mirror of
https://github.com/gryf/coach.git
synced 2026-01-27 10:35:45 +01:00
9.1 KiB
9.1 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 | Entropy/Mean | Entropy/Stdev | Entropy/Max | Entropy/Min | Advantages/Mean | Advantages/Stdev | Advantages/Max | Advantages/Min | Values/Mean | Values/Stdev | Values/Max | Values/Min | Value Loss/Mean | Value Loss/Stdev | Value Loss/Max | Value Loss/Min | Policy Loss/Mean | Policy Loss/Stdev | Policy Loss/Max | Policy Loss/Min |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 1 | 0.0 | 1.0 | 172.0 | 1.0 | 172.0 | 172.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 3 | 2 | 0.0 | 1.0 | 79.0 | 1.0 | 79.0 | 251.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 4 | 3 | 0.0 | 1.0 | 96.0 | 1.0 | 96.0 | 347.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 5 | 4 | 0.0 | 1.0 | 371.0 | 1.0 | 371.0 | 718.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 6 | 5 | 0.0 | 1.0 | 344.0 | 1.0 | 344.0 | 1062.0 | 0.0 | 0.0 | |||||||||||||||||||||||||||||||||||||
| 7 | 6 | 13.0 | 0.0 | 256.0 | 1.0 | 256.0 | 1318.0 | 0.0 | 6.0 | 80.0 | 0.0 | 0.1939039 | 0.23357692 | 0.7368739000000001 | 0.0009891555 | 1.7914561999999998 | 6.275484000000001e-05 | 1.7915926 | 1.7912834 | 0.08362045530580647 | 0.2835083108977154 | 1.0021963119506836 | -0.026535123586654663 | 0.018534478 | 0.011672256499999999 | 0.05661176 | 0.0029842237 | 0.09798307 | 0.12070587 | 0.37835634 | 6.473914999999999e-07 | 0.36854994 | 0.46473694 | 1.4749139999999998 | -0.025393225 | |||||||||||
| 8 | 7 | 26.0 | 0.0 | 246.0 | 1.0 | 246.0 | 1564.0 | 0.0 | 1.0 | 30.0 | 0.0 | 0.08165244 | 0.23873971 | 0.9071625 | 0.0013907178 | 1.7913811000000002 | 8.768854999999999e-05 | 1.7915218999999998 | 1.7910584999999999 | 0.052433485892834135 | 0.2362189112368607 | 0.9958824515342712 | -0.06492356210947038 | 0.08651774400000001 | 0.014406506000000001 | 0.11471594 | 0.062262025 | 0.028855542 | 0.09916820400000001 | 0.37237929999999997 | 5.4554444000000004e-06 | 0.090015836 | 0.3950097 | 1.4550724 | -0.11501935 | |||||||||||
| 9 | 8 | 39.0 | 0.0 | 250.0 | 1.0 | 250.0 | 1814.0 | 0.0 | 2.0 | 15.0 | 0.0 | 0.118730865 | 0.23050676 | 0.8342859 | 0.0062873980000000005 | 1.7910561999999999 | 0.00013169227 | 1.7913713 | 1.7907045 | 0.06942775857642414 | 0.27387010426111824 | 0.995813012123108 | -0.12133988738059998 | 0.14098579 | 0.01700316 | 0.17010905 | 0.11456248 | 0.03815781 | 0.094594575 | 0.33464396 | 2.4685245e-05 | 0.1061271 | 0.38644782 | 1.3102351 | -0.21626873 | |||||||||||
