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

gryf/coach

mirror of https://github.com/gryf/coach.git synced 2026-02-24 11:15:45 +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	0.011159177685519406	0.014670889632016437	0.05586982890963554	0.00014776474563404918	0.00010000000000000002	1.3552527156068802e-20	0.0001	0.0001	0.06980593	0.04550845	0.23672238	0.012701003
7	6	70.0	0.0	1335.0	1335.0	75.0	1335.0	0.999724780000006	2.0	15.0	0.011363721369937258	0.01113743869358625	0.02980226650834084	0.00037189509021118283	0.0001	0.0	0.0001	0.0001	0.061391924	0.02929353	0.110355645	0.014809295
8	7	91.0	0.0	1422.0	1422.0	87.0	1422.0	0.9996386500000078	1.0	15.0	0.011624419426966813	0.013655546794886331	0.04332234337925911	0.0002809247234836221	0.0001	1.3552527156068802e-20	0.0001	0.0001	0.065822564	0.03866646	0.16192491	0.021505926
9	8	159.0	0.0	1693.0	1693.0	271.0	1693.0	0.9993703600000136	5.0	55.0	0.008774163406046885	0.01056874345135505	0.042830634862184525	0.0001717623672448099	0.00010000000000000003	2.7105054312137605e-20	0.0001	0.0001	0.05377827	0.032895934	0.16196515	0.00941183
10	9	201.0	0.0	1861.0	1861.0	168.0	1861.0	0.9992040400000172	3.0	50.0	0.005785983745660079	0.00916921106544553	0.04197276383638382	0.00021147351071704182	0.00010000000000000002	1.3552527156068802e-20	0.0001	0.0001	0.04083436	0.028236978	0.14960715	0.012452139499999999
11	10	279.0	0.0	2172.0	2172.0	311.0	2172.0	0.998896150000024	4.0	65.0	0.009643888652461987	0.012217253908083524	0.056894369423389435	0.00016667474119458348	0.00010000000000000003	4.0657581468206416e-20	0.0001	0.0001	0.0560394	0.039682023	0.1913731	0.008496345
12	11	440.0	0.0	2815.0	2815.0	643.0	2815.0	0.9982595800000378	10.0	335.0	0.00861433394022231	0.010348496102126023	0.04432229697704315	0.0001522430102340877	0.00010000000000000002	1.3552527156068802e-20	0.0001	0.0001	0.05220816	0.03156275	0.16941099999999998	0.009055335999999999	0.023975812000000003	0.012025122	0.040999293	0.0039341394
13	12	458.0	0.0	2888.0	2888.0	73.0	2888.0	0.9981873100000394	2.0	45.0	0.009530787179957971	0.010701133845478595	0.03999783843755722	0.00031216014758683736	0.0001	0.0	0.0001	0.0001	0.062311728	0.026771976	0.14921491	0.02184285
14	13	478.0	0.0	2969.0	2969.0	81.0	2969.0	0.9981071200000412	0.0	0.0	0.006778308925277089	0.00818221383451154	0.02816874161362648	0.0002485926379449665	0.0001	0.0	0.0001	0.0001	0.044908725	0.026523566000000002	0.117372274	0.016029207	-0.012888752	0.011372567	-0.0004688017	-0.031455092000000004
15	14	532.0	0.0	3183.0	3183.0	214.0	3183.0	0.9978952600000456	4.0	50.0	0.0069169835669863795	0.009669208516406907	0.030461043119430545	0.0002085747983073816	0.00010000000000000003	2.7105054312137605e-20	0.0001	0.0001	0.047045134	0.03206875	0.123922676	0.010909475
16	15	551.0	0.0	3262.0	3262.0	79.0	3262.0	0.9978170500000474	2.0	15.0	0.008465479291963243	0.01222064269286522	0.04136095941066742	0.00024427170865237713	0.0001	0.0	0.0001	0.0001	0.051463115999999996	0.036649507000000005	0.14754368	0.013367546000000001
