A Reward Optimization Method Based on Action Subrewards in Hierarchical Reinforcement Learning

Reinforcement learning (RL) is one kind of interactive learning methods. Its main characteristics are “trial and error” and “related reward.” A hierarchical reinforcement learning method based on action subrewards is proposed to solve the problem of “curse of dimensionality,” which means that the st...

Descripción completa

Detalles Bibliográficos
Autores principales: Fu, Yuchen, Liu, Quan, Ling, Xionghong, Cui, Zhiming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2014
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3926376/
https://www.ncbi.nlm.nih.gov/pubmed/24600318
http://dx.doi.org/10.1155/2014/120760

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3926376/
https://www.ncbi.nlm.nih.gov/pubmed/24600318
http://dx.doi.org/10.1155/2014/120760

Ejemplares similares