mirror of
https://github.com/gryf/coach.git
synced 2026-01-28 02:55:46 +01:00
7.7 KiB
7.7 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 | 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 | |||||||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 573.0 | 573.0 | 87.0 | 573.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 722.0 | 722.0 | 149.0 | 722.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 1057.0 | 1057.0 | 335.0 | 1057.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 6 | 5 | 51.0 | 0.0 | 1260.0 | 1260.0 | 203.0 | 1260.0 | 0.999817300000006 | 3.0 | 30.0 | 0.0 | 0.009654946979186634 | 0.013951627370580843 | 0.04929021373391152 | 0.0001001853379420936 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.042711925 | 0.038432162 | 0.14662997 | 0.008449959 | |||||||
| 7 | 6 | 116.0 | 0.0 | 1519.0 | 1519.0 | 259.0 | 1519.0 | 0.9995842000000136 | 3.0 | 30.0 | 0.0 | 0.009395824597763398 | 0.010559114500164793 | 0.04425281286239624 | 0.0001856916933320463 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.046624955 | 0.030083885 | 0.14953406 | 0.013629041000000001 | |||||||
| 8 | 7 | 154.0 | 0.0 | 1673.0 | 1673.0 | 154.0 | 1673.0 | 0.9994456000000184 | 0.0 | 0.0 | 0.0 | 0.006763404418483046 | 0.007932211375540843 | 0.02884973213076592 | 0.00011230179370613767 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.03772134 | 0.024497243 | 0.086253904 | 0.008246866 | |||||||
| 9 | 8 | 188.0 | 0.0 | 1809.0 | 1809.0 | 136.0 | 1809.0 | 0.9993232000000224 | 0.0 | 0.0 | 0.0 | 0.00579419282696429 | 0.009409663949944837 | 0.03068150021135807 | 0.00011524958244990556 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.033371154 | 0.03126849 | 0.13397211 | 0.010591073000000001 | |||||||
| 10 | 9 | 218.0 | 0.0 | 1927.0 | 1927.0 | 118.0 | 1927.0 | 0.9992170000000258 | 4.0 | 50.0 | 0.0 | 0.005470155894242149 | 0.008703123279081676 | 0.02919070795178413 | 7.498881313949823e-05 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.03059395 | 0.028292075 | 0.10207387 | 0.006532367 | |||||||
| 11 | 10 | 239.0 | 0.0 | 2013.0 | 2013.0 | 86.0 | 2013.0 | 0.9991396000000284 | 1.0 | 25.0 | 0.0 | 0.007070470374726158 | 0.01125100662056102 | 0.04263514280319214 | 9.615141607355326e-05 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.038667627 | 0.033031862 | 0.13103388 | 0.009553337 | |||||||
| 12 | 11 | 285.0 | 0.0 | 2197.0 | 2197.0 | 184.0 | 2197.0 | 0.9989740000000338 | 5.0 | 75.0 | 0.0 | 0.004922990176767243 | 0.009157177817938416 | 0.0440991148352623 | 5.839417281094938e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.02870986 | 0.029140014 | 0.12825716 | 0.005925636999999999 | |||||||
| 13 | 12 | 309.0 | 0.0 | 2293.0 | 2293.0 | 96.0 | 2293.0 | 0.9988876000000366 | 2.0 | 15.0 | 0.0 | 0.004973496080917054 | 0.007834190985915203 | 0.027832549065351486 | 0.00011880028614541516 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.029258594 | 0.024372704 | 0.0919232 | 0.009084637 | |||||||
| 14 | 13 | 353.0 | 0.0 | 2467.0 | 2467.0 | 174.0 | 2467.0 | 0.9987310000000418 | 2.0 | 35.0 | 0.0 | 0.0045068665432071685 | 0.007321273060575792 | 0.02869480662047863 | 6.573591963388026e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.027796077000000002 | 0.025970899 | 0.09446095 | 0.0046847034 | |||||||
| 15 | 14 | 400.0 | 0.0 | 2658.0 | 2658.0 | 191.0 | 2658.0 | 0.9985591000000474 | 1.0 | 25.0 | 0.0 | 0.00977239356019554 | 0.010343679461906952 | 0.030321182683110237 | 0.00018286058912053704 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.048518963 | 0.02922272 | 0.11681272 | 0.009786125 | 0.050078813 | 0.025057722 | 0.08571987 | 0.020499324 | |||
| 16 | 15 | 420.0 | 0.0 | 2737.0 | 2737.0 | 79.0 | 2737.0 | 0.9984880000000498 | 3.0 | 30.0 | 0.0 | 0.008876862422766862 | 0.009404707731271193 | 0.028901334851980213 | 0.00018610457482282072 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.04794182599999999 | 0.029056482 | 0.12552716 | 0.015941316 | |||||||
| 17 | 16 | 441.0 | 0.0 | 2822.0 | 2822.0 | 85.0 | 2822.0 | 0.9984115000000524 | 1.0 | 20.0 | 0.0 | 0.011170348666685944 | 0.009764524297967085 | 0.030193831771612167 | 0.0002611538511700928 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.05474482 | 0.031951982999999996 | 0.13531010000000002 | 0.01605481 | |||||||
