gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-03-30 00:23:32 +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

12
rl_coach/traces/Atari_C51_pong/trace.csv
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
1,0.0,1.0,1117.0,1117.0,1117.0,1117.0,1.0,,,0.0,,,,,,,,,,,,,,,,,,,
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,3.9302156448364256,0.0010496846440389027,3.931553840637207,3.9267423152923584,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0021735325,0.0023975547,0.015546012,0.0008601941499999999,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9983655100000356,-21.0,-21.0,0.0,,,,3.9287387797465687,0.0010725536875668584,3.930054426193237,3.92205548286438,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0014352581,0.0022775119,0.016661283,0.0005455515,0.06143524280438877,0.010833295539136235,0.0730189699679619,0.04586568772792873
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,3.9281875890071,0.0009267313904696912,3.9292049407958975,3.9252440929412837,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0012879773,0.0025753588,0.018626466,0.00030493445,0.06362535804510176,0.0053005873567461975,0.06891775093972746,0.053885202482343325
5,892.0,0.0,4684.0,4684.0,901.0,4684.0,0.9964686700000768,-20.0,-20.0,0.0,,,,3.9280550532870815,0.0009707394231859632,3.9289817810058594,3.9241018295288086,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.00088581746,0.0017567717,0.016409054,0.00022121534999999999,0.06359539761518496,0.005375292811606972,0.07293013073504026,0.05364551693201117
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
1,0.0,1.0,1117.0,1117.0,1117.0,1117.0,1.0,,,0.0,,,,,,,,,,,,,,,,-1.5180229894995567,0.6998808293377133,-0.08930329112720292,-3.148474706421977,,,,
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,3.9305681682214506,0.0009982327410686944,3.9316465854644775,3.926915407180786,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0018689651999999998,0.0020046625,0.012255268,0.0008047835000000001,-2.3361342922088504,0.784322378590693,-0.38878391807422696,-3.369599601005491,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9983655100000356,-21.0,-21.0,0.0,,,,3.929541920240109,0.0010681346138543732,3.930777311325073,3.9228343963623047,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0012420595,0.001847766,0.013259928999999998,0.0005541933400000001,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,0.029271987701456326,0.007044414085294216,0.04094065204262795,0.022607963532209983
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,3.9289580902715366,0.0009148473718069287,3.92997932434082,3.926001310348511,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0010492479,0.0020559301999999997,0.015287617,0.00028366325,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,0.031816515512765015,0.0037668773678035884,0.03839177079498832,0.027437280490995003
5,892.0,0.0,4684.0,4684.0,901.0,4684.0,0.9964686700000768,-20.0,-20.0,0.0,,,,3.9287068123287625,0.0009553953918798189,3.929911375045776,3.924695730209351,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0007680645,0.0015440129,0.014315132,0.00020842048999999998,-2.012872425274268,0.6709095073776362,-0.4256446851738544,-3.2469842373013775,0.03543573763842443,0.004500463100191639,0.0407443653792148,0.024707648903132096
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 1117.0 1117.0 1117.0 1117.0 1.0 0.0 -1.5180229894995567 0.6998808293377133 -0.08930329112720292 -3.148474706421977
3 2 205.0 0.0 1937.0 1937.0 820.0 1937.0 0.9991882000000176 -21.0 -21.0 0.0 3.9302156448364256 3.9305681682214506 0.0010496846440389027 0.0009982327410686944 3.931553840637207 3.9316465854644775 3.9267423152923584 3.926915407180786 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.0021735325 0.0018689651999999998 0.0023975547 0.0020046625 0.015546012 0.012255268 0.0008601941499999999 0.0008047835000000001 -2.3361342922088504 0.784322378590693 -0.38878391807422696 -3.369599601005491
4 3 413.0 0.0 2768.0 2768.0 831.0 2768.0 0.9983655100000356 -21.0 -21.0 0.0 3.9287387797465687 3.929541920240109 0.0010725536875668584 0.0010681346138543732 3.930054426193237 3.930777311325073 3.92205548286438 3.9228343963623047 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.0014352581 0.0012420595 0.0022775119 0.001847766 0.016661283 0.013259928999999998 0.0005455515 0.0005541933400000001 -2.320394201181889 0.6047235028955231 -0.7105532272722921 -3.350537576335216 0.06143524280438877 0.029271987701456326 0.010833295539136235 0.007044414085294216 0.0730189699679619 0.04094065204262795 0.04586568772792873 0.022607963532209983
5 4 667.0 0.0 3783.0 3783.0 1015.0 3783.0 0.9973606600000572 -20.0 -20.0 0.0 3.9281875890071 3.9289580902715366 0.0009267313904696912 0.0009148473718069287 3.9292049407958975 3.92997932434082 3.9252440929412837 3.926001310348511 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0012879773 0.0010492479 0.0025753588 0.0020559301999999997 0.018626466 0.015287617 0.00030493445 0.00028366325 -1.7531357837449677 0.7448577440634202 -0.1288331810939122 -3.2971074888190803 0.06362535804510176 0.031816515512765015 0.0053005873567461975 0.0037668773678035884 0.06891775093972746 0.03839177079498832 0.053885202482343325 0.027437280490995003
6 5 892.0 0.0 4684.0 4684.0 901.0 4684.0 0.9964686700000768 -20.0 -20.0 0.0 3.9280550532870815 3.9287068123287625 0.0009707394231859632 0.0009553953918798189 3.9289817810058594 3.929911375045776 3.9241018295288086 3.924695730209351 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.00088581746 0.0007680645 0.0017567717 0.0015440129 0.016409054 0.014315132 0.00022121534999999999 0.00020842048999999998 -2.012872425274268 0.6709095073776362 -0.4256446851738544 -3.2469842373013775 0.06359539761518496 0.03543573763842443 0.005375292811606972 0.004500463100191639 0.07293013073504026 0.0407443653792148 0.05364551693201117 0.024707648903132096