Self-organizing neural architecture for reinforcement learning

Authors:
Ah-Hwee Tan
Affiliations:
Intelligent Systems Centre and School of Computer Engineering, Nanyang Technological University, Singapore
Venue:
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Year:
2006

Citing 4
Cited 4

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

Neural Networks
Technical Note: \cal Q-Learning

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)

Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)

Intelligence Through Interaction: Towards a Unified Theory for Learning

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Scaling Up Multi-agent Reinforcement Learning in Complex Domains

WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 02
Agent-augmented co-space: toward merging of real world and cyberspace

ATC'10 Proceedings of the 7th international conference on Autonomic and trusted computing
A hybrid neural network model based reinforcement learning agent

ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

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 states, 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.