GENERAL MODEL FOR ORGANIZING INTERACTIONS IN MULTI-AGENT SYSTEMS

Authors

  • Anton Kabysh
  • Vladimir Golovko

DOI:

https://doi.org/10.47839/ijc.11.3.566

Keywords:

Multi-agent system, reinforcement learning, Q-Learning, coordination graph, influences learning.

Abstract

In this article we describe a model for finding optimal for learning the behavior of a group of agents in a collaborative multiagent setting. This model contains a set of scalable techniques that organize behavior of a multi- agent system. As a basis we use the framework of coordination graphs which exploits the dependencies between agents to decompose the global payoff function into a sum of local terms. To estimate a quality of interactions between agents we are using the concepts of the influence value learning paradigm. In last section we present the implementation of the considered model via reinforcement learning and experimental results of the use of this paradigm.

References

L. Panait and S. Luke, Cooperative multi-agent learning: the state of the art, Autonomous Agents and Multi-Agent Systems, (11) 3 (2005), pp. 387-434.

T. Gabel, Multi-Agent Reinforcement Learning Approaches for Distributed Job-Shop Scheduling Problems. PhD Thesis, University of Osnabrueck, 2009, 175 p.

E. Lee, S. Neuendorffer, M.J. Wirthlin, Actor-oriented design of embedded hardware and software systems, Journal of Circuits, Systems and Computers, 12 (2003), pp 231-260.

N. Monekosso, P. Remagnino, The analysis and performance evaluation of the pheromone-Q-learning algorithm, Expert Systems, (21) 2 (2004), pp. 80-91.

B. Dennis, Luiz M. G. Goncalves, Influence Value Q-Learning: A Reinforcement Learning Algorithm for Multi Agent Systems, in: Meng Joo Er and Yi Zhou (Eds.), Theory and Novel Applications of Machine Learning, Book, I-Tech, Vienna, Austria, 2009, pp. 376.

J. R. Kok, N. Vlassis, Sparse cooperative q-learning, In Proceedings of the XXI international conference on Machine Learning. Banff, Alberta, Canada, (2004), pp. 61.

C. Guestrin, D. Koller, R. Parr, Multiagent planning with factored MDPs, In Advances in Neural Information Processing Systems (NIPS) 14. The MIT Press, (2002), pp. 1523-1530.

J Kok, N Vlassis, Using the max-plus algorithm for multiagent decision making in coordination graphs, RoboCup 2005: Robot Soccer World Cup IX, 2006.

R. S. Sutton, A. G. Barto, Reinforcement Learning: an Introduction, MIT Press, 1998.

А. Kabysh, Graph Modeling Framework, BrSTU Robotics Wiki (www.robotics.bstu.by/mwiki), (2012), http://robotics.bstu.by/mwiki/index.php? title=Библиотека_моделирования_на_графах (in Russian).

V. A. Golovko, A. S. Kabysh, Collective behavior in multiagent systems based on reinforcement learning, Proceedings of the Tenth International Conference «Pattern recognition and image processing» (PRIP–2009), Minsk, Belarus, (19-21 May 2009), pp. 260-264.

A. Kabysh, V. Golovko, A. Lipnickas, Influence learning for multi-agent system based on reinforcement learning, International Journal of Computing, (11) 1 (2012) pp. 39-44.

Downloads

Published

2014-08-01

How to Cite

Kabysh, A., & Golovko, V. (2014). GENERAL MODEL FOR ORGANIZING INTERACTIONS IN MULTI-AGENT SYSTEMS. International Journal of Computing, 11(3), 224-233. https://doi.org/10.47839/ijc.11.3.566

Issue

Section

Articles