Abstract
In comparison to single agent learning, reinforcement learning in a multiagent scenario is more challenging, since there is an increase in the space of combination of actions that may have to be explored before agents learn an efficient policy. Among other approaches, there has been a proposition to address this problem by means of biasing the exploration. We follow this track using an organizational structure where low-level agents mainly use reinforcement learning, while also getting recommendations from agents possessing a broader view. These agents keep a base of cases in order to give such recommendations, orchestrating the process. We show that this approach is able to accelerate and improve learning in penalty games, a especial case of coordination games.
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
Bazzan, A.L.C.: Coordinating many agents in stochastic games. In: Proc. of the IEEE IJCNN 2012 (June 2012)
Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, pp. 746–752 (1998)
Guestrin, C., Lagoudakis, M.G., Parr, R.: Coordinated reinforcement learning. In: Proceedings of the Nineteenth International Conference on Machine Learning (ICML), pp. 227–234. Morgan Kaufmann, San Francisco (2002)
Hines, G., Larson, K.: Learning when to take advice: A statistical test for achieving a correlated equilibrium. In: McAllester, D.A., Myllymäki, P. (eds.) UAI, pp. 274–281. AUAI Press (2008)
Hu, J., Wellman, M.P.: Multiagent reinforcement learning: Theoretical framework and an algorithm. In: Proc. 15th International Conf. on Machine Learning, pp. 242–250. Morgan Kaufmann (1998)
Kapetanakis, S., Kudenko, D.: Reinforcement learning of coordination in cooperative multi-agent systems. In: AAAI/IAAI, pp. 326–331 (2002)
Kuminov, D., Tennenholtz, M.: As safe as it gets: Near-optimal learning in multi-stage games with imperfect monitoring. In: Proceeding of the ECAI 2008, pp. 438–442. IOS Press, Amsterdam (2008)
Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: Proc. 17th International Conference on Machine Learning, pp. 535–542. Morgan Kaufmann, San Francisco (2000)
Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the 11th International Conference on Machine Learning, ML, pp. 157–163. Morgan Kaufmann, New Brunswick (1994)
Wang, X., Sandholm, T.: Reinforcement learning to play an optimal nash equilibrium in team markov games. In: Advances in Neural Information Processing Systems 15, NIPS 2002 (2002)
Zhang, C., Abdallah, S., Lesser, V.: Integrating organizational control into multi-agent learning. In: Sichman, J.S., Decker, K.S., Sierra, C., Castelfranchi, C. (eds.) Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Budapest, Hungary (2009)
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
Bazzan, A.L.C. (2012). Orchestrating Multiagent Learning of Penalty Games. In: Barros, L.N., Finger, M., Pozo, A.T., Gimenénez-Lugo, G.A., Castilho, M. (eds) Advances in Artificial Intelligence - SBIA 2012. SBIA 2012. Lecture Notes in Computer Science(), vol 7589. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34459-6_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-34459-6_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34458-9
Online ISBN: 978-3-642-34459-6
eBook Packages: Computer ScienceComputer Science (R0)