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

Eduardo Alonso, Esther Mondragón

2013

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.

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