Abstract
In this paper, Expected Success Probability (ESP) is defined and a reinforcement learning method Stable Profit Sharing with Expected Failure Probability (SPSwithEFP) is proposed. In SPSwithEFP, Expected Failure Probability (EFP) is used in the roulette wheel selection method and ESP is used in the update equation of the weight of a rule. EFP can discard risky actions and ESP can make the distribution of learned results smaller. The effectiveness is shown with simulation experiments for a maze environment with pitfalls.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Miyazaki, K., Yamamura, M., Kobayashi, S.: On the rationality of profit sharing in reinforcement learning. In: Proceedings of the 3rd International Conference on Fuzzy Logic, Neural Nets and Soft Computing, pp. 285–288 (1994)
Miyazaki, K., Kobayashi, S.: Exploitation-oriented learning PS-r#. J. Adv. Comput. Intell. Intell. Inf. 13(6), 624–630 (2009)
Miyazaki, K., Muraoka, H., Kobayashi, H.: Proposal of a propagation algorithm of the expected failure probability and the effectiveness on multi-agent environments. In: SICE Annual Conference 2013, pp. 1067–1072 (2013)
Miyazaki, K., Furukawa, K., Kobayashi, H.: Proposal of PSwithEFP and its evaluation in multi-agent reinforcement learning. J. Adv. Comput. Intell. Intell. Inf. 21(5), 930–938 (2017)
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. In: NIPS Deep Learning Workshop 2013 (2013)
Stone, P., Sutton, R.S., Kuhlamann, G.: Reinforcement learning toward RoboCup soccer keepaway. Adapt. Behav. 13(3), 165–188 (2005)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book. MIT Press, Cambridge (1998)
Acknowledgements
This work was supported by JSPS KAKENHI Grant Number 17K00327.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Mizuno, D., Miyazaki, K., Kobayashi, H. (2019). On Stable Profit Sharing Reinforcement Learning with Expected Failure Probability. In: Samsonovich, A. (eds) Biologically Inspired Cognitive Architectures 2018. BICA 2018. Advances in Intelligent Systems and Computing, vol 848. Springer, Cham. https://doi.org/10.1007/978-3-319-99316-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-319-99316-4_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-99315-7
Online ISBN: 978-3-319-99316-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)