Abstract
Recently much attention has been paid to intelligent systems which can adapt themselves to dynamic and/or unknown environments by the use of learning methods. However, traditional learning methods have a disadvantage that learning requires enormously long amounts of time with the degree of complexity of systems and environments to be considered. We thus propose a novel reinforcement learning method based on adaptive immunity. Our proposed method can provide a near-optimal solution with less learning time by self-learning using the concept of adaptive immunity. The validity of our method is demonstrated through some simulations with Sutton’s maze problem.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Sutton RS, Barto AG (1988) Reinforcement Learning. MIT, MA, USA
Grefenstette JJ (1988) Credit assignment in rule discovery systems based on genetic algorithms. Machine Learning 3(2–3):225–245
Miyazaki K, Yamamura M, Kobayashi S (1994) On the rationality of profit sharing in reinforcement learning. In: Proceedings of 3rd International Conference on Fuzzy Logic, Neural Nets and Soft Computing, pp 285–288
de Castro LN, Timmis J (2002) Artificial immune systems: a new computational intelligence approach. Springer, London, UK
Farmer JD, Packard NH, Perelson AS (1986) The immune system, adaptation, and machine learning. Physica 22D:187–204
Jerne NK (1984) Idiotypic networks and other preconceived ideas. Immunological Reviews 79:5–24
Luh GC, Liu WW (2004) Reactive immune network based mobile robot navigation. In: 3rd International Conference on Artificial Immune Systems, pp 119–132
Ito J, Sakurama K, Nakano K (2005) A soccer robot control design based on the immune system. In: The 10th International Symposium on Artificial Life and Robotics, GS23-4
Watkins CJCH (1992) Q-learning. Machine Learning 8:279–292
Uemura W, Ueno A, Tatsumi S (2006) A profit sharing method for forgetting past experiences effectively (in Japanese). Trans Japanese Soci Artifi Intelligence 21(1):81–93
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was present 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
Ito, J., Nakano, K., Sakurama, K. et al. Adaptive immunity based reinforcement learning. Artif Life Robotics 13, 188–193 (2008). https://doi.org/10.1007/s10015-008-0579-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-008-0579-4