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

gryf/coach

mirror of https://github.com/gryf/coach.git synced 2026-01-09 07:14:19 +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

7.4 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	269.0	269.0	269.0	269.0	7.0
3	2	0.0	1.0	531.0	531.0	262.0	531.0	8.0
4	3	0.0	1.0	654.0	654.0	123.0	654.0	0.0
5	4	0.0	1.0	1173.0	1173.0	519.0	1173.0	2.0
6	5	100.0	0.0	1572.0	1572.0	399.0	1572.0	8.0	10.0	310.0	0.006223844418564113	0.008294042663087463	0.03155895695090294	9.275647607864812e-05	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.005592896	0.0043458864	0.015006336	0.0010827626
7	6	160.0	0.0	1812.0	1812.0	240.0	1812.0	4.0	7.0	130.0	0.008564803576276366	0.010985852447389552	0.04601012542843819	0.00010247386671835555	0.00025	0.0	0.00025	0.00025	0.0060127693999999995	0.005001401	0.020867711	0.0012939627
8	7	185.0	0.0	1914.0	1914.0	102.0	1914.0	8.0	2.0	15.0	0.005707002155832015	0.009575807855094808	0.03112555481493473	0.00017016606580000368	0.00025	0.0	0.00025	0.00025	0.0047362293	0.004079403	0.014057411	0.0019318176000000002
9	8	229.0	0.0	2090.0	2090.0	176.0	2090.0	7.0	2.0	15.0	0.00864216006702072	0.013155937701958298	0.061171818524599075	0.00018360336252953854	0.00025	0.0	0.00025	0.00025	0.0063004736	0.0053449036	0.02487476	0.0019890803
10	9	244.0	0.0	2149.0	2149.0	59.0	2149.0	5.0	2.0	15.0	0.006669382058524727	0.0073984037571708594	0.015499015338718891	0.0002397242496954277	0.0002500000000000001	1.0842021724855042e-19	0.00025	0.00025	0.0056597376	0.0035718853999999996	0.0101093175	0.0022593176
11	10	267.0	0.0	2239.0	2239.0	90.0	2239.0	3.0	2.0	35.0	0.0062163660673515714	0.008715943338641199	0.030871812254190445	0.00019301722932141277	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0052448297	0.003933181500000001	0.013718200000000002	0.0018610907000000002
12	11	314.0	0.0	2430.0	2430.0	191.0	2430.0	8.0	3.0	30.0	0.005064984451622722	0.009464219831212449	0.04566681012511253	0.00017265054339077324	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0042512245	0.0038818533000000003	0.016594999	0.0016967895000000002	0.027018031	0.010441347	0.0474995	0.016540313
13	12	334.0	0.0	2508.0	2508.0	78.0	2508.0	0.0	2.0	45.0	0.009793104943941887	0.011249256480204521	0.030716722831130024	0.0001681474968791008	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.006330653	0.0047096196	0.014098721000000002	0.0016581904999999999
14	13	378.0	0.0	2684.0	2684.0	176.0	2684.0	5.0	0.0	0.0	0.01011617302819187	0.013193202268065932	0.04607892408967018	0.00014670072414446622	0.00025	0.0	0.00025	0.00025	0.0067802290000000005	0.005344481	0.022279864	0.0016253429999999998	0.027286835	0.0073864055	0.03329719	0.016612418
15	14	425.0	0.0	2872.0	2872.0	188.0	2872.0	0.0	0.0	0.0	0.00757620267153896	0.010181129044846313	0.03055970929563045	0.00019950376008637252	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.005839123000000001	0.004426101	0.01861591	0.0021889664000000002
16	15	449.0	0.0	2967.0	2967.0	95.0	2967.0	6.0	3.0	30.0	0.0070000348653896545	0.011226164764985254	0.04456117376685143	0.00021107358043082056	0.00025	0.0	0.00025	0.00025	0.005659159	0.0046324306	0.021839907000000002	0.0021402768
17	16	469.0	0.0	3049.0	3049.0	82.0	3049.0	3.0	0.0	0.0	0.012940272329433357	0.009718707321816513	0.030684769153594967	0.0003000017604790628	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.008273507	0.0035852243	0.013593527	0.0028905305
