mirror of
https://github.com/gryf/coach.git
synced 2026-02-15 05:25:55 +01:00
6.2 KiB
6.2 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 | 0.9997990300000044 | 5.0 | 55.0 | 0.0 | 0.01115525748330173 | 0.01482958817978088 | 0.05945311859250069 | 9.304942068411036e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.06464555 | 0.044470195 | 0.23793462 | 0.007608571999999999 | 1.5742518458459676 | 1.1031375801910266 | 3.252515696371334 | 0.0 | |||||||
| 7 | 6 | 70.0 | 0.0 | 1335.0 | 1335.0 | 75.0 | 1335.0 | 0.999724780000006 | 2.0 | 15.0 | 0.0 | 0.011412088440633131 | 0.011330222103483587 | 0.030992994084954262 | 0.00042172591201961035 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.05938535599999999 | 0.02777386 | 0.11668128 | 0.020656634 | 0.630055465573955 | 0.7534012288320482 | 1.886384871716129 | 0.0 | |||||||
| 8 | 7 | 91.0 | 0.0 | 1422.0 | 1422.0 | 87.0 | 1422.0 | 0.9996386500000078 | 1.0 | 15.0 | 0.0 | 0.011660500895231962 | 0.013899003705844034 | 0.04478336870670319 | 0.0002201012684963644 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.06497177 | 0.03783021 | 0.16582458 | 0.011831452 | 0.2731692938539037 | 0.40901966584690697 | 1.0 | 0.0 | |||||||
| 9 | 8 | 159.0 | 0.0 | 1693.0 | 1693.0 | 271.0 | 1693.0 | 0.9993703600000136 | 5.0 | 55.0 | 0.0 | 0.008784510728463516 | 0.010676103421827277 | 0.044153913855552666 | 0.00017267921066377312 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.052586783 | 0.03147318 | 0.16514115 | 0.01360802 | 1.3777471984624352 | 0.8115021837176055 | 3.11412900057984 | 0.0 | |||||||
| 10 | 9 | 201.0 | 0.0 | 1861.0 | 1861.0 | 168.0 | 1861.0 | 0.9992040400000172 | 3.0 | 50.0 | 0.0 | 0.0057493484051693005 | 0.009297238709482698 | 0.04292438179254532 | 0.0001674733939580619 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.038713556 | 0.02916971 | 0.15294549 | 0.012743682 | 0.9971291228971556 | 0.7740837108535874 | 2.18976824447548 | 0.0 | |||||||
| 11 | 10 | 279.0 | 0.0 | 2172.0 | 2172.0 | 311.0 | 2172.0 | 0.998896150000024 | 4.0 | 65.0 | 0.0 | 0.009585858937032008 | 0.012244045271861657 | 0.05662017315626144 | 8.848439028952271e-05 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.053857964 | 0.037834246 | 0.18018270000000003 | 0.0054985806000000005 | 1.0234306140936356 | 0.5002579938176909 | 2.1008995427938943 | 0.0 | |||||||
| 12 | 11 | 406.0 | 0.0 | 2681.0 | 2681.0 | 509.0 | 2681.0 | 0.9983922400000348 | 9.0 | 320.0 | 0.0 | 0.008271162704208052 | 0.010108575283067541 | 0.04325417801737785 | 0.00013097573537379503 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.051466412999999996 | 0.02947413 | 0.15955271 | 0.007228236 | 1.5487425802799972 | 0.9434112651663112 | 4.0430534797383535 | 0.0 | 0.010711596 | 0.012882838 | 0.024684543 | -0.014303938 | |||
| 13 | 12 | 471.0 | 0.0 | 2941.0 | 2941.0 | 260.0 | 2941.0 | 0.9981348400000404 | 7.0 | 110.0 | 0.0 | 0.009526190986910548 | 0.01270130936938865 | 0.0587114579975605 | 0.0002338076883461326 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.054751746 | 0.034732427 | 0.20657991 | 0.011495937 | 1.9247686125714616 | 1.4763974008694143 | 4.5174296147906645 | 0.0 | |||||||
