gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-04-02 18:13:32 +02:00
Code Issues Projects Releases Wiki Activity

trace tests update

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

8
rl_coach/traces/Atari_DDQN_with_PER_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,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,,,,
2,197.0,0.0,1905.0,1905.0,788.0,1905.0,0.9992198800000168,-21.0,-21.0,0.0,,,,0.0064866334039760465,0.004131804922553068,0.03104443661868572,1.4448891306528823e-05,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.03878765,0.023484444,0.22815436,0.00323429,-2.4312329564518818,0.5717677860635341,-0.7105532272722921,-3.3662833646890835,,,,
3,436.0,0.0,2862.0,2862.0,957.0,2862.0,0.9982724500000376,-20.0,-20.0,0.0,,,,0.005787130516174904,0.00260959432086106,0.01427764445543289,0.0001548390282550827,6.250000000000003e-05,2.7105054312137605e-20,6.25e-05,6.25e-05,0.028759224,0.011704876000000001,0.07163235,0.008223475,-1.9651299496437336,0.7810357358559473,-0.3655772928295825,-3.2941461345643885,-0.16823806,0.05095485599999999,-0.08356075,-0.26015088
4,627.0,0.0,3623.0,3623.0,761.0,3623.0,0.997519060000054,-21.0,-21.0,0.0,,,,0.005963045392452745,0.0028514600960427012,0.014360946603119372,2.424295598757453e-05,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.027299996,0.012375978999999999,0.07347562,0.0030203340000000004,-2.5196481268264272,0.5839729089128289,-0.7105532272722921,-3.3699982440767453,,,,
5,855.0,0.0,4535.0,4535.0,912.0,4535.0,0.9966161800000736,-20.0,-20.0,0.0,,,,0.006235880403357697,0.002686495318714779,0.015876490622758862,0.00016267428873106837,6.250000000000003e-05,2.7105054312137605e-20,6.25e-05,6.25e-05,0.028169753,0.01084809,0.07740243,0.011433218,-1.9480557195901917,0.7908203737498453,-0.21371412100620468,-3.2726053764291825,-0.19339468,0.031096203,-0.15218829999999997,-0.26763937
2,197.0,0.0,1905.0,1905.0,788.0,1905.0,0.9992198800000168,-21.0,-21.0,0.0,,,,0.008022314603535016,0.0045835976267830465,0.034036897122859955,4.404132778290659e-05,6.250000000000001e-05,1.3552527156068802e-20,6.25e-05,6.25e-05,0.04622123400000001,0.03147308,0.35551727,0.0068541886,-2.4312329564518818,0.5717677860635341,-0.7105532272722921,-3.3662833646890835,,,,
3,436.0,0.0,2861.0,2861.0,956.0,2861.0,0.9982734400000376,-20.0,-20.0,0.0,,,,0.007125079098864356,0.0033463100786013263,0.02057763934135437,6.804851000197232e-05,6.250000000000003e-05,2.7105054312137605e-20,6.25e-05,6.25e-05,0.028711626,0.013181531000000002,0.08534362,0.005308075,-1.9661750356661605,0.7201571479030581,-0.2377786744047345,-3.3208045867789826,-0.110634394,0.06718283,-0.021104777,-0.22330762
4,678.0,0.0,3827.0,3827.0,966.0,3827.0,0.9973171000000582,-19.0,-19.0,0.0,,,,0.005711167145360257,0.002484417648740395,0.015254315920174122,6.606345414184034e-05,6.250000000000003e-05,2.7105054312137605e-20,6.25e-05,6.25e-05,0.021287484,0.012238965,0.09981554,0.007149023000000001,-1.7559525724754523,0.8941220204944008,0.35366714208714395,-3.334054446646881,,,,
