A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
Technical Note: \cal Q-Learning
Machine Learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Statistical Reasoning Strategies in the Pursuit and Evasion Domain
ECAL '99 Proceedings of the 5th European Conference on Advances in Artificial Life
Efficient Exploration In Reinforcement Learning
Efficient Exploration In Reinforcement Learning
Probabilistic policy reuse in a reinforcement learning agent
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Intelligence Through Interaction: Towards a Unified Theory for Learning
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Cognitive Agents Integrating Rules and Reinforcement Learning for Context-Aware Decision Support
WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 02
Direct code access in self-organizing neural networks for reinforcement learning
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Heuristic search based exploration in reinforcement learning
IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
Vision-Based Pursuit-Evasion in a Grid
SIAM Journal on Discrete Mathematics
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
Exploration is necessary during reinforcement learning to discover new solutions in a given problem space. Most reinforcement learning systems, however, adopt a simple strategy, by randomly selecting an action among all the available actions. This paper proposes a novel exploration strategy, known as Knowledge-based Exploration, for guiding the exploration of a family of self-organizing neural networks in reinforcement learning. Specifically, exploration is directed towards unexplored and favorable action choices while steering away from those negative action choices that are likely to fail. This is achieved by using the learned knowledge of the agent to identify prior action choices leading to low $Q$-values in similar situations. Consequently, the agent is expected to learn the right solutions in a shorter time, improving overall learning efficiency. Using a Pursuit-Evasion problem domain, we evaluate the efficacy of the knowledge-based exploration strategy, in terms of task performance, rate of learning and model complexity. Comparison with random exploration and three other heuristic-based directed exploration strategies show that Knowledge-based Exploration is significantly more effective and robust for reinforcement learning in real time.