Cargando...

Context Transfer in Reinforcement Learning Using Action-Value Functions

This paper discusses the notion of context transfer in reinforcement learning tasks. Context transfer, as defined in this paper, implies knowledge transfer between source and target tasks that share the same environment dynamics and reward function but have different states or action spaces. In othe...

Descripción completa

Guardado en:
Detalles Bibliográficos
Publicado en:Comput Intell Neurosci
Autores principales: Mousavi, Amin, Nadjar Araabi, Babak, Nili Ahmadabadi, Majid
Formato: Artigo
Lenguaje:Inglês
Publicado: Hindawi Publishing Corporation 2014
Materias:
Acceso en línea:https://ncbi.nlm.nih.gov/pmc/articles/PMC4293791/
https://ncbi.nlm.nih.gov/pubmed/25610457
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1155/2014/428567
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!