Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003499901> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3003499901 endingPage "644" @default.
- W3003499901 startingPage "636" @default.
- W3003499901 abstract "In multiagent cooperative systems with value-based reinforcement learning, agents learn how to complete the task by an optimal policy learned through value-policy improvement iterations. But how to design a policy that avoids cooperation dilemmas and comes to a common consensus between agents is an important issue. A method that improves the coordination ability of agents in cooperative systems by assessing the cooperative tendency and increases the collective payoff by candidate policy is proposed in this article. The method learns the cooperative rules by recording the cooperation probabilities for agents in a multitier reinforcement learning model. The candidate action sets are selected through the candidate policy which considers the payoff of the coalition. Then, the optimal strategy is selected through the Nash bargaining solution (NBS) from these candidate action sets. The method is tested using two cooperative tasks. The results show that the proposed algorithm, which addresses the instability and ambiguity in a win or learning fast policy hill-climbing (WoLF-PHC) and requires significantly less memory space than the NBS, is more stable and more efficient than other methods." @default.
- W3003499901 created "2020-02-07" @default.
- W3003499901 creator A5013665827 @default.
- W3003499901 creator A5049705446 @default.
- W3003499901 creator A5058795369 @default.
- W3003499901 creator A5061189209 @default.
- W3003499901 creator A5066851929 @default.
- W3003499901 creator A5084150509 @default.
- W3003499901 date "2020-09-01" @default.
- W3003499901 modified "2023-09-27" @default.
- W3003499901 title "A Multitier Reinforcement Learning Model for a Cooperative Multiagent System" @default.
- W3003499901 cites W169931978 @default.
- W3003499901 cites W1980737627 @default.
- W3003499901 cites W1981289969 @default.
- W3003499901 cites W2103076989 @default.
- W3003499901 cites W2107544712 @default.
- W3003499901 cites W2108267069 @default.
- W3003499901 cites W2124716489 @default.
- W3003499901 cites W2164913115 @default.
- W3003499901 cites W2491537827 @default.
- W3003499901 cites W2561001448 @default.
- W3003499901 cites W2586106701 @default.
- W3003499901 cites W2761465998 @default.
- W3003499901 cites W2783134749 @default.
- W3003499901 cites W2789901741 @default.
- W3003499901 cites W4233776596 @default.
- W3003499901 cites W4242450948 @default.
- W3003499901 doi "https://doi.org/10.1109/tcds.2020.2970487" @default.
- W3003499901 hasPublicationYear "2020" @default.
- W3003499901 type Work @default.
- W3003499901 sameAs 3003499901 @default.
- W3003499901 citedByCount "5" @default.
- W3003499901 countsByYear W30034999012020 @default.
- W3003499901 countsByYear W30034999012021 @default.
- W3003499901 countsByYear W30034999012022 @default.
- W3003499901 countsByYear W30034999012023 @default.
- W3003499901 crossrefType "journal-article" @default.
- W3003499901 hasAuthorship W3003499901A5013665827 @default.
- W3003499901 hasAuthorship W3003499901A5049705446 @default.
- W3003499901 hasAuthorship W3003499901A5058795369 @default.
- W3003499901 hasAuthorship W3003499901A5061189209 @default.
- W3003499901 hasAuthorship W3003499901A5066851929 @default.
- W3003499901 hasAuthorship W3003499901A5084150509 @default.
- W3003499901 hasConcept C119857082 @default.
- W3003499901 hasConcept C144237770 @default.
- W3003499901 hasConcept C154945302 @default.
- W3003499901 hasConcept C162324750 @default.
- W3003499901 hasConcept C187736073 @default.
- W3003499901 hasConcept C188116033 @default.
- W3003499901 hasConcept C199360897 @default.
- W3003499901 hasConcept C22171661 @default.
- W3003499901 hasConcept C2780451532 @default.
- W3003499901 hasConcept C2780522230 @default.
- W3003499901 hasConcept C33923547 @default.
- W3003499901 hasConcept C41008148 @default.
- W3003499901 hasConcept C97541855 @default.
- W3003499901 hasConceptScore W3003499901C119857082 @default.
- W3003499901 hasConceptScore W3003499901C144237770 @default.
- W3003499901 hasConceptScore W3003499901C154945302 @default.
- W3003499901 hasConceptScore W3003499901C162324750 @default.
- W3003499901 hasConceptScore W3003499901C187736073 @default.
- W3003499901 hasConceptScore W3003499901C188116033 @default.
- W3003499901 hasConceptScore W3003499901C199360897 @default.
- W3003499901 hasConceptScore W3003499901C22171661 @default.
- W3003499901 hasConceptScore W3003499901C2780451532 @default.
- W3003499901 hasConceptScore W3003499901C2780522230 @default.
- W3003499901 hasConceptScore W3003499901C33923547 @default.
- W3003499901 hasConceptScore W3003499901C41008148 @default.
- W3003499901 hasConceptScore W3003499901C97541855 @default.
- W3003499901 hasFunder F4320321001 @default.
- W3003499901 hasIssue "3" @default.
- W3003499901 hasLocation W30034999011 @default.
- W3003499901 hasOpenAccess W3003499901 @default.
- W3003499901 hasPrimaryLocation W30034999011 @default.
- W3003499901 hasRelatedWork W1966682685 @default.
- W3003499901 hasRelatedWork W1972847450 @default.
- W3003499901 hasRelatedWork W2073900753 @default.
- W3003499901 hasRelatedWork W2154793587 @default.
- W3003499901 hasRelatedWork W2169203366 @default.
- W3003499901 hasRelatedWork W2386664274 @default.
- W3003499901 hasRelatedWork W3074294383 @default.
- W3003499901 hasRelatedWork W4206669594 @default.
- W3003499901 hasRelatedWork W4319083788 @default.
- W3003499901 hasRelatedWork W77396219 @default.
- W3003499901 hasVolume "12" @default.
- W3003499901 isParatext "false" @default.
- W3003499901 isRetracted "false" @default.
- W3003499901 magId "3003499901" @default.
- W3003499901 workType "article" @default.