coach/rl_coach/traces/Atari_A3C_LSTM_space_invaders/trace.csv at a16d7249633a4069aaa9c218abbcf1e8226c5ab4

gryf/coach

mirror of https://github.com/gryf/coach.git synced 2026-02-16 22:25:47 +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

8.7 KiB

Raw Blame History

1	Episode #	Training Iter	In Heatup	ER #Transitions	ER #Episodes	Episode Length	Total steps	Shaped Training Reward	Training Reward	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	248.0	1.0	248.0	248.0
3	2	0.0	1.0	123.0	1.0	123.0	371.0
4	3	0.0	1.0	88.0	1.0	88.0	459.0
5	4	0.0	1.0	187.0	1.0	187.0	646.0
6	5	0.0	1.0	86.0	1.0	86.0	732.0
7	6	0.0	1.0	331.0	1.0	331.0	1063.0
8	7	37.0	0.0	753.0	1.0	753.0	1816.0	18.0	275.0	0.19276376	0.24904153	0.8257747	0.00013455142	1.7914727	0.00030057304	1.7917566000000003	1.7904335	0.2119369695934143	0.4029896256601249	1.8961015939712524	-0.038109242916107185	0.059407155999999996	0.06025871	0.20562454	-0.0059952493999999995	0.10879397	0.13543734	0.42884704	1.0928144400000001e-07	0.37946862	0.4819447	1.3135536	-0.039071497000000004
9	8	43.0	0.0	107.0	1.0	107.0	1923.0	0.0	0.0	0.015239561	0.0024996148	0.019516254	0.011843238999999998	1.7906417000000001	0.0002779353	1.7917081999999998	1.790199	-0.027609226256608964	0.013555497071717059	-0.002493098378181457	-0.054812923073768616	0.23526458	0.013103152	0.25880286	0.2149402	0.0010658596000000002	4.0590476e-05	0.0011093322	0.0010099161	-0.04934317	0.011472803	-0.039747406	-0.06998761
10	9	47.0	0.0	73.0	1.0	73.0	1996.0	1.0	25.0	0.36924744	0.48345366	1.0529541999999998	0.027382427999999997	1.7904778000000001	0.00029410556	1.7917029999999998	1.7902383999999998	0.2182698796192805	0.4074832854303497	0.9812830686569214	-0.05661928653717041	0.29025623	0.01401644	0.3092764	0.27106556	0.12317172	0.1714658	0.36566097	0.0019109361999999999	0.39213285	0.6270856	1.2789414	-0.0569774
11	10	60.0	0.0	251.0	1.0	251.0	2247.0	4.0	30.0	0.43863640000000004	0.85959023	2.5217259999999997	0.035312783	1.7856493000000002	0.0015894786999999999	1.7916044999999998	1.7811941999999998	0.11047004585464797	0.4511292058995869	1.8077605962753296	-0.14487385749816895	0.61056226	0.07753438	0.79911625	0.4961661	0.1471402	0.31318584	0.8826119	0.0050534373	0.1947745	0.6780483	1.7730703	-0.1461431
12	11	66.0	0.0	121.0	1.0	121.0	2368.0	0.0	0.0	0.14871785	0.02547766	0.19108213	0.12211705	1.7780668000000002	0.0027863213	1.7913043000000002	1.7759546000000002	-0.10607111632823944	0.05572927975960492	-0.009624600410461426	-0.19753050804138186	1.0220673	0.034096994	1.0672632	0.95422196	0.021255326	0.0012313497	0.023416747999999998	0.019953651	-0.18968049	0.016377756	-0.16716708	-0.21171494
13	12	71.0	0.0	99.0	1.0	99.0	2467.0	0.0	0.0	0.15555012	0.04610389	0.23511228	0.12260077	1.7795043000000001	0.0023333197	1.7912293999999997	1.7773554	-0.09951297342777253	0.055938959522401716	-0.003077983856201172	-0.1911371946334839	1.0086769	0.036691166000000004	1.0868968	0.96416116	0.02108366	0.0023025707	0.02351839	0.018744798	-0.17643596	0.02231863	-0.14677188	-0.20941082
14	13	98.0	0.0	534.0	1.0	534.0	3001.0	13.0	340.0	0.7437658	1.1363528999999999	3.4128056000000004	0.025902914	1.7773186	0.003927723	1.7911369	1.7642651000000003	0.1266731635882304	0.41158095902457936	1.7730363607406616	-0.30260801315307617	0.9577929000000001	0.23765793	1.6504846999999998	0.7122954	0.15221074	0.20607093	0.757879	0.008616385	0.22623166	0.6171821	1.5555726	-0.30132666
15	14	102.0	0.0	73.0	1.0	73.0	3074.0	0.0	0.0	0.21133159	0.027693717000000003	0.24578243	0.17797336	1.7719979	0.004124344	1.7904103	1.7675488999999998	-0.18784045577049252	0.09607193868630864	-0.01820123195648193	-0.3348844051361084	1.8157914000000002	0.008718997	1.8383793000000002	1.7924569	0.056422543	0.0016911370000000001	0.05787156	0.054050256	-0.33337316	0.013935573	-0.3163426	-0.35047740000000005
16	15	110.0	0.0	156.0	1.0	156.0	3230.0	2.0	35.0	0.62405765	0.9592649999999999	2.9572167	0.12969549	1.7828823	0.0024880429999999997	1.7908226999999999	1.7776691000000002	-0.06490173169544765	0.3036005258432666	1.5683243274688718	-0.3259851932525635	1.7211465	0.029713133	1.7807939999999998	1.678612	0.12291474	0.17745444	0.5574187	0.04589054	-0.112290025	0.43601707	0.9523574	-0.32423943
