LEARNING BY OBSERVATION IN SOFTWARE AGENTS

Paulo Costa, Luis Botelho

2012

Abstract

In a society of similar agents, all of them using the same kind of knowledge representation, learning with others could be achieved through direct transfer of knowledge from experts to apprentices. However, not all agents use the same kind of representation methods, hence learning by direct communication of knowledge is not always possible. In such cases, learning by observation might be of key importance. This paper presents an agent architecture that provides software agents with learning by observation capabilities similar to those observed in superior mammals. The main contribution of our proposal is to let software agents learn by direct observation of the actions being performed by expert agents. This is possible because, using the proposed architecture, agents may see one another.

Paper Citation

in Harvard Style

Costa P. and Botelho L. (2012). LEARNING BY OBSERVATION IN SOFTWARE AGENTS . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-8425-96-6, pages 276-281. DOI: 10.5220/0003834502760281

in Bibtex Style

@conference{icaart12,
author={Paulo Costa and Luis Botelho},
title={LEARNING BY OBSERVATION IN SOFTWARE AGENTS},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2012},
pages={276-281},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003834502760281},
isbn={978-989-8425-96-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - LEARNING BY OBSERVATION IN SOFTWARE AGENTS
SN - 978-989-8425-96-6
AU - Costa P.
AU - Botelho L.
PY - 2012
SP - 276
EP - 281
DO - 10.5220/0003834502760281