mirror of
https://github.com/gryf/coach.git
synced 2026-01-07 14:24:16 +01:00
7.6 KiB
7.6 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 | 36.46216820501814 | 49.49063725100042 | 199.14385986328125 | 0.2370053380727768 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 8.106395 | 7.653527 | 37.918265999999996 | 1.4823846999999999 | 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 | 39.21498674154281 | 40.966334498138956 | 99.45429229736328 | 0.2783645689487457 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 11.493177000000001 | 8.143372 | 27.88594 | 2.804944 | 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 | 37.997530142466225 | 47.686402373955495 | 148.0321502685547 | 0.3659912347793579 | 5e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 12.492678 | 8.967174 | 43.69277 | 4.7538095 | 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 | 28.93536954673369 | 35.996568840218124 | 147.71107482910156 | 0.4109263420104981 | 5.0000000000000016e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 11.921192999999999 | 7.154584 | 35.408936 | 5.475621 | 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 | 19.01853317235197 | 31.73065188890599 | 145.7387237548828 | 0.4107859432697296 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 10.154241 | 7.8330517 | 47.878605 | 5.396381400000001 | 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 | 32.07186578519833 | 41.966178693622524 | 194.7534942626953 | 0.3353344798088074 | 5.0000000000000016e-05 | 2.0328790734103208e-20 | 5e-05 | 5e-05 | 18.104782 | 13.075563 | 84.22504 | 3.6740150000000003 | 1.0234306140936356 | 0.5002579938176909 | 2.1008995427938943 | 0.0 | |||||||
| 12 | 11 | 440.0 | 0.0 | 2815.0 | 2815.0 | 643.0 | 2815.0 | 0.9982595800000378 | 10.0 | 335.0 | 0.0 | 28.241446902848182 | 34.85627948916873 | 144.36659240722656 | 0.4909345805644989 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 19.778129999999997 | 12.654268 | 88.67351500000001 | 6.610262 | 1.3803392321717662 | 1.096111017851517 | 4.070269499186656 | 0.0 | 0.014711282060209972 | 0.0029370955585178325 | 0.01916578561475035 | 0.011431378351990134 | |||
| 13 | 12 | 458.0 | 0.0 | 2888.0 | 2888.0 | 73.0 | 2888.0 | 0.9981873100000394 | 2.0 | 45.0 | 0.0 | 31.499239090416175 | 37.45303116914551 | 141.36285400390625 | 0.9536997675895692 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 29.248409999999996 | 15.650569 | 71.87909 | 14.681288 | 0.6193548093911652 | 0.6855072221487064 | 1.8179069375972308 | 0.0 | |||||||
| 14 | 13 | 478.0 | 0.0 | 2969.0 | 2969.0 | 81.0 | 2969.0 | 0.9981071200000412 | 0.0 | 0.0 | 0.0 | 21.9556499183178 | 27.275734589849755 | 96.1314468383789 | 1.0587046146392822 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 24.860376000000002 | 5.973276 | 40.390087 | 16.44971 | 0.0 | 0.0 | 0.0 | 0.0 | 0.015622645472152119 | 0.003616398338992898 | 0.022574815150001086 | 0.011153336142306215 | |||
| 15 | 14 | 532.0 | 0.0 | 3183.0 | 3183.0 | 214.0 | 3183.0 | 0.9978952600000456 | 4.0 | 50.0 | 0.0 | 22.150840351978943 | 31.378442000167443 | 94.2119140625 | 0.774277925491333 | 5.0000000000000016e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 23.761226999999998 | 16.20461 | 72.71788000000001 | 11.1300535 | 1.1449070106363344 | 0.7411479181777391 | 2.363283716034233 | 0.0 | |||||||
| 16 | 15 | 551.0 | 0.0 | 3262.0 | 3262.0 | 79.0 | 3262.0 | 0.9978170500000474 | 2.0 | 15.0 | 0.0 | 26.64994892321135 | 38.88476731133048 | 134.13800048828122 | 0.7795231938362122 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 30.691628 | 28.987253000000003 | 114.957954 | 11.542784 | 0.7209514730836505 | 0.7680412970584659 | 1.8953382542587165 | 0.0 | |||||||
