,,,
2,0.0,1.0,1849.0,1849.0,940.0,1849.0,0.0,,,0.0,,,,,,,,,,,,,,,,-2.0850702358812647,0.5206151988478068,-0.7105532272722921,-3.229858453919355,,,,
3,191.0,0.0,2612.0,2612.0,763.0,2612.0,0.0,-21.0,-21.0,0.0,,,,0.012449520095178359,0.013048937023542005,0.048593450337648385,0.0007832169649191201,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.011991171,0.0049315933,0.031664677,0.005639204,-2.5178046202451694,0.5843148195084643,-0.7105532272722921,-3.3699982440767453,,,,
4,460.0,0.0,3688.0,3688.0,1076.0,3688.0,0.06158000603318215,-19.0,-19.0,0.0,,,,0.013090697613537835,0.01423496703653869,0.06296952068805695,0.0003786738670896739,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.01207951,0.0049282457,0.02845837,0.0044667325,-1.600130842171531,0.7841052063633746,-0.05879559276456229,-3.1930866215011884,-0.027162252,0.0089824805,-0.0103284065,-0.038634557
5,679.0,0.0,4563.0,4563.0,875.0,4563.0,0.0686592236161232,-21.0,-21.0,0.0,,,,0.01267829067451182,0.01314711143634318,0.06590334326028824,0.0006290889577940106,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.012010485,0.0045945253,0.02634775,0.005362396,-2.206191047518212,0.5577254452906393,-0.7105532272722921,-3.3372597252516765,-0.020140575,0.010422909000000001,-0.0047886134,-0.037010644
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 1.0 909.0 909.0 909.0 909.0 0.0 0.0 -1.9655950472199328 0.7232623981585671 -0.33416993016801505 -3.2856761435887236
3 2 0.0 1.0 1849.0 1849.0 940.0 1849.0 0.0 0.0 -2.0850702358812647 0.5206151988478068 -0.7105532272722921 -3.229858453919355
4 3 191.0 0.0 2612.0 2612.0 763.0 2612.0 0.0 -21.0 -21.0 0.0 0.0130545203534384 0.012449520095178359 0.01309133522881885 0.013048937023542005 0.050950419157743454 0.048593450337648385 0.0006263511604629457 0.0007832169649191201 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.013740225 0.011991171 0.005418419 0.0049315933 0.03539303 0.031664677 0.0058373637 0.005639204 -2.5178046202451694 0.5843148195084643 -0.7105532272722921 -3.3699982440767453
5 4 460.0 0.0 3688.0 3688.0 1076.0 3688.0 0.04093054309487343 0.06158000603318215 -19.0 -19.0 0.0 0.01353417751470193 0.013090697613537835 0.013991631199855073 0.01423496703653869 0.060094203799963 0.06296952068805695 0.0007772938697598875 0.0003786738670896739 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.012196413 0.01207951 0.0043717 0.0049282457 0.027787974 0.02845837 0.0044747777 0.0044667325 -1.600130842171531 0.7841052063633746 -0.05879559276456229 -3.1930866215011884 -0.028111902999999997 -0.027162252 0.007774155 0.0089824805 -0.014797297 -0.0103284065 -0.03953904 -0.038634557
6 5 679.0 0.0 4563.0 4563.0 875.0 4563.0 0.03276534005999565 0.0686592236161232 -21.0 -21.0 0.0 0.013156805880639923 0.01267829067451182 0.01289872044109124 0.01314711143634318 0.05886143445968627 0.06590334326028824 0.0005613723187707366 0.0006290889577940106 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.012954918999999999 0.012010485 0.00410382 0.0045945253 0.028127436000000002 0.02634775 0.0051577645 0.005362396 -2.206191047518212 0.5577254452906393 -0.7105532272722921 -3.3372597252516765 -0.006553585 -0.020140575 0.009180349 0.010422909000000001 0.011637015 -0.0047886134 -0.020697306999999998 -0.037010644