Heuristically accelerated reinforcement learning modularization for multi-agent multi-objective problems

Página do item simplificado
dc.contributor.authorFerreira L.A.
dc.contributor.authorCosta Ribeiro C.H.
dc.contributor.authorDa Costa Bianchi R.A.
dc.date.accessioned2019-08-19T23:45:22Z
dc.date.available2019-08-19T23:45:22Z
dc.date.issued2014
dc.description.abstractThis article presents two new algorithms for finding the optimal solution of a Multi-agent Multi-objective Reinforcement Learning problem. Both algorithms make use of the concepts of modularization and acceleration by a heuristic function applied in standard Reinforcement Learning algorithms to simplify and speed up the learning process of an agent that learns in a multi-agent multi-objective environment. In order to verify performance of the proposed algorithms, we considered a predator-prey environment in which the learning agent plays the role of prey that must escape the pursuing predator while reaching for food in a fixed location. The results show that combining modularization and acceleration using a heuristics function indeed produced simplification and speeding up of the learning process in a complex problem when comparing with algorithms that do not make use of acceleration or modularization techniques, such as Q-Learning and Minimax-Q. © 2014 Springer Science+Business Media New York.
dc.description.firstpage551
dc.description.issuenumber2
dc.description.lastpage562
dc.description.volume41
dc.identifier.citationFERREIRA, LEONARDO ANJOLETTO; COSTA RIBEIRO, CARLOS HENRIQUE; DA COSTA BIANCHI, REINALDO AUGUSTO. Heuristically accelerated reinforcement learning modularization for multi-agent multi-objective problems. Applied Intelligence (Boston), v. 1, p. 1-12, 2014.
dc.identifier.doi10.1007/s10489-014-0534-0
dc.identifier.issn0924-669X
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/1241
dc.relation.ispartofApplied Intelligence
dc.rightsAcesso Restrito
dc.subject.otherlanguageHeuristically accelerated reinforcement learning
dc.subject.otherlanguageMulti-agent systems
dc.subject.otherlanguageMulti-objective problems
dc.subject.otherlanguageReinforcement learning
dc.titleHeuristically accelerated reinforcement learning modularization for multi-agent multi-objective problems
dc.typeArtigo
fei.scopus.citations8
fei.scopus.eid2-s2.0-84906780922
fei.scopus.subjectComplex problems
fei.scopus.subjectHeuristic functions
fei.scopus.subjectHeuristics functions
fei.scopus.subjectLearning agents
fei.scopus.subjectLearning process
fei.scopus.subjectModularization techniques
fei.scopus.subjectMulti-objective problem
fei.scopus.subjectOptimal solutions
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84906780922&origin=inward
Arquivos
Coleções
Artigos