Publication Type

Journal Article

Version

acceptedVersion

Publication Date

6-2014

Abstract

The use of domain knowledge in learning systems is expected to improve learning efficiency and reduce model complexity. However, due to the incompatibility with knowledge structure of the learning systems and real-time exploratory nature of reinforcement learning (RL), domain knowledge cannot be inserted directly. In this paper, we show how self-organizing neural networks designed for online and incremental adaptation can integrate domain knowledge and RL. Specifically, symbol-based domain knowledge is translated into numeric patterns before inserting into the self-organizing neural networks. To ensure effective use of domain knowledge, we present an analysis of how the inserted knowledge is used by the self-organizing neural networks during RL. To this end, we propose a vigilance adaptation and greedy exploitation strategy to maximize exploitation of the inserted domain knowledge while retaining the plasticity of learning and using new knowledge. Our experimental results based on the pursuit-evasion and minefield navigation problem domains show that such self-organizing neural network can make effective use of domain knowledge to improve learning efficiency and reduce model complexity.

Keywords

Adaptive resonance theory (ART), domain knowledge, reinforcement learning (RL), self-organizing neural networks

Discipline

Computer and Systems Architecture | Databases and Information Systems | OS and Networks

Research Areas

Data Science and Engineering

Publication

IEEE Transactions on Neural Networks and Learning Systems

Volume

26

Issue

5

First Page

889

Last Page

902

ISSN

2162-2388

Identifier

10.1109/TNNLS.2014.2327636

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TNNLS.2014.2327636

Download

Share

COinS