Constructing Temporally Extended Actions through Incremental Community Detection

Hierarchical reinforcement learning works on temporally extended actions or skills to facilitate learning. How to automatically form such abstraction is challenging, and many efforts tackle this issue in the options framework. While various approaches exist to construct options from different perspe...

Descripción completa

Detalles Bibliográficos
Autores principales: Xu, Xiao, Yang, Mei, Li, Ge
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2018
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5937602/
https://www.ncbi.nlm.nih.gov/pubmed/29849543
http://dx.doi.org/10.1155/2018/2085721

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5937602/
https://www.ncbi.nlm.nih.gov/pubmed/29849543
http://dx.doi.org/10.1155/2018/2085721

Ejemplares similares