coach/rl_coach/traces/Atari_DDQN_space_invaders/trace.csv at 72a1d9d426004269997f8b40bdd64f8ee582d91e

gryf/coach

mirror of https://github.com/gryf/coach.git synced 2026-01-29 19:55:56 +01:00

Files

Itai Caspi 72a1d9d426 Itaicaspi/episode reset refactoring (#105 )

* reordering of the episode reset operation and allowing to store episodes only when they are terminated

* reordering of the episode reset operation and allowing to store episodes only when they are terminated

* revert tensorflow-gpu to 1.9.0 + bug fix in should_train()

* tests readme file and refactoring of policy optimization agent train function

* Update README.md

* Update README.md

* additional policy optimization train function simplifications

* Updated the traces after the reordering of the environment reset

* docker and jenkins files

* updated the traces to the ones from within the docker container

* updated traces and added control suite to the docker

* updated jenkins file with the intel proxy + updated doom basic a3c test params

* updated line breaks in jenkins file

* added a missing line break in jenkins file

* refining trace tests ignored presets + adding a configurable beta entropy value

* switch the order of trace and golden tests in jenkins + fix golden tests processes not killed issue

* updated benchmarks for dueling ddqn breakout and pong

* allowing dynamic updates to the loss weights + bug fix in episode.update_returns

