Please use this identifier to cite or link to this item: http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/30
Strategic interactions against non-stationary agents
PABLO FRANCISCO HERNANDEZ LEAL
Acceso Abierto
Atribución-NoComercial-SinDerivadas
Learning
Repeated games
Opponent modeling
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.
Instituto Nacional de Astrofísica, Óptica y Electrónica
11-01-2015
Tesis de doctorado
Inglés
Público en general
Hernandez-Leal P. F.
INSTRUCCIONES ARITMÉTICAS Y DE MÁQUINA
Appears in Collections:Doctorado en Ciencias Computacionales

Upload archives


File Description SizeFormat 
HernandezLePF.pdf6.22 MBAdobe PDFView/Open