mirror of
https://github.com/gryf/coach.git
synced 2026-01-05 21:34:18 +01:00
6.1 KiB
6.1 KiB
| 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 | 486.0 | 486.0 | 486.0 | 486.0 | 1.0 | 0.0 | 1.027285241237078 | 0.8961037725396955 | 3.502959469093688 | 0.0 | |||||||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 573.0 | 573.0 | 87.0 | 573.0 | 1.0 | 0.0 | 0.2991949731169189 | 0.4147830569909918 | 1.0 | 0.0 | |||||||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 722.0 | 722.0 | 149.0 | 722.0 | 1.0 | 0.0 | 1.089942054123867 | 0.6773639260883686 | 1.9560606270183023 | 0.0 | |||||||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 1057.0 | 1057.0 | 335.0 | 1057.0 | 1.0 | 0.0 | 1.6150170189100268 | 1.2171006279541683 | 4.3034191502088746 | 0.0 | |||||||||||||||||||||
| 6 | 5 | 51.0 | 0.0 | 1260.0 | 1260.0 | 203.0 | 1260.0 | 0.999817300000006 | 5.0 | 55.0 | 0.0 | 0.011210492118170448 | 0.014767014885939737 | 0.05533798784017563 | 0.0001473492011427879 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.05707659599999999 | 0.04158878 | 0.21503627 | 0.013312756 | 1.5742518458459676 | 1.1031375801910266 | 3.252515696371334 | 0.0 | |||||||
| 7 | 6 | 70.0 | 0.0 | 1335.0 | 1335.0 | 75.0 | 1335.0 | 0.9997498000000082 | 2.0 | 15.0 | 0.0 | 0.011414097540852564 | 0.01121910665123708 | 0.029740048572421074 | 0.0004330868541728705 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.058900263 | 0.027915347000000004 | 0.11027232599999999 | 0.02339791 | 0.630055465573955 | 0.7534012288320482 | 1.886384871716129 | 0.0 | |||||||
| 8 | 7 | 91.0 | 0.0 | 1422.0 | 1422.0 | 87.0 | 1422.0 | 0.9996715000000108 | 1.0 | 15.0 | 0.0 | 0.01167219927412502 | 0.013875076164169707 | 0.043948281556367874 | 0.00028215046040713787 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.06262833 | 0.037401546 | 0.14943606 | 0.020271355 | 0.2731692938539037 | 0.40901966584690697 | 1.0 | 0.0 | |||||||
| 9 | 8 | 159.0 | 0.0 | 1693.0 | 1693.0 | 271.0 | 1693.0 | 0.9994276000000188 | 5.0 | 55.0 | 0.0 | 0.008753844233422623 | 0.010620677350002777 | 0.04268157482147217 | 0.00019746257748920468 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.050806154000000006 | 0.03303038 | 0.14730394 | 0.013462662 | 1.3777471984624352 | 0.8115021837176055 | 3.11412900057984 | 0.0 | |||||||
| 10 | 9 | 201.0 | 0.0 | 1861.0 | 1861.0 | 168.0 | 1861.0 | 0.9992764000000238 | 3.0 | 50.0 | 0.0 | 0.005769514246605381 | 0.009300229770420849 | 0.04301084950566292 | 0.00012095135753042996 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.03691972 | 0.028310942000000002 | 0.12708472 | 0.010599906000000001 | 0.9971291228971556 | 0.7740837108535874 | 2.18976824447548 | 0.0 | |||||||
| 11 | 10 | 279.0 | 0.0 | 2172.0 | 2172.0 | 311.0 | 2172.0 | 0.9989965000000329 | 4.0 | 65.0 | 0.0 | 0.009682108745040843 | 0.012429802966425272 | 0.05656500905752183 | 8.809752034721896e-05 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.051116365999999996 | 0.037895918 | 0.16268665 | 0.0067432327 | 1.0234306140936356 | 0.5002579938176909 | 2.1008995427938943 | 0.0 | |||||||
| 12 | 11 | 406.0 | 0.0 | 2681.0 | 2681.0 | 509.0 | 2681.0 | 0.998538400000048 | 9.0 | 320.0 | 0.0 | 0.008329823643989369 | 0.010283429206659646 | 0.0445377342402935 | 0.00011704764619935305 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.04747526 | 0.030370482999999997 | 0.15215631 | 0.009974633 | 1.5487425802799972 | 0.9434112651663112 | 4.0430534797383535 | 0.0 | 0.053110827 | 0.010893389 | 0.063433684 | 0.036038034 | |||
