mirror of
https://github.com/gryf/coach.git
synced 2026-01-28 19:15:46 +01:00
6.0 KiB
6.0 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 | 269.0 | 269.0 | 269.0 | 269.0 | 7.0 | 0.0 | |||||||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 531.0 | 531.0 | 262.0 | 531.0 | 3.0 | 0.0 | |||||||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 642.0 | 642.0 | 111.0 | 642.0 | 7.0 | 0.0 | |||||||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 910.0 | 910.0 | 268.0 | 910.0 | 5.0 | 0.0 | |||||||||||||||||||||
| 6 | 5 | 0.0 | 1.0 | 1073.0 | 1073.0 | 163.0 | 1073.0 | 1.0 | 0.0 | |||||||||||||||||||||
| 7 | 6 | 50.0 | 0.0 | 1272.0 | 1272.0 | 199.0 | 1272.0 | 0.0 | 3.0 | 30.0 | 0.0 | 0.0060499068777426146 | 0.008313927440521758 | 0.031962748616933816 | 0.00017436122288927436 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.006024469 | 0.004143363 | 0.015487617 | 0.0021843307 | |||||||
| 8 | 7 | 69.0 | 0.0 | 1350.0 | 1350.0 | 78.0 | 1350.0 | 9.0 | 2.0 | 15.0 | 0.0 | 0.003501874725579431 | 0.008346458210326759 | 0.03235147148370743 | 0.0001113867838284932 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.0035943978000000003 | 0.003989689 | 0.015995007 | 0.0016262016 | |||||||
| 9 | 8 | 119.0 | 0.0 | 1550.0 | 1550.0 | 200.0 | 1550.0 | 5.0 | 2.0 | 45.0 | 0.0 | 0.007876217254815856 | 0.009940253725264405 | 0.031399693340063095 | 0.00010039866901934148 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.005710288399999999 | 0.005156745999999999 | 0.020595245 | 0.0013811021 | |||||||
| 10 | 9 | 201.0 | 0.0 | 1878.0 | 1878.0 | 328.0 | 1878.0 | 7.0 | 5.0 | 75.0 | 0.0 | 0.006828064881829494 | 0.010099699510598852 | 0.03090276196599007 | 0.00011350225395290181 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.0051478767 | 0.0047958459999999994 | 0.0203429 | 0.001394469 | |||||||
| 11 | 10 | 312.0 | 0.0 | 2322.0 | 2322.0 | 444.0 | 2322.0 | 1.0 | 1.0 | 30.0 | 0.0 | 0.005469505370988905 | 0.008928910220019012 | 0.044973984360694885 | 0.00013608467997983098 | 0.0002500000000000001 | 1.0842021724855042e-19 | 0.00025 | 0.00025 | 0.00466364 | 0.0040628504999999995 | 0.021865747999999997 | 0.0016691639999999999 | |||||||
| 12 | 11 | 342.0 | 0.0 | 2441.0 | 2441.0 | 119.0 | 2441.0 | 8.0 | 2.0 | 15.0 | 0.0 | 0.00828334405135441 | 0.010910730739359574 | 0.04589846357703209 | 0.0001410357654094696 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.005825627 | 0.005012808400000001 | 0.019443423 | 0.0015227376000000001 | |||||||
| 13 | 12 | 385.0 | 0.0 | 2611.0 | 2611.0 | 170.0 | 2611.0 | 1.0 | 3.0 | 30.0 | 0.0 | 0.005404766050010356 | 0.008490796312006945 | 0.030357897281646732 | 0.00013974733883515 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.0044133128 | 0.0039297505 | 0.013841972 | 0.0012999868 | |||||||
| 14 | 13 | 456.0 | 0.0 | 2898.0 | 2898.0 | 287.0 | 2898.0 | 6.0 | 5.0 | 90.0 | 0.0 | 0.004022052818597754 | 0.007086255561643891 | 0.030808655545115467 | 0.00014122753054834902 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.0038387226 | 0.0034813196000000003 | 0.013518038999999999 | 0.0014702336999999998 | |||||||
| 15 | 14 | 497.0 | 0.0 | 3062.0 | 3062.0 | 164.0 | 3062.0 | 4.0 | 0.0 | 0.0 | 0.0 | 0.0042548857908979885 | 0.0074758880380001455 | 0.03025482408702373 | 0.00016087367839645594 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.0039765667 | 0.0035351904 | 0.013480025 | 0.0016169035 | |||||||
| 16 | 15 | 617.0 | 0.0 | 3542.0 | 3542.0 | 480.0 | 3542.0 | 1.0 | 6.0 | 75.0 | 0.0 | 0.006593966874910014 | 0.009290417878413549 | 0.030973667278885838 | 0.000136182876303792 | 0.0002500000000000001 | 1.0842021724855042e-19 | 0.00025 | 0.00025 | 0.004996340300000001 | 0.004391069 | 0.02013114 | 0.001432074 | 0.014001195 | 0.0048342915 | 0.020594118 | 0.0064951440000000004 | |||