* remove docker and jenkins file

2018-09-04 15:07:54 +03:00

6.3 KiB

Raw Blame History

1	Episode #	Training Iter	In Heatup	ER #Transitions	ER #Episodes	Episode Length	Total steps	Epsilon	Shaped Training Reward	Training Reward	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	486.0	486.0	486.0	486.0	1.0
3	2	0.0	1.0	573.0	573.0	87.0	573.0	1.0
4	3	0.0	1.0	722.0	722.0	149.0	722.0	1.0
5	4	0.0	1.0	1057.0	1057.0	335.0	1057.0	1.0
6	5	51.0	0.0	1260.0	1260.0	203.0	1260.0	0.9997990300000044	5.0	55.0	0.011007826140734787	0.014603481057153478	0.05728723481297492	0.00017679380835033953	0.00025	0.0	0.00025	0.00025	0.05001448	0.03673725	0.18864875	0.012782556
7	6	70.0	0.0	1335.0	1335.0	75.0	1335.0	0.999724780000006	2.0	15.0	0.011499390747447154	0.010961000063645872	0.0315467044711113	0.0005441936664283277	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.05759323400000001	0.024992667000000003	0.11028934	0.022131458
8	7	91.0	0.0	1422.0	1422.0	87.0	1422.0	0.9996386500000078	1.0	15.0	0.01132884354696476	0.013429386203264964	0.04364541172981262	0.000340703729307279	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.055466358	0.03408065	0.13973257	0.016833907
9	8	159.0	0.0	1693.0	1693.0	271.0	1693.0	0.9993703600000136	5.0	55.0	0.008705972996627245	0.01046594152738398	0.04259247332811356	0.00026405457174405456	0.00025	0.0	0.00025	0.00025	0.04516968	0.027806934	0.12673344	0.0123512
10	9	201.0	0.0	1861.0	1861.0	168.0	1861.0	0.9992040400000172	3.0	50.0	0.005878299186449675	0.009437852632040231	0.04434124007821083	0.00013726821634918449	0.00025	0.0	0.00025	0.00025	0.031320102999999995	0.02600094	0.118447885	0.008186511
11	10	279.0	0.0	2172.0	2172.0	311.0	2172.0	0.998896150000024	4.0	65.0	0.009727142530699404	0.012268936533653787	0.05482503771781922	0.00013224119902588427	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.045818377	0.03322848	0.13469987	0.006579738000000001
12	11	440.0	0.0	2815.0	2815.0	643.0	2815.0	0.9982595800000378	10.0	335.0	0.008651261723684205	0.01035218743544492	0.0460522323846817	0.00012582635099533943	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.042565465	0.027683503999999998	0.13492820000000003	0.0055641527	0.010471878	0.016772145	0.03140713	-0.011288109
13	12	458.0	0.0	2888.0	2888.0	73.0	2888.0	0.9981873100000394	2.0	45.0	0.009507577900270313	0.010686165551315943	0.03972183912992477	0.0004233591898810118	0.00025	0.0	0.00025	0.00025	0.04721937	0.025519945	0.11107015	0.016729604
14	13	478.0	0.0	2969.0	2969.0	81.0	2969.0	0.9981071200000412	0.0	0.0	0.006916543132683728	0.008256373671042505	0.02793971076607704	0.00034270941978320485	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.03785228	0.023063693	0.090955265	0.014428139	-0.0006935441000000001	0.008459795	0.012772851000000002	-0.010573764
15	14	532.0	0.0	3183.0	3183.0	214.0	3183.0	0.9978952600000456	4.0	50.0	0.0069841391733562975	0.009727930525240285	0.030958421528339383	0.00019982327648904172	0.00025	0.0	0.00025	0.00025	0.03517378	0.028121071	0.09745253599999999	0.007200333000000001
16	15	551.0	0.0	3262.0	3262.0	79.0	3262.0	0.9978170500000474	2.0	15.0	0.008571460710587226	0.012479903064922505	0.043056368827819824	0.0001790421229088679	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.03861944	0.03349347	0.12367985	0.008007733000000001
17	16	626.0	0.0	3560.0	3560.0	298.0	3560.0	0.9975220300000538	6.0	145.0	0.00916061567428138	0.00985262607730402	0.03863134235143662	0.00022459866886492819	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.04501683	0.026303627000000003	0.10941381	0.010795511	-0.007507985	0.015376373999999998	0.009678967	-0.030438615
18	17	885.0	0.0	4598.0	4598.0	1038.0	4598.0	0.996494410000076	12.0	210.0	0.007690413830856681	0.009722273214587109	0.04484198987483978	0.00014540684060193598	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.040153995	0.028107608	0.13334101	0.007176003	0.01752627	0.018640606	0.05206203	-0.006777686
19	18	903.0	0.0	4668.0	4668.0	70.0	4668.0	0.9964251100000776	2.0	15.0	0.008374075151925139	0.00685058487549806	0.01695725508034229	0.00013643733109347522	0.00025	0.0	0.00025	0.00025	0.041769784	0.025388801000000003	0.0693266	0.006554181
20	19	924.0	0.0	4754.0	4754.0	86.0	4754.0	0.9963399700000796	2.0	35.0	0.006986255206616728	0.009138039512187723	0.029435122385621067	0.00023959197278600186	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.03765729	0.027741422999999998	0.09483457	0.009779892
21	20	988.0	0.0	5007.0	5007.0	253.0	5007.0	0.9960895000000848	1.0	5.0	0.008958109939518932	0.010352110018017849	0.04120930656790733	0.00026069089653901756	0.00025	0.0	0.00025	0.00025	0.044280123	0.027352182000000003	0.10559346	0.010518369
22	21	1009.0	0.0	5092.0	5092.0	85.0	5092.0	0.9960053500000868	0.0	0.0	0.009729027376687596	0.007417915393123158	0.026410818099975586	0.0005171290249563754	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.05305024	0.022927448	0.11149109	0.019090652
23	22	1041.0	0.0	5221.0	5221.0	129.0	5221.0	0.9958776400000896	1.0	10.0	0.0065109121378554855	0.009705144564042924	0.04230054095387459	0.0002464384888298809	0.00025	0.0	0.00025	0.00025	0.03857564	0.029652012999999998	0.13166025	0.008339129	0.022667855	0.029822525	0.073469676	-0.01822071
24	23	1101.0	0.0	5461.0	5461.0	240.0	5461.0	0.9956400400000948	6.0	85.0	0.007464758036803688	0.008871554942636414	0.04159108921885489	9.95906739262864e-05	0.00025	0.0	0.00025	0.00025	0.040631982999999997	0.027780425	0.1273076	0.0052087842
25	24	1167.0	0.0	5724.0	5724.0	263.0	5724.0	0.9953796700001004	1.0	25.0	0.007049951021944059	0.008145597856309148	0.029556380584836006	0.00024747068528085947	0.00025	0.0	0.00025	0.00025	0.03756183	0.025077598	0.10530927	0.010631736000000001
26	25	1188.0	0.0	5808.0	5808.0	84.0	5808.0	0.995296510000102	0.0	0.0	0.008849835848585437	0.008812960520326749	0.028190467506647113	0.00018663128139451146	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.04469130599999999	0.028627316	0.10585028	0.008268119

6.3 KiB Raw Blame History

6.3 KiB

Raw Blame History