| 18 | 17 | 529.0 | 0.0 | 3174.0 | 3174.0 | 352.0 | 3174.0 | 0.9980947000000628 | 6.0 | 105.0 | 0.0 | 0.008561450651871961 | 0.010388056521305884 | 0.04236683994531632 | 0.00017452481552027166 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.044565108 | 0.029229562999999997 | 0.12811051 | 0.012664802 | |||||||
| 19 | 18 | 618.0 | 0.0 | 3527.0 | 3527.0 | 353.0 | 3527.0 | 0.9977770000000732 | 4.0 | 80.0 | 0.0 | 0.007443786804798762 | 0.010177603763426246 | 0.04463248327374458 | 6.0651469539152465e-05 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.03917629 | 0.02873507 | 0.13048278 | 0.0059215119999999994 | 0.026613249 | 0.008946453 | 0.04138826 | 0.013779217 | |||
| 20 | 19 | 638.0 | 0.0 | 3610.0 | 3610.0 | 83.0 | 3610.0 | 0.9977023000000756 | 1.0 | 10.0 | 0.0 | 0.00947287489034352 | 0.009120686342052368 | 0.02835406921803952 | 0.00023163050354924053 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.04728116 | 0.025211213 | 0.08812934 | 0.015696856999999998 | |||||||
| 21 | 20 | 674.0 | 0.0 | 3754.0 | 3754.0 | 144.0 | 3754.0 | 0.99757270000008 | 0.0 | 0.0 | 0.0 | 0.006512744492485783 | 0.01084231610224011 | 0.054297078400850296 | 0.00013670953921973703 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.039536193 | 0.03681436 | 0.19717765 | 0.009255781999999999 | 0.029463767999999998 | 0.013992969 | 0.055506807000000005 | 0.011549842 | |||
| 22 | 21 | 703.0 | 0.0 | 3869.0 | 3869.0 | 115.0 | 3869.0 | 0.9974692000000832 | 4.0 | 55.0 | 0.0 | 0.007595785371638064 | 0.01278862092663838 | 0.0568322204053402 | 0.00016743995365686717 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.038325354 | 0.03308432 | 0.14259322 | 0.008637958000000001 | |||||||
| 23 | 22 | 724.0 | 0.0 | 3953.0 | 3953.0 | 84.0 | 3953.0 | 0.9973936000000858 | 2.0 | 50.0 | 0.0 | 0.0057669557267910855 | 0.009239934908058463 | 0.02947502583265305 | 0.00018409341282676905 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.03457182 | 0.026093084 | 0.09026415 | 0.0123431515 | |||||||
| 24 | 23 | 784.0 | 0.0 | 4192.0 | 4192.0 | 239.0 | 4192.0 | 0.9971785000000928 | 5.0 | 75.0 | 0.0 | 0.00809967934183078 | 0.01036380041696798 | 0.041483376175165176 | 0.00016024033538997173 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.04329346 | 0.031746197000000004 | 0.14067882 | 0.009837331999999999 | |||||||
| 25 | 24 | 831.0 | 0.0 | 4380.0 | 4380.0 | 188.0 | 4380.0 | 0.9970093000000984 | 0.0 | 0.0 | 0.0 | 0.006891696457813018 | 0.007546929211673221 | 0.029366210103034977 | 0.0002085421874653548 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.040272716 | 0.023695845 | 0.08822828 | 0.010775305 | |||||||
| 26 | 25 | 906.0 | 0.0 | 4681.0 | 4681.0 | 301.0 | 4681.0 | 0.9967384000001074 | 7.0 | 80.0 | 0.0 | 0.007030442795269968 | 0.008971783795469862 | 0.029756365343928337 | 9.572327689966188e-05 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.040413715 | 0.029355139 | 0.10548375 | 0.0072385157 | 0.041193675 | 0.02736831 | 0.07621856 | 0.00037608482000000003 | |||
| 27 | 26 | 959.0 | 0.0 | 4893.0 | 4893.0 | 212.0 | 4893.0 | 0.9965476000001136 | 3.0 | 30.0 | 0.0 | 0.007057454745765151 | 0.009452664953293057 | 0.030209349468350414 | 0.00010792172543006018 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.039197296 | 0.027908783 | 0.104838766 | 0.008230781 | |||||||
| 28 | 27 | 1048.0 | 0.0 | 5247.0 | 5247.0 | 354.0 | 5247.0 | 0.9962290000001242 | 5.0 | 75.0 | 0.0 | 0.008188762073535891 | 0.009436714275711092 | 0.04216104745864868 | 0.00015023039304651317 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.044641394 | 0.028307599999999995 | 0.12660655 | 0.00902969 | |||||||
| 29 | 28 | 1083.0 | 0.0 | 5387.0 | 5387.0 | 140.0 | 5387.0 | 0.9961030000001284 | 1.0 | 20.0 | 0.0 | 0.004326820851253745 | 0.0064877273362216065 | 0.015882819890975952 | 0.00010518966882955284 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.027057504 | 0.023942256000000002 | 0.07126255 | 0.006638075699999999 | |||||||
| 30 | 29 | 1131.0 | 0.0 | 5581.0 | 5581.0 | 194.0 | 5581.0 | 0.9959284000001339 | 4.0 | 60.0 | 0.0 | 0.008834963679722327 | 0.008607911806343238 | 0.03031262755393982 | 0.000106745348602999 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.045785952000000005 | 0.027331235 | 0.11430588 | 0.0062478506 | |||||||
| 31 | 30 | 1236.0 | 0.0 | 6002.0 | 6002.0 | 421.0 | 6002.0 | 0.9955495000001464 | 8.0 | 125.0 | 0.0 | 0.006107945965985503 | 0.007809515316612659 | 0.03002355806529522 | 0.00015217895270325243 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.035095777 | 0.025743425 | 0.101090685 | 0.008217704499999999 |