gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-03-17 23:33:37 +01:00
Code Issues Projects Releases Wiki Activity

trace tests update

Browse Source
This commit is contained in:
Shadi Endrawis
2018-10-02 17:55:16 +03:00
parent 51726a5b80
commit f7990d4003
79 changed files with 10105 additions and 9539 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rl_coach/traces/Atari_A3C_LSTM_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,Discounted Return/Mean,Discounted Return/Stdev,Discounted Return/Max,Discounted Return/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
1,0.0,1.0,772.0,1.0,772.0,772.0,0.0,,,0.0,,,,,,,,,,,,,,,,-2.437332009209832,0.5666975756966289,-0.7105532272722921,-3.364332223379411,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,821.0,1.0,821.0,1593.0,0.0,,,0.0,,,,,,,,,,,,,,,,-2.3375427452853184,0.562882024173797,-0.7105532272722921,-3.3225778431943085,,,,,,,,,,,,,,,,,,,,
3,38.0,0.0,763.0,1.0,763.0,2356.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.2098866000000001,1.449215,5.3609241999999995,0.00244356,-2.5178046202451694,0.5843148195084643,-0.7105532272722921,-3.3699982440767453,1.7662544999999998,0.03266678,1.7917435000000002,1.6590552,-0.09202062882188904,0.4331878633448028,0.8984384536743164,-0.9984065890312196,-1.7017021,1.594185,-0.041688699999999995,-4.9379349999999995,0.22111915,0.19444092,0.59284925,2.0590694e-05,-0.1670907,0.6072369000000001,0.91119975,-1.4746135
4,75.0,0.0,740.0,1.0,740.0,3096.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.9744401999999999,0.8914412,4.1053777,0.54077625,-2.533184641659896,0.5861942513660167,-0.7105532272722921,-3.3699982440767453,1.1498803,0.17261624,1.7622604,0.99270844,0.19542027049594451,0.4488243660076464,0.9995923042297364,-0.9500741958618164,-5.264807,0.15003455,-4.995072,-5.481164,0.22140607,0.09454554,0.4738923,0.1269643,0.24964908,0.42948514,0.77320266,-0.62486225
5,113.0,0.0,755.0,1.0,755.0,3851.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.6745409,0.7766086999999999,3.4373443,0.42763662,-2.5246431129611286,0.5835765895797549,-0.7105532272722921,-3.3699982440767453,0.8715389000000001,0.11778103,1.3657371999999999,0.70607877,0.02502031455168853,0.4342484515718581,0.8662590980529785,-0.9686682224273682,-3.4500135999999997,0.4302874,-3.1447627999999996,-4.761848400000001,0.10419229,0.05407177,0.22493912,0.052366237999999996,0.030020599999999995,0.3442417,0.68716383,-0.674335
3,38.0,0.0,763.0,1.0,763.0,2356.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,0.9789834999999999,1.335424,5.44189,0.0016743626999999998,-2.5178046202451694,0.5843148195084643,-0.7105532272722921,-3.3699982440767453,1.7676028999999998,0.03572973,1.791706,1.671823,-0.15197662177900048,0.42457358040248205,0.7191236019134521,-1.0115903615951538,-1.094308,1.2064375,0.07422362,-3.9562736000000003,0.18559802,0.18026318,0.5619888000000001,6.661260000000001e-06,-0.27577358,0.58109426,0.6487745,-1.4974867
4,75.0,0.0,740.0,1.0,740.0,3096.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,2.0474174,1.1940155000000001,5.4071739999999995,0.46045935,-2.533184641659896,0.5861942513660167,-0.7105532272722921,-3.3699982440767453,1.4143568000000002,0.19615947,1.7779577000000002,1.16588,0.22533110479513804,0.4591070601365748,1.1359987258911133,-0.9571647644042968,-5.57011,0.6552074999999999,-4.209009,-6.2400413,0.2781368,0.12522699,0.57409745,0.15991631,0.31805104,0.5110617999999999,1.0385043999999999,-0.8121315
