Abstract
Reinforcement Learning, also sometimes called learning by rewards and punishments is the problem faced by an agent that must learn behavior through trial-and-error interactions with a dynamic environment [1]. With repeated trials however, it is expected that the agent learns to perfect its behavior overtime. In this paper we simulate the reinforcement learning process of a mobile agent on a grid space and examine the situation in which multiple reinforcement learning agents can be used to speed up the learning process by sharing their Q-values. We propose a sharing method which takes into consideration the weight of the experience acquired by each agent on the occasion of visiting a state and taking an action.
Keywords
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
Wharton, A.: Simulation and Investigation of MARL for Building Evacuation Scenario (2009)
Csaba Szepesvari, K.: Reinforcement Learning: Dynamic Programming. In: MLSS 2008 (2008)
Poole, D., Mackworth, A.: Artificial Intelligence: Foundations of Computational Agents. Cambridge University Press, Cambridge (2010)
Cline, B.E.: Tuning Q-Learning Parameters with a Genetic Algorithm (2004)
Partalas, I., Feneris, I., Vlahavas, I.: Multi-Agent Reinforcement Learning using Strategies and Voting. ICTAI (2), 318–324 (2007)
Ahmadabadi, M.N., Asadpour, M., Nakano, E.: Cooperative Q-learning: the knowledge sharing issue (2001)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yu, L., Abdulai, I. (2012). A Multi-agent Reinforcement Learning with Weighted Experience Sharing. In: Huang, DS., Gan, Y., Gupta, P., Gromiha, M.M. (eds) Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence. ICIC 2011. Lecture Notes in Computer Science(), vol 6839. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25944-9_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-25944-9_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25943-2
Online ISBN: 978-3-642-25944-9
eBook Packages: Computer ScienceComputer Science (R0)