Dealing with Errors in a Cooperative Multi-agent Learning System

  • Constança Oliveira e Sousa
  • Luis Custódio
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3898)


This paper presents some methods of dealing with the problem of cooperative learning in a multi-agent system, in error prone environments. A system is developed that learns by reinforcement and is robust to errors that can come from the agents’ sensors, from another agent that shares wrong information or even from the communication channel.


Optimal Policy Reinforcement Learn Position Error Multiagent System Goal State 
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.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning, An Introduction. MIT Press, UK (1998)Google Scholar
  2. 2.
    Russel, S.J., Norvig, P.: Artificial Intelligence, A Modern Approach. Prentice Hall, New Jersey (2003)Google Scholar
  3. 3.
    Vlassis, N.: Multiagent Systems and Distributed AI. In: Intelligent Autonomous Systems. Informatics Institute, University of Amsterdam (2003)Google Scholar
  4. 4.
    Sousa, C., Custdio, L.: Cooperative Reinforcement Learning: exploring Communication and Cooperation Problems. In: Proceedings of the 6th IEEE International Symposium on Computational Intelligence in Robotics and Automation (2005)Google Scholar
  5. 5.
    Dietterich, T.G.: The MAXQ Method for Hierarquical Reinforcement Learning. In: International Conference on Machine Learning (1998)Google Scholar
  6. 6.
    Parr, R., Russel, S.: Reinforcement Learning with Hierarchies of Machines, Computer Science Division, UC Berkeley, CA (1998)Google Scholar
  7. 7.
    Makar, R., Mahadevan, S., Ghavamzadeh, M.: Hierarquical Multi-Agent RL, Department of Computer Science. Michigan State University (2001)Google Scholar
  8. 8.
    Arai, S., Sycara, K.: Credit Assignment Method for Learning Effective Stochastic Policies in Uncertain Domains. In: Proceedings of Genetic and Evolutionary Computation Conference (2001)Google Scholar
  9. 9.
    Arai, S., Sycara, K., Payne, T.: Experience-based RL to Acquire Effective Behaviour in a Multi-agent Domain. In: Proc. of the 6th Pacific Rim Int. Conference on Artificial Intelligence, Lecture Notes in AI 1886, pp. 125–135. Springer, Heidelberg (2000)Google Scholar
  10. 10.
    Arai, S., Sycara, K.: Effective Learning Approach for Planning and Scheduling n Multi-agent Domain. In: Proceedings oh the 6th ISAB - From animals to animats, pp. 507–516 (2000)Google Scholar
  11. 11.
    Arai, S., Sycara, K.: Multi-agent RL for Planning and Conflict Resolution in a ynamic Domain. Carnegie Mellon University (2000)Google Scholar
  12. 12.
    Arai, S., Sycara, K., Payne, T.: Multi-agent Reinforcement Learning for Planning nd Scheduling Multiple Goals. In: Proceedings of Fourth International Conference n Multi-Agent Systems (2000)Google Scholar
  13. 13.
    Wahab, M.: Reinforcement Learning in Multi-Agent Systems. McGill Univ. School f Computer ScienceGoogle Scholar
  14. 14.
    Ghavamzadeh, M., Mahadevan, S.: Learning to Communicate and Act in Cooperative ultiagent Systems using Hierarchical Reinforcement Learning. In: Third nternational Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004, vol. 3, pp. 1114–1121 (2004)Google Scholar
  15. 15.
    Tan, M.: Multi-Agent RL: Independent vs. Cooperative Agents. In: Proceedings of he Tenth International Conference on Machine Learning, pp. 330–337 (1993)Google Scholar
  16. 16.
    Bowling, M., Veloso, M.: An Analysis of Stochastic Game Theory for Multiagent einforcement Learning, CMU-CS-00-165 (2000)Google Scholar
  17. 17.
    Bowling, M.: Multiagent Learning in the Presence of Agents with Limitations, PhD. Thesis, Carnegie Mellon University, Pittsburg (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Constança Oliveira e Sousa
    • 1
  • Luis Custódio
    • 1
  1. 1.Institute for Systems and Robotics, Instituto Superior TécnicoLisboaPortugal

Personalised recommendations