mirror of
https://github.com/gryf/coach.git
synced 2026-01-30 20:35:47 +01:00
7.6 KiB
7.6 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 | 36.39371548271647 | 49.45138568291551 | 199.1195526123047 | 0.19053678214550016 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 7.532597999999999 | 7.1016245 | 33.78272 | 1.4505563999999997 | 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 | 39.265952220872826 | 41.12147905803706 | 99.56693267822266 | 0.20913273096084595 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 9.42191 | 7.0360494000000005 | 23.090874 | 2.064445 | 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 | 37.98109634149642 | 47.905636816865616 | 148.4886474609375 | 0.2750575840473175 | 5e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 10.243463499999999 | 7.6128125 | 32.07251 | 3.250062 | 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 | 28.930436090746927 | 36.11691394038722 | 147.92953491210938 | 0.3181586265563965 | 5.0000000000000016e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 10.44046 | 6.4473057 | 32.9211 | 4.3905983 | 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 | 18.96833928142275 | 31.799296642491196 | 146.1549530029297 | 0.3456725478172302 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 8.966327 | 7.091922 | 41.89229 | 4.5536304 | 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 | 32.09392697803485 | 42.13298296371022 | 195.0815734863281 | 0.2923644483089447 | 5.0000000000000016e-05 | 2.0328790734103208e-20 | 5e-05 | 5e-05 | 15.759795 | 11.353839 | 70.18659 | 3.342692 | 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 | 28.14659144123149 | 34.815239080658415 | 144.4326171875 | 0.4303665161132813 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 18.55 | 12.039677000000001 | 87.61861 | 5.962619999999999 | 1.3803392321717662 | 1.096111017851517 | 4.070269499186656 | 0.0 | 0.017199665581962714 | 0.0031208499377391747 | 0.021268549477972555 | 0.013525613469537349 | |||
| 13 | 12 | 458.0 | 0.0 | 2888.0 | 2888.0 | 73.0 | 2888.0 | 0.9981873100000394 | 2.0 | 45.0 | 0.0 | 31.14651732312309 | 36.85799012635688 | 138.88088989257812 | 1.0084846019744873 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 29.951015 | 16.332592 | 75.88148000000001 | 14.728288000000001 | 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 | 21.76374124884605 | 26.82507406559877 | 94.766845703125 | 1.2202812433242798 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 26.107689999999998 | 6.088878 | 41.73264 | 17.984592000000003 | 0.0 | 0.0 | 0.0 | 0.0 | 0.01866802644651519 | 0.004178971677646881 | 0.023218704897008138 | 0.011671426802058705 | |||
| 15 | 14 | 532.0 | 0.0 | 3183.0 | 3183.0 | 214.0 | 3183.0 | 0.9978952600000456 | 4.0 | 50.0 | 0.0 | 22.0509301479216 | 31.086725403761662 | 93.48860931396484 | 0.800851583480835 | 5.0000000000000016e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 24.249879999999997 | 15.414260999999998 | 74.55404 | 11.378158 | 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 | 26.60526430606842 | 38.69304492048134 | 133.52310180664062 | 0.7627888321876526 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 29.563177000000003 | 27.568185999999997 | 111.50503 | 11.430572 | 0.7209514730836505 | 0.7680412970584659 | 1.8953382542587165 | 0.0 | |||||||
| 17 | 16 | 632.0 | 0.0 | 3584.0 | 3584.0 | 322.0 | 3584.0 | 0.9974982700000544 | 6.0 | 145.0 | 0.0 | 26.971557103097442 | 31.434959821173138 | 125.12825012207031 | 0.910109519958496 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 33.74196 | 20.234205 | 147.04688000000002 | 13.579481 | 1.1770031212416605 | 0.8262292064074209 | 3.0179431656102578 | 0.0 | 0.013656995417435005 | 0.005333211900559342 | 0.01954438033906626 | 0.006371547533963168 | |||