| 10 | 9 | 50.0 | 0.0 | 210.0 | 1.0 | 210.0 | 2024.0 | 0.0 | 3.0 | 20.0 | 0.0 | 0.23193313 | 0.30449572 | 0.9311134 | 0.00899503 | 1.7905103 | 0.00020560848 | 1.7909009999999999 | 1.7899324 | 0.10523414221547897 | 0.33149382287277845 | 0.9781109094619752 | -0.1670859158039093 | 0.24934901 | 0.042353228 | 0.32058814 | 0.16610189 | 0.05836196 | 0.096441336 | 0.28652105 | 8.585327e-05 | 0.16659279999999999 | 0.41485137 | 1.1323245000000002 | -0.29839557 | |||||||||||
| 11 | 10 | 61.0 | 0.0 | 212.0 | 1.0 | 212.0 | 2236.0 | 0.0 | 4.0 | 70.0 | 0.0 | 0.32342659999999995 | 0.30790272 | 0.8555848 | 0.013926556999999999 | 1.7894892 | 0.00039297919999999997 | 1.7902182 | 1.7887098000000001 | 0.08880569367181687 | 0.3488985080475792 | 0.9698122143745422 | -0.3336267471313477 | 0.36182004 | 0.022110098999999998 | 0.4138433 | 0.33095813 | 0.06438857 | 0.08437334 | 0.22828464 | 0.000108950946 | 0.124975175 | 0.42336643 | 0.88634026 | -0.59684265 | |||||||||||
| 12 | 11 | 66.0 | 0.0 | 85.0 | 1.0 | 85.0 | 2321.0 | 0.0 | 1.0 | 30.0 | 0.0 | 0.41213423 | 0.41036695 | 0.9209540999999999 | 0.02874862 | 1.7878921000000003 | 0.00040299798 | 1.7886634 | 1.7874249 | 0.01413497199182925 | 0.3305238214394232 | 0.9422454833984376 | -0.4276147782802582 | 0.474797 | 0.025047962000000003 | 0.5020342000000001 | 0.42557920000000005 | 0.05761523 | 0.07662827 | 0.19414958 | 0.0001560097 | -0.035874914 | 0.48606595 | 0.770897 | -0.7607916 | |||||||||||
| 13 | 12 | 80.0 | 0.0 | 269.0 | 1.0 | 269.0 | 2590.0 | 0.0 | 10.0 | 155.0 | 0.0 | 0.7854741 | 0.61122286 | 2.0192683000000002 | 0.08156464 | 1.7877086 | 0.0004950542400000001 | 1.7886578999999998 | 1.7865233 | 0.23643413107350186 | 0.4508260846357569 | 1.7852727174758911 | -0.5098529458045961 | 0.5770814999999999 | 0.057316255 | 0.7294182 | 0.5092656 | 0.12958637 | 0.11670861 | 0.34610382 | 0.0011639375999999999 | 0.35314107 | 0.6014643 | 1.3190441000000002 | -0.8972452 | |||||||||||
| 14 | 13 | 96.0 | 0.0 | 307.0 | 1.0 | 307.0 | 2897.0 | 0.0 | 2.0 | 55.0 | 0.0 | 0.6835559 | 0.7919847 | 2.5515141 | 0.11776459 | 1.7864368000000002 | 0.0008910961 | 1.7882001 | 1.7847111 | -0.007878692790528332 | 0.32175653645309904 | 1.0167803764343262 | -0.7849382162094116 | 0.8201937 | 0.044757877 | 0.9314514000000002 | 0.7363194000000001 | 0.060591087 | 0.11536394 | 0.30912948 | 0.0013666659 | -0.06033127 | 0.57552105 | 1.2361087 | -1.4030191 | |||||||||||
| 15 | 14 | 108.0 | 0.0 | 234.0 | 1.0 | 234.0 | 3131.0 | 0.0 | 3.0 | 30.0 | 0.0 | 0.78226376 | 0.9813715000000001 | 3.151555 | 0.14258601 | 1.7866498 | 0.0005507571599999999 | 1.7877802999999999 | 1.7852042000000001 | 0.02568793296813965 | 0.40875480381736573 | 1.7683660984039309 | -0.8106249570846558 | 0.8077873000000001 | 0.045067918 | 0.9006464 | 0.71874654 | 0.09711338 | 0.18768145 | 0.63309157 | 0.0015460347 | -0.038251024 | 0.6832404000000001 | 1.6775835 | -1.4815241000000001 | |||||||||||