| 17 | 16 | 749.0 | 0.0 | 4069.0 | 4069.0 | 527.0 | 4069.0 | 9.0 | 14.0 | 245.0 | 0.0 | 0.008309065473440569 | 0.010667314782975073 | 0.04523996263742447 | 0.00016428592789452526 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.0059988964 | 0.004459505999999999 | 0.02182284 | 0.0017576158 | 0.02046494 | 0.008859338000000001 | 0.037309642999999997 | 0.0034312569 | |||
| 18 | 17 | 781.0 | 0.0 | 4198.0 | 4198.0 | 129.0 | 4198.0 | 7.0 | 1.0 | 15.0 | 0.0 | 0.006336112672215678 | 0.008304921845849803 | 0.03077610209584236 | 0.0001919775095302612 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.00534597 | 0.0037583890000000004 | 0.014207858 | 0.0021436373 | |||||||
| 19 | 18 | 841.0 | 0.0 | 4438.0 | 4438.0 | 240.0 | 4438.0 | 9.0 | 2.0 | 15.0 | 0.0 | 0.005212442750053015 | 0.009321893945503649 | 0.044901248067617416 | 0.00017039758677128702 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.004599525 | 0.004160135 | 0.021621725 | 0.0018743542999999998 | 0.026541417 | 0.010017343 | 0.039867945 | 0.010387515 | |||
| 20 | 19 | 900.0 | 0.0 | 4674.0 | 4674.0 | 236.0 | 4674.0 | 1.0 | 4.0 | 50.0 | 0.0 | 0.0056087239258192575 | 0.008758416501990723 | 0.030815929174423218 | 0.0001515848562121391 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.004823039 | 0.0045088935 | 0.020195715 | 0.0017171134 | 0.013790057 | 0.008472809 | 0.030765671 | 0.00264489 | |||
| 21 | 20 | 938.0 | 0.0 | 4824.0 | 4824.0 | 150.0 | 4824.0 | 8.0 | 3.0 | 70.0 | 0.0 | 0.007760794000013878 | 0.009675916785758777 | 0.030620882287621495 | 0.00015613727737218142 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.005812586999999999 | 0.005044727 | 0.020025931 | 0.0016528887 | 0.019592494 | 0.010325795 | 0.031668893999999996 | 0.0011506106 | |||
| 22 | 21 | 998.0 | 0.0 | 5064.0 | 5064.0 | 240.0 | 5064.0 | 5.0 | 4.0 | 40.0 | 0.0 | 0.006734883858734974 | 0.01012093517361649 | 0.04593200609087944 | 0.00015258873463608325 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.0050609284 | 0.004594935 | 0.022529753 | 0.0015191837 | 0.03485959 | 0.008621039 | 0.045938405999999994 | 0.022119842 | |||
| 23 | 22 | 1018.0 | 0.0 | 5145.0 | 5145.0 | 81.0 | 5145.0 | 6.0 | 1.0 | 15.0 | 0.0 | 0.006149832173832692 | 0.008713121196366134 | 0.030442113056778908 | 0.00017446294077672064 | 0.0002500000000000001 | 5.421010862427521e-20 | 0.00025 | 0.00025 | 0.0048099845 | 0.0038082603999999996 | 0.013654656999999999 | 0.0017780153 | 0.020728394 | 0.007859956 | 0.031289592000000005 | 0.005306163000000001 | |||
| 24 | 23 | 1043.0 | 0.0 | 5244.0 | 5244.0 | 99.0 | 5244.0 | 6.0 | 0.0 | 0.0 | 0.0 | 0.005615412016632035 | 0.010374376530714843 | 0.04561242461204529 | 0.00014486268628388646 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.004630377 | 0.0049269767 | 0.022269842999999998 | 0.0015429979999999999 | |||||||
| 25 | 24 | 1096.0 | 0.0 | 5458.0 | 5458.0 | 214.0 | 5458.0 | 4.0 | 4.0 | 50.0 | 0.0 | 0.007605906390587201 | 0.011603800537879164 | 0.045488771051168435 | 0.00015640168567188084 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.005479771 | 0.005164023 | 0.022413598 | 0.0016174479999999998 | 0.016956704 | 0.0052281856 | 0.027700908 | 0.010438837 | |||
| 26 | 25 | 1112.0 | 0.0 | 5522.0 | 5522.0 | 64.0 | 5522.0 | 4.0 | 2.0 | 15.0 | 0.0 | 0.007761852173644002 | 0.010677922322799452 | 0.03070169128477573 | 0.00017511004989501092 | 0.00025 | 0.0 | 0.00025 | 0.00025 | 0.005504951 | 0.004377631 | 0.014095218999999999 | 0.0019523804999999998 |