gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-04-10 15:13:40 +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

12
rl_coach/traces/Atari_A3C_LSTM_pong/trace.csv
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,Advantages/Mean,Advantages/Stdev,Advantages/Max,Advantages/Min,Values/Mean,Values/Stdev,Values/Max,Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min,Policy Loss/Mean,Policy Loss/Stdev,Policy Loss/Max,Policy Loss/Min
1,0.0,1.0,772.0,1.0,772.0,772.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,821.0,1.0,821.0,1593.0,0.0,,,0.0,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
3,47.0,0.0,960.0,1.0,960.0,2553.0,0.0,-20.0,-20.0,0.0,,,,,,,,,,,,1.1341655000000002,1.3580534,5.892931,0.0023950292,1.7183144000000001,0.11223783,1.7917048999999998,1.2778816000000002,0.04575298835242915,0.4587136251645712,1.7850174903869631,-1.000868558883667,-2.1548557,1.8245186999999998,0.0046853945000000004,-5.0325212,0.2002191,0.18291572,0.6043339,3.6701476e-06,0.053236503,0.61648566,1.385742,-1.489837
4,88.0,0.0,802.0,1.0,802.0,3355.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.3043066,0.5805045999999999,3.1598291,0.34928647,0.9577253000000001,0.112086765,1.7206139999999999,0.84311396,0.06997428238391876,0.3966030207984067,0.8193864822387695,-0.957106113433838,-3.1394837000000004,0.53956544,-2.564023,-4.4771279999999996,0.10647102,0.06113237,0.296035,0.04434104,0.07748371,0.32128,0.67603266,-0.5327814999999999
5,129.0,0.0,815.0,1.0,815.0,4170.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.392543,0.8525935,3.4830544000000003,0.1963895,0.90076345,0.08584659,1.5318372,0.77205926,-0.06867338344454765,0.4191816209286624,0.5097661018371582,-0.9805699586868286,-2.2598412,0.26356682,-1.9182776999999998,-2.800033,0.09539665,0.07594069999999999,0.25968197,0.031170906,-0.07717073,0.33031166,0.287632,-0.91986656
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,Advantages/Mean,Advantages/Stdev,Advantages/Max,Advantages/Min,Values/Mean,Values/Stdev,Values/Max,Values/Min,Value Loss/Mean,Value Loss/Stdev,Value Loss/Max,Value Loss/Min,Policy Loss/Mean,Policy Loss/Stdev,Policy Loss/Max,Policy Loss/Min
1,0.0,1.0,772.0,1.0,772.0,772.0,0.0,,,0.0,,,,,,,,,,,,,,,,-2.437332009209832,0.5666975756966289,-0.7105532272722921,-3.364332223379411,,,,,,,,,,,,,,,,,,,,
2,0.0,1.0,821.0,1.0,821.0,1593.0,0.0,,,0.0,,,,,,,,,,,,,,,,-2.3375427452853184,0.562882024173797,-0.7105532272722921,-3.3225778431943085,,,,,,,,,,,,,,,,,,,,
3,38.0,0.0,763.0,1.0,763.0,2356.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.2098866000000001,1.449215,5.3609241999999995,0.00244356,-2.5178046202451694,0.5843148195084643,-0.7105532272722921,-3.3699982440767453,1.7662544999999998,0.03266678,1.7917435000000002,1.6590552,-0.09202062882188904,0.4331878633448028,0.8984384536743164,-0.9984065890312196,-1.7017021,1.594185,-0.041688699999999995,-4.9379349999999995,0.22111915,0.19444092,0.59284925,2.0590694e-05,-0.1670907,0.6072369000000001,0.91119975,-1.4746135
4,75.0,0.0,740.0,1.0,740.0,3096.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.9744401999999999,0.8914412,4.1053777,0.54077625,-2.533184641659896,0.5861942513660167,-0.7105532272722921,-3.3699982440767453,1.1498803,0.17261624,1.7622604,0.99270844,0.19542027049594451,0.4488243660076464,0.9995923042297364,-0.9500741958618164,-5.264807,0.15003455,-4.995072,-5.481164,0.22140607,0.09454554,0.4738923,0.1269643,0.24964908,0.42948514,0.77320266,-0.62486225
