TY  - GEN 
AU  - Fernández, Fernando
AU  - Borrajo, Daniel
AU  - Matellán Olivera, Vicente
A4  - Arquitectura y Tecnologia de Computadores
DA  - 1999/09/09
PY  - 2012
UR  - http://hdl.handle.net/10612/1921
AB  - 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...
LA  - eng
KW  - Informática
KW  - Conocimiento
KW  - Robótica
KW  - VQQL
KW  - Aprendizaje
TI  - VQQL: a model to generalize in reinforcement learning
ER  -