mirror of
https://github.com/gryf/coach.git
synced 2026-01-30 04:05:51 +01:00
10 KiB
10 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 | Entropy/Mean | Entropy/Stdev | Entropy/Max | Entropy/Min | Advantages/Mean | Advantages/Stdev | Advantages/Max | Advantages/Min | Values/Mean | Values/Stdev | Values/Max | Values/Min | Value Loss/Mean | Value Loss/Stdev | Value Loss/Max | Value Loss/Min | Policy Loss/Mean | Policy Loss/Stdev | Policy Loss/Max | Policy Loss/Min |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 1 | 0.0 | 1.0 | 248.0 | 1.0 | 248.0 | 248.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 123.0 | 1.0 | 123.0 | 371.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 88.0 | 1.0 | 88.0 | 459.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 187.0 | 1.0 | 187.0 | 646.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 6 | 5 | 0.0 | 1.0 | 86.0 | 1.0 | 86.0 | 732.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 7 | 6 | 0.0 | 1.0 | 331.0 | 1.0 | 331.0 | 1063.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 8 | 7 | 15.0 | 0.0 | 283.0 | 1.0 | 283.0 | 1346.0 | 0.0 | 4.0 | 60.0 | 0.0 | 0.19038728 | 0.37413179999999996 | 1.085708 | 0.0005235527 | 1.7916272 | 5.3056545e-05 | 1.7917521 | 1.7915139 | 0.7594709227977354 | 0.7875483274351753 | 2.654857397079468 | -0.01272570714354515 | 0.01685313 | 0.026051456 | 0.06775641 | -0.010952383999999999 | 0.15764348 | 0.3329968 | 1.0256157 | 1.0381776e-06 | 0.39576545 | 0.7969487 | 2.2923334 | -0.015413323999999999 | |||||||||||
| 9 | 8 | 28.0 | 0.0 | 260.0 | 1.0 | 260.0 | 1606.0 | 0.0 | 1.0 | 5.0 | 0.0 | 0.04208376 | 0.116426505 | 0.44519386 | 0.005088003 | 1.7914166 | 9.428363000000001e-05 | 1.7916368000000003 | 1.791266 | 0.03226857285548017 | 0.1964720915841794 | 0.985376238822937 | -0.03431656211614609 | 0.10270161 | 0.014737441 | 0.123610094 | 0.014027433 | 0.02014357 | 0.06890331 | 0.25883156 | 0.00014790757 | 0.050990395 | 0.24849062 | 0.9112610999999999 | -0.04358855 | |||||||||||
| 10 | 9 | 41.0 | 0.0 | 258.0 | 1.0 | 258.0 | 1864.0 | 0.0 | 3.0 | 50.0 | 0.0 | 0.15317139 | 0.29834458 | 0.88614666 | 0.0067990692000000005 | 1.7912786 | 0.00014624497 | 1.7915285 | 1.7909831000000003 | 0.11791496871469112 | 0.3335888662422885 | 0.9964320659637452 | -0.11552873998880385 | 0.14228675 | 0.02709809 | 0.19294438 | 0.023462784 | 0.06762212 | 0.14083381 | 0.3970459 | 0.0002949245 | 0.21089181 | 0.5367635999999999 | 1.4676753999999999 | -0.16865353 | |||||||||||
| 11 | 10 | 60.0 | 0.0 | 379.0 | 1.0 | 379.0 | 2243.0 | 0.0 | 2.0 | 15.0 | 0.0 | 0.13247547 | 0.28383696 | 0.9851553 | 0.017279061999999998 | 1.7896857 | 0.0005040495 | 1.7909534 | 1.7888476999999998 | 0.03593501462428658 | 0.25046052313640216 | 0.9846256971359252 | -0.20018021762371066 | 0.30096403 | 0.05548007 | 0.4147089 | 0.039941877 | 0.039800237999999995 | 0.10806426400000001 | 0.35698512 | 0.0011615867999999999 | 0.06293697 | 0.38049793 | 1.1996851 | -0.2838259 | |||||||||||
