Abstract
The immune system is attracting attention as a new biological information processing-type paradigm. It is a large-scale system equipped with a complicated biological defense function. It has functions of memory and learning that use interactions such as stimulus and suppression between immune cells. In this article, we propose and construct a reinforcement learning method based on an immune network adapted to a semi-Markov decision process (SMDP). We show that the proposed method is capable of dealing with a problem which is modeled as a SMDP environment through computer simulation.
Similar content being viewed by others
References
Ishiguro A, Watanabe Y, Kondo T, et al (1997) Construction of a decentralized consensus-making network based on the immune system: application to an action arbitration for an autonomous mobile robot (in Japanese). Trans Soc Instrum Control Eng 33:524–532
Ishiguro A, Kondo T, Watanabe Y, et al (1997) An evolutionary construction of immune network-based behavior arbitration mechanism mobile robot (in Japanese). IEEJ Trans Electron Inf Syst 117-C:865–873
Diao Y, Passino KM (2002) Immunity-based hybrid learning methods for approximator structure and parameter adjustment. Eng Appl Artif Intell 15:587–600
Polat K, Günes S, Tosum S (2006) Diagnosis of heart disease using artificial immune recognition system and fuzzy weighted preprocessing. Patt Recog 39:2186–2193
Ishida Y, Fujita H, Mori K, et al (1998) Immunity-based systems and its applications: intelligent systems by artificial immune systems (in Japanese). Corona, Japan
Kimura H, Miyazaki K, Kobayashi S (1999) A guideline for designing reinforcement learning systems (in Japanese). J Soc Instrum Control Eng 38:618–623
Sutton RS, Barto AG (1998) Reinforcement learning: an introduction (adaptive computation and machine learning). MIT Press, Cambridge
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008
About this article
Cite this article
Kogawa, N., Obayashi, M., Kobayashi, K. et al. A reinforcement learning method based on an immune network adapted to a semi-Markov decision process. Artif Life Robotics 13, 538–542 (2009). https://doi.org/10.1007/s10015-008-0599-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-008-0599-0