Transfer in Reinforcement Learning Domains
In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow...
Clasificación: | Libro Electrónico |
---|---|
Autor principal: | Taylor, Matthew (Autor) |
Autor Corporativo: | SpringerLink (Online service) |
Formato: | Electrónico eBook |
Idioma: | Inglés |
Publicado: |
Berlin, Heidelberg :
Springer Berlin Heidelberg : Imprint: Springer,
2009.
|
Edición: | 1st ed. 2009. |
Colección: | Studies in Computational Intelligence,
216 |
Temas: | |
Acceso en línea: | Texto Completo |
Ejemplares similares
-
Reinforcement Learning State-of-the-Art /
Publicado: (2012) -
Adaptive Representations for Reinforcement Learning
por: Whiteson, Shimon
Publicado: (2010) -
Design of Experiments for Reinforcement Learning
por: Gatti, Christopher
Publicado: (2015) -
Innovation through Knowledge Transfer
Publicado: (2010) -
Innovation through Knowledge Transfer 2012
Publicado: (2013)