| 12 | 11 | 68.0 | 0.0 | 155.0 | 1.0 | 155.0 | 2398.0 | 0.0 | 4.0 | 90.0 | 0.0 | 0.366822 | 0.27297008 | 0.85500246 | 0.056615636 | 1.7862365000000002 | 0.0014941338 | 1.7889153999999998 | 1.7834325 | 0.07147985940459389 | 0.3777481010142403 | 0.9432406425476074 | -0.4365565776824951 | 0.5416776 | 0.08939341 | 0.6384013000000001 | 0.08678746 | 0.120208606 | 0.1047605 | 0.29189906 | 0.005644179399999999 | 0.12151067 | 0.40066546 | 0.74686474 | -0.6290473000000001 | |||||||||||
| 13 | 12 | 72.0 | 0.0 | 63.0 | 1.0 | 63.0 | 2461.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.380458 | 0.5025457 | 1.2508503 | 0.0845396 | 1.7842273000000002 | 0.00016402099999999998 | 1.7845758000000003 | 1.7839825 | -0.15644778052965802 | 0.19377771679160247 | -0.006263315677642822 | -0.6633321642875671 | 0.66913104 | 0.10687629 | 0.72362936 | 0.13550685 | 0.043720815 | 0.057323013 | 0.143007 | 0.010515749 | -0.31537065 | 0.3354341 | -0.11016506 | -0.8962283999999999 | |||||||||||
| 14 | 13 | 92.0 | 0.0 | 395.0 | 1.0 | 395.0 | 2856.0 | 0.0 | 7.0 | 80.0 | 0.0 | 0.7341813 | 0.8931361999999999 | 3.4697776 | 0.08773655 | 1.7756039000000001 | 0.007125674 | 1.7904316999999998 | 1.7572613999999998 | 0.0531010530869581 | 0.35287025941667083 | 0.9526851177215576 | -0.43425774574279785 | 1.2777001000000001 | 0.4850268 | 2.382248 | 0.14852436 | 0.15513632 | 0.17681737 | 0.525007 | 0.012881841000000002 | 0.07083849 | 0.47545427 | 1.1537104 | -0.4574643 | |||||||||||
| 15 | 14 | 99.0 | 0.0 | 136.0 | 1.0 | 136.0 | 2992.0 | 0.0 | 3.0 | 35.0 | 0.0 | 2.3274047 | 3.6074872000000004 | 11.039786 | 0.282328 | 1.7519287000000001 | 0.004642716 | 1.7601723999999999 | 1.7432127 | -0.3301314194997152 | 0.7044738896059562 | 1.4541268348693848 | -2.5556342601776123 | 2.4971607000000002 | 0.26111710000000005 | 2.6487439999999998 | 0.5862286999999999 | 0.53202635 | 0.7275212 | 2.252977 | 0.09076643 | -0.6792965999999999 | 1.2040575 | 0.35570467 | -3.540179 | |||||||||||
| 16 | 15 | 103.0 | 0.0 | 72.0 | 1.0 | 72.0 | 3064.0 | 0.0 | 2.0 | 40.0 | 0.0 | 4.007548 | 3.65184 | 10.018075 | 0.15519248 | 1.7376648999999997 | 0.0027116186 | 1.7455993000000003 | 1.7320668000000001 | -0.2714320342791708 | 0.9907989894898622 | 0.8220000267028809 | -2.4204037189483643 | 2.1503487 | 0.2635579 | 2.4204037 | 0.5985670999999999 | 0.77588123 | 0.7991889 | 2.1323647 | 0.06468646 | -0.646171 | 1.7660096999999997 | 0.74871886 | -3.6078562999999995 | |||||||||||
| 17 | 16 | 116.0 | 0.0 | 258.0 | 1.0 | 258.0 | 3322.0 | 0.0 | 5.0 | 75.0 | 0.0 | 1.6523731 | 2.4698055 | 8.083523 | 0.13003878 | 1.7277107 | 0.0052154507 | 1.7423832 | 1.7133006999999998 | -0.039007020375085265 | 0.6065334628968307 | 1.6601608991622925 | -2.028516292572021 | 2.0747602 | 0.20532979 | 2.3914117999999998 | 0.51776755 | 0.3199724 | 0.44089985 | 1.3816912000000001 | 0.045208815 | -0.14023370000000002 | 1.0421013000000001 | 1.9057945 | -2.6204767 | |||||||||||
| 18 | 17 | 126.0 | 0.0 | 187.0 | 1.0 | 187.0 | 3509.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.92402875 | 2.2525914 | 7.679933500000001 | 0.10234933 | 1.6913862000000002 | 0.00811164 | 1.7129078000000002 | 1.6787053 | -0.3290705545382066 | 0.4870754997377705 | -0.00916290283203125 | -2.0534813404083248 | 1.8546785 | 0.17576595 | 2.0647898000000002 | 0.58214456 | 0.20426781 | 0.49021757 | 1.6748041 | 0.0308303 | -0.6092503 | 0.87516916 | -0.23161256 | -3.2324522 | |||||||||||
