mirror of
https://github.com/gryf/coach.git
synced 2026-01-08 23:04:15 +01:00
6.1 KiB
6.1 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 | 0.011183103105377444 | 0.014410822062387516 | 0.05476783961057663 | 0.0003677908971440047 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.055503722 | 0.032865092 | 0.16610849 | 0.021884395 | 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 | 0.01158408456371705 | 0.011209879212701484 | 0.03173057734966278 | 0.0005988621851429343 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.05140475 | 0.027607668 | 0.10046375 | 0.015951207 | 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 | 0.012028654183571538 | 0.013925151158931906 | 0.0453290306031704 | 0.000580522115342319 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.05280188 | 0.033149354 | 0.12848708 | 0.014346301 | 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 | 0.008890328782874702 | 0.010611031343599557 | 0.0433015301823616 | 0.0002625669294502586 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.044512487999999996 | 0.028437497000000003 | 0.1261624 | 0.011307655 | 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 | 0.00593758387826494 | 0.00914683642113945 | 0.042670093476772315 | 0.00034154887543991213 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.033279017 | 0.022491325 | 0.10537 | 0.012801617 | 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 | 0.009939338280393992 | 0.012428604102262037 | 0.0576869547367096 | 0.00017358829791191963 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.04424335 | 0.031942975 | 0.13327447 | 0.0067878882 | 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 | 0.00870171979070433 | 0.01037270494336379 | 0.04583200067281723 | 0.00026610741042532027 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.041462347000000004 | 0.027223505 | 0.12059208 | 0.009434708 | 1.3803392321717662 | 1.096111017851517 | 4.070269499186656 | 0.0 | 0.027678333 | 0.016764535 | 0.053045444000000004 | 0.0045971097 | |||
| 13 | 12 | 458.0 | 0.0 | 2888.0 | 2888.0 | 73.0 | 2888.0 | 0.9981873100000394 | 2.0 | 45.0 | 0.0 | 0.009584656547910223 | 0.010643640586108307 | 0.04042205587029457 | 0.0006025769980624317 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.049134042 | 0.021210407999999997 | 0.10733061 | 0.022078212000000003 | 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 | 0.007050403149332852 | 0.008387780876226303 | 0.02977199479937553 | 0.000406973238568753 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.037633214 | 0.021981938 | 0.09354922 | 0.009606971 | 0.0 | 0.0 | 0.0 | 0.0 | 0.010962226 | 0.0059837530000000005 | 0.017315589 | 0.0030681575 | |||
| 15 | 14 | 532.0 | 0.0 | 3183.0 | 3183.0 | 214.0 | 3183.0 | 0.9978952600000456 | 4.0 | 50.0 | 0.0 | 0.0069784580067520155 | 0.009686524769251392 | 0.030508352443575863 | 0.00021116754214745012 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.03361736 | 0.027158314 | 0.090094596 | 0.006826394 | 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 | 0.008487855488630501 | 0.012149024477944621 | 0.041097059845924384 | 0.00016619838424958291 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.037613284 | 0.031661812000000004 | 0.11693966 | 0.0077320784 | 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 | 0.009145274811827048 | 0.009826568464368279 | 0.03911060467362404 | 0.00029626555624417966 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.04454368400000001 | 0.024877137 | 0.116107136 | 0.011620078 | 1.2555763711101595 | 0.9240906493644656 | 3.083943769311809 | 0.0 | -0.009515476 | 0.014890236999999999 | 0.008131558 | -0.026531402000000003 | |||
| 18 | 17 | 916.0 | 0.0 | 4719.0 | 4719.0 | 1159.0 | 4719.0 | 0.9963746200000788 | 22.0 | 340.0 | 0.0 | 0.007740728036050909 | 0.009543641335623288 | 0.04788558185100555 | 0.00019856891594827172 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.040538322 | 0.027717842000000003 | 0.13175875 | 0.007012263 | 1.7863437362163082 | 1.2694439341830603 | 5.47755081893663 | 0.0 | 0.029519184 | 0.023950322000000003 | 0.08333874 | -0.007110496 | |||
| 19 | 18 | 943.0 | 0.0 | 4830.0 | 4830.0 | 111.0 | 4830.0 | 0.9962647300000812 | 3.0 | 45.0 | 0.0 | 0.01004010205226088 | 0.011472325922009141 | 0.04534837231040001 | 0.0003742414410226047 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.048849717 | 0.02810786 | 0.105786964 | 0.012940223999999998 | 0.9476068702387164 | 1.155150613645887 | 2.9121653479069898 | 0.0 | |||||||
| 20 | 19 | 1006.0 | 0.0 | 5081.0 | 5081.0 | 251.0 | 5081.0 | 0.9960162400000864 | 0.0 | 0.0 | 0.0 | 0.011529832825838256 | 0.010865886687557577 | 0.04211260378360748 | 0.00035901699448004365 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.052312527000000004 | 0.028365135 | 0.14662467 | 0.01172117 | 0.0 | 0.0 | 0.0 | 0.0 | |||||||
| 21 | 20 | 1059.0 | 0.0 | 5291.0 | 5291.0 | 210.0 | 5291.0 | 0.9958083400000909 | 5.0 | 75.0 | 0.0 | 0.007634635624818435 | 0.009146711582695735 | 0.04330553486943245 | 0.00023420021170750258 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.041878007 | 0.026667656 | 0.12924000000000002 | 0.009081989 | 1.6777845523030963 | 0.9783362942105612 | 3.4696586199088006 | 0.0 | 0.028786177000000003 | 0.02283817 | 0.063100584 | 0.0019607039 |