| 14 | 13 | 506.0 | 0.0 | 3082.0 | 3082.0 | 141.0 | 3082.0 | 0.9979952500000436 | 0.0 | 0.0 | 0.0 | 0.008103997894379844 | 0.010146384256501963 | 0.02888230979442596 | 0.00016939456691034138 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.054213032 | 0.03339996 | 0.123893134 | 0.00751579 | 0.0 | 0.0 | 0.0 | 0.0 | 0.021964371 | 0.014109812 | 0.037105702000000004 | -0.004680969 | |||
| 15 | 14 | 569.0 | 0.0 | 3331.0 | 3331.0 | 249.0 | 3331.0 | 0.9977487400000488 | 7.0 | 110.0 | 0.0 | 0.007924241924727892 | 0.009418823926395129 | 0.04199397563934326 | 0.00015404188889078796 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.04968934 | 0.028010858 | 0.16092885 | 0.010448261 | 2.0098751682981617 | 1.1093871734323564 | 4.000165956499947 | 0.0 | |||||||
| 16 | 15 | 655.0 | 0.0 | 3677.0 | 3677.0 | 346.0 | 3677.0 | 0.9974062000000564 | 0.0 | 0.0 | 0.0 | 0.009106423050980084 | 0.010111300667633431 | 0.03859076648950577 | 0.00029026111587882037 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.05579937 | 0.029248272999999998 | 0.14688299999999999 | 0.014692408 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0037893213 | 0.013087699 | 0.021280576000000002 | -0.02601921 | |||
| 17 | 16 | 674.0 | 0.0 | 3753.0 | 3753.0 | 76.0 | 3753.0 | 0.997330960000058 | 1.0 | 10.0 | 0.0 | 0.005520004818160822 | 0.006733671599695406 | 0.015792973339557648 | 0.00023233161482494327 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.038671996 | 0.022766063 | 0.07300336 | 0.007988145 | 0.42667230386804816 | 0.4209997414589432 | 1.0 | 0.0 | |||||||
| 18 | 17 | 723.0 | 0.0 | 3948.0 | 3948.0 | 195.0 | 3948.0 | 0.997137910000062 | 0.0 | 0.0 | 0.0 | 0.006315292267554097 | 0.009919354506782935 | 0.03862195461988449 | 0.000192232575500384 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.044760402000000005 | 0.03878928 | 0.16543822 | 0.006780449 | 0.0 | 0.0 | 0.0 | 0.0 | |||||||
| 19 | 18 | 754.0 | 0.0 | 4073.0 | 4073.0 | 125.0 | 4073.0 | 0.9970141600000648 | 2.0 | 15.0 | 0.0 | 0.005961802070810189 | 0.007226799990202231 | 0.025835121050477028 | 0.0001774366246536374 | 9.999999999999996e-05 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.045393094 | 0.024198316 | 0.12546872 | 0.009217705 | 0.4379218073475659 | 0.6904045765467619 | 1.886384871716129 | 0.0 | 0.028437674 | 0.010936578999999998 | 0.04250892 | 0.011872215 | |||
| 20 | 19 | 831.0 | 0.0 | 4381.0 | 4381.0 | 308.0 | 4381.0 | 0.9967092400000714 | 4.0 | 90.0 | 0.0 | 0.006491211289842311 | 0.00892109273291234 | 0.038520261645317085 | 7.680161797907203e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.046867255 | 0.03352056 | 0.15879646 | 0.0045105475 | 1.0691845626589795 | 0.8498240160885151 | 2.745451683091903 | 0.0 | |||||||
| 21 | 20 | 933.0 | 0.0 | 4789.0 | 4789.0 | 408.0 | 4789.0 | 0.9963053200000802 | 5.0 | 35.0 | 0.0 | 0.007263708718728237 | 0.009710189245773595 | 0.05345397442579269 | 0.0001070786820491776 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.046955697000000005 | 0.031957038 | 0.18837799 | 0.0063061723 | 0.9497113318517078 | 0.5665372653893023 | 1.841181516831549 | 0.0 | 0.049459755 | 0.012578323999999998 | 0.07545762 | 0.038475648 |