ART2 neural network interacting with environment

Authors:
Jian Fan;Yang Song;MinRui Fei
Affiliations:
Shanghai Key Laboratory of Power Station Automation Technology, School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, PR China and Operations Research Center, Na ...;Shanghai Key Laboratory of Power Station Automation Technology, School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, PR China;Shanghai Key Laboratory of Power Station Automation Technology, School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, PR China
Venue:
Neurocomputing
Year:
2008

Citing 5
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
Intrusion Detection Based on An Improved ART2 Neural Network

PDCAT '05 Proceedings of the Sixth International Conference on Parallel and Distributed Computing Applications and Technologies
An approach based on the Adaptive Resonance Theory for analysing the viability of recommender systems in a citizen Web portal

Expert Systems with Applications: An International Journal
Vector quantization of images using modified adaptive resonance algorithm for hierarchical clustering

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

It is common to train a neural network by using samples so that it can realize the required input-output characteristics. However, to obtain such samples is difficult or even impossible in some cases. This paper proposes the use of on-line reinforcement learning (RL) algorithms to train adaptive-resonance-theory-based (ART2) neural networks through interaction with environments, namely RL-ART2 neural network. By utilizing its adaptation ability to a dynamic environment, RL is able to evaluate and select ART2 classification patterns without training samples. The connection weights can be automatically modified according to the running effect evaluation of classification pattern of neural networks. The proposed novel RL-ART2 neural network is applied to implement the collaboration movement of mobile robots. Simulation results are presented to demonstrate the feasibility and performance of the proposed algorithm.