arrow
返回

Actor-Critic Learning Control Based on l2-Regularized Temporal-Difference Prediction With Gradient Correction

delete2018-12-01
delete7
PRE
AI
L
Luntong Li
D
Dazi Li *
T
Tianheng Song
徐鑫 封面图
徐鑫 (Xin Xu)
DOI:10.1109/TNNLS.2018.2808203delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Actor-critic based on the policy gradient (PG-based AC) methods have been widely studied to solve learning control problems. In order to increase the data efficiency of learning prediction in the critic of PG-based AC, studies on how to use recursive least-squares temporal difference (RLS-TD) algorithms for policy evaluation have been conducted in recent years. In such contexts, the critic RLS-TD evaluates an unknown mixed policy generated by a series of different actors, but not one fixed policy generated by the current actor. Therefore, this AC framework with RLS-TD critic cannot be proved to converge to the optimal fixed point of learning problem. To address the above problem, this paper proposes a new AC framework named critic-iteration PG (CIPG), which learns the state-value function of current policy in an on-policy way and performs gradient ascent in the direction of improving discounted total reward. During each iteration, CIPG keeps the policy parameters fixed and evaluates the resulting fixed policy by l(2)-regularized RLS-TD critic. Our convergence analysis extends previous convergence analysis of PG with function approximation to the case of RLS-TD critic. The simulation results demonstrate that the l(2)-regularization term in the critic of CIPG is undamped during the learning process, and CIPG has better learning efficiency and faster convergence rate than conventional AC learning control methods.
Keyword:
l(2)-regularization
actor-critic (AC)
policy gradient (PG)
reinforcement learning (RL)
value function approximation
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Neural Networks and Learning Systems 封面图
IEEE Transactions on Neural Networks and Learning Systems
IF:
8.9
论文数:
7.6K
被引数:
7.2W

机构

B
Beijing University of Chemical Technology
学者数:
3.1W
论文数: 2.2W
被引数: 4.5W
N
national university of defense technology - china
学者数:
1.8W
论文数: 1.4W
被引数: 9
引用论文

引用论文

Natural Actor-Critic
err2008-03-01
err643
PREAI
errPeters, Jan; Schaal, Stefan
err分享
err收藏
Opening Platforms: How, When and Why?
err2008-01-01
err0
PREAI
errThomas R. Eisenmann; Geoffrey Parker; Marshall W. Van Alstyne
err分享
err收藏
Does natural-resource-dependency create the need of green innovation?
err2023-08-01
err0
PREAI
errZhichao Yu; Ik Joong Youn; Noha Alessa; Hela Borgi
err分享
err收藏
Evidence for a Ubiquitous Seismic Discontinuity at the Base of the Mantle
err1999-11-12
err0
PREAI
errIgor Sidorin; Michael Gurnis; Don V. Helmberger
err分享
err收藏
学者 查看更多内容