An Improved Q-Learning Algorithm Using Synthetic Pheromones

  • Ndedi Monekosso
  • Paolo Remagnino
  • Adam Szarowicz
Conference paper

DOI: 10.1007/3-540-45941-3_21

Part of the Lecture Notes in Computer Science book series (LNCS, volume 2296)
Cite this paper as:
Monekosso N., Remagnino P., Szarowicz A. (2002) An Improved Q-Learning Algorithm Using Synthetic Pheromones. In: Dunin-Keplicz B., Nawarecki E. (eds) From Theory to Practice in Multi-Agent Systems. CEEMAS 2001. Lecture Notes in Computer Science, vol 2296. Springer, Berlin, Heidelberg

Abstract

In this paper we propose an algorithm for multi-agent Q-learning. The algorithm is inspired by the natural behaviour of ants, which deposit pheromone in the environment to communicate. The benefit besides simulating ant behaviour in a colony is to design complex multi-agent systems. Complex behaviour can emerge from relatively simple interacting agents. The proposed Q-learning update equation includes a belief factor. The belief factor reflects the confidence the agent has in the pheromone detected in its environment. Agents communicate implicitly to co-ordinate and co-operate in learning to solve a problem.

Keywords

Machine Learning Multi-agents Pheromones Coordination Communication 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Ndedi Monekosso
    • 1
  • Paolo Remagnino
    • 1
  • Adam Szarowicz
    • 1
  1. 1.Digital Imaging Research CentreSchool of Computing and Information Systems Kingston UniversityUK

Personalised recommendations