1
0
mirror of https://github.com/gryf/coach.git synced 2026-04-02 18:13:32 +02:00

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,,,,
2,197.0,0.0,1905.0,1905.0,788.0,1905.0,0.9992908000000232,-21.0,-21.0,0.0,,,,0.0067403961892786675,0.0043218267539128705,0.03104443661868572,4.4621716369874775e-05,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.023866987000000003,0.01743193,0.22815436,0.004472835,-2.4312329564518818,0.5717677860635341,-0.7105532272722921,-3.3662833646890835,,,,
3,436.0,0.0,2862.0,2862.0,957.0,2862.0,0.9984295000000516,-20.0,-20.0,0.0,,,,0.006779984783655944,0.003341004393095993,0.01628851890563965,0.00037204055115580564,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.01701229,0.0063794130000000004,0.042816594000000006,0.0057905857,-1.9651299496437336,0.7810357358559473,-0.3655772928295825,-3.2941461345643885,-0.031879205,0.019740151,-0.0044416133,-0.077873565
4,627.0,0.0,3623.0,3623.0,761.0,3623.0,0.9977446000000744,-21.0,-21.0,0.0,,,,0.006753587473251269,0.003223489523106914,0.014178510755300522,0.0004225387529004365,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.014921344,0.0052625714,0.032878317000000004,0.0076742154,-2.5196481268264272,0.5839729089128289,-0.7105532272722921,-3.3699982440767453,,,,
5,855.0,0.0,4535.0,4535.0,912.0,4535.0,0.9969238000001012,-20.0,-20.0,0.0,,,,0.006566466095376343,0.0032564465770561412,0.01596076600253582,0.00040981321944855154,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.013728661999999999,0.00475778,0.04037358,0.00424472,-1.9480557195901917,0.7908203737498453,-0.21371412100620468,-3.2726053764291825,-0.038136218,0.013395666,-0.016326109,-0.0594768
2,197.0,0.0,1905.0,1905.0,788.0,1905.0,0.9992908000000232,-21.0,-21.0,0.0,,,,0.0061254552800413965,0.0043050134300493936,0.034036897122859955,6.793363718315959e-05,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.024838297000000002,0.026057651,0.35551727,0.007053303,-2.4312329564518818,0.5717677860635341,-0.7105532272722921,-3.3662833646890835,,,,
3,436.0,0.0,2862.0,2862.0,957.0,2862.0,0.9984295000000516,-20.0,-20.0,0.0,,,,0.005806613470321504,0.0030052668817285165,0.014995453879237175,0.00033133718534372747,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.016070435,0.005444049,0.042856682,0.0075193606,-1.9651299496437336,0.7810357358559473,-0.3655772928295825,-3.2941461345643885,0.049539614,0.019873414,0.07862351,0.014469368
4,627.0,0.0,3623.0,3623.0,761.0,3623.0,0.9977446000000744,-21.0,-21.0,0.0,,,,0.006210500930166361,0.0030342874917922576,0.01707890443503857,0.0003939484595321119,0.0002500000000000001,5.421010862427521e-20,0.00025,0.00025,0.014544703,0.0057146824,0.039981294,0.004752383,-2.5196481268264272,0.5839729089128289,-0.7105532272722921,-3.3699982440767453,,,,
5,855.0,0.0,4535.0,4535.0,912.0,4535.0,0.9969238000001012,-20.0,-20.0,0.0,,,,0.005768066168489065,0.0026172456712171143,0.012438178062438965,0.0004492225707508624,0.0002500000000000001,1.0842021724855042e-19,0.00025,0.00025,0.012245178999999998,0.0040054265,0.02887605,0.005628841,-1.9480557195901917,0.7908203737498453,-0.21371412100620468,-3.2726053764291825,0.04762842,0.011995862,0.06981121,0.027042279
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 0.9992908000000232 -21.0 -21.0 0.0 0.0067403961892786675 0.0061254552800413965 0.0043218267539128705 0.0043050134300493936 0.03104443661868572 0.034036897122859955 4.4621716369874775e-05 6.793363718315959e-05 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.023866987000000003 0.024838297000000002 0.01743193 0.026057651 0.22815436 0.35551727 0.004472835 0.007053303 -2.4312329564518818 0.5717677860635341 -0.7105532272722921 -3.3662833646890835
4 3 436.0 0.0 2862.0 2862.0 957.0 2862.0 0.9984295000000516 -20.0 -20.0 0.0 0.006779984783655944 0.005806613470321504 0.003341004393095993 0.0030052668817285165 0.01628851890563965 0.014995453879237175 0.00037204055115580564 0.00033133718534372747 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.01701229 0.016070435 0.0063794130000000004 0.005444049 0.042816594000000006 0.042856682 0.0057905857 0.0075193606 -1.9651299496437336 0.7810357358559473 -0.3655772928295825 -3.2941461345643885 -0.031879205 0.049539614 0.019740151 0.019873414 -0.0044416133 0.07862351 -0.077873565 0.014469368
5 4 627.0 0.0 3623.0 3623.0 761.0 3623.0 0.9977446000000744 -21.0 -21.0 0.0 0.006753587473251269 0.006210500930166361 0.003223489523106914 0.0030342874917922576 0.014178510755300522 0.01707890443503857 0.0004225387529004365 0.0003939484595321119 0.0002500000000000001 5.421010862427521e-20 0.00025 0.00025 0.014921344 0.014544703 0.0052625714 0.0057146824 0.032878317000000004 0.039981294 0.0076742154 0.004752383 -2.5196481268264272 0.5839729089128289 -0.7105532272722921 -3.3699982440767453
6 5 855.0 0.0 4535.0 4535.0 912.0 4535.0 0.9969238000001012 -20.0 -20.0 0.0 0.006566466095376343 0.005768066168489065 0.0032564465770561412 0.0026172456712171143 0.01596076600253582 0.012438178062438965 0.00040981321944855154 0.0004492225707508624 0.0002500000000000001 1.0842021724855042e-19 0.00025 0.00025 0.013728661999999999 0.012245178999999998 0.00475778 0.0040054265 0.04037358 0.02887605 0.00424472 0.005628841 -1.9480557195901917 0.7908203737498453 -0.21371412100620468 -3.2726053764291825 -0.038136218 0.04762842 0.013395666 0.011995862 -0.016326109 0.06981121 -0.0594768 0.027042279