Abstract
It is possible to exploit automated learning from sensed data for practical applications - in essence facilitating reasoning about particular problem domains based on a combination of environmental awareness and insights elicited from past decisions. We explore some enhanced Reinforcement Learning (RL) methods used for achieving such machine learning using software agents in order to address two questions. Can RL implementations/methods be accelerated by using a Multi-Agent approach? Can an agent learn composite skills in single-pass?
This is a preview of subscription content, log in via an institution to check access.
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
Puterman,M.L., Markov Decision Processes: Discrete Stochastic Dynamic Programming. 2005: Wiley-Interscience
Sutton,R. & Barto,A., Reinforcement Learning: An Introduction. 1998: MIT Press
Watkins,C. & Dayan,P., Q-Learning. Machine Learning, 8(3-4):279–292, 1992, 1992
Bell, Luo & McCollum, Skill Combination in Reinforcement Learning, 2008
Tesauro,G. Temporal Difference Learning & TD-Gammon, 1995
Agogino,A. & Tumer,K, Quicker Q-Learning in Multi-Agent Systems, 2008
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag London
About this paper
Cite this paper
Graham, C., Bell, D., Luo, Z. (2010). Multi-Agent Reinforcement Learning – An Exploration Using Q-Learning. In: Bramer, M., Ellis, R., Petridis, M. (eds) Research and Development in Intelligent Systems XXVI. Springer, London. https://doi.org/10.1007/978-1-84882-983-1_21
Download citation
DOI: https://doi.org/10.1007/978-1-84882-983-1_21
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-84882-982-4
Online ISBN: 978-1-84882-983-1
eBook Packages: Computer ScienceComputer Science (R0)