Gradient Based Method for Symmetric and Asymmetric Multiagent Reinforcement Learning

  • Ville Könönen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2690)


A gradient based method for both symmetric and asymmetric multiagent reinforcement learning is introduced in this paper. Symmetric multiagent reinforcement learning addresses the problem with agents involved in the learning task having equal information states. Respectively, in asymmetric multiagent reinforcement learning, the information states are not equal, i.e. some agents (leaders) try to encourage agents with less information (followers) to select actions that lead to improved overall utility value for the leaders. In both cases, there is a huge number of parameters to learn and we thus need to use some parametric function approximation methods to represent the value functions of the agents. The method proposed in this paper is based on the VAPS framework that is extended to utilize the theory of Markov games, i.e. a natural basis of multiagent reinforcement learning.


Nash Equilibrium Matrix Game Stackelberg Equilibrium Nash Equilibrium Point Asymmetric Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Baird, L., Moore, A.: Gradient descent for general reinforcement learning. In: Kearns, M., Solla, S., Cohn, D. (eds.) Advances in Neural Information Processing Systems, Cambridge, MA, USA, vol. 11. MIT Press, Cambridge (1999)Google Scholar
  2. 2.
    Cottle, R.W., Stone, R.E., Pang, J.-S.: The Linear Complementarity Problem. Academic Press, New York (1992)zbMATHGoogle Scholar
  3. 3.
    Filar, J.A., Vrieze, K.: Competitive Markov Decision Processes. Springer, New York (1997)zbMATHGoogle Scholar
  4. 4.
    Hu, J., Wellman, M.P.: Multiagent reinforcement learning: Theoretical framework and an algorithm. In: Proceedings of the Fifteenth International Conference on Machine Learning (ICML 1998), Madison, Wisconsin, USA. Morgan Kaufmann Publishers, San Francisco (July 1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Ville Könönen
    • 1
  1. 1.Neural Networks Research CentreHelsinki University of TechnologyFinland

Personalised recommendations