| 16 | 15 | 122.0 | 0.0 | 278.0 | 1.0 | 278.0 | 3409.0 | 0.0 | 5.0 | 55.0 | 0.0 | 0.8513360000000001 | 0.82638085 | 2.795295 | 0.22822826 | 1.7804738000000002 | 0.0008289394 | 1.7820467 | 1.7777349999999998 | -0.00817263213387371 | 0.375063986240502 | 1.6957457065582275 | -0.8087333440780641 | 1.0294096 | 0.079321235 | 1.1694813999999998 | 0.80778354 | 0.07585998 | 0.109308355 | 0.32657412 | 0.0031131029 | -0.047679655 | 0.5682114 | 1.0088061 | -1.4467055 | |||||||||||
| 17 | 16 | 134.0 | 0.0 | 227.0 | 1.0 | 227.0 | 3636.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.48871526 | 0.82123524 | 3.195592 | 0.09071884 | 1.7821561000000001 | 0.0012469257 | 1.784389 | 1.7793628000000001 | -0.13936789671913916 | 0.2279292829991838 | 0.0393567681312561 | -0.9175797104835509 | 0.7584516 | 0.09492830000000001 | 0.9175796999999999 | 0.6327223000000001 | 0.038895883 | 0.115141146 | 0.4206835 | 0.0009816721 | -0.26428798 | 0.42974713 | -0.040148623 | -1.6828988999999999 | |||||||||||
| 18 | 17 | 140.0 | 0.0 | 104.0 | 1.0 | 104.0 | 3740.0 | 0.0 | 2.0 | 55.0 | 0.0 | 0.7989983 | 0.81866854 | 2.0175614 | 0.13499123 | 1.7826772000000002 | 0.0005859441000000001 | 1.7836678 | 1.7805796000000003 | 0.08999087292457296 | 0.4078624577461926 | 0.9879480600357056 | -0.612851619720459 | 0.58374363 | 0.013967522 | 0.6385208 | 0.5463154 | 0.09809959 | 0.11959576599999999 | 0.32074562 | 0.0018951653 | 0.021689498999999998 | 0.6981469 | 1.3021398000000002 | -1.0750053 | |||||||||||
| 19 | 18 | 151.0 | 0.0 | 206.0 | 1.0 | 206.0 | 3946.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.30109861 | 0.42863026 | 1.6318218 | 0.024273846 | 1.7810868000000002 | 0.0018248269 | 1.7836068999999999 | 1.7771342 | -0.07027812360548506 | 0.08544758471104902 | 0.03890836238861084 | -0.5683711171150208 | 0.6190444 | 0.08390967 | 0.7634859 | 0.49114496 | 0.01740619 | 0.045553422999999996 | 0.16130316 | 0.00016215799 | -0.18555973 | 0.25699073 | 0.017696667 | -0.9813569999999999 | |||||||||||
| 20 | 19 | 156.0 | 0.0 | 97.0 | 1.0 | 97.0 | 4043.0 | 0.0 | 3.0 | 30.0 | 0.0 | 0.8886533000000001 | 0.7262031999999999 | 1.8018917 | 0.10955945 | 1.7840089 | 0.00088417256 | 1.7852848000000001 | 1.7817863999999999 | 0.22950440749179485 | 0.5369416196236759 | 1.736410140991211 | -0.5863370895385742 | 0.5336522 | 0.030709412000000002 | 0.6000352 | 0.48364946 | 0.17067215 | 0.19014555 | 0.52218485 | 0.0016030882999999998 | 0.2313029 | 0.9121447 | 1.7663547999999998 | -0.98603886 | |||||||||||
