Publication Type

Journal Article

Version

publishedVersion

Publication Date

12-2007

Abstract

Temporal-Difference–Fusion Architecture for Learning, Cognition, and Navigation (TD-FALCON) is a generalization of adaptive resonance theory (a class of self-organizing neural networks) that incorporates TD methods for real-time reinforcement learning. In this paper, we investigate how a team of TD-FALCON networks may cooperate to learn and function in a dynamic multiagent environment based on minefield navigation and a predator/prey pursuit tasks. Experiments on the navigation task demonstrate that TD-FALCON agent teams are able to adapt and function well in a multiagent environment without an explicit mechanism of collaboration. In comparison, traditional Q-learning agents using gradient-descent-based feedforward neural networks, trained with the standard backpropagation and the resilient-propagation (RPROP) algorithms, produce a significantly poorer level of performance. For the predator/prey pursuit task, we experiment with various cooperative strategies and find that a combination of a high-level compressed state representation and a hybrid reward function produces the best results. Using the same cooperative strategy, the TD-FALCON team also outperforms the RPROP-based reinforcement learners in terms of both task completion rate and learning efficiency.

Keywords

Multiagent cooperative learning, reinforcement learning (RL), self-organizing neural architectures

Discipline

Computer and Systems Architecture | Computer Engineering | Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Volume

37

Issue

6

First Page

1567

Last Page

1580

ISSN

1083-4419

Identifier

10.1109/TSMCB.2007.907040

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Additional URL

https://doi.org/10.1109/TSMCB.2007.907040

Share

COinS