ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Improved sleeping bandits with stochastic actions sets and adversarial rewards

Saha, A and Gaillard, P and Valko, M (2020) Improved sleeping bandits with stochastic actions sets and adversarial rewards. In: 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, pp. 8327-8335.

Full text not available from this repository.


In this paper, we consider the problem of sleeping bandits with stochastic action sets and adversarial rewards. In this setting, in contrast to most work in bandits, the actions may not be available at all times. For instance, some products might be out of stock in item recommendation. The best existing efficient (i.e., polynomial-time) algorithms for this problem only guarantee an O(T2=3) upperbound on the regret. Yet, inefficient algorithms based on EXP4 can achieve O( p T). In this paper, we provide a new computationally efficient algorithm inspired by EXP3 satisfying a regret of order O( p T) when the availabilities of each action i 2 A are independent. We then study the most general version of the problem where at each round available sets are generated from some unknown arbitrary distribution (i.e., without the independence assumption) and propose an efficient algorithm with O( p 2KT) regret guarantee. Our theoretical results are corroborated with experimental evaluations. Copyright © 2020 by the Authors. All rights reserved.

Item Type: Conference Paper
Publication: 37th International Conference on Machine Learning, ICML 2020
Publisher: International Machine Learning Society (IMLS)
Additional Information: The copyright for this article belongs to International Machine Learning Society (IMLS)
Keywords: Machine learning; Polynomial approximation, Action sets; Arbitrary distribution; Computationally efficient; Experimental evaluation; General version; Independence assumption; Out of stock; Polynomial-time, Stochastic systems
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Date Deposited: 04 Aug 2021 06:24
Last Modified: 04 Aug 2021 06:24
URI: http://eprints.iisc.ac.in/id/eprint/68989

Actions (login required)

View Item View Item