Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980297462> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2980297462 endingPage "162138" @default.
- W2980297462 startingPage "162127" @default.
- W2980297462 abstract "Multi-agent reinforcement learning approaches can be roughly classified into two categories. One is the agent-based approach which can be implemented in real distributed systems, though most approaches of this type cannot provide meaningful theoretical verifications. The other can be seen as the more formalized approach, which can provide theoretical results. However, most of current algorithms usually require unrealistic global communication, which makes them impractical for real distributed systems. In this article, we propose a dynamic correlation matrix based multi-agent reinforcement learning approach where the meta-parameters are evolved using an evolutionary algorithm. We believe that our approach is able to fill the gap between the two kinds of traditional multi-agent reinforcement learning approaches by providing both agent-level implementation and system-level convergence verification. The basic idea of this approach is that agents learn not only from local environmental feedback, i.e., their own experiences and rewards, but also from other agents' experiences. In this way, the agents' learning speed can be increased significantly. The performance of the proposed algorithm is demonstrated on a number of application scenarios, including blackjack games, urban traffic control systems and multi-robot foraging." @default.
- W2980297462 created "2019-10-18" @default.
- W2980297462 creator A5019886822 @default.
- W2980297462 creator A5033106028 @default.
- W2980297462 creator A5056532148 @default.
- W2980297462 date "2019-01-01" @default.
- W2980297462 modified "2023-10-14" @default.
- W2980297462 title "A New Multi-Agent Reinforcement Learning Method Based on Evolving Dynamic Correlation Matrix" @default.
- W2980297462 cites W1500288288 @default.
- W2980297462 cites W1542941925 @default.
- W2980297462 cites W1657704689 @default.
- W2980297462 cites W1966224968 @default.
- W2980297462 cites W1988071716 @default.
- W2980297462 cites W2017908696 @default.
- W2980297462 cites W2058412232 @default.
- W2980297462 cites W2074535878 @default.
- W2980297462 cites W2077391629 @default.
- W2980297462 cites W2081525555 @default.
- W2980297462 cites W2102506086 @default.
- W2980297462 cites W2108892923 @default.
- W2980297462 cites W2110007425 @default.
- W2980297462 cites W2111104611 @default.
- W2980297462 cites W2119120935 @default.
- W2980297462 cites W2120399547 @default.
- W2980297462 cites W2126554879 @default.
- W2980297462 cites W2147958279 @default.
- W2980297462 cites W2148979180 @default.
- W2980297462 cites W2156486793 @default.
- W2980297462 cites W2159093508 @default.
- W2980297462 cites W2162813238 @default.
- W2980297462 cites W2162844575 @default.
- W2980297462 cites W2164780411 @default.
- W2980297462 cites W2171426878 @default.
- W2980297462 cites W2337676674 @default.
- W2980297462 cites W2338351427 @default.
- W2980297462 cites W2523367208 @default.
- W2980297462 cites W2783156804 @default.
- W2980297462 cites W2897975793 @default.
- W2980297462 cites W2911891464 @default.
- W2980297462 cites W2928977918 @default.
- W2980297462 cites W2940740707 @default.
- W2980297462 cites W2968764495 @default.
- W2980297462 cites W2973843138 @default.
- W2980297462 cites W2975330064 @default.
- W2980297462 cites W2976344064 @default.
- W2980297462 cites W1964488926 @default.
- W2980297462 doi "https://doi.org/10.1109/access.2019.2946848" @default.
- W2980297462 hasPublicationYear "2019" @default.
- W2980297462 type Work @default.
- W2980297462 sameAs 2980297462 @default.
- W2980297462 citedByCount "10" @default.
- W2980297462 countsByYear W29802974622019 @default.
- W2980297462 countsByYear W29802974622020 @default.
- W2980297462 countsByYear W29802974622021 @default.
- W2980297462 countsByYear W29802974622022 @default.
- W2980297462 crossrefType "journal-article" @default.
- W2980297462 hasAuthorship W2980297462A5019886822 @default.
- W2980297462 hasAuthorship W2980297462A5033106028 @default.
- W2980297462 hasAuthorship W2980297462A5056532148 @default.
- W2980297462 hasBestOaLocation W29802974621 @default.
- W2980297462 hasConcept C119857082 @default.
- W2980297462 hasConcept C154945302 @default.
- W2980297462 hasConcept C162324750 @default.
- W2980297462 hasConcept C2777303404 @default.
- W2980297462 hasConcept C41008148 @default.
- W2980297462 hasConcept C41550386 @default.
- W2980297462 hasConcept C50522688 @default.
- W2980297462 hasConcept C90509273 @default.
- W2980297462 hasConcept C97541855 @default.
- W2980297462 hasConceptScore W2980297462C119857082 @default.
- W2980297462 hasConceptScore W2980297462C154945302 @default.
- W2980297462 hasConceptScore W2980297462C162324750 @default.
- W2980297462 hasConceptScore W2980297462C2777303404 @default.
- W2980297462 hasConceptScore W2980297462C41008148 @default.
- W2980297462 hasConceptScore W2980297462C41550386 @default.
- W2980297462 hasConceptScore W2980297462C50522688 @default.
- W2980297462 hasConceptScore W2980297462C90509273 @default.
- W2980297462 hasConceptScore W2980297462C97541855 @default.
- W2980297462 hasFunder F4320321001 @default.
- W2980297462 hasLocation W29802974621 @default.
- W2980297462 hasLocation W29802974622 @default.
- W2980297462 hasOpenAccess W2980297462 @default.
- W2980297462 hasPrimaryLocation W29802974621 @default.
- W2980297462 hasRelatedWork W2024136090 @default.
- W2980297462 hasRelatedWork W2031695474 @default.
- W2980297462 hasRelatedWork W2138720691 @default.
- W2980297462 hasRelatedWork W2586732548 @default.
- W2980297462 hasRelatedWork W2964765435 @default.
- W2980297462 hasRelatedWork W3049728571 @default.
- W2980297462 hasRelatedWork W4306904969 @default.
- W2980297462 hasRelatedWork W4362501864 @default.
- W2980297462 hasRelatedWork W4380318855 @default.
- W2980297462 hasRelatedWork W2585069576 @default.
- W2980297462 hasVolume "7" @default.
- W2980297462 isParatext "false" @default.
- W2980297462 isRetracted "false" @default.
- W2980297462 magId "2980297462" @default.
- W2980297462 workType "article" @default.