Case-based multiagent reinforcement learning: Cases as heuristics for selection of actions

Página do item simplificado
dc.contributor.authorReinaldo Bianchi
dc.contributor.authorLOPEZ DE MANTARAS, R.
dc.contributor.authorOrcidhttps://orcid.org/0000-0001-9097-827X
dc.date.accessioned2022-01-12T22:04:13Z
dc.date.available2022-01-12T22:04:13Z
dc.date.issued2010-08-17
dc.description.abstractThis work presents a new approach that allows the use of cases in a case base as heuristics to speed up Multiagent Reinforcement Learning algorithms, combining Case-Based Reasoning (CBR) and Multiagent Reinforcement Learning (MRL) techniques. This approach, called Case-Based Heuristically Accelerated Multiagent Reinforcement Learning (CB-HAMRL), builds upon an emerging technique, Heuristic Accelerated Reinforcement Learning (HARL), in which RL methods are accelerated by making use of heuristic information. CB-HAMRL is a subset of MRL that makes use of a heuristic function ℋ derived from a case base, in a Case-Based Reasoning manner. An algorithm that incorporates CBR techniques into the Heuristically Accelerated Minimax-Q is also proposed and a set of empirical evaluations were conducted in a simulator for the Littman's robot soccer domain, comparing the three solutions for this problem: MRL, HAMRL and CB-HAMRL. Experimental results show that using CB-HAMRL, the agents learn faster than using RL or HAMRL methods. © 2010 The authors and IOS Press. All rights reserved.
dc.description.firstpage355
dc.description.lastpage360
dc.description.volume215
dc.identifier.citationBIANCHI, R.; LOPEZ DE MANTARAS, R. Case-based multiagent reinforcement learning: Cases as heuristics for selection of actions. Frontiers in Artificial Intelligence and Applications, v.215, p. 35-360, 2010.
dc.identifier.doi10.3233/978-1-60750-606-5-355
dc.identifier.issn0922-6389
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/4256
dc.relation.ispartofFrontiers in Artificial Intelligence and Applications
dc.rightsAcesso Restrito
dc.titleCase-based multiagent reinforcement learning: Cases as heuristics for selection of actions
dc.typeArtigo de evento
fei.scopus.citations10
fei.scopus.eid2-s2.0-77956041284
fei.scopus.subjectCasebased reasonings (CBR)
fei.scopus.subjectEmpirical evaluations
fei.scopus.subjectHeuristic functions
fei.scopus.subjectHeuristic information
fei.scopus.subjectMulti-agent reinforcement learning
fei.scopus.subjectMultiagent reinforcement learning algorithm
fei.scopus.subjectNew approaches
fei.scopus.subjectThree solutions
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=77956041284&origin=inward
Arquivos
Coleções
Artigos