1
0
mirror of https://github.com/gryf/coach.git synced 2026-03-16 14:43:36 +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,,,,3.9305681682214506,0.0009982327410686944,3.9316465854644775,3.926915407180786,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0018689651999999998,0.0020046625,0.012255268,0.0008047835000000001,-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,,,,3.929541920240109,0.0010681346138543732,3.930777311325073,3.9228343963623047,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0012420595,0.001847766,0.013259928999999998,0.0005541933400000001,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,0.029271987701456326,0.007044414085294216,0.04094065204262795,0.022607963532209983
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,3.9289580902715366,0.0009148473718069287,3.92997932434082,3.926001310348511,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0010492479,0.0020559301999999997,0.015287617,0.00028366325,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,0.031816515512765015,0.0037668773678035884,0.03839177079498832,0.027437280490995003
5,892.0,0.0,4684.0,4684.0,901.0,4684.0,0.9964686700000768,-20.0,-20.0,0.0,,,,3.9287068123287625,0.0009553953918798189,3.929911375045776,3.924695730209351,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0007680645,0.0015440129,0.014315132,0.00020842048999999998,-2.012872425274268,0.6709095073776362,-0.4256446851738544,-3.2469842373013775,0.03543573763842443,0.004500463100191639,0.0407443653792148,0.024707648903132096
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,3.9304792799600734,0.0010089336974329131,3.931626558303833,3.92692494392395,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0020478016,0.0020630334,0.012544215,0.00089145615,-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,,,,3.929040307035813,0.0010817403254347628,3.9303982257843018,3.922320127487183,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.0013938454,0.0020394863,0.01589611,0.0005865627,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,0.06064815086623099,0.017702449170361085,0.09529060125351008,0.03914397135377001
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,3.928387508617611,0.000912089578133192,3.9293906688690186,3.925499677658081,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.0011918317,0.0023538542000000003,0.01751554,0.00031032125,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,0.06327697044859387,0.00742494439575548,0.0744991898536688,0.055326233059168416
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,3.9282448422908782,0.0009522609916870672,3.929300546646118,3.924246072769165,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.00093484356,0.0019195807,0.016940815,0.00020796485,-2.406465837413259,0.5636980823469648,-0.7105532272722921,-3.36383697254212,0.0616140041810777,0.007093012206363309,0.07764012068510129,0.048625472933054525
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 3.9305681682214506 3.9304792799600734 0.0009982327410686944 0.0010089336974329131 3.9316465854644775 3.931626558303833 3.926915407180786 3.92692494392395 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.0018689651999999998 0.0020478016 0.0020046625 0.0020630334 0.012255268 0.012544215 0.0008047835000000001 0.00089145615 -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 3.929541920240109 3.929040307035813 0.0010681346138543732 0.0010817403254347628 3.930777311325073 3.9303982257843018 3.9228343963623047 3.922320127487183 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.0012420595 0.0013938454 0.001847766 0.0020394863 0.013259928999999998 0.01589611 0.0005541933400000001 0.0005865627 -2.320394201181889 0.6047235028955231 -0.7105532272722921 -3.350537576335216 0.029271987701456326 0.06064815086623099 0.007044414085294216 0.017702449170361085 0.04094065204262795 0.09529060125351008 0.022607963532209983 0.03914397135377001
5 4 667.0 0.0 3783.0 3783.0 1015.0 3783.0 0.9973606600000572 -20.0 -20.0 0.0 3.9289580902715366 3.928387508617611 0.0009148473718069287 0.000912089578133192 3.92997932434082 3.9293906688690186 3.926001310348511 3.925499677658081 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.0010492479 0.0011918317 0.0020559301999999997 0.0023538542000000003 0.015287617 0.01751554 0.00028366325 0.00031032125 -1.7531357837449677 0.7448577440634202 -0.1288331810939122 -3.2971074888190803 0.031816515512765015 0.06327697044859387 0.0037668773678035884 0.00742494439575548 0.03839177079498832 0.0744991898536688 0.027437280490995003 0.055326233059168416
6 5 892.0 867.0 0.0 4684.0 4585.0 4684.0 4585.0 901.0 802.0 4684.0 4585.0 0.9964686700000768 0.9965666800000744 -20.0 -21.0 -20.0 -21.0 0.0 3.9287068123287625 3.9282448422908782 0.0009553953918798189 0.0009522609916870672 3.929911375045776 3.929300546646118 3.924695730209351 3.924246072769165 0.0002500000000000001 1.0842021724855042e-19 5.421010862427521e-20 0.00025 0.00025 0.0007680645 0.00093484356 0.0015440129 0.0019195807 0.014315132 0.016940815 0.00020842048999999998 0.00020796485 -2.012872425274268 -2.406465837413259 0.6709095073776362 0.5636980823469648 -0.4256446851738544 -0.7105532272722921 -3.2469842373013775 -3.36383697254212 0.03543573763842443 0.0616140041810777 0.004500463100191639 0.007093012206363309 0.0407443653792148 0.07764012068510129 0.024707648903132096 0.048625472933054525