Pruning dominated policies in multiobjective Pareto Q-learning

dc.contributor.author	Mandow-Andaluz, Lorenzo
dc.contributor.author	Pérez-de-la-Cruz-Molina, José Luis
dc.date.accessioned	2019-10-18T12:34:39Z
dc.date.available	2019-10-18T12:34:39Z
dc.date.created	2018
dc.date.issued	2019-10-18
dc.identifier.uri	https://hdl.handle.net/10630/18600
dc.description.abstract	The solution for a Multi-Objetive Reinforcement Learning problem is a set of Pareto optimal policies. MPQ-learning is a recent algorithm that approximates the whole set of all Pareto-optimal deterministic policies by directly generalizing Q-learning to the multiobjective setting. In this paper we present a modification of MPQ-learning that avoids useless cyclical policies and thus improves the number of training steps required for convergence.	en_US
dc.description.sponsorship	Supported by: the Spanish Government, Agencia Estatal de Investigaci´on (AEI) and European Union, Fondo Europeo de Desarrollo Regional (FEDER), grant TIN2016-80774-R (AEI/FEDER, UE); and Plan Propio de Investigación de la Universidad de Málaga - Campus de Excelencia Internacional Andalucía Tech.	en_US
dc.language.iso	eng	en_US
dc.rights	info:eu-repo/semantics/openAccess	en_US
dc.subject	Aprendizaje	en_US
dc.title	Pruning dominated policies in multiobjective Pareto Q-learning	en_US
dc.type	info:eu-repo/semantics/article	es_ES
dc.centro	E.T.S.I. Informática	en_US
dc.identifier.doi	https://doi.org/10.1007/978-3-030-00374-6_23
dc.type.hasVersion	info:eu-repo/semantics/submittedVersion	es_ES