An Extended Q Learning System with Emotion State to Make Up an Agent with Individuality

Masanao Obayashi, Shunsuke Uto, Takashi Kuremoto, Shingo Mabu, Kunikazu Kobayashi

2015

Abstract

Recently, researches for the intelligent robots incorporating knowledge of neuroscience have been actively carried out. In particular, a lot of researchers making use of reinforcement learning have been seen, especially, "Reinforcement learning methods with emotions", that has already proposed so far, is very attractive method because it made us possible to achieve the complicated object, which could not be achieved by the conventional reinforcement learning method, taking into account of emotions. In this paper, we propose an extended reinforcement (Q) learning system with amygdala (emotion) models to make up individual emotions for each agent. In addition, through computer simulations that the proposed method is applied to the goal search problem including a variety of distinctive solutions, it finds that each agent is able to have each individual solution.

Paper Citation

in Harvard Style

Obayashi M., Uto S., Kuremoto T., Mabu S. and Kobayashi K. (2015). An Extended Q Learning System with Emotion State to Make Up an Agent with Individuality . In Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015) ISBN 978-989-758-157-1, pages 70-78. DOI: 10.5220/0005616500700078

in Bibtex Style

@conference{ncta15,
author={Masanao Obayashi and Shunsuke Uto and Takashi Kuremoto and Shingo Mabu and Kunikazu Kobayashi},
title={An Extended Q Learning System with Emotion State to Make Up an Agent with Individuality},
booktitle={Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015)},
year={2015},
pages={70-78},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005616500700078},
isbn={978-989-758-157-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 3: NCTA, (ECTA 2015)
TI - An Extended Q Learning System with Emotion State to Make Up an Agent with Individuality
SN - 978-989-758-157-1
AU - Obayashi M.
AU - Uto S.
AU - Kuremoto T.
AU - Mabu S.
AU - Kobayashi K.
PY - 2015
SP - 70
EP - 78
DO - 10.5220/0005616500700078