The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
Bookmark and Share
An Integrating Planning SARSA(λ) Algorithm of Reinforcement Learning
Author(s): 
Pages: 325-327
Year: Issue:  3
Journal: JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY

Keyword:  强化学习Markov决策过程SARSA学习规划;
Abstract: 提出一种新的集成规划的SARSA(λ)强化学习算法.该算法的主要思想是充分利用已有的经验数据,在无模型学习的同时估计系统模型,每进行一次无模型学习的试验后,利用模型在所记忆的状态/行动对组成的表中进行规划,同时利用该表给出了在学习和规划之间的量化折中参考.实验结果表明,本算法比单纯的无模型学习SARSA(λ)算法有效.
Related Articles
No related articles found