17	16	122.0	0.0	238.0	1.0	238.0	3468.0	1.0	10.0	0.15554756	0.054277197	0.29741687	0.08846552	1.7868587	0.0007967119500000001	1.7910342000000001	1.7857143	-0.1573395555669611	0.12615047772660626	0.7546746730804443	-0.3632258176803589	1.6729587	0.17595315	1.9944772000000002	1.502953	0.05232538	0.035234198	0.15977861	0.03124919	-0.28081256	0.079151474	-0.07227526599999999	-0.35482806
18	17	132.0	0.0	185.0	1.0	185.0	3653.0	0.0	0.0	0.08596161	0.024157293	0.13088742	0.04359092	1.7865810000000002	0.0008728278999999999	1.7914173999999998	1.7849907999999999	-0.1145426501830419	0.06364297653654805	-0.008004307746887207	-0.26171672344207764	1.1001204	0.17392394	1.4450287	0.87743527	0.016055183	0.005272877	0.027343987	0.009870462	-0.20479403	0.033908524	-0.15814927	-0.26577490000000004
19	18	156.0	0.0	469.0	1.0	469.0	4122.0	7.0	300.0	0.44079409999999997	0.6836350999999999	2.4870617000000004	0.025862668	1.7806060000000001	0.0046418053	1.7915317	1.7732808999999998	0.062453726452329876	0.3429879814155853	0.985063374042511	-0.20165133476257324	0.92002445	0.10120275599999999	1.1328447	0.7651458999999999	0.091498	0.13105219999999998	0.42509866	0.007523017	0.11129719	0.47185699999999997	1.4228208	-0.21573834
20	19	170.0	0.0	276.0	1.0	276.0	4398.0	3.0	20.0	0.40178663	0.6728098000000001	2.4094729999999998	0.039225254	1.7645447	0.0042648454999999995	1.790634	1.7581539000000002	-0.00800227591624627	0.3189828889920542	1.685505986213684	-0.2216334342956543	1.1304478999999998	0.038905688	1.2024312	1.0620688999999999	0.0786909	0.1614253	0.58035713	0.012360237	-0.011329556999999999	0.4500582	1.2747773999999998	-0.24353555
21	20	191.0	0.0	420.0	1.0	420.0	4818.0	7.0	315.0	0.36499518	0.3705313	1.1575621	0.04431529	1.7636738	0.004579304	1.7901049	1.7550941999999998	0.021820819079875944	0.3071232093063115	0.947787582874298	-0.2100141644477844	0.9154280999999999	0.09096202	1.1273426000000002	0.75912726	0.07179129	0.09326242	0.24904189999999998	0.0062419563	0.040330485	0.34031707	0.7956849	-0.22417025
22	21	197.0	0.0	104.0	1.0	104.0	4922.0	1.0	30.0	0.5144350000000001	0.718648	1.9511981	0.12453204400000001	1.761423	0.0056095775	1.7902006999999998	1.7571856	0.05070284008979797	0.3168600697896934	0.925861954689026	-0.16295456886291504	0.88745534	0.012690918	0.93781537	0.8751633	0.06495949599999999	0.11300202	0.2909634	0.008293057	0.078482285	0.45015374	0.97864294	-0.15680452
23	22	203.0	0.0	113.0	1.0	113.0	5035.0	2.0	15.0	0.64118826	0.86793905	2.3767917	0.18172713	1.7537029999999998	0.006172906	1.7896771	1.749237	0.08747740507125855	0.4437113729234238	1.7083609104156494	-0.18463540077209475	0.9569305	0.024823021	1.0054495	0.92341274	0.12694135	0.23306239999999998	0.5930651	0.009591491	0.15546985	0.65049607	1.4562124	-0.19140014
24	23	212.0	0.0	162.0	1.0	162.0	5197.0	1.0	5.0	0.16368598	0.041053284	0.22597034	0.10290782	1.7606709999999999	0.004070151	1.7898455000000002	1.7559046999999999	-0.06407594718039036	0.13353017492122013	0.855490505695343	-0.17702490091323853	0.83308256	0.035228863	0.9194645	0.7807996	0.020336542	0.032399733	0.10603105	0.007155789	-0.11351252	0.08716212	0.11233470599999999	-0.18262672
25	24	216.0	0.0	69.0	1.0	69.0	5266.0	0.0	0.0	0.18022996	0.014585165	0.19933702	0.16394733	1.7644328999999999	0.005773647	1.7902433999999998	1.7603636000000003	-0.07377323607603709	0.04112314147691277	-0.0068422555923461905	-0.1422249674797058	0.7145154	0.026194045	0.7514143	0.6838747	0.006449179300000001	0.00046015754999999996	0.006775117	0.0057984180000000005	-0.12904127	0.008062066	-0.118956625	-0.13869014
26	25	238.0	0.0	432.0	1.0	432.0	5698.0	6.0	85.0	0.33006436	0.35617912	1.3067303999999997	0.06890332	1.7717101999999998	0.004106822	1.7902195	1.7627416	0.07911585221687953	0.3249530771268533	0.9620689153671264	-0.13253813982009888	0.5261719	0.06930914	0.7088074000000001	0.44418199999999997	0.06108107	0.09490778	0.29277053	0.0023036576	0.140708	0.41082802	1.2361767	-0.12985662

8.7 KiB Raw Blame History

8.7 KiB

Raw Blame History