18	17	533.0	0.0	3306.0	3306.0	257.0	3306.0	1.0	5.0	55.0	0.007539691670444881	0.009121751516234046	0.03060857020318508	0.00022119178902357817	0.00025	0.0	0.00025	0.00025	0.00609803	0.0035867486	0.013320565	0.002192039
19	18	585.0	0.0	3511.0	3511.0	205.0	3511.0	7.0	0.0	0.0	0.005838182990213253	0.007284520898622485	0.01573643647134304	0.00017755883163772523	0.00025	0.0	0.00025	0.00025	0.0050161253	0.0035143814	0.010200171999999999	0.0018448817
20	19	632.0	0.0	3701.0	3701.0	190.0	3701.0	5.0	2.0	25.0	0.006030775471020767	0.008624205468393242	0.030819704756140712	0.00014619529247283936	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0049460824	0.004009163499999999	0.014025801000000001	0.0014488354999999998
21	20	680.0	0.0	3891.0	3891.0	190.0	3891.0	4.0	0.0	0.0	0.0062177468741235024	0.009185724365931972	0.030945468693971637	0.00016168373986147344	0.00025	0.0	0.00025	0.00025	0.0048525543	0.0041472296999999995	0.014570421	0.0015842235999999998
22	21	729.0	0.0	4090.0	4090.0	199.0	4090.0	9.0	4.0	50.0	0.0066686894893717525	0.009633275859106637	0.03070710971951485	0.00016243076242972163	0.00025	0.0	0.00025	0.00025	0.005217642	0.0044929385	0.01947369	0.00170155	0.021158978	0.011703089	0.040702187	0.0043722745
23	22	804.0	0.0	4390.0	4390.0	300.0	4390.0	9.0	5.0	60.0	0.007745159575574075	0.010264969595287615	0.0457281582057476	0.0001735425612423569	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.005858070999999999	0.004608556	0.02206757	0.0016346257
24	23	862.0	0.0	4619.0	4619.0	229.0	4619.0	6.0	3.0	30.0	0.0073957111507249795	0.010238454419935428	0.045198917388916016	0.00018422666471451518	0.00025	0.0	0.00025	0.00025	0.005702048	0.0044779684	0.019911936	0.0017970852
25	24	882.0	0.0	4699.0	4699.0	80.0	4699.0	6.0	0.0	0.0	0.007019620326900622	0.010097406329511898	0.030556553974747658	0.00021815481886733326	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0058081313	0.0048652836	0.019417763	0.0023302154
26	25	945.0	0.0	4951.0	4951.0	252.0	4951.0	5.0	4.0	50.0	0.005672615208563262	0.007662691003304536	0.02989559806883335	0.00017223272880073634	0.00025	0.0	0.00025	0.00025	0.004905078	0.0036695688	0.013604815	0.0018130213	0.031090358	0.004259917	0.037605517000000005	0.025178626000000003
27	26	995.0	0.0	5152.0	5152.0	201.0	5152.0	8.0	2.0	15.0	0.006299167421530001	0.008046825175071413	0.030643418431282043	0.00017975828086491674	0.00025	0.0	0.00025	0.00025	0.005176335	0.003915025999999999	0.014020402	0.0017273452	0.026928194	0.009660842	0.041887067	0.010047999
28	27	1017.0	0.0	5242.0	5242.0	90.0	5242.0	1.0	2.0	35.0	0.005731220244011969	0.008559611287002292	0.03012747503817081	0.00019501463975757358	0.0002500000000000001	5.421010862427521e-20	0.00025	0.00025	0.0051502184999999995	0.004566707	0.01945674	0.0021261019	0.02149797	0.010033373	0.03370452	0.008069546
29	28	1072.0	0.0	5462.0	5462.0	220.0	5462.0	3.0	2.0	55.0	0.008864355713336004	0.011839999879392651	0.046134039759635925	0.0001610755716683343	0.00025	0.0	0.00025	0.00025	0.0062677735	0.0050042396999999995	0.020127073	0.0017192016	0.02061991	0.0075885756	0.034549624	0.010614768
30	29	1118.0	0.0	5646.0	5646.0	184.0	5646.0	4.0	3.0	20.0	0.0072352889821761185	0.008737181206568531	0.030466778203845024	0.00018102813919540492	0.00025	0.0	0.00025	0.00025	0.005792571999999999	0.004318339	0.019932609	0.0020496019
31	30	1175.0	0.0	5874.0	5874.0	228.0	5874.0	4.0	5.0	85.0	0.008313204468972149	0.011042285375825469	0.045756932348012924	0.00019610222079791129	0.00025	0.0	0.00025	0.00025	0.005883634	0.0046995464	0.022168385	0.001801039	0.0073951124	0.010906539	0.025537572999999997	-0.0070570237

7.4 KiB Raw Blame History

7.4 KiB

Raw Blame History