Abstract
Creating coordinated multiagent policies in an environment with uncertainties is a challenging issue in the research of multiagent learning. In this paper, a coordinated learning approach is proposed to enable agents to learn both individual policies and coordinated behaviors by exploiting independent relationships inherent in many multiagent systems. We illustrate how this approach is employed to solve coordination problems in robot navigation domains. Experimental results of different scales of domains prove the effectiveness of our learning approach.
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.
Similar content being viewed by others
References
Melo, F.S., Veloso, M.: Decentralized MDPs with sparse interactions. Artif. Intel. 175, 1757–1789 (2011)
Yu, C., Zhang, M., Ren, F.: Coordinated Learning for Loosely Coupled Agents with Sparse Interactions. In: Wang, D., Reynolds, M. (eds.) AI 2011. LNCS, vol. 7106, pp. 392–401. Springer, Heidelberg (2011)
De Hauwere, Y.M., Vrancx, P., Nowé, A.: Learning multi-agent state space representations. In: AAMAS 2010, pp. 715–722. IFAAMAS, Richland (2010)
Allen, M., Zilberstein, S.: Complexity of decentralized control: Special cases. In: Adv. Neural Inform. Proc. Systems, vol. 22, pp. 19–27 (2009)
Spaan, M., Melo, F.S.: Interaction-driven Markov games for decentralized multiagent planning under uncertainty. In: AAMAS 2008, pp. 525–532. IFAAMAS, Richland (2008)
Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. C. Appl. Re. 38(2), 156–172 (2008)
Roth, M., Simmons, R., Veloso, M.: Exploiting factored representations for decentralized execution in multiagent teams. In: AAMAS 2007, pp. 469–475. ACM Press, New York (2007)
Ghavamzadeh, M., Mahadevan, S., Makar, R.: Hierarchical multi-agent reinforcement learning. In: AAMAS, vol. 13(2), pp. 197–229. Springer, Heidelberg (2006)
Kok, J.R., Hoen, P., Bakker, B., Vlassis, N.: Utile coordination: Learning interdependencies among cooperative agents. In: CIG 2005, pp. 29–36. IEEE Press, New York (2005)
Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of Markov decision processes. Math. Oper. Re. 27(4), 819–840 (2002)
Guestrin, C., Lagoudakis, M., Parr, R.: Coordinated reinforcement learning. In: ICML, pp. 227–234 (2002)
Boutilier, C.: Planning, learning and coordination in multiagent decision processes. In: TARK, pp. 195–210 (1996)
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, C., Zhang, M., Ren, F. (2012). Exploiting Independent Relationships in Multiagent Systems for Coordinated Learning. In: Anthony, P., Ishizuka, M., Lukose, D. (eds) PRICAI 2012: Trends in Artificial Intelligence. PRICAI 2012. Lecture Notes in Computer Science(), vol 7458. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32695-0_60
Download citation
DOI: https://doi.org/10.1007/978-3-642-32695-0_60
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32694-3
Online ISBN: 978-3-642-32695-0
eBook Packages: Computer ScienceComputer Science (R0)