Function approximation method based on weights gradient descent in reinforcement learning

Function approximation has gained significant attention in reinforcement learning research as it effectively addresses problems with large-scale, continuous state, and action space.Although the function approximation algorithm based on gradient descent method is one of the most widely used methods i...

Celý popis

Podrobná bibliografie

Hlavní autor:	Xiaoyan QIN, Yuhan LIU, Yunlong XU, Bin LI
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	POSTS&TELECOM PRESS Co., LTD 2023-08-01
Edice:	网络与信息安全学报
Témata:	function approximation reinforcement learning gradient descent least-squares weights gradient descent
On-line přístup:	https://www.infocomm-journal.com/cjnis/CN/10.11959/j.issn.2096-109x.2023050
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!