File(s) under permanent embargo
An empirical study of reward structures for actor-critic reinforcement learning in air combat manoeuvring simulation
conference contribution
posted on 2019-01-01, 00:00 authored by B Kurniawan, P Vamplew, M Papasimeon, Richard DazeleyRichard Dazeley, C FoaleReinforcement learning techniques for solving complex problems are resource-intensive and take a long time to converge, prompting a need for methods that encourage faster learning. In this paper we show our successful application of actor-critic reinforcement learning to the air combat simulation domain and how reward structures affect the learning speed to find effective air combat tactics.
History
Event
Artificial Intelligence. Conference (32nd : 2019 : Adelaide, S. Aust.)Volume
11919Series
Artificial Intelligence ConferencePagination
54 - 65Publisher
SpringerLocation
Adelaide, S. Aust.Place of publication
Cham, SwitzerlandPublisher DOI
Start date
2019-12-02End date
2019-12-05ISSN
0302-9743eISSN
1611-3349ISBN-13
9783030352875Language
engPublication classification
E1 Full written paper - refereedEditor/Contributor(s)
Jixue Liu, James BaileyTitle of proceedings
AI 2019: Advances in artificial intelligence : Proceedings of the 32nd Australian Joint Conference on Artificial Intelligence 2019Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC