A novel neural network based reinforcement learning

Authors:
Jian Fan;Yang Song;MinRui Fei;Qijie Zhao
Affiliations:
Shanghai Key Laboratory of Power Station Automation Technology, Collgeg of Mechatronics Engineering and Automation, Shanghai University, Shanghai, China and Operations Research Center, Nanjing Arm ...;Shanghai Key Laboratory of Power Station Automation Technology, Collgeg of Mechatronics Engineering and Automation, Shanghai University, Shanghai, China;Shanghai Key Laboratory of Power Station Automation Technology, Collgeg of Mechatronics Engineering and Automation, Shanghai University, Shanghai, China;Collgeg of Mechatronics Engineering and Automation, Shanghai University, Shanghai, China
Venue:
LSMS'07 Proceedings of the Life system modeling and simulation 2007 international conference on Bio-Inspired computational intelligence and applications
Year:
2007

Citing 3
Cited 0

Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Comparing Object Encodings

TACS '97 Proceedings of the Third International Symposium on Theoretical Aspects of Computer Software

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many function-approaching methods such as neural network, fuzzy method are used in reinforcement learning methods for solving its huge problem space dimensions. This paper presents a novel ART2 neural network based reinforcement learning method (ART2-RL) to solve the space problem. Because of its adaptive resonance characteristic, ART2 neural network is used to process the space measurement of reinforcement learning and improve the learning speed. This paper also gives the reinforcement learning algorithm based on ART2. A simulation of path planning of mobile robot has been developed to prove the validity of ART2-RL. As the complexity of the simulation increased, the result shows that the number of collision between robot and obstacles is effectively decreased; the novel neural network model provides significant improvement in the space measurement of reinforcement learning.