coach/rl_coach/traces/Atari_C51_space_invaders/trace.csv at 72a1d9d426004269997f8b40bdd64f8ee582d91e

gryf/coach

mirror of https://github.com/gryf/coach.git synced 2026-01-28 11:05:46 +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

6.6 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	3.931745547874301	1.1304143308005733e-05	3.9317700862884517	3.9316890239715576	0.00025	0.0	0.00025	0.00025	0.0015866637	0.0023147496	0.009720516	0.0007565144
7	6	70.0	0.0	1335.0	1335.0	75.0	1335.0	0.999724780000006	2.0	15.0	3.931735929689909	7.235250669185713e-06	3.9317455291748047	3.931711912155152	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.001755927	0.0026373637	0.009641058000000001	0.0007148395500000001
8	7	91.0	0.0	1422.0	1422.0	87.0	1422.0	0.9996386500000078	1.0	15.0	3.931701206025623	5.099185273705093e-05	3.93173623085022	3.931553602218628	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.00282516	0.0035993564000000003	0.009418896999999999	0.00070036505
9	8	159.0	0.0	1693.0	1693.0	271.0	1693.0	0.9993703600000136	5.0	55.0	3.931656876606728	9.226522325134514e-05	3.931716203689575	3.9311599731445312	0.00025	0.0	0.00025	0.00025	0.0017165048	0.0027771054	0.012550428999999998	0.00063557597
10	9	201.0	0.0	1861.0	1861.0	168.0	1861.0	0.9992040400000172	3.0	50.0	3.93158137230646	0.00010474746316658029	3.93165135383606	3.931158781051636	0.00025	0.0	0.00025	0.00025	0.0017799592	0.002852903	0.009889938000000001	0.0006321495
11	10	279.0	0.0	2172.0	2172.0	311.0	2172.0	0.998896150000024	4.0	65.0	3.9314154325387416	0.00022279076273676361	3.931581258773804	3.930070638656616	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0026444625	0.004101368	0.019448647	0.00062298455
12	11	407.0	0.0	2683.0	2683.0	511.0	2683.0	0.9983902600000351	9.0	320.0	3.931240767240524	0.00015854553450050932	3.931373834609986	3.9305694103240967	0.0002500000000000001	1.0842021724855042e-19	0.00025	0.00025	0.0017362889000000002	0.0029191163	0.011232911000000002	0.0005518816	0.024129094928503625	0.00904320207528025	0.04169573485851341	0.012993395328522341
13	12	424.0	0.0	2754.0	2754.0	71.0	2754.0	0.9983199700000364	1.0	15.0	3.9310134579153617	0.000358822446065362	3.9312620162963863	3.93019700050354	0.00025	0.0	0.00025	0.00025	0.0032191304	0.0045680365999999995	0.011846525	0.0005631294
14	13	457.0	0.0	2886.0	2886.0	132.0	2886.0	0.9981892900000392	2.0	25.0	3.931020930409432	0.00018348520436412824	3.93116307258606	3.9301931858062735	0.00025	0.0	0.00025	0.00025	0.0016074966000000001	0.002708108	0.012189938999999999	0.00064319023
15	14	504.0	0.0	3074.0	3074.0	188.0	3074.0	0.9980031700000432	3.0	35.0	3.931025738301485	0.00015399033015145469	3.9311008453369136	3.9300034046173096	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0009836307000000001	0.0015528154999999999	0.011335916000000001	0.0005281837	0.021890531852842	0.014466196029404797	0.03762449622154298	-0.00010702610015811408
16	15	528.0	0.0	3167.0	3167.0	93.0	3167.0	0.9979111000000452	1.0	15.0	3.931034368017445	6.681329033129075e-05	3.9310910701751713	3.9308130741119385	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0016258046	0.0031157003000000004	0.011724828999999999	0.0004990724
17	16	598.0	0.0	3449.0	3449.0	282.0	3449.0	0.9976319200000514	2.0	55.0	3.930865437643869	0.0002831683814269127	3.9310925006866455	3.9296932220458975	0.00025	0.0	0.00025	0.00025	0.0021639192000000003	0.0036756303	0.012480825	0.00047580682	0.0305326876540985	0.00923045073371262	0.0438561670482166	0.021990178897977525
18	17	668.0	0.0	3729.0	3729.0	280.0	3729.0	0.9973547200000574	4.0	45.0	3.930601644515991	0.0003480949830888473	3.9308652877807617	3.9292240142822266	0.00025	0.0	0.00025	0.00025	0.0027047140000000004	0.0042121527	0.013903748	0.0006515036	0.029686454000572925	0.01902240661079521	0.058909925818443724	-0.002814809605478502
19	18	738.0	0.0	4008.0	4008.0	279.0	4008.0	0.9970785100000634	3.0	45.0	3.930277814183917	0.0005110864544539217	3.930636167526245	3.9281198978424072	0.00025	0.0	0.00025	0.00025	0.0036887865999999997	0.0051101656	0.02086526	0.0008114038499999999
20	19	792.0	0.0	4223.0	4223.0	215.0	4223.0	0.9968656600000679	4.0	90.0	3.930134093319928	0.00047399490243328624	3.930522918701172	3.9284942150115967	0.00025	0.0	0.00025	0.00025	0.0037553142999999997	0.004891396	0.0151908295	0.0010129308999999999	0.030484313207368687	0.012861465171913404	0.04339803867042122	0.011251759901643564
21	20	893.0	0.0	4630.0	4630.0	407.0	4630.0	0.9964627300000768	10.0	115.0	3.929736850285294	0.000766311293002325	3.930368661880493	3.926426649093628	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.004180377	0.006044741700000001	0.031209853	0.0009457401	0.0355303921426342	0.014215304187277478	0.05135452747345026	0.012931596487761264
22	21	937.0	0.0	4805.0	4805.0	175.0	4805.0	0.9962894800000806	1.0	5.0	3.930479177208834	0.00023689537153461093	3.930684328079224	3.929489135742188	0.00025	0.0	0.00025	0.00025	0.0021777323	0.0034656142999999998	0.014414535	0.00058991817
23	22	1022.0	0.0	5146.0	5146.0	341.0	5146.0	0.995951890000088	3.0	65.0	3.93046441078186	0.00035790579075833815	3.9307262897491455	3.929075956344605	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0024591651999999998	0.0041425275	0.014986968	0.00047587089999999996
24	23	1120.0	0.0	5538.0	5538.0	392.0	5538.0	0.9955638100000964	6.0	80.0	3.9300818811986864	0.0004955548155674863	3.930469751358032	3.928221464157105	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0027119769	0.0042804847	0.020022545	0.00057932467	0.035476823337376714	0.014014476077534626	0.04927191920578547	0.007030519843102157
25	24	1165.0	0.0	5718.0	5718.0	180.0	5718.0	0.9953856100001002	3.0	55.0	3.9300585714253513	0.00053408662096811	3.9305152893066406	3.928401231765747	0.00025	0.0	0.00025	0.00025	0.0033172776	0.004863477299999999	0.016010353	0.0006072133999999999
26	25	1190.0	0.0	5815.0	5815.0	97.0	5815.0	0.9952895800001024	0.0	0.0	3.9299856324990587	0.0004047671393024133	3.9302456378936768	3.9285967350006095	0.00025	0.0	0.00025	0.00025	0.0030563176	0.004401815999999999	0.016188376	0.0011075826

6.6 KiB Raw Blame History

6.6 KiB

Raw Blame History