1
0
mirror of https://github.com/gryf/coach.git synced 2026-03-13 21:25:51 +01:00

new traces

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

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,Entropy/Mean,Entropy/Stdev,Entropy/Max,Entropy/Min,Q/Mean,Q/Stdev,Q/Max,Q/Min,Q Values/Mean,Q Values/Stdev,Q Values/Max,Q Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min
1,0.0,1.0,1117.0,1.0,1117.0,1117.0,0.5,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
2,166.0,0.0,834.0,1.0,834.0,1951.0,0.4918267999999965,-20.0,-20.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,-0.049309142,0.05955426,0.11067552,-0.31385273,0.10965226,0.25779134,0.96019816,1.650419e-05
3,343.0,0.0,883.0,1.0,883.0,2834.0,0.4831733999999927,-20.0,-20.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,0.00039612237,0.022137828,0.047817677,-0.057933766,0.05449706,0.15011412,0.8670572,0.0013089271000000001
4,495.0,0.0,759.0,1.0,759.0,3593.0,0.4757351999999895,-21.0,-21.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,-0.013107545,0.014792551000000001,0.02346693,-0.051909205,0.09606385,0.22936918,0.84131515,0.00357637
5,646.0,0.0,755.0,1.0,755.0,4348.0,0.4683361999999863,-21.0,-21.0,0.0,,,,,,,,,,,,,,,,,,,,,,,,-0.056291025,0.024121637999999997,0.011681341000000001,-0.11741245,0.111964785,0.24955077,0.79120165,0.0038064622999999997
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,Q/Mean,Q/Stdev,Q/Max,Q/Min,Q Values/Mean,Q Values/Stdev,Q Values/Max,Q Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min
1,0.0,1.0,1117.0,1.0,1117.0,1117.0,0.5,,,0.0,,,,,,,,,,,,,,,,-1.5180229894995567,0.6998808293377133,-0.08930329112720292,-3.148474706421977,,,,,,,,,,,,,,,,
2,163.0,0.0,821.0,1.0,821.0,1938.0,0.4919541999999965,-21.0,-21.0,0.0,,,,,,,,,,,,,,,,-2.405652578063971,0.6237147471281423,-0.7105532272722921,-3.3691179328950627,,,,,,,,,0.25339470000000003,0.06996354,0.40677336,-0.35897204,0.035283737,0.10252844,1.0475135,1.1831225500000001e-05
3,320.0,0.0,782.0,1.0,782.0,2720.0,0.4842905999999932,-21.0,-21.0,0.0,,,,,,,,,,,,,,,,-2.4614277069600043,0.5586658402302739,-0.7105532272722921,-3.354852824180864,,,,,,,,,0.20715186,0.062277785999999995,0.35004243,0.0036477323,0.05950941,0.13284620000000003,0.55984885,1.9053832e-05
4,522.0,0.0,1009.0,1.0,1009.0,3729.0,0.4744023999999889,-19.0,-19.0,0.0,,,,,,,,,,,,,,,,-1.74034851817599,0.8736518980911252,0.29537702481737355,-3.229858453919355,,,,,,,,,0.1964524,0.06919237,0.40447715,0.0016004617,0.08728501,0.21507107,0.96532106,3.7585607e-05
5,673.0,0.0,755.0,1.0,755.0,4484.0,0.4670033999999857,-21.0,-21.0,0.0,,,,,,,,,,,,,,,,-2.5246431129611286,0.5835765895797549,-0.7105532272722921,-3.3699982440767453,,,,,,,,,0.16121916,0.030521521,0.26771998,0.09214279,0.11407282,0.2374467,0.7852985,0.00861873
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 Q/Mean Q/Stdev Q/Max Q/Min Q Values/Mean Q Values/Stdev Q Values/Max Q Values/Min Value Loss/Mean Value Loss/Stdev Value Loss/Max Value Loss/Min
2 1 0.0 1.0 1117.0 1.0 1117.0 1117.0 0.5 0.0 -1.5180229894995567 0.6998808293377133 -0.08930329112720292 -3.148474706421977
3 2 166.0 163.0 0.0 834.0 821.0 1.0 834.0 821.0 1951.0 1938.0 0.4918267999999965 0.4919541999999965 -20.0 -21.0 -20.0 -21.0 0.0 -2.405652578063971 0.6237147471281423 -0.7105532272722921 -3.3691179328950627 -0.049309142 0.25339470000000003 0.05955426 0.06996354 0.11067552 0.40677336 -0.31385273 -0.35897204 0.10965226 0.035283737 0.25779134 0.10252844 0.96019816 1.0475135 1.650419e-05 1.1831225500000001e-05
4 3 343.0 320.0 0.0 883.0 782.0 1.0 883.0 782.0 2834.0 2720.0 0.4831733999999927 0.4842905999999932 -20.0 -21.0 -20.0 -21.0 0.0 -2.4614277069600043 0.5586658402302739 -0.7105532272722921 -3.354852824180864 0.00039612237 0.20715186 0.022137828 0.062277785999999995 0.047817677 0.35004243 -0.057933766 0.0036477323 0.05449706 0.05950941 0.15011412 0.13284620000000003 0.8670572 0.55984885 0.0013089271000000001 1.9053832e-05
5 4 495.0 522.0 0.0 759.0 1009.0 1.0 759.0 1009.0 3593.0 3729.0 0.4757351999999895 0.4744023999999889 -21.0 -19.0 -21.0 -19.0 0.0 -1.74034851817599 0.8736518980911252 0.29537702481737355 -3.229858453919355 -0.013107545 0.1964524 0.014792551000000001 0.06919237 0.02346693 0.40447715 -0.051909205 0.0016004617 0.09606385 0.08728501 0.22936918 0.21507107 0.84131515 0.96532106 0.00357637 3.7585607e-05
6 5 646.0 673.0 0.0 755.0 1.0 755.0 4348.0 4484.0 0.4683361999999863 0.4670033999999857 -21.0 -21.0 0.0 -2.5246431129611286 0.5835765895797549 -0.7105532272722921 -3.3699982440767453 -0.056291025 0.16121916 0.024121637999999997 0.030521521 0.011681341000000001 0.26771998 -0.11741245 0.09214279 0.111964785 0.11407282 0.24955077 0.2374467 0.79120165 0.7852985 0.0038064622999999997 0.00861873