mirror of
https://github.com/gryf/coach.git
synced 2026-01-27 02:25:45 +01:00
7.8 KiB
7.8 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 | 0.011318223166074629 | 0.01535703511542496 | 0.059677407145500176 | 5.930410770815797e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.043334834 | 0.041464914 | 0.18977661 | 0.005382849 | 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 | 0.01159630703133237 | 0.011785072587684268 | 0.03072714060544968 | 0.0002724393270909786 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.04802381 | 0.02912287 | 0.10194262 | 0.016022025 | 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 | 0.011623838611523666 | 0.014016462654731877 | 0.04371790960431099 | 0.00030537351267412305 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.0527369 | 0.033248365 | 0.12047498 | 0.017427322 | 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 | 0.00871512985335656 | 0.010619126303001072 | 0.0428631566464901 | 0.000175730005139485 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.04345967 | 0.02999792 | 0.12813029 | 0.010443105 | 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 | 0.005778238893808086 | 0.009339010441951916 | 0.04285115376114845 | 0.00013575046614278108 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.031826954 | 0.025600772 | 0.10499059 | 0.010177706 | 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 | 0.009664556885325463 | 0.012497959675064443 | 0.057257801294326775 | 6.420304998755455e-05 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.044185962999999995 | 0.03414627 | 0.13320610000000002 | 0.0049573337 | 1.0234306140936356 | 0.5002579938176909 | 2.1008995427938943 | 0.0 | |||||||
| 12 | 11 | 440.0 | 0.0 | 2815.0 | 2815.0 | 643.0 | 2815.0 | 0.998417800000052 | 10.0 | 335.0 | 0.0 | 0.008570355002374984 | 0.010485077345910785 | 0.04492178559303284 | 0.00012292989413253966 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.043720617999999996 | 0.029798117000000002 | 0.12859769 | 0.009503558 | 1.3803392321717662 | 1.096111017851517 | 4.070269499186656 | 0.0 | 0.023210553 | 0.012247342 | 0.045721915 | 0.0085688755 | |||
| 13 | 12 | 458.0 | 0.0 | 2888.0 | 2888.0 | 73.0 | 2888.0 | 0.9983521000000544 | 2.0 | 45.0 | 0.0 | 0.009655450009934915 | 0.011082975101418072 | 0.04116561636328697 | 0.0003870627551805228 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.048649742999999995 | 0.025572757999999998 | 0.108848594 | 0.019374162 | 0.6193548093911652 | 0.6855072221487064 | 1.8179069375972308 | 0.0 | |||||||
| 14 | 13 | 478.0 | 0.0 | 2969.0 | 2969.0 | 81.0 | 2969.0 | 0.9982792000000568 | 0.0 | 0.0 | 0.0 | 0.006699338816542878 | 0.008218773784238768 | 0.02777592279016972 | 0.00018887671467382458 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.040117297 | 0.025047436 | 0.09513988 | 0.013411026999999999 | 0.0 | 0.0 | 0.0 | 0.0 | |||||||
| 15 | 14 | 532.0 | 0.0 | 3183.0 | 3183.0 | 214.0 | 3183.0 | 0.998086600000063 | 4.0 | 50.0 | 0.0 | 0.0068422133381655275 | 0.009747521796643477 | 0.03026608750224113 | 0.00010871817357838154 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.03618256 | 0.029936017000000002 | 0.10048853599999999 | 0.007838896 | 1.1449070106363344 | 0.7411479181777391 | 2.363283716034233 | 0.0 | |||||||
| 16 | 15 | 551.0 | 0.0 | 3262.0 | 3262.0 | 79.0 | 3262.0 | 0.9980155000000652 | 2.0 | 15.0 | 0.0 | 0.008475733149680309 | 0.01248567219959208 | 0.04252954199910164 | 0.00013467879034578797 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.040572915 | 0.036634777 | 0.13019583 | 0.009758638 | 0.7209514730836505 | 0.7680412970584659 | 1.8953382542587165 | 0.0 | |||||||
