Abstract
We study the loss version of adversarial multi-armed bandit problems with one lossless arm. We show an adversary’s strategy that forces any player to suffer \(K-1-O(1/T)\) loss where K is the number of arms and T is the number of rounds.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: The nonstochastic multiarmed bandit problem. SIAM J. Comput. 32(1), 48–77 (2003)
Bubeck, S., Cesa-Bianchi, N.: Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Found. Trends Mach. Learn. 5(1), 1–122 (2012)
Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, Cambridge (2006)
Acknowledgment
We would like to thank anonymous reviewers for helpful comments. This work was partially supported by JSPS KAKENHI Grant Number 25280079.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Nakamura, A., Helmbold, D.P., Warmuth, M.K. (2016). Noise Free Multi-armed Bandit Game. In: Dediu, AH., Janoušek, J., Martín-Vide, C., Truthe, B. (eds) Language and Automata Theory and Applications. LATA 2016. Lecture Notes in Computer Science(), vol 9618. Springer, Cham. https://doi.org/10.1007/978-3-319-30000-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-319-30000-9_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-29999-0
Online ISBN: 978-3-319-30000-9
eBook Packages: Computer ScienceComputer Science (R0)