Improved automatic discovery of subgoals for options in hierarchical

Options have been shown to be a key step in extending reinforcement learning beyond low-level reactionary systems to higher-level, planning systems. Most of the options research involves hand-crafted options; there has been only very limited work in the automated discovery of options. We extend earl...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kretchmar, R. Matthew, Feil, Todd, Bansal, Rohit
Formato: Articulo
Lenguaje:Inglés
Publicado: 2003
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/9461
http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Oct03-2.pdf
Aporte de:
Descripción
Sumario:Options have been shown to be a key step in extending reinforcement learning beyond low-level reactionary systems to higher-level, planning systems. Most of the options research involves hand-crafted options; there has been only very limited work in the automated discovery of options. We extend early work in automated option discovery with a flexible and robust method.