| 13 | 12 | 471.0 | 0.0 | 2941.0 | 2941.0 | 260.0 | 2941.0 | 0.9983044000000558 | 7.0 | 110.0 | 0.0 | 0.009523575568947798 | 0.012773694341856209 | 0.057992663234472275 | 0.00016727412003092468 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.051192068 | 0.032075062 | 0.16018695 | 0.013662121000000001 | 1.9247686125714616 | 1.4763974008694143 | 4.5174296147906645 | 0.0 | |||||||
| 14 | 13 | 506.0 | 0.0 | 3082.0 | 3082.0 | 141.0 | 3082.0 | 0.99817750000006 | 0.0 | 0.0 | 0.0 | 0.008007026730670726 | 0.01029245846308962 | 0.029297087341547005 | 0.0001405462680850178 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.045082795999999994 | 0.03179963 | 0.109106116 | 0.011687999999999999 | 0.0 | 0.0 | 0.0 | 0.0 | |||||||
| 15 | 14 | 569.0 | 0.0 | 3331.0 | 3331.0 | 249.0 | 3331.0 | 0.9979534000000674 | 7.0 | 110.0 | 0.0 | 0.007932257684226516 | 0.009543168465309 | 0.042618278414011 | 0.00011194428952876477 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.045031127000000004 | 0.029050167999999998 | 0.14467546 | 0.009375976999999999 | 2.0098751682981617 | 1.1093871734323564 | 4.000165956499947 | 0.0 | |||||||
| 16 | 15 | 655.0 | 0.0 | 3677.0 | 3677.0 | 346.0 | 3677.0 | 0.9976420000000776 | 0.0 | 0.0 | 0.0 | 0.009127436689342112 | 0.010257305206635236 | 0.03943319246172905 | 0.0002078899706248194 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.05149697 | 0.029421799 | 0.13166036 | 0.014206918 | 0.0 | 0.0 | 0.0 | 0.0 | 0.04757643 | 0.016885458 | 0.07303583 | 0.02113696 | |||
| 17 | 16 | 674.0 | 0.0 | 3753.0 | 3753.0 | 76.0 | 3753.0 | 0.99757360000008 | 1.0 | 10.0 | 0.0 | 0.005484539830879504 | 0.006795569837575163 | 0.0154302716255188 | 0.00017697594012133777 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.036069945 | 0.022439636000000002 | 0.069248274 | 0.009636641 | 0.42667230386804816 | 0.4209997414589432 | 1.0 | 0.0 | |||||||
| 18 | 17 | 723.0 | 0.0 | 3948.0 | 3948.0 | 195.0 | 3948.0 | 0.9973981000000856 | 0.0 | 0.0 | 0.0 | 0.006387538266515511 | 0.010204732097936466 | 0.03978605568408966 | 6.994287832640111e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.03934187 | 0.037892744 | 0.15384565 | 0.0044907904 | 0.0 | 0.0 | 0.0 | 0.0 | |||||||
| 19 | 18 | 754.0 | 0.0 | 4073.0 | 4073.0 | 125.0 | 4073.0 | 0.9972856000000894 | 2.0 | 15.0 | 0.0 | 0.006051351961721066 | 0.007342749165180953 | 0.026289632543921467 | 0.0001778418372850865 | 9.999999999999996e-05 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.04496351 | 0.025081284 | 0.12487566 | 0.011489005 | 0.4379218073475659 | 0.6904045765467619 | 1.886384871716129 | 0.0 | |||||||
| 20 | 19 | 831.0 | 0.0 | 4381.0 | 4381.0 | 308.0 | 4381.0 | 0.9970084000000984 | 4.0 | 90.0 | 0.0 | 0.006579432781262613 | 0.009149961848058668 | 0.03981969878077507 | 9.064121695701032e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.04215214 | 0.03175498 | 0.15315908 | 0.008631183 | 1.0691845626589795 | 0.8498240160885151 | 2.745451683091903 | 0.0 | |||||||
| 21 | 20 | 933.0 | 0.0 | 4789.0 | 4789.0 | 408.0 | 4789.0 | 0.9966412000001106 | 5.0 | 35.0 | 0.0 | 0.007360744663125004 | 0.00991559016300195 | 0.053987301886081696 | 0.00010086009569931777 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.043688238 | 0.031371932000000005 | 0.17327562 | 0.005278009 | 0.9497113318517078 | 0.5665372653893023 | 1.841181516831549 | 0.0 | 0.07077642 | 0.020417793 | 0.11111065 | 0.047004115 |