mirror of
https://github.com/gryf/coach.git
synced 2026-01-28 11:05:46 +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 | 0.9997990300000044 | 5.0 | 55.0 | 0.0 | 0.011083870362627377 | 0.014686622348556997 | 0.054807450622320175 | 8.600389992352575e-05 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.044719514 | 0.033888377000000004 | 0.15844104 | 0.006255531700000001 | 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 | 0.01160521360763692 | 0.011407942994633451 | 0.03328811377286911 | 0.0005630382802337407 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.051803865 | 0.029654076 | 0.12591287 | 0.018302478 | 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 | 0.011435289681512155 | 0.01356485692548739 | 0.04386129975318909 | 0.0003138938918709755 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.049575187 | 0.030825942999999998 | 0.12139501400000001 | 0.01762898 | 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 | 0.008754079026402906 | 0.010493087956226587 | 0.04199719801545143 | 0.00022145826369524 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.043745343 | 0.029057967 | 0.12578213 | 0.009329067 | 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 | 0.005790353046211835 | 0.00924501194200579 | 0.04264310002326965 | 0.00015841521963011473 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.029974802999999998 | 0.02480581 | 0.10272589 | 0.006583053 | 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 | 0.009652879799642295 | 0.012284496966573208 | 0.056258566677570336 | 8.341699867742136e-05 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.04328928 | 0.03246331 | 0.13359663 | 0.006534694000000001 | 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 | 0.008536474057301511 | 0.01028302387210362 | 0.045296579599380486 | 0.00012202279322082175 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.04192782 | 0.027328676 | 0.12006431 | 0.0078535825 | 1.3803392321717662 | 1.096111017851517 | 4.070269499186656 | 0.0 | 0.0023848657 | 0.025200281 | 0.042012468 | -0.036088865 | |||
| 13 | 12 | 458.0 | 0.0 | 2888.0 | 2888.0 | 73.0 | 2888.0 | 0.9981873100000394 | 2.0 | 45.0 | 0.0 | 0.009459823424953759 | 0.010695092095359921 | 0.0402686782181263 | 0.0004647395689971745 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.046102643 | 0.024324505 | 0.107099675 | 0.018588312 | 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 | 0.006749217664764729 | 0.008090573080945502 | 0.02682654373347759 | 0.00027168722590431566 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.036704935 | 0.024102442 | 0.087217584 | 0.010512206000000001 | 0.0 | 0.0 | 0.0 | 0.0 | 0.000485022 | 0.008587205 | 0.009356956999999999 | -0.011517284 | |||
| 15 | 14 | 532.0 | 0.0 | 3183.0 | 3183.0 | 214.0 | 3183.0 | 0.9978952600000456 | 4.0 | 50.0 | 0.0 | 0.006886512735002692 | 0.009553768326298295 | 0.030248582363128662 | 0.00014440309314522892 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.035955932 | 0.028305838 | 0.10123628 | 0.00730699 | 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 | 0.008461739830779965 | 0.012206836783855724 | 0.040975090116262436 | 0.00011308784451102837 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.037445724 | 0.03204159 | 0.11201507 | 0.006310343 | 0.7209514730836505 | 0.7680412970584659 | 1.8953382542587165 | 0.0 | |||||||
| 17 | 16 | 626.0 | 0.0 | 3560.0 | 3560.0 | 298.0 | 3560.0 | 0.9975220300000538 | 6.0 | 145.0 | 0.0 | 0.009029203843965659 | 0.009722502175700065 | 0.03697861731052399 | 0.00021903477318119255 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.045156802999999995 | 0.026322339 | 0.11680761 | 0.011919108000000001 | 1.2555763711101595 | 0.9240906493644656 | 3.083943769311809 | 0.0 | -0.021607108 | 0.020686936 | 0.009232186 | -0.05197674 | |||
