Policy gradient fuzzy reinforcement learning

被引：0

作者：

Wang, XN ^{[1
]}

Xu, X ^{[1
]}

He, HG ^{[1
]}

机构：

[1] Natl Univ Def Technol, Inst Automat, Changsha 410073, Peoples R China

来源：

PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7 | 2004年

关键词：

reinforcement learning; fuzzy control; policy gradient; gradient estimate;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a new approach for tuning conclusions of fuzzy rules based on reinforcement learning. Unlike the most of existing fuzzy reinforcement learning algorithms which are based on value function, while our approach called policy gradient fuzzy reinforcement learning (PGFRL) bases on gradient estimate. In PGFRL, The algorithm GPOMDP is employed to estimate the performance gradient with respect to the parameters of fuzzy rules. In our work we prove the convergence of fuzzy rules' parameters to a local optimum given necessary conditions. The experiment results show the effectiveness of PGFRL.

引用

页码：992 / 995

页数：4

共 50 条

[1] A policy gradient reinforcement learning algorithm with fuzzy function approximation
Gu, DB
Yang, EF
IEEE ROBIO 2004: Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2004, : 936 - 940
[2] Reinforcement Learning to Rank with Pairwise Policy Gradient
Xu, Jun
Wei, Zeng
Xia, Long
Lan, Yanyan
Yin, Dawei
Cheng, Xueqi
Wen, Ji-Rong
PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20), 2020, : 509 - 518
[3] On the use of the policy gradient and Hessian in inverse reinforcement learning
Metelli, Alberto Maria
Pirotta, Matteo
Restelli, Marcello
INTELLIGENZA ARTIFICIALE, 2020, 14 (01) : 117 - 150
[4] Batch Reinforcement Learning With a Nonparametric Off-Policy Policy Gradient
Tosatto, Samuele
Carvalho, Joao
Peters, Jan
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (10) : 5996 - 6010
[5] A Residual Gradient Fuzzy Reinforcement Learning Algorithm for Differential Games
Awheda, Mostafa D.
Schwartz, Howard M.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS, 2017, 19 (04) : 1058 - 1076
[6] A Residual Gradient Fuzzy Reinforcement Learning Algorithm for Differential Games
Mostafa D. Awheda
Howard M. Schwartz
International Journal of Fuzzy Systems, 2017, 19 : 1058 - 1076
[7] Hessian matrix distribution for Bayesian policy gradient reinforcement learning
Ngo Anh Vien
Yu, Hwanjo
Chung, TaeChoong
INFORMATION SCIENCES, 2011, 181 (09) : 1671 - 1685
[8] Adaptive Natural Policy Gradient in Reinforcement Learning
Li, Dazi
Qiao, Zengyuan
Song, Tianheng
Jin, Qibing
PROCEEDINGS OF 2018 IEEE 7TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE (DDCLS), 2018, : 605 - 610
[9] Traffic Light Control with Policy Gradient-Based Reinforcement Learning
Tas, Mehmet Bilge Han
Ozkan, Kemal
Saricicek, Inci
Yazici, Ahmet
32ND IEEE SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU 2024, 2024,
[10] Survey of Deep Reinforcement Learning Based on Value Function and Policy Gradient
Liu J.-W.
Gao F.
Luo X.-L.
Jisuanji Xuebao/Chinese Journal of Computers, 2019, 42 (06): : 1406 - 1438

← 1 2 3 4 5 →