| 19 | 18 | 142.0 | 0.0 | 304.0 | 1.0 | 304.0 | 3813.0 | 0.0 | 8.0 | 135.0 | 0.0 | 1.0899202 | 1.2234477 | 4.604091599999999 | 0.09670285 | 1.6710208999999998 | 0.017265387 | 1.7212131000000002 | 1.6353879999999998 | 0.038843880938396386 | 0.4414781879982783 | 1.6555359363555908 | -1.5750807523727417 | 1.5963658 | 0.12633687 | 1.7319156999999998 | 0.49549833 | 0.20850252 | 0.22034019 | 0.7669623999999999 | 0.024377807999999997 | -0.022250907 | 0.6641187 | 1.1199272 | -1.9804106 | |||||||||||
| 20 | 19 | 154.0 | 0.0 | 229.0 | 1.0 | 229.0 | 4042.0 | 0.0 | 3.0 | 30.0 | 0.0 | 1.2594553 | 1.3803116000000002 | 3.5145763999999997 | 0.16982433 | 1.5893492 | 0.020280475 | 1.7202836 | 1.5471966000000001 | 0.018158039344208586 | 0.4246180314783785 | 0.9802966117858888 | -1.4079413414001465 | 1.9309628 | 0.13179472 | 2.00963 | 0.55298984 | 0.16962524 | 0.19235095 | 0.5845739000000001 | 0.036804248 | -0.12052882 | 0.73935986 | 1.0234607 | -1.7943251 | |||||||||||
| 21 | 20 | 159.0 | 0.0 | 94.0 | 1.0 | 94.0 | 4136.0 | 0.0 | 2.0 | 45.0 | 0.0 | 2.433933 | 2.4023757000000003 | 6.9298470000000005 | 0.361035 | 1.5338767 | 0.009024621 | 1.5852808 | 1.5249511 | -0.07727590973457593 | 0.6763922700521872 | 0.9142348766326904 | -2.0492594242095947 | 1.9556553 | 0.17559198 | 2.0944297 | 0.6989957 | 0.43858927 | 0.53540176 | 1.4796344 | 0.038060218 | -0.40701088 | 1.2666613000000002 | 0.9898828000000002 | -2.7505924999999998 | |||||||||||
| 22 | 21 | 167.0 | 0.0 | 160.0 | 1.0 | 160.0 | 4296.0 | 0.0 | 1.0 | 30.0 | 0.0 | 1.1918872999999999 | 2.3961012000000004 | 7.528841000000001 | 0.21041411 | 1.5789443 | 0.032899573 | 1.6285396 | 1.5285223999999997 | -0.3033659016931212 | 0.4753093769161661 | 0.6735560894012451 | -1.957652568817139 | 1.7269223999999999 | 0.17983046 | 1.9576526 | 0.65285933 | 0.23161101 | 0.49035895 | 1.5254883 | 0.02308034 | -0.5342293 | 0.74790174 | -0.17959394 | -2.5103128 | |||||||||||
| 23 | 22 | 177.0 | 0.0 | 196.0 | 1.0 | 196.0 | 4492.0 | 0.0 | 6.0 | 50.0 | 0.0 | 1.9176056000000001 | 1.4854782 | 5.182706 | 0.1296832 | 1.600741 | 0.007108025699999999 | 1.6213428 | 1.5850583 | 0.13868192747235294 | 0.6509546583268273 | 0.9652938842773438 | -1.4699276685714722 | 1.5411451999999999 | 0.12013785 | 1.6934890999999999 | 0.48539475 | 0.29114074 | 0.25261027 | 0.9247953999999999 | 0.02226338 | 0.20969613 | 0.9626545 | 1.3314689 | -2.1836848 | |||||||||||
| 24 | 23 | 181.0 | 0.0 | 64.0 | 1.0 | 64.0 | 4556.0 | 0.0 | 2.0 | 15.0 | 0.0 | 1.7134898 | 1.7741624 | 4.7404027 | 0.31171557 | 1.5784401000000001 | 0.0042786077 | 1.5924774 | 1.5698988 | -0.2495364295808893 | 0.7244287028836092 | 0.8197289705276489 | -1.6387592554092407 | 1.5626915000000001 | 0.14662078 | 1.6555089 | 0.5695728 | 0.39968159999999997 | 0.42479333 | 1.1206775 | 0.023818979 | -0.60248417 | 1.3273264 | 0.47739142 | -2.8594353 | |||||||||||