| 17 | 16 | 626.0 | 0.0 | 3560.0 | 3560.0 | 298.0 | 3560.0 | 0.9977473000000742 | 6.0 | 145.0 | 0.0 | 0.009113661061918892 | 0.010068202774623678 | 0.039926819503307336 | 0.0002249046228826046 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.047559105 | 0.029203411000000002 | 0.11576410000000001 | 0.013620954 | 1.2555763711101595 | 0.9240906493644656 | 3.083943769311809 | 0.0 | 0.0077286431999999995 | 0.013353446000000001 | 0.034945004 | -0.0063670003 | |||
| 18 | 17 | 684.0 | 0.0 | 3794.0 | 3794.0 | 234.0 | 3794.0 | 0.9975367000000812 | 4.0 | 45.0 | 0.0 | 0.008931795351411987 | 0.010972572222718682 | 0.045623280107975006 | 0.000198069799807854 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.04554412 | 0.030431528 | 0.12100394 | 0.013383543000000001 | 1.2202506793333543 | 0.9239408887260988 | 2.9738245545408817 | 0.0 | 0.043180794 | 0.017604817 | 0.06408879 | 0.012553655 | |||
| 19 | 18 | 763.0 | 0.0 | 4108.0 | 4108.0 | 314.0 | 4108.0 | 0.9972541000000904 | 3.0 | 30.0 | 0.0 | 0.00774911735593028 | 0.009318798210356413 | 0.039029747247695916 | 0.00011983128933934498 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.045264978 | 0.031311095 | 0.14044714 | 0.0088686375 | 0.883333156456609 | 0.7108712685048966 | 2.6822034344079513 | 0.0 | |||||||
| 20 | 19 | 802.0 | 0.0 | 4264.0 | 4264.0 | 156.0 | 4264.0 | 0.9971137000000949 | 3.0 | 55.0 | 0.0 | 0.008181322184846533 | 0.010204339807983949 | 0.03963562101125717 | 0.00011176375119248404 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.045041375 | 0.03236003 | 0.13761885 | 0.005883736999999999 | 0.8928330243328357 | 0.7520539156556657 | 2.307797210601436 | 0.0 | |||||||
| 21 | 20 | 844.0 | 0.0 | 4433.0 | 4433.0 | 169.0 | 4433.0 | 0.9969616000001 | 2.0 | 30.0 | 0.0 | 0.007086637573853034 | 0.00824327512493469 | 0.028365319594740868 | 9.797862003324552e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.039589286 | 0.027504257999999997 | 0.09817823 | 0.009308107 | 0.7427821380444694 | 0.5599617203743822 | 1.7323033696543972 | 0.0 | |||||||
| 22 | 21 | 863.0 | 0.0 | 4509.0 | 4509.0 | 76.0 | 4509.0 | 0.9968932000001024 | 2.0 | 15.0 | 0.0 | 0.008739061410060936 | 0.01230256416501932 | 0.04154407978057861 | 0.00027482287259772415 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.045247022000000005 | 0.030827425 | 0.121021785 | 0.015011917 | 0.6418633989324495 | 0.7553819304493669 | 1.886384871716129 | 0.0 | 0.058504984 | 0.023636952000000003 | 0.09839016 | 0.018560277 | |||
| 23 | 22 | 906.0 | 0.0 | 4682.0 | 4682.0 | 173.0 | 4682.0 | 0.9967375000001074 | 2.0 | 35.0 | 0.0 | 0.005804569350466197 | 0.007566970748929549 | 0.029328102245926857 | 6.812938954681158e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.034811117 | 0.028401693 | 0.12241203 | 0.0060415830000000005 | 0.3476715604560838 | 0.6137927888256194 | 1.8345137614500877 | 0.0 | |||||||
| 24 | 23 | 950.0 | 0.0 | 4857.0 | 4857.0 | 175.0 | 4857.0 | 0.9965800000001126 | 1.0 | 5.0 | 0.0 | 0.009173317925075914 | 0.010788118668524528 | 0.03016231954097748 | 0.00014141239807941017 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.047155652 | 0.031286374 | 0.099857986 | 0.0096386755 | 0.4300921794892178 | 0.29086756478918485 | 1.0 | 0.0 | |||||||
| 25 | 24 | 979.0 | 0.0 | 4971.0 | 4971.0 | 114.0 | 4971.0 | 0.996477400000116 | 5.0 | 75.0 | 0.0 | 0.00920597339753495 | 0.009767043277672268 | 0.02918428927659988 | 0.00019687860913109034 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.048427854000000006 | 0.030248376 | 0.11728333 | 0.012892841 | 1.4559939753072315 | 1.1521239363126603 | 3.6563807386784655 | 0.0 | |||||||
| 26 | 25 | 1037.0 | 0.0 | 5203.0 | 5203.0 | 232.0 | 5203.0 | 0.9962686000001229 | 1.0 | 30.0 | 0.0 | 0.007875580906141391 | 0.009565175586670395 | 0.044340502470731735 | 0.0001106132986024022 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.04639761 | 0.031155868 | 0.14288062 | 0.0070327367 | 0.3645595035371356 | 0.280258633956571 | 1.0 | 0.0 |