A case study in hybrid multi-threading and hierarchical reinforcement learning approach for cooperative multi-agent systems

Show simple item record

dc.contributor.author Ponce Espinosa, Hiram Eredín
dc.date.accessioned 2017-10-24T22:37:12Z
dc.date.available 2017-10-24T22:37:12Z
dc.date.issued 2016
dc.identifier.citation Ponce Espinosa, H. E., Padilla, P., Davalos, A., Herrasti, A., Pichardo, C. y Dovali, D. (2016). A case study in hybrid multi-threading and hierarchical reinforcement learning approach for cooperative multi-agent systems. En: Sidorov, G. (editor), Fourteenth Mexican International Conference on Artificial Intelligence : Advances in Artificial Intelligence : MICAI 2015 : proceedings : 25-31 October 2015, Cuernavaca, Morelos, Mexico, (pp. 87-93). Los Alamitos, CA : Conference Publishing Services, IEEE Computer Society. DOI: 10.1109/MICAI.2015.20
dc.identifier.isbn 9781509003235
dc.identifier.other Campus Ciudad de México
dc.identifier.uri http://scripta.up.edu.mx/xmlui/handle/123456789/803
dc.identifier.uri http://dx.doi.org/10.1109/MICAI.2015.20
dc.description.abstract This paper describes a case study about a multi-agent system for cooperative tasks, i.e. a mixing color task given three different sources of color. A reinforcement learning approach was performed by the agents, however, this type of learning exploits exponentially when the number of states in the environment is very large. In that sense, the paper proposes to use the MaxQ-Q hierarchical reinforcement learning algorithm to obtain a suitable policy for agents in order to minimize the time process to achieve the goal, and to reduce the state space. In addition, since the multi-agent system runs in a software application, a multi-threading paradigm was proposed to use. Experimental results show that this multi-agent system can reduce the time process and still maintain independence of agents. © 2015 IEEE.
dc.description.statementofresponsibility Investigadores
dc.description.statementofresponsibility Estudiantes
dc.description.statementofresponsibility Maestros
dc.description.statementofresponsibility Público en general
dc.description.tableofcontents Ingeniería
dc.publisher Institute of Electrical and Electronics Engineers Inc.
dc.relation Versión del editor
dc.relation.ispartof REPOSITORIO SCRIPTA
dc.relation.ispartof REPOSITORIO NACIONAL CONACYT
dc.relation.ispartof OPENAIRE
dc.rights Acceso Cerrado
dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/4.0
dc.source Proceedings - 14th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence, MICAI 2015
dc.source Fourteenth Mexican International Conference on Artificial Intelligence : Advances in Artificial Intelligence : MICAI 2015 : proceedings : 25-31 October 2015, Cuernavaca, Morelos, Mexico
dc.subject Beliefs
dc.subject Cooperative tasks
dc.subject Hierarchical reinforcement learning
dc.subject Multi-agent systems
dc.subject Multi-threading
dc.subject Application programs
dc.subject Artificial intelligence
dc.subject Computer architecture
dc.subject Hierarchical systems
dc.subject Intelligent agents
dc.subject Learning algorithms
dc.subject Reconfigurable hardware
dc.subject Reinforcement learning
dc.subject Software agents
dc.subject Cooperative tasks
dc.subject Hierarchical reinforcement learning
dc.subject Multi-threading
dc.subject Number of state
dc.subject Reinforcement learning approach
dc.subject Software applications
dc.subject Multi agent systems
dc.subject.classification INGENIERIA Y TECNOLOGIA
dc.title A case study in hybrid multi-threading and hierarchical reinforcement learning approach for cooperative multi-agent systems
dc.type contribución a congreso


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Acceso Cerrado Except where otherwise noted, this item's license is described as Acceso Cerrado

Search Scripta


Advanced Search

Browse

My Account