The Need for Improved Reinforcement Learning Techniques in Intelligent Agents
Reinforcement learning is an integral part of intelligent agent research. The development of this field, however, has been largely independent of the latest developments in neural networks. As a result, the most popular designs for intelligent agents utilize neural network architectures from several years ago. This article recommends newer, proven designs for reinforcement learning. The recommended designs share historical roots with the most popular architectures in place today, allowing improved performance without radical redesign of existing agents.
D. C. Wunsch, "The Need for Improved Reinforcement Learning Techniques in Intelligent Agents," Neural Networks, 1997. International Conference on Neural Networks, vol. 4, pp. 2279-2282, Institute of Electrical and Electronics Engineers (IEEE), Jan 1997.
The definitive version is available at http://dx.doi.org/10.1109/ICNN.1997.614403
IEEE International Conference on Neural Networks (1997: Jun. 9-12, Houston, TX)
Electrical and Computer Engineering
International Standard Book Number (ISBN)
Article - Conference proceedings
© 1997 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.