Self-organizing neural architecture for reinforcement learning

Author

Ah-hwee TAN, Singapore Management UniversityFollow

Publication Type

Conference Proceeding Article

Publication Date

5-2006

Abstract

Self-organizing neural networks are typically associated with unsupervised learning. This paper presents a self-organizing neural architecture, known as TD-FALCON, that learns cognitive codes across multi-modal pattern spaces, involving sensory input, actions, and rewards, and is capable of adapting and functioning in a dynamic environment with external evaluative feedback signals. We present a case study of TD-FALCON on a mine avoidance and navigation cognitive task, and illustrate its performance by comparing with a state-of-the-art reinforcement learning approach based on gradient descent backpropagation algorithm

Discipline

Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Publication

J. Wang et al. (Eds.): International Symposium on Neural Networks (ISNN) 2006, LNCS 3971

Volume

3971 LNCS

Identifier

10.1007/11759966_70

Publisher

Springer

City or Country

Chengdu, China

Citation

1