1
0
mirror of https://github.com/gryf/coach.git synced 2026-04-03 10:43:33 +02:00

trace tests update

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

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,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
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,36.34445524564603,41.993139542609136,200.13507080078125,2.573660135269165,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,12.7432995,10.766466000000001,81.03363,3.42582,-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,,,,37.543445411783,41.50272860065348,266.24258422851557,2.552807331085205,5.0000000000000016e-05,1.3552527156068802e-20,5e-05,5e-05,38.67631,34.089546,285.27133,8.399524000000001,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,-0.018642622935246142,0.009556171435240226,-0.004845094565243928,-0.03212798437627499
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,35.145844577804326,33.76140476143935,133.99909973144528,3.20855712890625,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,51.623084999999996,26.665253000000003,171.20616,25.264019,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,-0.04896596012507265,0.012271451729615605,-0.028249878564020038,-0.0641258182382444
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,33.21861356735229,33.802230749750514,171.11648559570312,3.1988396644592285,5.000000000000001e-05,6.776263578034403e-21,5e-05,5e-05,51.510967,29.626279999999998,225.32596,27.11263,-2.406465837413259,0.5636980823469648,-0.7105532272722921,-3.36383697254212,-0.03616584410942476,0.011201886243875388,-0.015056172198383141,-0.05481453027576209
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 36.35055454649577 36.34445524564603 42.01083151839504 41.993139542609136 200.2666015625 200.13507080078125 2.5633368492126465 2.573660135269165 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 12.832593 12.7432995 10.057858999999999 10.766466000000001 67.494545 81.03363 3.6044636 3.42582 -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 38.11564019780893 37.543445411783 42.376735792713546 41.50272860065348 272.359375 266.24258422851557 2.4792284965515137 2.552807331085205 5.0000000000000016e-05 1.3552527156068802e-20 5e-05 5e-05 34.642643 38.67631 34.25269 34.089546 297.7308 285.27133 7.9129830000000005 8.399524000000001 -2.320394201181889 0.6047235028955231 -0.7105532272722921 -3.350537576335216 -0.01613784648589596 -0.018642622935246142 0.007600676424319005 0.009556171435240226 -0.0064334499527467425 -0.004845094565243928 -0.029101890049059883 -0.03212798437627499
5 4 667.0 0.0 3783.0 3783.0 1015.0 3783.0 0.9973606600000572 -20.0 -20.0 0.0 35.282302475351045 35.145844577804326 34.09448844961585 33.76140476143935 136.95803833007812 133.99909973144528 2.902939319610596 3.20855712890625 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 54.845543000000006 51.623084999999996 31.036062 26.665253000000003 200.47519 171.20616 21.653633 25.264019 -1.7531357837449677 0.7448577440634202 -0.1288331810939122 -3.2971074888190803 -0.04853760938043706 -0.04896596012507265 0.011840542664502246 0.012271451729615605 -0.034349839405913365 -0.028249878564020038 -0.06640744950796945 -0.0641258182382444
6 5 867.0 0.0 4585.0 4585.0 802.0 4585.0 0.9965666800000744 -21.0 -21.0 0.0 33.2309649837017 33.21861356735229 33.90203852171519 33.802230749750514 171.3233184814453 171.11648559570312 3.0904791355133057 3.1988396644592285 5.000000000000001e-05 6.776263578034403e-21 5e-05 5e-05 56.7774 51.510967 34.80046 29.626279999999998 265.04214 225.32596 27.841105 27.11263 -2.406465837413259 0.5636980823469648 -0.7105532272722921 -3.36383697254212 -0.036413699361194936 -0.03616584410942476 0.009885933390973514 0.011201886243875388 -0.017495695663383236 -0.015056172198383141 -0.05450057732872665 -0.05481453027576209