Abstract
Watkins’ Q-learning is the most popular and an effective model-free method. However, comparing model-based approach, Q-learning with various exploration strategies require a large number of trial-and- error interactions for finding an optimal policy. To overcome this drawback, we propose a new model-based learning method extending Q-learning. This method has separated EI and ER functions for learning exploitation-based and exploration-based model, respectively. EI function based on statistics indicates the best action. The another ER function based on the information of exploration leads the learner to wellunknown region in the global state space by backing up in each step. Then, we introduce a new criterion as the information of exploration. Using combined these function, we can effectively proceed exploitation and exploration strategies and can select an action which considers each strategy simultaneously.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Tom Mitchell, Machine Learning, McGraw Hill, p367–390, 1997.
Atkeson, C. G. and Santamaria, J. C., A comparison of direct and model-based reinforcement learning, International Conference on Robotics and Automation, 1997.
Watkins, C. J. C. H., Dayan, P. Technical Note: Q-learning, Machine Learning 8, p55–68, 1992.
Leslie Pack Kaelbling, Michael L. Littman, Andrew W. Moore, Reinforcement Learning: A Survey, Journal of Artificial Intelligence Research 4, p237–285, 1996.
Sutton R., Barto A., Reinforcement Learning: An Introduction, MIT Press, 1998.
S. D. Whitehead and D. H. Ballard, Learning to perceive and act by trial and error, Machine Learning, 7, p45–83, 1991.
Feller, W. An Introduction to Probability Theory and Its Applications, Modern Asia Editions, 1960.
Richard S. Sutton, Temporal Credit Assignment in Reinforcement Learning, PhD thesis, University of Massachusetts, Amherst, Massachusetts, 1984.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Iwata, K., Ito, N., Yamauchi, K., Ishii, N. (2000). Combining Exploitation-Based and Exploration-Based Approach in Reinforcement Learning. In: Leung, K.S., Chan, LW., Meng, H. (eds) Intelligent Data Engineering and Automated Learning — IDEAL 2000. Data Mining, Financial Engineering, and Intelligent Agents. IDEAL 2000. Lecture Notes in Computer Science, vol 1983. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44491-2_47
Download citation
DOI: https://doi.org/10.1007/3-540-44491-2_47
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41450-6
Online ISBN: 978-3-540-44491-6
eBook Packages: Springer Book Archive