Self-Organizing Neural Networks Integrating Domain Knowledge and Reinforcement Learning
- 20 June 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 26 (5) , 889-902
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
This publication has 23 references indexed in Scilit:
- Continuous state/action reinforcement learning: A growing self-organizing map approachNeurocomputing, 2011
- The kNN-TD Reinforcement Learning AlgorithmLecture Notes in Computer Science, 2009
- Cognitive Agents Integrating Rules and Reinforcement Learning for Context-Aware Decision Support2008
- Integrating Temporal Difference Methods and Self-Organizing Neural Networks for Reinforcement Learning With Delayed Evaluative FeedbackIEEE Transactions on Neural Networks, 2008
- Integrating symbolic knowledge in reinforcement learning2002
- Using background knowledge to speed reinforcement learning in physical agents2001
- Statistical Reasoning Strategies in the Pursuit and Evasion Domain1999
- Incorporating prior information in machine learning by creating virtual examplesProceedings of the IEEE, 1998
- A massively parallel architecture for a self-organizing neural pattern recognition machineComputer Vision, Graphics, and Image Processing, 1987
- How many memory systems are there?American Psychologist, 1985