Abstract
The policy gradient method is a popular technique for implementing reinforcement learning in an agent system. One of the reasons is that a policy gradient learner has a simple design and strong theoretical properties in single-agent domains. Previously, Williams showed that the REINFORCE algorithm is a special case of policy gradient learning. He also showed that a learning automaton could be seen as a special case of the REINFORCE algorithm. Learning automata theory guarantees that a group of automata will converge to a stable equilibrium in team games. In this paper we will show a theoretical connection between learning automata and policy gradient methods to transfer this theoretical result to multi-agent policy gradient learning. An appropriate exploration technique is crucial for the convergence of a multi-agent system. Since learning automata are guaranteed to converge, they posses such an exploration. We identify the identical mapping of a learning automaton onto the Boltzmann exploration strategy with an suitable temperature setting. The novel idea is that the temperature of the Boltzmann function is not dependent on time but on the action probabilities of the agents.
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
Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific (1996)
Sutton, R.S., McAllester, D., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems (NIPS 1999), Denver, CO, pp. 1057–1063 (2000)
Bowling, M., Veloso, M.M.: Multiagent learning using a variable learning rate. Artificial Intelligence 136(2), 454–460 (2002)
Peshkin, L., Kim, K.E., Meuleau, N., Kaelbling, L.P.: Learning to cooperate via policy-search. In: Proceedings of the Sixteenth Conference on Uncertainty in Artifical Intelligence (UAI 2000), Stanford, CA, pp. 489–496 (2000)
Könönen, V.: Gradient based method for symmetric and asymmetric multiagent reinforcement learning. Web Intelligence and Agent Systems: An International Journal (WIAS) 3(1), 17–30 (2005)
Könönen, V.: Multiagent Reinforcement Learning in Markov Games: Asymmetric and Symmetric Approaches. PhD thesis, Helsinki University of Technology, Helsinki, Finland (2004)
Tsetlin, M.L.: Automata Theory and Modeling of Biological Systems. Academic Press, New York (1973)
Thathachar, M.A.L., Sastry, P.S.: Networks of Learning Automata: Techniques for Online Stochastic Optimization. Kluwer Academic Publishers, Dordrecht (2004)
Narendra, K.S., Thathachar, M.A.L.: Learning Automata: An Introduction. Prentice Hall, Englewood Cliffs (1989)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning 8(3–4) (1992)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Filar, J.A., Vrieze, K.: Competitive Markov Decision Processes. Springer, Heidelberg (1997)
Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference of Artificial Intelligence (AAAI 1998), Madison, WI, pp. 746–752 (1998)
Bowker, A.H.: Bowker’s test for symmetry. Journal of the American Statistical Association 43, 75–83 (1984)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Peeters, M., Könönen, V., Verbeeck, K., Nowé, A. (2008). A Learning Automata Approach to Multi-agent Policy Gradient Learning. In: Lovrek, I., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2008. Lecture Notes in Computer Science(), vol 5178. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85565-1_48
Download citation
DOI: https://doi.org/10.1007/978-3-540-85565-1_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85564-4
Online ISBN: 978-3-540-85565-1
eBook Packages: Computer ScienceComputer Science (R0)