Associative Reinforcement Learning - A Proposal to Build Truly Adaptive Agents and Multi-agent Systems

Eduardo Alonso, Esther Mondragón

Abstract

In this position paper we propose to enhance learning algorithms, reinforcement learning in particular, for agents and for multi-agent systems, with the introduction of concepts and mechanisms borrowed from associative learning theory. It is argued that existing algorithms are limited in that they adopt a very restricted view of what “learning” is, partly due to the constraints imposed by the Markov assumption upon which they are built. Interestingly, psychological theories of associative learning account for a wide range of social behaviours, making it an ideal framework to model learning in single agent scenarios as well as in multi-agent domains.

References

  1. Alonso, E., (2002). AI and Agents: State of the Art. AI Magazine, 23, 25-29.
  2. Bowling, M. and Veloso, M., (2001), Rational and convergent learning in stochastic games. In Proceedings of the Seventeenth International Joint Conference on Artificial Inelligence (IJCAI-2001), pages 1021-1026, Seattle, WA.
  3. Claus, C. and Boutilier, C., (1998), The dynamics of reinforcement learning in cooperative multiagent systems. In Proceedings of the Fifteenth National Conference on Artificial Intelligence, pages 746-752.
  4. Greenwald, A., Hall, K., and Serrano, R., (2002), Correlated-Q learning. In NIPS Workshop on Multiagent Learning.
  5. Griffin, A. S., (2004), Social learning about predators: A review and prospectus. Learning & Behavior 32(1), 131-140.
  6. Hu, J. and Wellman, M., (2001), Learning about other agents in a dynamic multiagent system. Journal of Cognitive Systems Research, 2:67-79.
  7. Littman, M. L., (2001), Friend-or-foe Q-learning in general-sum games. In Proceedings of the Eighteen International Conference on Machine Learning.
  8. Littman, M. L., (1994), Markov games as a framework for multi-agent reinforcement learning. In Proceedings of the 11th International Conference on Machine Learning, 157-163.
  9. Mataric, M., (1994), Learning to behave socially. In Proceedings of the Third International Conference on Simulation and Adaptive Behavior.
  10. Sen , S., Sekaran, M., and Hale, J., (1994), Learning to coordinate without sharing information. In Proceedings of the Twelfth National Conference on Artificial Intelligence, 426-431, Seattle, WA.
  11. Shoham, Y., Powers, R., and Grenager, T., (2003), MultiAgent Reinforcement Learning: a critical survey. Technical Report.
  12. Stone, P. and Veloso, M., (2000), Multiagent Systems: A Survey from a Machine Learning Perspective, Autonomous Robots, Volume 8( 3), 345-383.
  13. Suematsu, N. and Hayashi, A., (2002), A multiagent reinforcement learning algorithm using extended optimal response. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence (IJCAI-97), 370-377.
  14. Sutton, R. S. and Barto, A. G., (1998), Reinforcement Learning: An Introduction, Cambridge, MA: The MIT Press.
  15. Wang, X. and Sandholm, T., (2002), Reinforcement learning to play an optimal Nash equilibrium in team Markov games. In Advances in Neural Information Processing Systems (NIPS-2002).
Download


Paper Citation


in Harvard Style

Alonso E. and Mondragón E. (2013). Associative Reinforcement Learning - A Proposal to Build Truly Adaptive Agents and Multi-agent Systems . In Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-8565-38-9, pages 141-146. DOI: 10.5220/0004175601410146


in Bibtex Style

@conference{icaart13,
author={Eduardo Alonso and Esther Mondragón},
title={Associative Reinforcement Learning - A Proposal to Build Truly Adaptive Agents and Multi-agent Systems},
booktitle={Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2013},
pages={141-146},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004175601410146},
isbn={978-989-8565-38-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Associative Reinforcement Learning - A Proposal to Build Truly Adaptive Agents and Multi-agent Systems
SN - 978-989-8565-38-9
AU - Alonso E.
AU - Mondragón E.
PY - 2013
SP - 141
EP - 146
DO - 10.5220/0004175601410146