5,886.0,0.0,4660.0,4660.0,833.0,4660.0,0.996492430000076,-21.0,-21.0,0.0,,,,0.005441138387071148,0.002467626446986541,0.011788716539740562,0.000472158775664866,6.250000000000003e-05,2.7105054312137605e-20,6.25e-05,6.25e-05,0.015550702,0.0050054654,0.037898443999999996,0.006809624,-2.3374918938861518,0.5767458576234249,-0.7105532272722921,-3.359993917983808,-0.009537455,0.020503985,0.035534262999999996,-0.04081138
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 2 197.0 0.0 1905.0 1905.0 788.0 1905.0 0.9992198800000168 -21.0 -21.0 0.0 0.0064866334039760465 0.008022314603535016 0.004131804922553068 0.0045835976267830465 0.03104443661868572 0.034036897122859955 1.4448891306528823e-05 4.404132778290659e-05 6.250000000000001e-05 1.3552527156068802e-20 6.25e-05 6.25e-05 0.03878765 0.04622123400000001 0.023484444 0.03147308 0.22815436 0.35551727 0.00323429 0.0068541886 -2.4312329564518818 0.5717677860635341 -0.7105532272722921 -3.3662833646890835
4 3 436.0 0.0 2862.0 2861.0 2862.0 2861.0 957.0 956.0 2862.0 2861.0 0.9982724500000376 0.9982734400000376 -20.0 -20.0 0.0 0.005787130516174904 0.007125079098864356 0.00260959432086106 0.0033463100786013263 0.01427764445543289 0.02057763934135437 0.0001548390282550827 6.804851000197232e-05 6.250000000000003e-05 2.7105054312137605e-20 6.25e-05 6.25e-05 0.028759224 0.028711626 0.011704876000000001 0.013181531000000002 0.07163235 0.08534362 0.008223475 0.005308075 -1.9651299496437336 -1.9661750356661605 0.7810357358559473 0.7201571479030581 -0.3655772928295825 -0.2377786744047345 -3.2941461345643885 -3.3208045867789826 -0.16823806 -0.110634394 0.05095485599999999 0.06718283 -0.08356075 -0.021104777 -0.26015088 -0.22330762
5 4 627.0 678.0 0.0 3623.0 3827.0 3623.0 3827.0 761.0 966.0 3623.0 3827.0 0.997519060000054 0.9973171000000582 -21.0 -19.0 -21.0 -19.0 0.0 0.005963045392452745 0.005711167145360257 0.0028514600960427012 0.002484417648740395 0.014360946603119372 0.015254315920174122 2.424295598757453e-05 6.606345414184034e-05 6.250000000000001e-05 6.250000000000003e-05 1.3552527156068802e-20 2.7105054312137605e-20 6.25e-05 6.25e-05 0.027299996 0.021287484 0.012375978999999999 0.012238965 0.07347562 0.09981554 0.0030203340000000004 0.007149023000000001 -2.5196481268264272 -1.7559525724754523 0.5839729089128289 0.8941220204944008 -0.7105532272722921 0.35366714208714395 -3.3699982440767453 -3.334054446646881
6 5 855.0 886.0 0.0 4535.0 4660.0 4535.0 4660.0 912.0 833.0 4535.0 4660.0 0.9966161800000736 0.996492430000076 -20.0 -21.0 -20.0 -21.0 0.0 0.006235880403357697 0.005441138387071148 0.002686495318714779 0.002467626446986541 0.015876490622758862 0.011788716539740562 0.00016267428873106837 0.000472158775664866 6.250000000000003e-05 2.7105054312137605e-20 6.25e-05 6.25e-05 0.028169753 0.015550702 0.01084809 0.0050054654 0.07740243 0.037898443999999996 0.011433218 0.006809624 -1.9480557195901917 -2.3374918938861518 0.7908203737498453 0.5767458576234249 -0.21371412100620468 -0.7105532272722921 -3.2726053764291825 -3.359993917983808 -0.19339468 -0.009537455 0.031096203 0.020503985 -0.15218829999999997 0.035534262999999996 -0.26763937 -0.04081138