| 18 | 17 | 671.0 | 0.0 | 3742.0 | 3742.0 | 158.0 | 3742.0 | 0.9973418500000576 | 2.0 | 15.0 | 0.0 | 28.62383951132114 | 32.79578258247046 | 93.93648529052734 | 0.9729704260826112 | 4.999999999999999e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 32.46002 | 18.16512 | 81.844734 | 14.586188 | 0.6005911651530309 | 0.5453746168835384 | 1.5870367819374844 | 0.0 | 0.03191614872266655 | 0.00667430942512365 | 0.04514769844769035 | 0.023792251308041155 | |||
| 19 | 18 | 692.0 | 0.0 | 3823.0 | 3823.0 | 81.0 | 3823.0 | 0.9972616600000594 | 2.0 | 15.0 | 0.0 | 25.202779620885853 | 30.552071620815717 | 125.29591369628906 | 1.7230273485183716 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 39.337395 | 21.905525 | 132.3519 | 25.856197 | 0.7922353902907879 | 0.6952623969580528 | 1.8179069375972308 | 0.0 | |||||||
| 20 | 19 | 724.0 | 0.0 | 3954.0 | 3954.0 | 131.0 | 3954.0 | 0.9971319700000624 | 3.0 | 60.0 | 0.0 | 22.967615332454443 | 25.815068446331463 | 86.47146606445312 | 1.1379579305648804 | 5e-05 | 0.0 | 5e-05 | 5e-05 | 33.888259999999995 | 16.320104999999998 | 92.47138000000001 | 16.30554 | 0.9800021878033628 | 0.8735070818924148 | 2.46433739265332 | 0.0 | |||||||
| 21 | 20 | 892.0 | 0.0 | 4624.0 | 4624.0 | 670.0 | 4624.0 | 0.9964686700000768 | 10.0 | 120.0 | 0.0 | 26.94163532028655 | 32.71184937290853 | 172.76866149902344 | 0.6505141854286194 | 5e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 37.312836 | 23.1887 | 165.69048999999998 | 9.836427 | 1.3694909525397223 | 0.977245098695965 | 4.034435997798811 | 0.0 | 0.03216368277622071 | 0.01633922464087734 | 0.06566673704037385 | 0.004426548708725025 | |||
| 22 | 21 | 1039.0 | 0.0 | 5212.0 | 5212.0 | 588.0 | 5212.0 | 0.9958865500000892 | 7.0 | 305.0 | 0.0 | 25.77646716922319 | 30.437974512340155 | 129.35916137695312 | 0.7989792227745056 | 5.0000000000000016e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 35.62171 | 19.011225 | 129.2298 | 11.903933 | 0.8833582927089424 | 0.6666778268136587 | 2.4487212795420223 | 0.0 | 0.01983640661286093 | 0.005789663785793397 | 0.027688373105920615 | 0.013402554265921934 | |||
| 23 | 22 | 1062.0 | 0.0 | 5306.0 | 5306.0 | 94.0 | 5306.0 | 0.9957934900000912 | 1.0 | 30.0 | 0.0 | 28.046357004538827 | 35.999259041663095 | 129.90437316894528 | 0.7184672355651855 | 4.999999999999999e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 34.574165 | 28.98651 | 119.78352 | 10.539461 | 0.2925741106831343 | 0.4098911262217585 | 1.0 | 0.0 | |||||||
| 24 | 23 | 1121.0 | 0.0 | 5540.0 | 5540.0 | 234.0 | 5540.0 | 0.9955618300000963 | 5.0 | 65.0 | 0.0 | 27.472846814270678 | 31.7742525124272 | 119.24581909179688 | 1.3385473489761353 | 5.000000000000001e-05 | 6.776263578034403e-21 | 5e-05 | 5e-05 | 45.069244 | 29.056599 | 165.97798 | 20.73777 | 1.2611240480922348 | 0.9471053795173676 | 2.9127534883249893 | 0.0 | |||||||
| 25 | 24 | 1159.0 | 0.0 | 5692.0 | 5692.0 | 152.0 | 5692.0 | 0.9954113500000996 | 0.0 | 0.0 | 0.0 | 22.508516057541495 | 29.69980634890218 | 134.62515258789062 | 1.1457782983779907 | 4.999999999999999e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 36.56114 | 22.830523 | 142.84929 | 18.496206 | 0.0 | 0.0 | 0.0 | 0.0 | |||||||
| 26 | 25 | 1211.0 | 0.0 | 5901.0 | 5901.0 | 209.0 | 5901.0 | 0.995204440000104 | 3.0 | 55.0 | 0.0 | 21.163342314270828 | 25.83502308281645 | 95.9129867553711 | 0.8334482908248901 | 5.0000000000000016e-05 | 1.3552527156068802e-20 | 5e-05 | 5e-05 | 26.855858 | 13.416523999999999 | 70.00622 | 12.89766 | 0.952000039655271 | 0.6733299902533258 | 2.0831709161120813 | 0.0 |