mirror of
https://github.com/gryf/coach.git
synced 2026-01-07 14:24:16 +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 | 0.011426913155945856 | 0.014756518976957641 | 0.05680577829480171 | 0.0002147645864170045 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.07435301 | 0.045047246 | 0.24352701 | 0.016394855 | 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 | 0.011545363522600384 | 0.011331178069383907 | 0.03035823628306389 | 0.0005611731903627515 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.05962084 | 0.03063415 | 0.11521778 | 0.016333662 | 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 | 0.011873709826475188 | 0.013816552960862651 | 0.04414435476064682 | 0.00033102076849900186 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.06603781 | 0.04036743 | 0.16048972 | 0.020163156 | 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 | 0.00892895733921983 | 0.010597634284905831 | 0.043597646057605736 | 0.00032593513606116176 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.05429927 | 0.032025557 | 0.16306725 | 0.010466161 | 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 | 0.005954749794216782 | 0.009202235379131387 | 0.04198700934648514 | 0.00025118381017819047 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.041775707 | 0.02735304 | 0.13903868 | 0.012313978 | 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 | 0.009854780438054616 | 0.012550867252094849 | 0.059424202889204025 | 0.0002813946339301765 | 0.00010000000000000003 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.0545313 | 0.03862215 | 0.19712389 | 0.007967907 | 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 | 0.008705651807137447 | 0.010365609478213463 | 0.04515113309025765 | 0.00027332009631209075 | 0.00010000000000000002 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.051797643 | 0.030422362 | 0.16835181 | 0.011892918999999998 | 1.3803392321717662 | 1.096111017851517 | 4.070269499186656 | 0.0 | 0.030506922000000002 | 0.009463024 | 0.043351725 | 0.017570784 | |||
| 13 | 12 | 458.0 | 0.0 | 2888.0 | 2888.0 | 73.0 | 2888.0 | 0.9981873100000394 | 2.0 | 45.0 | 0.0 | 0.009799879244787412 | 0.010812766104832236 | 0.0411992110311985 | 0.0004764955374412239 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.06231578 | 0.023420273999999998 | 0.14000057 | 0.027787858999999998 | 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 | 0.006886815359030152 | 0.00822154572400499 | 0.028151353821158413 | 0.0002291356067871675 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.044036895 | 0.027623571 | 0.11985183 | 0.015210131000000002 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0012964243 | 0.0077345967000000005 | 0.012726211000000001 | -0.011794438999999999 | |||
| 15 | 14 | 532.0 | 0.0 | 3183.0 | 3183.0 | 214.0 | 3183.0 | 0.9978952600000456 | 4.0 | 50.0 | 0.0 | 0.006956237401162206 | 0.009541872186932865 | 0.03044747933745384 | 0.00018875976093113422 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.045752503 | 0.029793812000000003 | 0.12070799 | 0.009390408000000001 | 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 | 0.008442848150336527 | 0.012173384099094577 | 0.04232653975486755 | 0.0002570757351350039 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.04716655 | 0.037182163 | 0.14443676 | 0.010955643000000001 | 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 | 0.009251012113275687 | 0.010029887794973515 | 0.03953123837709427 | 0.00017335088341496885 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.053577467999999996 | 0.029333506000000002 | 0.15917644 | 0.008500515 | 1.2555763711101595 | 0.9240906493644656 | 3.083943769311809 | 0.0 | 0.00013416121000000002 | 0.008821717 | 0.015920052 | -0.008326407 | |||
