gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-04-18 13:43:32 +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_QR_DQN_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,,,,36.60464997756772,42.04124769391064,201.15611267089844,2.788020610809326,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,14.734329999999998,11.578652,83.24656999999999,3.6869566,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9983655100000356,-21.0,-21.0,0.0,,,,37.448825304324814,40.97555825854826,265.18701171875,2.7428863048553467,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,46.146587,37.73792,313.11514,12.797323,-0.02228271633396313,0.010482918460358506,-0.008034438502509147,-0.03863051085398183
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,35.222983159418185,33.638557732845605,134.39295959472656,3.3111674785614014,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,54.700793999999995,28.679327,185.94606000000002,25.897139000000003,-0.05276434649310735,0.013212184652596557,-0.03154730399168329,-0.06887179555138573
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,33.36415538668633,33.794293936783085,170.81182861328125,3.2840056419372563,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,53.996002000000004,31.833138,239.36745,27.415855,-0.03878277134735982,0.010679782367249705,-0.01826882790250238,-0.05715514831594193
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,,,,36.35055454649577,42.01083151839504,200.2666015625,2.5633368492126465,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,12.832593,10.057858999999999,67.494545,3.6044636,-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,,,,38.11564019780893,42.376735792713546,272.359375,2.4792284965515137,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,34.642643,34.25269,297.7308,7.9129830000000005,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,-0.01613784648589596,0.007600676424319005,-0.0064334499527467425,-0.029101890049059883
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,35.282302475351045,34.09448844961585,136.95803833007812,2.902939319610596,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,54.845543000000006,31.036062,200.47519,21.653633,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,-0.04853760938043706,0.011840542664502246,-0.034349839405913365,-0.06640744950796945
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,33.2309649837017,33.90203852171519,171.3233184814453,3.0904791355133057,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,56.7774,34.80046,265.04214,27.841105,-2.406465837413259,0.5636980823469648,-0.7105532272722921,-3.36383697254212,-0.036413699361194936,0.009885933390973514,-0.017495695663383236,-0.05450057732872665
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 36.60464997756772 36.35055454649577 42.04124769391064 42.01083151839504 201.15611267089844 200.2666015625 2.788020610809326 2.5633368492126465 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 14.734329999999998 12.832593 11.578652 10.057858999999999 83.24656999999999 67.494545 3.6869566 3.6044636 -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 37.448825304324814 38.11564019780893 40.97555825854826 42.376735792713546 265.18701171875 272.359375 2.7428863048553467 2.4792284965515137 5.0000000000000016e-05 1.3552527156068802e-20 5e-05 5e-05 46.146587 34.642643 37.73792 34.25269 313.11514 297.7308 12.797323 7.9129830000000005 -2.320394201181889 0.6047235028955231 -0.7105532272722921 -3.350537576335216 -0.02228271633396313 -0.01613784648589596 0.010482918460358506 0.007600676424319005 -0.008034438502509147 -0.0064334499527467425 -0.03863051085398183 -0.029101890049059883
5 4 667.0 0.0 3783.0 3783.0 1015.0 3783.0 0.9973606600000572 -20.0 -20.0 0.0 35.222983159418185 35.282302475351045 33.638557732845605 34.09448844961585 134.39295959472656 136.95803833007812 3.3111674785614014 2.902939319610596 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 54.700793999999995 54.845543000000006 28.679327 31.036062 185.94606000000002 200.47519 25.897139000000003 21.653633 -1.7531357837449677 0.7448577440634202 -0.1288331810939122 -3.2971074888190803 -0.05276434649310735 -0.04853760938043706 0.013212184652596557 0.011840542664502246 -0.03154730399168329 -0.034349839405913365 -0.06887179555138573 -0.06640744950796945
6 5 867.0 0.0 4585.0 4585.0 802.0 4585.0 0.9965666800000744 -21.0 -21.0 0.0 33.36415538668633 33.2309649837017 33.794293936783085 33.90203852171519 170.81182861328125 171.3233184814453 3.2840056419372563 3.0904791355133057 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 53.996002000000004 56.7774 31.833138 34.80046 239.36745 265.04214 27.415855 27.841105 -2.406465837413259 0.5636980823469648 -0.7105532272722921 -3.36383697254212 -0.03878277134735982 -0.036413699361194936 0.010679782367249705 0.009885933390973514 -0.01826882790250238 -0.017495695663383236 -0.05715514831594193 -0.05450057732872665