Realistic Actor-Critic: A framework for balance between value overestimation and underestimation

INTRODUCTION: The value approximation bias is known to lead to suboptimal policies or catastrophic overestimation bias accumulation that prevent the agent from making the right decisions between exploration and exploitation. Algorithms have been proposed to mitigate the above contradiction. However,...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Sicen, Tang, Qinyun, Pang, Yiming, Ma, Xinmeng, Wang, Gang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9868235/
https://www.ncbi.nlm.nih.gov/pubmed/36699950
http://dx.doi.org/10.3389/fnbot.2022.1081242

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9868235/
https://www.ncbi.nlm.nih.gov/pubmed/36699950
http://dx.doi.org/10.3389/fnbot.2022.1081242

Ejemplares similares