1
0
mirror of https://github.com/gryf/coach.git synced 2026-03-17 07:13:37 +01:00

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,,,,0.012876360744334441,0.013169937079938372,0.058244716376066215,3.0656796297989786e-05,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.08459491,0.07130137,0.5982875,0.0070038475,-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,,,,0.013282082582778595,0.013458619568678002,0.08588293939828873,0.00010849477257579564,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.05503054,0.028424903999999997,0.1483146,0.009207340999999999,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,-0.015621655,0.008273302,-0.0005000639,-0.026964545
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,0.013194311608587424,0.012947686004709887,0.054273433983325965,7.553023169748485e-05,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.051557817,0.026205682999999997,0.15292059,0.007897207,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,-0.03597512,0.008356134,-0.020397818,-0.04812158
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,0.012997063024049566,0.012349733954071369,0.05852360650897026,3.451433076406829e-05,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.055003084,0.041335538,0.28613466,0.0044473526,-2.406465837413259,0.5636980823469648,-0.7105532272722921,-3.36383697254212,-0.07864461,0.018148461,-0.04457518,-0.106537335
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,0.015207937956012491,0.014492317883834838,0.09301766008138657,0.0001782444742275402,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.11822851,0.110184506,0.5651076,0.01738942,-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,,,,0.01633638746737303,0.014181652421716769,0.08328360319137572,8.370452269446105e-05,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.082309455,0.06658171,0.32533133,0.006842116,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,-0.02331494,0.005804968000000001,-0.011170000000000001,-0.029942054
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,0.015355665049212366,0.01424748090137614,0.08354021608829497,2.827002754202113e-05,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.07492155,0.061100102999999996,0.44151178,0.0039172773,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,-0.011196605,0.004126583,-0.00447652,-0.017569061
5,892.0,0.0,4684.0,4684.0,901.0,4684.0,0.9964686700000768,-20.0,-20.0,0.0,,,,0.015270625980984831,0.01304286284704392,0.07593831419944763,0.0012584527721628547,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.055711348,0.018893627,0.1257123,0.03050933,-2.012872425274268,0.6709095073776362,-0.4256446851738544,-3.2469842373013775,-0.026350275,0.00818921,-0.012880649,-0.039243348
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 0.012876360744334441 0.015207937956012491 0.013169937079938372 0.014492317883834838 0.058244716376066215 0.09301766008138657 3.0656796297989786e-05 0.0001782444742275402 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.08459491 0.11822851 0.07130137 0.110184506 0.5982875 0.5651076 0.0070038475 0.01738942 -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 0.013282082582778595 0.01633638746737303 0.013458619568678002 0.014181652421716769 0.08588293939828873 0.08328360319137572 0.00010849477257579564 8.370452269446105e-05 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.05503054 0.082309455 0.028424903999999997 0.06658171 0.1483146 0.32533133 0.009207340999999999 0.006842116 -2.320394201181889 0.6047235028955231 -0.7105532272722921 -3.350537576335216 -0.015621655 -0.02331494 0.008273302 0.005804968000000001 -0.0005000639 -0.011170000000000001 -0.026964545 -0.029942054
5 4 667.0 0.0 3783.0 3783.0 1015.0 3783.0 0.9973606600000572 -20.0 -20.0 0.0 0.013194311608587424 0.015355665049212366 0.012947686004709887 0.01424748090137614 0.054273433983325965 0.08354021608829497 7.553023169748485e-05 2.827002754202113e-05 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.051557817 0.07492155 0.026205682999999997 0.061100102999999996 0.15292059 0.44151178 0.007897207 0.0039172773 -1.7531357837449677 0.7448577440634202 -0.1288331810939122 -3.2971074888190803 -0.03597512 -0.011196605 0.008356134 0.004126583 -0.020397818 -0.00447652 -0.04812158 -0.017569061
6 5 867.0 892.0 0.0 4585.0 4684.0 4585.0 4684.0 802.0 901.0 4585.0 4684.0 0.9965666800000744 0.9964686700000768 -21.0 -20.0 -21.0 -20.0 0.0 0.012997063024049566 0.015270625980984831 0.012349733954071369 0.01304286284704392 0.05852360650897026 0.07593831419944763 3.451433076406829e-05 0.0012584527721628547 0.0002500000000000001 5.421010862427521e-20 1.0842021724855042e-19 0.00025 0.00025 0.055003084 0.055711348 0.041335538 0.018893627 0.28613466 0.1257123 0.0044473526 0.03050933 -2.406465837413259 -2.012872425274268 0.5636980823469648 0.6709095073776362 -0.7105532272722921 -0.4256446851738544 -3.36383697254212 -3.2469842373013775 -0.07864461 -0.026350275 0.018148461 0.00818921 -0.04457518 -0.012880649 -0.106537335 -0.039243348