| 18 | 17 | 891.0 | 0.0 | 4619.0 | 4619.0 | 1059.0 | 4619.0 | 0.9964736200000766 | 19.0 | 300.0 | 0.0 | 0.007645681498952226 | 0.009414058271007344 | 0.04135562479496002 | 0.00017916453361976892 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.04925753 | 0.030359953999999998 | 0.15788195 | 0.008305753 | 1.6717339663032367 | 1.1690778545783265 | 5.771819446417341 | 0.0 | 0.009137043000000001 | 0.022298122000000004 | 0.04927585599999999 | -0.031120421000000002 | |||
| 19 | 18 | 909.0 | 0.0 | 4694.0 | 4694.0 | 75.0 | 4694.0 | 0.9963993700000782 | 1.0 | 5.0 | 0.0 | 0.0075578728930041595 | 0.008679731951877039 | 0.03108345903456211 | 0.00022933213040232656 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.046490382000000004 | 0.025032546 | 0.11267102 | 0.01251911 | 0.26449254728127203 | 0.4117036621664033 | 1.0 | 0.0 | |||||||
| 20 | 19 | 946.0 | 0.0 | 4841.0 | 4841.0 | 147.0 | 4841.0 | 0.9962538400000812 | 5.0 | 100.0 | 0.0 | 0.0115111036446049 | 0.011489895299968134 | 0.031763449311256416 | 0.00027352251345291734 | 0.0001 | 1.3552527156068802e-20 | 0.0001 | 0.0001 | 0.06159561 | 0.031588662 | 0.13237359 | 0.015935825 | 2.2849837878539345 | 0.971178517444138 | 4.095674290907237 | 0.0 | |||||||
| 21 | 20 | 1042.0 | 0.0 | 5224.0 | 5224.0 | 383.0 | 5224.0 | 0.9958746700000896 | 7.0 | 80.0 | 0.0 | 0.009199454678006685 | 0.009978617442663974 | 0.05764783918857575 | 0.00031337159452959895 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.054836433 | 0.028541432999999998 | 0.185097 | 0.012546482 | 1.4071924202269357 | 0.99635982836491 | 3.4401906119270684 | 0.0 | -0.04649626 | 0.018119393 | -0.01145938 | -0.062069237 | |||
| 22 | 21 | 1088.0 | 0.0 | 5409.0 | 5409.0 | 185.0 | 5409.0 | 0.9956915200000936 | 2.0 | 55.0 | 0.0 | 0.00816560124677262 | 0.008514436323755096 | 0.027968401089310646 | 0.00028431529062800115 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.050769784000000005 | 0.025596844 | 0.121238366 | 0.016692609 | 0.7074657547333786 | 0.5792561355925516 | 1.7778213593991463 | 0.0 | |||||||
| 23 | 22 | 1118.0 | 0.0 | 5530.0 | 5530.0 | 121.0 | 5530.0 | 0.995571730000096 | 0.0 | 0.0 | 0.0 | 0.005226385891243504 | 0.006668131240954576 | 0.01606620848178864 | 0.00025087088579311967 | 9.999999999999998e-05 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.03845106 | 0.023627792999999998 | 0.07521168 | 0.010804271 | 0.0 | 0.0 | 0.0 | 0.0 | |||||||
| 24 | 23 | 1163.0 | 0.0 | 5710.0 | 5710.0 | 180.0 | 5710.0 | 0.9953935300001 | 2.0 | 15.0 | 0.0 | 0.008218312517618127 | 0.009096067919224612 | 0.029108991846442226 | 0.0002737445756793022 | 0.00010000000000000003 | 2.7105054312137605e-20 | 0.0001 | 0.0001 | 0.05207102 | 0.02900738 | 0.12575926 | 0.009468661 | 0.5801064677283798 | 0.40876075847832055 | 1.358748297681892 | 0.0 | |||||||
| 25 | 24 | 1195.0 | 0.0 | 5837.0 | 5837.0 | 127.0 | 5837.0 | 0.9952678000001028 | 3.0 | 30.0 | 0.0 | 0.007723447829184512 | 0.010716549149525923 | 0.04435421526432037 | 0.00026090070605278015 | 9.999999999999996e-05 | 4.0657581468206416e-20 | 0.0001 | 0.0001 | 0.04838518 | 0.028496007 | 0.13656300000000002 | 0.013654276000000002 | 0.5503377956235296 | 0.8800124539264379 | 2.6487275860632327 | 0.0 | |||||||
| 26 | 25 | 1235.0 | 0.0 | 5997.0 | 5997.0 | 160.0 | 5997.0 | 0.9951094000001062 | 1.0 | 20.0 | 0.0 | 0.007402585188538067 | 0.008799383002252224 | 0.028625858947634693 | 0.00024910399224609137 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 0.04521679 | 0.030048715 | 0.12970752 | 0.010519697 | 0.4557785878050034 | 0.28863887894732576 | 1.0 | 0.0 |