2024-03-28T10:40:07Zhttp://buleria.unileon.es/oai/requestoai:buleria.unileon.es:10612/19212023-05-30T11:13:24Zcom_10612_17col_10612_21
VQQL: a model to generalize in reinforcement learning
Fernández, Fernando
Borrajo, Daniel
Matellán Olivera, Vicente
Arquitectura y Tecnologia de Computadores
Informática
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
2012-10-18T12:20:09Z
2012-10-18T12:20:09Z
2012-10-18T12:20:09Z
2012-10-18
info:eu-repo/semantics/conferenceObject
European Conference on Planning, Septiembre, 1999, Durham, Reino Unido
http://hdl.handle.net/10612/1921
info:eu-repo/semantics/openAccess