gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-04-20 23:41:24 +02:00
Code Issues Projects Releases Wiki Activity

new traces

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files
rl_coach/traces/Atari_Dueling_DDQN_pong/trace.csv
+6 -6
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,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,,,,,,,,,,,,,,,,,,,
2,205.0,0.0,1937.0,1937.0,820.0,1937.0,0.9991882000000176,-21.0,-21.0,0.0,,,,0.014763841533212831,0.013646937264058223,0.06725655496120453,2.0758947357535362e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.17952479999999998,0.13626544,0.9860897,0.0053134440000000005,,,,
3,413.0,0.0,2768.0,2768.0,831.0,2768.0,0.9983655100000356,-21.0,-21.0,0.0,,,,0.012111850191891229,0.013912744765592264,0.08914861083030699,1.7985148588195443e-05,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.057201855,0.04205291,0.26596984,0.0031672046,-0.04456665,0.009031756,-0.031443898,-0.059377108
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,0.013269104183936587,0.013449185914245043,0.07771021127700806,1.3188657248974778e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.098453455,0.109315164,0.9814589,0.0024465397,-0.008853295,0.009689603,0.0003574537,-0.028319128
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,0.01383970570535894,0.013677503957050816,0.0817062109708786,5.106279422761872e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.108334474,0.0749226,0.40531653,0.006287096,-0.018026425,0.047121227,0.035217006,-0.070681214
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,,,,0.012080228037293859,0.012880618698819657,0.0570480152964592,6.0431495512602844e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.11952291400000001,0.07146234,0.36756375,0.010074032,-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,,,,0.01158361631276578,0.013744570346194931,0.08763836324214935,1.3804149602947293e-05,0.00010000000000000003,2.7105054312137605e-20,0.0001,0.0001,0.06339365,0.045202352,0.3223001,0.0032100508,-2.320394201181889,0.6047235028955231,-0.7105532272722921,-3.350537576335216,-0.05946256,0.0071155433999999995,-0.048334688,-0.071884885
4,667.0,0.0,3783.0,3783.0,1015.0,3783.0,0.9973606600000572,-20.0,-20.0,0.0,,,,0.011621401665309342,0.011997949188739438,0.047944877296686166,1.704720125417225e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.061558142,0.038367815,0.19478188,0.0040269657,-1.7531357837449677,0.7448577440634202,-0.1288331810939122,-3.2971074888190803,-0.06831099,0.009751156,-0.05039859,-0.08132484599999999
5,867.0,0.0,4585.0,4585.0,802.0,4585.0,0.9965666800000744,-21.0,-21.0,0.0,,,,0.011371218297681479,0.01218400722584616,0.059932790696620934,1.6583624528720975e-05,0.00010000000000000002,1.3552527156068802e-20,0.0001,0.0001,0.06680599999999999,0.04423054,0.21688205,0.0034790002000000004,-2.406465837413259,0.5636980823469648,-0.7105532272722921,-3.36383697254212,-0.048574314,0.009597616,-0.036119547,-0.06607885
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 0.014763841533212831 0.012080228037293859 0.013646937264058223 0.012880618698819657 0.06725655496120453 0.0570480152964592 2.0758947357535362e-05 6.0431495512602844e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.17952479999999998 0.11952291400000001 0.13626544 0.07146234 0.9860897 0.36756375 0.0053134440000000005 0.010074032 -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 0.012111850191891229 0.01158361631276578 0.013912744765592264 0.013744570346194931 0.08914861083030699 0.08763836324214935 1.7985148588195443e-05 1.3804149602947293e-05 0.00010000000000000003 2.7105054312137605e-20 0.0001 0.0001 0.057201855 0.06339365 0.04205291 0.045202352 0.26596984 0.3223001 0.0031672046 0.0032100508 -2.320394201181889 0.6047235028955231 -0.7105532272722921 -3.350537576335216 -0.04456665 -0.05946256 0.009031756 0.0071155433999999995 -0.031443898 -0.048334688 -0.059377108 -0.071884885
5 4 667.0 0.0 3783.0 3783.0 1015.0 3783.0 0.9973606600000572 -20.0 -20.0 0.0 0.013269104183936587 0.011621401665309342 0.013449185914245043 0.011997949188739438 0.07771021127700806 0.047944877296686166 1.3188657248974778e-05 1.704720125417225e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.098453455 0.061558142 0.109315164 0.038367815 0.9814589 0.19478188 0.0024465397 0.0040269657 -1.7531357837449677 0.7448577440634202 -0.1288331810939122 -3.2971074888190803 -0.008853295 -0.06831099 0.009689603 0.009751156 0.0003574537 -0.05039859 -0.028319128 -0.08132484599999999
6 5 867.0 0.0 4585.0 4585.0 802.0 4585.0 0.9965666800000744 -21.0 -21.0 0.0 0.01383970570535894 0.011371218297681479 0.013677503957050816 0.01218400722584616 0.0817062109708786 0.059932790696620934 5.106279422761872e-05 1.6583624528720975e-05 0.00010000000000000002 1.3552527156068802e-20 0.0001 0.0001 0.108334474 0.06680599999999999 0.0749226 0.04423054 0.40531653 0.21688205 0.006287096 0.0034790002000000004 -2.406465837413259 0.5636980823469648 -0.7105532272722921 -3.36383697254212 -0.018026425 -0.048574314 0.047121227 0.009597616 0.035217006 -0.036119547 -0.070681214 -0.06607885