2021-07-01-atsidakou21a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Combinatorial Blocking Bandits with Stochastic Delays	Recent work has considered natural variations of the {\em multi-armed bandit} problem, where the reward distribution of each arm is a special function of the time passed since its last pulling. In this direction, a simple (yet widely applicable) model is that of {\em blocking bandits}, where an arm becomes unavailable for a deterministic number of rounds after each play. In this work, we extend the above model in two directions: (i) We consider the general combinatorial setting where more than one arms can be played at each round, subject to feasibility constraints. (ii) We allow the blocking time of each arm to be stochastic. We first study the computational/unconditional hardness of the above setting and identify the necessary conditions for the problem to become tractable (even in an approximate sense). Based on these conditions, we provide a tight analysis of the approximation guarantee of a natural greedy heuristic that always plays the maximum expected reward feasible subset among the available (non-blocked) arms. When the arms’ expected rewards are unknown, we adapt the above heuristic into a bandit algorithm, based on UCB, for which we provide sublinear (approximate) regret guarantees, matching the theoretical lower bounds in the limiting case of absence of delays.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	atsidakou21a	0	Combinatorial Blocking Bandits with Stochastic Delays	404	413	404-413	404	false	Atsidakou, Alexia and Papadigenopoulos, Orestis and Basu, Soumya and Caramanis, Constantine and Shakkottai, Sanjay	given family Alexia Atsidakou given family Orestis Papadigenopoulos given family Soumya Basu given family Constantine Caramanis given family Sanjay Shakkottai	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/atsidakou21a/atsidakou21a.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/atsidakou21a/atsidakou21a-supp.pdf