Título

Strategic interactions against non-stationary agents

Autor

PABLO FRANCISCO HERNANDEZ LEAL

Nivel de Acceso

Acceso Abierto

Licencia

http://creativecommons.org/licenses/by-nc-nd/4.0

Materias

Learning - (APRENDIZAJE) Repeated games - (REPETICIÓN) Opponent modeling - (MODELACIÓN) CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA - (CTI) MATEMÁTICAS - (CTI) CIENCIA DE LOS ORDENADORES - (CTI) INSTRUCCIONES ARITMÉTICAS Y DE MÁQUINA - (CTI)

Resumen o descripción

Designing an agent that is capable of interacting with another agent is an open problem. An

interaction happen when two or more agents perform an action in an environment and they obtain

an utility based on the performed joint action.Current multiagent learning techniques do not fare

well with agents that change their behavior during a repeated interaction. This happens because

they usually do not model the other agents’ behavior and instead make some assumptions that for

real scenarios are too restrictive. Furthermore, considering that many applications demand different

types of agents to work together this should be an important problem to solve. It does not matter if

the domain is cooperative (where agents have a common goal) or competitive (where objectives are

different), there is one common aspect: agents must learn how their counterpart is acting and react

quickly to changes in behavior.

Editor

Instituto Nacional de Astrofísica, Óptica y Electrónica

Fecha de publicación

11 de enero de 2015

Tipo de publicación

Tesis de doctorado

Recurso de información

http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/30

Formato

application/pdf

Idioma

Inglés

Audiencia

Público en general

Sugerencia de citación

Hernandez-Leal P. F.

Repositorio Orígen

Repositorio Institucional del INAOE

Descargas

2397