| 17 | 16 | 632.0 | 0.0 | 3584.0 | 3584.0 | 322.0 | 3584.0 | 0.9974982700000544 | 6.0 | 145.0 | 0.0 | 27.051017467677593 | 31.549487367040182 | 123.92398834228516 | 0.944594383239746 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 35.256115 | 21.881757999999998 | 163.08112 | 14.200109 | 1.1770031212416605 | 0.8262292064074209 | 3.0179431656102578 | 0.0 | 0.014364275371384188 | 0.006713234307642353 | 0.02478289117483655 | 0.0037042652317904865 | |||
| 18 | 17 | 671.0 | 0.0 | 3742.0 | 3742.0 | 158.0 | 3742.0 | 0.9973418500000576 | 2.0 | 15.0 | 0.0 | 28.817911947384854 | 33.12067221990375 | 95.75489044189452 | 0.9412024617195128 | 4.999999999999999e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 32.21356 | 18.489529 | 81.63014 | 14.253252 | 0.6005911651530309 | 0.5453746168835384 | 1.5870367819374844 | 0.0 | 0.03340592364123344 | 0.008006605849225681 | 0.050213053451152526 | 0.026884825304150584 | |||
| 19 | 18 | 692.0 | 0.0 | 3823.0 | 3823.0 | 81.0 | 3823.0 | 0.9972616600000594 | 2.0 | 15.0 | 0.0 | 25.17339034080505 | 30.799689979490736 | 126.7385025024414 | 1.6798182725906372 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 40.65267 | 22.928457 | 135.37898 | 25.454242999999998 | 0.7922353902907879 | 0.6952623969580528 | 1.8179069375972308 | 0.0 | |||||||
| 20 | 19 | 724.0 | 0.0 | 3954.0 | 3954.0 | 131.0 | 3954.0 | 0.9971319700000624 | 3.0 | 60.0 | 0.0 | 22.61877366527915 | 25.475957043383087 | 87.23521423339844 | 1.0491437911987305 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 36.468734999999995 | 18.711422 | 105.155396 | 15.084179999999998 | 0.9800021878033628 | 0.8735070818924148 | 2.46433739265332 | 0.0 | |||||||
| 21 | 20 | 892.0 | 0.0 | 4624.0 | 4624.0 | 670.0 | 4624.0 | 0.9964686700000768 | 10.0 | 120.0 | 0.0 | 26.76441630096493 | 32.312885508456546 | 172.42578125 | 0.6974627375602722 | 5e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 40.603745 | 25.413135999999998 | 183.58588999999998 | 10.761553 | 1.3694909525397223 | 0.977245098695965 | 4.034435997798811 | 0.0 | 0.03520899955342733 | 0.017470817679322934 | 0.0689028069091728 | 0.009736330420419109 | |||
| 22 | 21 | 1039.0 | 0.0 | 5212.0 | 5212.0 | 588.0 | 5212.0 | 0.9958865500000892 | 7.0 | 305.0 | 0.0 | 25.58388039652182 | 30.082226743252054 | 129.48117065429688 | 0.9502491354942322 | 5.0000000000000016e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 38.948544 | 20.306423000000002 | 137.17696999999998 | 13.764803 | 0.8833582927089424 | 0.6666778268136587 | 2.4487212795420223 | 0.0 | 0.02299263094427867 | 0.004950158129326472 | 0.02969474263940356 | 0.01672235769356121 | |||
| 23 | 22 | 1062.0 | 0.0 | 5306.0 | 5306.0 | 94.0 | 5306.0 | 0.9957934900000912 | 1.0 | 30.0 | 0.0 | 27.628428853076443 | 35.22442651288078 | 127.4379653930664 | 0.8532395958900452 | 4.999999999999999e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 38.605255 | 32.10079 | 132.49275 | 11.907950999999999 | 0.2925741106831343 | 0.4098911262217585 | 1.0 | 0.0 | |||||||
| 24 | 23 | 1121.0 | 0.0 | 5540.0 | 5540.0 | 234.0 | 5540.0 | 0.9955618300000963 | 5.0 | 65.0 | 0.0 | 27.369281474886268 | 31.415961676926877 | 117.39376831054688 | 1.6547856330871582 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 48.570988 | 30.103327 | 178.69554 | 25.50989 | 1.2611240480922348 | 0.9471053795173676 | 2.9127534883249893 | 0.0 | |||||||
| 25 | 24 | 1159.0 | 0.0 | 5692.0 | 5692.0 | 152.0 | 5692.0 | 0.9954113500000996 | 0.0 | 0.0 | 0.0 | 22.421022302226014 | 29.526073528236534 | 134.66459655761722 | 1.333237886428833 | 4.999999999999999e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 38.155884 | 22.256369 | 142.38083 | 20.779846 | 0.0 | 0.0 | 0.0 | 0.0 | |||||||
| 26 | 25 | 1211.0 | 0.0 | 5901.0 | 5901.0 | 209.0 | 5901.0 | 0.995204440000104 | 3.0 | 55.0 | 0.0 | 20.919890511494415 | 25.236920144182772 | 94.25011444091795 | 1.0202153921127322 | 5.0000000000000016e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 29.841938 | 14.481047 | 85.20053 | 14.958545 | 0.952000039655271 | 0.6733299902533258 | 2.0831709161120813 | 0.0 |