5,113.0,0.0,755.0,1.0,755.0,3851.0,0.0,-21.0,-21.0,0.0,,,,,,,,,,,,1.6745409,0.7766086999999999,3.4373443,0.42763662,-2.5246431129611286,0.5835765895797549,-0.7105532272722921,-3.3699982440767453,0.8715389000000001,0.11778103,1.3657371999999999,0.70607877,0.02502031455168853,0.4342484515718581,0.8662590980529785,-0.9686682224273682,-3.4500135999999997,0.4302874,-3.1447627999999996,-4.761848400000001,0.10419229,0.05407177,0.22493912,0.052366237999999996,0.030020599999999995,0.3442417,0.68716383,-0.674335
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 Advantages/Mean Advantages/Stdev Advantages/Max Advantages/Min Values/Mean Values/Stdev Values/Max Values/Min Value Loss/Mean Value Loss/Stdev Value Loss/Max Value Loss/Min Policy Loss/Mean Policy Loss/Stdev Policy Loss/Max Policy Loss/Min
2 1 0.0 1.0 772.0 1.0 772.0 772.0 0.0 0.0 -2.437332009209832 0.5666975756966289 -0.7105532272722921 -3.364332223379411
3 2 0.0 1.0 821.0 1.0 821.0 1593.0 0.0 0.0 -2.3375427452853184 0.562882024173797 -0.7105532272722921 -3.3225778431943085
4 3 47.0 38.0 0.0 960.0 763.0 1.0 960.0 763.0 2553.0 2356.0 0.0 -20.0 -21.0 -20.0 -21.0 0.0 1.1341655000000002 1.2098866000000001 1.3580534 1.449215 5.892931 5.3609241999999995 0.0023950292 0.00244356 -2.5178046202451694 0.5843148195084643 -0.7105532272722921 -3.3699982440767453 1.7183144000000001 1.7662544999999998 0.11223783 0.03266678 1.7917048999999998 1.7917435000000002 1.2778816000000002 1.6590552 0.04575298835242915 -0.09202062882188904 0.4587136251645712 0.4331878633448028 1.7850174903869631 0.8984384536743164 -1.000868558883667 -0.9984065890312196 -2.1548557 -1.7017021 1.8245186999999998 1.594185 0.0046853945000000004 -0.041688699999999995 -5.0325212 -4.9379349999999995 0.2002191 0.22111915 0.18291572 0.19444092 0.6043339 0.59284925 3.6701476e-06 2.0590694e-05 0.053236503 -0.1670907 0.61648566 0.6072369000000001 1.385742 0.91119975 -1.489837 -1.4746135
5 4 88.0 75.0 0.0 802.0 740.0 1.0 802.0 740.0 3355.0 3096.0 0.0 -21.0 -21.0 0.0 1.3043066 1.9744401999999999 0.5805045999999999 0.8914412 3.1598291 4.1053777 0.34928647 0.54077625 -2.533184641659896 0.5861942513660167 -0.7105532272722921 -3.3699982440767453 0.9577253000000001 1.1498803 0.112086765 0.17261624 1.7206139999999999 1.7622604 0.84311396 0.99270844 0.06997428238391876 0.19542027049594451 0.3966030207984067 0.4488243660076464 0.8193864822387695 0.9995923042297364 -0.957106113433838 -0.9500741958618164 -3.1394837000000004 -5.264807 0.53956544 0.15003455 -2.564023 -4.995072 -4.4771279999999996 -5.481164 0.10647102 0.22140607 0.06113237 0.09454554 0.296035 0.4738923 0.04434104 0.1269643 0.07748371 0.24964908 0.32128 0.42948514 0.67603266 0.77320266 -0.5327814999999999 -0.62486225
6 5 129.0 113.0 0.0 815.0 755.0 1.0 815.0 755.0 4170.0 3851.0 0.0 -21.0 -21.0 0.0 1.392543 1.6745409 0.8525935 0.7766086999999999 3.4830544000000003 3.4373443 0.1963895 0.42763662 -2.5246431129611286 0.5835765895797549 -0.7105532272722921 -3.3699982440767453 0.90076345 0.8715389000000001 0.08584659 0.11778103 1.5318372 1.3657371999999999 0.77205926 0.70607877 -0.06867338344454765 0.02502031455168853 0.4191816209286624 0.4342484515718581 0.5097661018371582 0.8662590980529785 -0.9805699586868286 -0.9686682224273682 -2.2598412 -3.4500135999999997 0.26356682 0.4302874 -1.9182776999999998 -3.1447627999999996 -2.800033 -4.761848400000001 0.09539665 0.10419229 0.07594069999999999 0.05407177 0.25968197 0.22493912 0.031170906 0.052366237999999996 -0.07717073 0.030020599999999995 0.33031166 0.3442417 0.287632 0.68716383 -0.91986656 -0.674335