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

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.

References

  1. Sutton R, Barto A, 1998. Reinforcement learning: an introduction. Bradford Book. The MIT Press, Cambridge.
  2. J.Moren, C.Balkenius, 2001. A Computational Model of Emotional Learning in the Amygdala. Cybernetics and Systems 32(6), pp.611-636 .
  3. H. Rouhani, A. Sadeghzadeh, C. Lucas, B. N. Araabi, 2007. Emotional learning based intelligent speed and position control applied to neurofazzy model of switched reluctance motor. Control and Cybernetics, Vol.36, No.1, pp.75-95.
  4. H.Rouhani, M.Jalili, B.N.Araabi, W.Eppler and C.Lucas, 2007. Brain Emotional Learning Based Intelligent Controller Applied to Neurofuzzy Model of Micro Heat Exchanger. Expert Systems with Applications, Vol.32, No.3, pp.911-918.
  5. Nils Goerke, 2006. EMOBOT:A Robot control architecture based on emotional-like internal values. Mobile Robotics, Moving Intelligence, J. Buchli ed., Chp. 4, intechopen.com.
  6. E. Daglari, H. Temeltas, M. Yesiloglu, 2009. Behavioral task processing for cognitive robots using artificial emotions. Neurocomputing, 72, pp.2835-2844..
  7. Obayashi, M.,Takuno, T, Kuremoto, T., and Kobayashi, K, 2012. An Emotional Model Embedded Reinforcement Learning System. Proceedings of the IEEE International Conference on System, Man, and Cybernetics (IEEE SMC 2012), pp. 1058-1063.
  8. Fuping Yang, Xuewen Zhen, 2014. Research on the Agent's Behavior Decision-making Based on Artificial Emotion. Journal of Information & computational science, vol.11, No.8, pp.2723-2733.
  9. Xue Hu, Ln Xie, Xin Lin, Zhiliang Wang, 2013. Emotion Expression of Robot with Personality. Mathematical Problems in Engineering.
  10. Kuremoto, T., Ohta, T., Kobayashi, K., and Obayashi, M., 2009. A Dynamic Associative Memory System Adopting Amygdala Model. Artificial Life and Robotics, Vol.13, No.2, pp.478-482.
  11. Rusell, James A, 1980. A circumplex model of affect. Journal of Personality and Social Psychology, Vol.39(6), pp.1161-1178.
Download


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