5,113.0,0.0,755.0,1.0,755.0,3851.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.5748503999999999,0.6886424,2.8886950000000002,0.46616986,-2.5246431129611286,0.5835765895797549,-0.7105532272722921,-3.3699982440767453,1.2100506000000002,0.029187731,1.4943258,1.1479353,0.08319399034654773,0.4409353372895212,1.0099096298217771,-0.9640896320343018,-4.039905,0.5391477,-3.5903852,-5.5438123,0.113760486,0.047593262000000004,0.21574955,0.062469393,0.0946553,0.4438318,0.6956541,-0.781316
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 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
2 1 0.0 1.0 772.0 1.0 772.0 772.0 0.0 0.0 -2.437332009209832 0.5666975756966289 -0.7105532272722921 -3.364332223379411
3 2 0.0 1.0 821.0 1.0 821.0 1593.0 0.0 0.0 -2.3375427452853184 0.562882024173797 -0.7105532272722921 -3.3225778431943085
4 3 38.0 0.0 763.0 1.0 763.0 2356.0 0.0 -21.0 -21.0 0.0 1.2098866000000001 0.9789834999999999 1.449215 1.335424 5.3609241999999995 5.44189 0.00244356 0.0016743626999999998 -2.5178046202451694 0.5843148195084643 -0.7105532272722921 -3.3699982440767453 1.7662544999999998 1.7676028999999998 0.03266678 0.03572973 1.7917435000000002 1.791706 1.6590552 1.671823 -0.09202062882188904 -0.15197662177900048 0.4331878633448028 0.42457358040248205 0.8984384536743164 0.7191236019134521 -0.9984065890312196 -1.0115903615951538 -1.7017021 -1.094308 1.594185 1.2064375 -0.041688699999999995 0.07422362 -4.9379349999999995 -3.9562736000000003 0.22111915 0.18559802 0.19444092 0.18026318 0.59284925 0.5619888000000001 2.0590694e-05 6.661260000000001e-06 -0.1670907 -0.27577358 0.6072369000000001 0.58109426 0.91119975 0.6487745 -1.4746135 -1.4974867
5 4 75.0 0.0 740.0 1.0 740.0 3096.0 0.0 -21.0 -21.0 0.0 1.9744401999999999 2.0474174 0.8914412 1.1940155000000001 4.1053777 5.4071739999999995 0.54077625 0.46045935 -2.533184641659896 0.5861942513660167 -0.7105532272722921 -3.3699982440767453 1.1498803 1.4143568000000002 0.17261624 0.19615947 1.7622604 1.7779577000000002 0.99270844 1.16588 0.19542027049594451 0.22533110479513804 0.4488243660076464 0.4591070601365748 0.9995923042297364 1.1359987258911133 -0.9500741958618164 -0.9571647644042968 -5.264807 -5.57011 0.15003455 0.6552074999999999 -4.995072 -4.209009 -5.481164 -6.2400413 0.22140607 0.2781368 0.09454554 0.12522699 0.4738923 0.57409745 0.1269643 0.15991631 0.24964908 0.31805104 0.42948514 0.5110617999999999 0.77320266 1.0385043999999999 -0.62486225 -0.8121315
6 5 113.0 0.0 755.0 1.0 755.0 3851.0 0.0 -21.0 -21.0 0.0 1.6745409 1.5748503999999999 0.7766086999999999 0.6886424 3.4373443 2.8886950000000002 0.42763662 0.46616986 -2.5246431129611286 0.5835765895797549 -0.7105532272722921 -3.3699982440767453 0.8715389000000001 1.2100506000000002 0.11778103 0.029187731 1.3657371999999999 1.4943258 0.70607877 1.1479353 0.02502031455168853 0.08319399034654773 0.4342484515718581 0.4409353372895212 0.8662590980529785 1.0099096298217771 -0.9686682224273682 -0.9640896320343018 -3.4500135999999997 -4.039905 0.4302874 0.5391477 -3.1447627999999996 -3.5903852 -4.761848400000001 -5.5438123 0.10419229 0.113760486 0.05407177 0.047593262000000004 0.22493912 0.21574955 0.052366237999999996 0.062469393 0.030020599999999995 0.0946553 0.3442417 0.4438318 0.68716383 0.6956541 -0.674335 -0.781316