17	16	626.0	0.0	3560.0	3560.0	298.0	3560.0	0.9975220300000538	6.0	145.0	0.00915405042571758	0.00990793648084188	0.038579311221838	0.0002719838812481612	0.00010000000000000003	2.7105054312137605e-20	0.0001	0.0001	0.055197	0.029597567	0.14903925	0.010181868	-0.011365135	0.013168923	0.013799908	-0.025668386
18	17	916.0	0.0	4719.0	4719.0	1159.0	4719.0	0.9963746200000788	22.0	340.0	0.00762058505652962	0.009529140287309196	0.04469184204936028	0.00013019611651543528	0.00010000000000000002	1.3552527156068802e-20	0.0001	0.0001	0.049977854	0.031034742999999997	0.15861663	0.008030025	0.016384887	0.018671772	0.056820348	-0.0064531965
19	18	943.0	0.0	4830.0	4830.0	111.0	4830.0	0.9962647300000812	3.0	45.0	0.009809370868390907	0.011517441918305206	0.04567621275782585	0.0002561989240348339	0.0001	1.3552527156068802e-20	0.0001	0.0001	0.058472212	0.027904749	0.13957499	0.021250565
20	19	1006.0	0.0	5081.0	5081.0	251.0	5081.0	0.9960162400000864	0.0	0.0	0.011435095637646171	0.011009362492248348	0.04369494318962097	0.0002374518953729421	0.00010000000000000003	2.7105054312137605e-20	0.0001	0.0001	0.06413252	0.03206017	0.17680877	0.015071165
21	20	1062.0	0.0	5304.0	5304.0	223.0	5304.0	0.9957954700000912	6.0	105.0	0.008425145343997948	0.010476737255273365	0.04278689250349999	0.0002318604965694249	0.00010000000000000002	1.3552527156068802e-20	0.0001	0.0001	0.05528172	0.033389688	0.16662869	0.013080816	0.02990371	0.01963076	0.059646500000000005	0.005463021
22	21	1081.0	0.0	5379.0	5379.0	75.0	5379.0	0.9957212200000928	2.0	15.0	0.007715215652225245	0.010669677149893777	0.03837666660547257	0.00035348522942513233	0.0001	0.0	0.0001	0.0001	0.055993587000000004	0.030775022000000003	0.13761143	0.023046900000000002
23	22	1125.0	0.0	5556.0	5556.0	177.0	5556.0	0.9955459900000968	2.0	35.0	0.007088124197418272	0.007553918383053855	0.02735380455851555	0.00016635317297186702	0.00010000000000000003	2.7105054312137605e-20	0.0001	0.0001	0.046250745999999995	0.027780753	0.12917177	0.009924813000000001
24	23	1169.0	0.0	5733.0	5733.0	177.0	5733.0	0.9953707600001004	3.0	30.0	0.007776185804686975	0.009135069977912141	0.03013703227043152	0.0002250532270409167	0.00010000000000000003	2.7105054312137605e-20	0.0001	0.0001	0.051641665	0.030256712999999998	0.13535246	0.012026708
25	24	1190.0	0.0	5815.0	5815.0	82.0	5815.0	0.9952895800001024	1.0	5.0	0.011108649816984931	0.010548835692936798	0.042301006615161896	0.00035882263910025364	0.0001	1.3552527156068802e-20	0.0001	0.0001	0.06612081	0.03200974	0.15909933	0.027230294
26	25	1212.0	0.0	5904.0	5904.0	89.0	5904.0	0.9952014700001042	1.0	10.0	0.004195408909502227	0.007376560022200305	0.025709044188261032	0.00019116624025627968	0.0001	1.3552527156068802e-20	0.0001	0.0001	0.03334951	0.028961857999999997	0.10913753	0.008333857

6.3 KiB Raw Blame History

6.3 KiB

Raw Blame History