Abstract
Profit Sharing is well known as a kind of reinforcement learning. In PS method, a reward is generally distributed with a geometrically decreasing function, and the common ratio of the function is called a discount rate. A large discount rate increases the learning speed, but a non-optimal policy may be learned. On the other hand, a small discount rate improves the performance of the policy, but the learning may not proceed smoothly due to the shallow learning depth. In this paper, in order to cope with these problems, we propose a method that reinforces detour paths and a non-detour path with different discount rates, respectively. Finally, this method is applied to an altruistic multi-agent environment to confirm its effectiveness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chrisman, L.: Reinforcement learning with perceptual aliasing: the perceptual distinctions approach. In: Proceedings of the 10th National Conference on Artificial Intelligence, pp. 183–188 (1992)
Miyazaki, K.: A study of an indirect reward on multi-agent environments. Procedia Comput. Sci. 88, 94–101 (2016)
Miyazaki, K., Yamamura, M., Kobayashi, S.: A theory of profit sharing in reinforcement learning. Trans. Jpn. Soc. Artif. Intell. 9(4), 580–587 (1994). (in Japanese)
Uemura, W., Tatsumi, S.: About the reinforcement function for profit sharing. Trans. Jpn. Soc. Artif. Intell. 19(4), 197–203 (2004). (in Japanese)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Shiraishi, D., Miyazaki, K., Kobayashi, H. (2018). Proposal of Detour Path Suppression Method in PS Reinforcement Learning and Its Application to Altruistic Multi-agent Environment. In: Miller, T., Oren, N., Sakurai, Y., Noda, I., Savarimuthu, B.T.R., Cao Son, T. (eds) PRIMA 2018: Principles and Practice of Multi-Agent Systems. PRIMA 2018. Lecture Notes in Computer Science(), vol 11224. Springer, Cham. https://doi.org/10.1007/978-3-030-03098-8_51
Download citation
DOI: https://doi.org/10.1007/978-3-030-03098-8_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03097-1
Online ISBN: 978-3-030-03098-8
eBook Packages: Computer ScienceComputer Science (R0)