Robot reinforcement learning accuracy-based learning classifier systems with Fuzzy Policy Gradient descent(XCS-FPGRL)

被引：0

作者：

Shao, Jie ^{[1
]}

Yu, Jingru ^{[1
]}

机构：

[1] Zhengzhou Chenggong Univ Finance & Econ, Dept Informat Engn, Zhengzhou 451200, Peoples R China

来源：

PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON ADVANCES IN MECHANICAL ENGINEERING AND INDUSTRIAL INFORMATICS | 2015年 / 15卷

关键词：

Convergence; Rrobot; Reinforcement learning; Accuracy-based learning classifier system with Gradient descent (XCS-FPGRL); XCS (Accuracy-based learning classifier system);

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presented a novel approach XCS-FPGRL to research on robot reinforcement learning. XCS-FPGRL combines covering operator and genetic algorithm. The systems is responsible for adjusting precision and reducing search space according to some reward obtained from the environment, acts as an innovation discovery component which is responsible for discovering new better reinforcement learning rules. The experiment and simulation showed that robot reinforcement learning can achieved convergence very quickly.

引用

页码：1013 / 1018

页数：6

共 50 条

[1] Swarm Robots Reinforcement Learning Convergence Accuracy-Based Learning Classifier Systems with Gradient Descent (XCS-GD)
Shao, Jie
Lin, Haixia
Zhang, Kaibian
2013 3RD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT), 2013, : 1306 - 1309
[2] Swarm robots reinforcement learning convergence accuracy-based learning classifier systems with gradient descent (XCS-GD)
Jie Shao
Haixia Lin
Kaibian Zhang
Neural Computing and Applications, 2014, 25 : 263 - 268
[3] Swarm robots reinforcement learning convergence accuracy-based learning classifier systems with gradient descent (XCS-GD)
Shao, Jie
Lin, Haixia
Zhang, Kaibian
NEURAL COMPUTING & APPLICATIONS, 2014, 25 (02): : 263 - 268
[4] Is Gradient Descent Update Consistent with Accuracy-Based Learning Classifier System?
Wada, Atsushi
Takadama, Keiki
JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2009, 13 (06) : 640 - 648
[5] Learning Optimality Theory for Accuracy-Based Learning Classifier Systems
Nakata, Masaya
Browne, Will N.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2021, 25 (01) : 61 - 74
[6] Accuracy-Based Learning Classifier Systems for Multistep Reinforcement Learning: A Fuzzy Logic Approach to Handling Continuous Inputs and Learning Continuous Actions
Chen, Gang
Douch, Colin I. J.
Zhang, Mengjie
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2016, 20 (06) : 953 - 971
[7] Backpropagation in accuracy-based neural learning classifier systems
O'Hara, Toby
Bull, Larry
LEARNING CLASSIFIER SYSTEMS, 2007, 4399 : 25 - 39
[8] Gradient descent methods in learning classifier systems: Improving XCS performance in multistep problems
Butz, MV
Goldberg, DE
Lanzi, PL
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2005, 9 (05) : 452 - 473
[9] Using Accuracy-Based Learning Classifier Systems for Imbalance Datasets
Udomthanapong, Sornchai
Tamee, Kreangsak
Pinngern, Ouen
ECTI-CON 2008: PROCEEDINGS OF THE 2008 5TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING/ELECTRONICS, COMPUTER, TELECOMMUNICATIONS AND INFORMATION TECHNOLOGY, VOLS 1 AND 2, 2008, : 21 - 24
[10] Theoretical Analysis of Accuracy-Based Fitness on Learning Classifier Systems
Sugawara, Rui
Nakata, Masaya
IEEE ACCESS, 2022, 10 : 64862 - 64872

← 1 2 3 4 5 →