Matches in SemOpenAlex for { <https://semopenalex.org/work/W2966476822> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2966476822 abstract "Multi-agent combat scenarios often appear in many real-time strategy games. Efficient learning for such scenarios is an indispensable step towards general artificial intelligence. Multi-agent reinforcement learning (MARL) algorithms have attracted much interests, but few of them have been shown effective for such scenarios. Most of previous research is focused on revising the learning mechanism of MARL algorithms, for example, trying different types of neural networks. The study of training techniques for improving the performance of MARL algorithms has not been paid much attention. In this paper we propose three efficient training techniques for a multi-agent combat problem which is originated from an unmanned aerial vehicle (UAV) combat scenario. The first one is the scenario-transfer training, which utilizes the experience obtained in simpler combat tasks to assist the training for complex tasks. The next one is the self-play training, which can continuously improve the performance by iteratively training agents and their counterparts. Finally, we consider using combat rules to assist the training, which is named as the rule-coupled training. We combine the three training techniques with two popular multi-agent reinforcement learning methods, multi-agent deep q-learning and multi-agent deep deterministic policy gradient (proposed by Open AI in 2017), respectively. The results show that both the converging speed and the performance of the two methods are significantly improved through the three training techniques." @default.
- W2966476822 created "2019-08-13" @default.
- W2966476822 creator A5005228383 @default.
- W2966476822 creator A5051002009 @default.
- W2966476822 creator A5055062652 @default.
- W2966476822 creator A5090074883 @default.
- W2966476822 date "2019-01-01" @default.
- W2966476822 modified "2023-10-16" @default.
- W2966476822 title "Efficient Training Techniques for Multi-Agent Reinforcement Learning in Combat Tasks" @default.
- W2966476822 doi "https://doi.org/10.1109/access.2019.2933454" @default.
- W2966476822 hasPublicationYear "2019" @default.
- W2966476822 type Work @default.
- W2966476822 sameAs 2966476822 @default.
- W2966476822 citedByCount "17" @default.
- W2966476822 countsByYear W29664768222020 @default.
- W2966476822 countsByYear W29664768222021 @default.
- W2966476822 countsByYear W29664768222022 @default.
- W2966476822 countsByYear W29664768222023 @default.
- W2966476822 crossrefType "journal-article" @default.
- W2966476822 hasAuthorship W2966476822A5005228383 @default.
- W2966476822 hasAuthorship W2966476822A5051002009 @default.
- W2966476822 hasAuthorship W2966476822A5055062652 @default.
- W2966476822 hasAuthorship W2966476822A5090074883 @default.
- W2966476822 hasBestOaLocation W29664768221 @default.
- W2966476822 hasConcept C119857082 @default.
- W2966476822 hasConcept C121332964 @default.
- W2966476822 hasConcept C153294291 @default.
- W2966476822 hasConcept C154945302 @default.
- W2966476822 hasConcept C2777211547 @default.
- W2966476822 hasConcept C41008148 @default.
- W2966476822 hasConcept C50644808 @default.
- W2966476822 hasConcept C97541855 @default.
- W2966476822 hasConceptScore W2966476822C119857082 @default.
- W2966476822 hasConceptScore W2966476822C121332964 @default.
- W2966476822 hasConceptScore W2966476822C153294291 @default.
- W2966476822 hasConceptScore W2966476822C154945302 @default.
- W2966476822 hasConceptScore W2966476822C2777211547 @default.
- W2966476822 hasConceptScore W2966476822C41008148 @default.
- W2966476822 hasConceptScore W2966476822C50644808 @default.
- W2966476822 hasConceptScore W2966476822C97541855 @default.
- W2966476822 hasFunder F4320321001 @default.
- W2966476822 hasLocation W29664768221 @default.
- W2966476822 hasOpenAccess W2966476822 @default.
- W2966476822 hasPrimaryLocation W29664768221 @default.
- W2966476822 hasRelatedWork W1546266526 @default.
- W2966476822 hasRelatedWork W1588651106 @default.
- W2966476822 hasRelatedWork W2026615874 @default.
- W2966476822 hasRelatedWork W2059539888 @default.
- W2966476822 hasRelatedWork W2113998737 @default.
- W2966476822 hasRelatedWork W2610462371 @default.
- W2966476822 hasRelatedWork W2785556016 @default.
- W2966476822 hasRelatedWork W2966848886 @default.
- W2966476822 hasRelatedWork W3005912127 @default.
- W2966476822 hasRelatedWork W3030585287 @default.
- W2966476822 hasRelatedWork W3049177821 @default.
- W2966476822 hasRelatedWork W3088004450 @default.
- W2966476822 hasRelatedWork W3091126461 @default.
- W2966476822 hasRelatedWork W3106394430 @default.
- W2966476822 hasRelatedWork W3116294947 @default.
- W2966476822 hasRelatedWork W3119643051 @default.
- W2966476822 hasRelatedWork W3158052368 @default.
- W2966476822 hasRelatedWork W3165469371 @default.
- W2966476822 hasRelatedWork W3187695488 @default.
- W2966476822 hasRelatedWork W3201419494 @default.
- W2966476822 isParatext "false" @default.
- W2966476822 isRetracted "false" @default.
- W2966476822 magId "2966476822" @default.
- W2966476822 workType "article" @default.