Abstract
Under complex, dynamic and uncertain environment, tasks in multi-agent system need to be distributed to agents dynamically and agents need to cooperate to complete tasks assigned dynamically. This paper proposes a dynamic task allocation model based on game theory and dynamic coordination in task execution based on coordination graph at each time step. The synthesized model is solved by reinforcement learning. The detailed algorithm is illustrated with an example and experimental results show that the method is an effective solution for dynamic task allocation and execution coordination under uncertain environment.
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
Gerkey, B.P., Matar, M.J.: A framework for studying multi-robot task allocation. In: Proceedings of the Multi-Robot Systems, Washington, USA, pp. 15–26 (2003)
Gerkey, B.P., Mataric, M.J.: A formal analysis and taxonomy of task allocation in multi-robot systems. International Journal of Robotics Research 23(9), 939–954 (2004)
Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proc. 15th Nation. Conf. on Articial Intelligence, Madison, WI
Jelle, R.K., Nikos, V.: Collaborative Multiagent Reinforcement Learning by Payoff Propagation. Journal of Machine Learning Research 7, 1789–1828 (2006)
Jelle, R.K., Nikos, V.: Sparse Cooperative Q-learning. In: Proceedings of the 21st International Conference on Machine Learning, Ban, Canada (2004)
Reinoud, E.: Anytime algorithms for multi-agent decision making, June 4 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, C., Zeng, W., Zhou, H., Cao, L., Yang, Y. (2011). Dynamic Task Allocation and Action Coordination under Uncertain Environment. In: Wang, Y., Li, T. (eds) Foundations of Intelligent Systems. Advances in Intelligent and Soft Computing, vol 122. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25664-6_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-25664-6_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25663-9
Online ISBN: 978-3-642-25664-6
eBook Packages: EngineeringEngineering (R0)