| 18 | 17 | 684.0 | 0.0 | 3794.0 | 3794.0 | 234.0 | 3794.0 | 0.9972903700000588 | 4.0 | 45.0 | 0.0 | 0.008949900330004186 | 0.0108696265998807 | 0.04665529727935791 | 0.00029459563666023314 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.042484716 | 0.026987998 | 0.10841252 | 0.0117550725 | 1.2202506793333543 | 0.9239408887260988 | 2.9738245545408817 | 0.0 | 0.026112242 | 0.027647123 | 0.061535902 | -0.01418671 | |||
| 19 | 18 | 763.0 | 0.0 | 4108.0 | 4108.0 | 314.0 | 4108.0 | 0.9969795100000656 | 3.0 | 30.0 | 0.0 | 0.007479070061377477 | 0.008896620879299575 | 0.036576714366674416 | 0.00020328086975496265 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.043070607000000004 | 0.029303582 | 0.13295116 | 0.008885576999999999 | 0.8837491256463907 | 0.7030397582930629 | 2.6667247893559085 | 0.0 | 0.022609236 | 0.020540563 | 0.054745227 | -0.00039339485 | |||
| 20 | 19 | 823.0 | 0.0 | 4348.0 | 4348.0 | 240.0 | 4348.0 | 0.9967419100000708 | 6.0 | 120.0 | 0.0 | 0.0077256423872313455 | 0.008924083916126141 | 0.03898797184228897 | 0.00013186871365178376 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.04132683 | 0.027561786 | 0.13284422 | 0.006342471999999999 | 1.5988277380263118 | 0.9509580660393312 | 3.1056467233551137 | 0.0 | |||||||
| 21 | 20 | 874.0 | 0.0 | 4552.0 | 4552.0 | 204.0 | 4552.0 | 0.9965399500000752 | 3.0 | 30.0 | 0.0 | 0.007347894184503648 | 0.009792918501568331 | 0.04169968888163567 | 0.00021092816314194354 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.03559589 | 0.026791284 | 0.108093284 | 0.00980423 | 0.8961957745502318 | 0.5239544190616746 | 1.9174072405700964 | 0.0 | 0.032443836000000004 | 0.025000658 | 0.07358496 | 0.00015714159 | |||
| 22 | 21 | 893.0 | 0.0 | 4627.0 | 4627.0 | 75.0 | 4627.0 | 0.9964657000000768 | 2.0 | 15.0 | 0.0 | 0.004670596711404964 | 0.008158781989459747 | 0.030096400529146194 | 0.00010540960647631435 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.022338616000000002 | 0.02347593 | 0.087533504 | 0.005530844 | 0.6504215775848821 | 0.7567320936767312 | 1.886384871716129 | 0.0 | |||||||
| 23 | 22 | 914.0 | 0.0 | 4713.0 | 4713.0 | 86.0 | 4713.0 | 0.9963805600000786 | 2.0 | 35.0 | 0.0 | 0.0067829833244017895 | 0.008080795635655384 | 0.028226209804415706 | 0.00015739010996185243 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.034749854 | 0.027055427000000003 | 0.09181212 | 0.008366535999999999 | 0.7082502636424372 | 0.7222731163417688 | 1.8429431933839264 | 0.0 | |||||||
| 24 | 23 | 964.0 | 0.0 | 4914.0 | 4914.0 | 201.0 | 4914.0 | 0.9961815700000828 | 4.0 | 50.0 | 0.0 | 0.010504917961661704 | 0.011773181256895185 | 0.0450880229473114 | 0.0001865942613221705 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.048508067 | 0.03061757 | 0.12784363 | 0.01017314 | 1.1770323827695204 | 0.9093313520815908 | 2.52258184188516 | 0.0 | |||||||
| 25 | 24 | 991.0 | 0.0 | 5022.0 | 5022.0 | 108.0 | 5022.0 | 0.9960746500000852 | 2.0 | 15.0 | 0.0 | 0.010385172195338572 | 0.009804020528278966 | 0.0299542136490345 | 0.00038964324630796915 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.050116464000000006 | 0.028762132000000003 | 0.12844692 | 0.011575635 | 0.30012966497153265 | 0.5570578527365648 | 1.8345137614500877 | 0.0 | |||||||
| 26 | 25 | 1044.0 | 0.0 | 5234.0 | 5234.0 | 212.0 | 5234.0 | 0.9958647700000898 | 0.0 | 0.0 | 0.0 | 0.007366582582527861 | 0.01016458659273742 | 0.04324457794427872 | 0.0002189573715440929 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.041527875 | 0.032172493999999996 | 0.14668968 | 0.008220247 | 0.0 | 0.0 | 0.0 | 0.0 | -0.025346689 | 0.011624134 | -0.01041002 | -0.045562238 |