| 25 | 24 | 190.0 | 0.0 | 173.0 | 1.0 | 173.0 | 4729.0 | 0.0 | 2.0 | 35.0 | 0.0 | 0.86420363 | 1.1505579 | 3.1139815 | 0.21101475 | 1.5583048000000002 | 0.017154397 | 1.6805171000000003 | 1.543207 | -0.04846956090229314 | 0.3673147151981751 | 1.5572770833969116 | -1.3467092514038086 | 1.4270504 | 0.10279469999999999 | 1.5661808000000002 | 0.55668885 | 0.13428058 | 0.21433474 | 0.55084944 | 0.018585313 | -0.23329782 | 0.7188769 | 1.2898462 | -1.7598825 | |||||||||||
| 26 | 25 | 205.0 | 0.0 | 287.0 | 1.0 | 287.0 | 5016.0 | 0.0 | 1.0 | 15.0 | 0.0 | 0.62027776 | 1.1781626 | 5.0210605 | 0.19690849 | 1.514342 | 0.03201414 | 1.5717763 | 1.4700277 | -0.17472102851591012 | 0.2584962285741155 | 0.7259573936462402 | -1.389548659324646 | 1.372163 | 0.19543384 | 1.6445271000000001 | 0.49026695 | 0.07691100000000001 | 0.1892716 | 0.77725166 | 0.012039252 | -0.2952007 | 0.3808548 | -0.022987355 | -1.7028612 | |||||||||||
| 27 | 26 | 213.0 | 0.0 | 148.0 | 1.0 | 148.0 | 5164.0 | 0.0 | 1.0 | 10.0 | 0.0 | 0.87788093 | 1.1205411 | 3.2541595 | 0.16302086 | 1.6190518999999999 | 0.027872879 | 1.6517131 | 1.5822551 | -0.02111946441689316 | 0.3623434091799364 | 0.9680911898612976 | -1.0958757400512695 | 0.85739833 | 0.11593313 | 1.0958757 | 0.43242526 | 0.10100008 | 0.15961096 | 0.4262519 | 0.0066352487 | -0.1389226 | 0.54876155 | 0.983246 | -1.2080108999999999 | |||||||||||
| 28 | 27 | 226.0 | 0.0 | 252.0 | 1.0 | 252.0 | 5416.0 | 0.0 | 7.0 | 80.0 | 0.0 | 0.5659744000000001 | 0.5525852 | 1.7838180000000001 | 0.114572525 | 1.6545971999999998 | 0.01972044 | 1.6865756999999997 | 1.6199006 | 0.12287720557182065 | 0.4328559747238113 | 1.8018977642059328 | -0.7886770963668823 | 0.6744036999999999 | 0.0695462 | 0.78889847 | 0.3162281 | 0.11731172 | 0.14342302 | 0.47155509999999995 | 0.0039760494 | 0.15986028 | 0.57722294 | 1.304932 | -1.0839018999999999 | |||||||||||
| 29 | 28 | 235.0 | 0.0 | 172.0 | 1.0 | 172.0 | 5588.0 | 0.0 | 3.0 | 30.0 | 0.0 | 0.5754373 | 0.53583986 | 1.652655 | 0.20605606 | 1.6293853999999999 | 0.009444112 | 1.6664357 | 1.6154865 | 0.022745465989722758 | 0.37979156365269456 | 0.9582107663154602 | -0.7535422444343567 | 0.760279 | 0.04507102 | 0.8029374 | 0.30640987 | 0.08912065 | 0.09862131 | 0.26244953 | 0.007173898000000001 | -0.031205913 | 0.53349096 | 0.8757472 | -1.2156468999999999 | |||||||||||
| 30 | 29 | 247.0 | 0.0 | 222.0 | 1.0 | 222.0 | 5810.0 | 0.0 | 5.0 | 50.0 | 0.0 | 0.58918446 | 0.6646291999999999 | 2.1683297 | 0.1408544 | 1.6602775 | 0.023379487999999997 | 1.6966393 | 1.6148347 | 0.06360590496453745 | 0.4046164354742885 | 1.7265342473983765 | -0.8571033477783203 | 0.60714984 | 0.087587655 | 0.85710335 | 0.35827366 | 0.09666201 | 0.123577625 | 0.3676509 | 0.00446005 | 0.06519471 | 0.5444627 | 1.2408435 | -1.1376678 | |||||||||||
| 31 | 30 | 257.0 | 0.0 | 194.0 | 1.0 | 194.0 | 6004.0 | 0.0 | 2.0 | 40.0 | 0.0 | 0.39171672 | 0.37535542 | 1.2922283 | 0.14345266 | 1.6632646 | 0.020220451 | 1.7691753000000001 | 1.6358597 | 0.057352830338609086 | 0.3057737359186611 | 0.9528021216392516 | -0.3989834487438202 | 0.5558522 | 0.04560928 | 0.62815917 | 0.24490662 | 0.05019971 | 0.07826413 | 0.22374696 | 0.0043086787 | 0.024740081 | 0.38840258 | 0.7919935 | -0.59568876 |