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...
Guardado en:
| 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: |
Ejemplares similares
-
Techniques for improving the perfomance and scalability of directory-based shared-memory multiprocessors : A survey
por: Acacio Sánchez, Manuel, et al.
Publicado: (2003) -
Knowledge discovery process for description of spatially referenced clusters
por: Róttoli, Giovanni, et al.
Publicado: (2017) -
The Age of Discovery, 1400-1600 /
por: Arnold, David, 1946-
Publicado: (2002) -
KDD (Knowledge Discovery in Databases): un proceso centrado en el usuario
por: Nigro, Oscar, et al.
Publicado: (2004) -
Knowledge discovery process for description of spatially referenced clusters
por: Rottoli, Giovanni Daián, et al.
Publicado: (2018)