| 21 | 20 | 166.0 | 0.0 | 183.0 | 1.0 | 183.0 | 4226.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.16478795 | 0.2597316 | 0.9318068000000002 | 0.041520268 | 1.7873531999999999 | 0.0010197633 | 1.7886186000000002 | 1.7846171999999998 | -0.07996185018023863 | 0.129189742252069 | 0.005220502614974976 | -0.4877886474132538 | 0.3611083 | 0.06760349 | 0.5029814 | 0.30043033 | 0.0131516205 | 0.03526333 | 0.11885357 | 0.00041889559999999995 | -0.15650481 | 0.25072926 | -0.038283065 | -0.90064216 | |||||||||||
| 22 | 21 | 182.0 | 0.0 | 305.0 | 1.0 | 305.0 | 4531.0 | 0.0 | 8.0 | 120.0 | 0.0 | 0.36005658 | 0.45654875 | 1.3189906 | 0.019862599999999998 | 1.7882812 | 0.0006836434 | 1.7891648999999998 | 1.7862711 | 0.14736928680155534 | 0.3950499387791654 | 1.8571623563766482 | -0.2961172163486481 | 0.34672654 | 0.06091405 | 0.45681846 | 0.2583802 | 0.08649684 | 0.13315138 | 0.42525712 | 0.0002329228 | 0.22294542 | 0.53374773 | 1.3210396999999998 | -0.507426 | |||||||||||
| 23 | 22 | 198.0 | 0.0 | 315.0 | 1.0 | 315.0 | 4846.0 | 0.0 | 1.0 | 15.0 | 0.0 | 0.12476806 | 0.15976351 | 0.5805328000000001 | 0.0331938 | 1.7890745 | 0.00061386684 | 1.7899171000000003 | 1.7873763999999999 | -0.016061681997580606 | 0.1462906548848707 | 0.9435402154922484 | -0.2866329252719879 | 0.34289262 | 0.030059232999999998 | 0.4223661 | 0.28609840000000003 | 0.012243593 | 0.035346977 | 0.14386486 | 0.00027169447 | -0.051272526 | 0.18682721 | 0.5297608 | -0.5158093 | |||||||||||
| 24 | 23 | 212.0 | 0.0 | 271.0 | 1.0 | 271.0 | 5117.0 | 0.0 | 8.0 | 145.0 | 0.0 | 0.48250297 | 0.47027257 | 1.6362126000000001 | 0.051737264000000005 | 1.7888765 | 0.00047472015 | 1.7899599 | 1.7875865000000002 | 0.1621383027596907 | 0.4242934661478944 | 1.7547135353088381 | -0.34980177879333496 | 0.39830664 | 0.04178729 | 0.48849440000000005 | 0.34308335 | 0.10240511 | 0.12464721 | 0.41274893 | 0.00043522472999999996 | 0.27840075 | 0.54285455 | 1.3755229 | -0.6290853 | |||||||||||
| 25 | 24 | 226.0 | 0.0 | 273.0 | 1.0 | 273.0 | 5390.0 | 0.0 | 7.0 | 110.0 | 0.0 | 0.64035225 | 0.6757314999999999 | 2.4957256 | 0.12514906 | 1.7852096999999998 | 0.0011479441 | 1.7868727 | 1.7825445 | 0.08592067488445126 | 0.3931141975744933 | 1.0465660095214844 | -0.4963456690311432 | 0.79777867 | 0.104742296 | 1.0267005 | 0.49577040000000006 | 0.08231286 | 0.10447255 | 0.3813585 | 0.0014453817000000002 | 0.11812396 | 0.54338455 | 1.4572146000000001 | -0.8762894 | |||||||||||
| 26 | 25 | 246.0 | 0.0 | 386.0 | 1.0 | 386.0 | 5776.0 | 0.0 | 1.0 | 10.0 | 0.0 | 0.40528044 | 0.70595944 | 3.3607516000000004 | 0.026335992000000003 | 1.7871827 | 0.0016742881 | 1.7896813999999999 | 1.7822630000000002 | -0.06738319613854697 | 0.21423599108892588 | 0.9312911033630372 | -0.8724940419197083 | 0.70102185 | 0.086727455 | 0.8822230999999999 | 0.54569244 | 0.031398702 | 0.089344375 | 0.37835726 | 0.0005658056500000001 | -0.141334 | 0.36514923 | 0.76326364 | -1.4879048000000001 |