Multi-agent multi-objective learning using heuristically accelerated reinforcement learning

Página do item simplificado
dc.contributor.authorFERREIRA, L. A.
dc.contributor.authorReinaldo Bianchi
dc.contributor.authorRIBEIRO, C. H. C.
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-9097-827X
dc.date.accessioned2022-01-12T22:02:03Z
dc.date.available2022-01-12T22:02:03Z
dc.date.issued2012-10-19
dc.description.abstractThis paper introduces two new algorithms aimed at solving multi-agent multi-objective reinforcement learning problems in which the learning agent must not only interact with multiples agents but also consider various objectives (or criteria) in order to solve the problem. The main concept behind the proposed algorithms is a modular approach that is used to divide the multiple objectives in modules, and making each one of these modules learn a different objective with different Action-Value and reinforcement functions. Besides the decomposition of objectives, both algorithms use a heuristic function to accelerate the learning process. The first algorithm learns one objective at a time, iterating along the objectives, while the second proposed algorithm also divides the problem in sub-problems but learns every objective simultaneously. The Predator-Prey problem was chosen to compare the performance of both proposed solutions with well known algorithms. In this problem, the learning agent plays the role of the prey and must learn to find food in a fixed position of a grid world while being pursued by the predator. The considered objectives are finding food and avoiding the predator. As the results shows, decomposing a multi-objective problem in sub-problems and using heuristics makes the learning process faster and easier to implement. We notice that the first algorithm introduced in this paper learns faster, but it is more difficult to implement in a real world environment. © 2012 IEEE.
dc.description.firstpage14
dc.description.lastpage20
dc.identifier.citationFERREIRA, L. A. ; BIANCHI, R.; RIBEIRO, C. H. C. Multi-agent multi-objective learning using heuristically accelerated reinforcement learning. Proceedings - 2012 Brazilian Robotics Symposium and Latin American Robotics Symposium, SBR-LARS 2012, p. 14-20, Oct. 2012.
dc.identifier.doi10.1109/SBR-LARS.2012.10
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4109
dc.relation.ispartofProceedings - 2012 Brazilian Robotics Symposium and Latin American Robotics Symposium, SBR-LARS 2012
dc.rightsAcesso Restrito
dc.subject.otherlanguageArtificial Intelligence
dc.subject.otherlanguageMachine Learning
dc.subject.otherlanguageMultiagent systems
dc.titleMulti-agent multi-objective learning using heuristically accelerated reinforcement learning
dc.typeArtigo de evento
fei.scopus.citations5
fei.scopus.eid2-s2.0-84871580385
fei.scopus.subjectHeuristic functions
fei.scopus.subjectLearning agents
fei.scopus.subjectLearning process
fei.scopus.subjectModular approach
fei.scopus.subjectMulti objective
fei.scopus.subjectMulti-objective problem
fei.scopus.subjectMultiple objectives
fei.scopus.subjectPredator-Prey
fei.scopus.subjectReal world environments
fei.scopus.subjectSub-problems
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84871580385&origin=inward
Arquivos
Coleções
Artigos