Mostrar el registro sencillo del ítem
dc.contributor | Escuela de Ingenierias Industrial, Informática y Aeroespacial | es_ES |
dc.contributor.author | Fernández, Fernando | |
dc.contributor.author | Borrajo, Daniel | |
dc.contributor.author | Matellán Olivera, Vicente | |
dc.contributor.other | Arquitectura y Tecnologia de Computadores | es_ES |
dc.date | 1999-09-10 | |
dc.date.accessioned | 2012-10-18T12:20:09Z | |
dc.date.available | 2012-10-18T12:20:09Z | |
dc.date.issued | 2012-10-18 | |
dc.identifier.citation | European Conference on Planning, Septiembre, 1999, Durham, Reino Unido | es_ES |
dc.identifier.uri | http://hdl.handle.net/10612/1921 | |
dc.description.abstract | Reinforcement learning har proven to be very successful for finding optimal policies on uncertian and/or dynamic domains. One of the problems on using such techniques appears with large state and action spaces. This problem appears very frequently given that most information in the type of tasks to which these techniques have been applied is continuous. In the paper, we describe a new mechanism for solving the states generalization problem in reinforcement learning algorithms, the VQQL technique | es_ES |
dc.language | eng | es_ES |
dc.subject | Informática | es_ES |
dc.subject.other | Conocimiento | es_ES |
dc.subject.other | Robótica | es_ES |
dc.subject.other | VQQL | es_ES |
dc.subject.other | Aprendizaje | es_ES |
dc.title | VQQL: a model to generalize in reinforcement learning | es_ES |
dc.type | info:eu-repo/semantics/conferenceObject | es_ES |
dc.type.other | info:eu-repo/semantics/lecture | es_ES |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es_ES |