Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Arms

TL;DR

This paper introduces a general framework for combinatorial multi-armed bandits with probabilistically triggered arms, providing algorithms with tight regret bounds and applying to complex nonlinear reward problems like social influence maximization.

Contribution

It extends CMAB models to include probabilistically triggered arms, develops a CUCB algorithm with optimal regret bounds, and demonstrates applications to nonlinear reward problems.

Findings

CUCB achieves O(log n) regret bounds.

Framework applies to nonlinear reward structures.

Improves regret bounds over previous combinatorial bandit models.

Abstract

We define a general framework for a large class of combinatorial multi-armed bandit (CMAB) problems, where subsets of base arms with unknown distributions form super arms. In each round, a super arm is played and the base arms contained in the super arm are played and their outcomes are observed. We further consider the extension in which more based arms could be probabilistically triggered based on the outcomes of already triggered arms. The reward of the super arm depends on the outcomes of all played arms, and it only needs to satisfy two mild assumptions, which allow a large class of nonlinear reward instances. We assume the availability of an offline (\alpha,\beta)-approximation oracle that takes the means of the outcome distributions of arms and outputs a super arm that with probability {\beta} generates an {\alpha} fraction of the optimal expected reward. The objective of an online learning algorithm for CMAB is to minimize (\alpha,\beta)-approximation regret, which is the difference between the \alpha{\beta} fraction of the expected reward when always playing the optimal super arm, and the expected reward of playing super arms according to the algorithm. We provide CUCB algorithm that achieves O(log n) distribution-dependent regret, where n is the number of rounds played, and we further provide distribution-independent bounds for a large class of reward functions. Our regret analysis is tight in that it matches the bound of UCB1 algorithm (up to a constant factor) for the classical MAB problem, and it significantly improves the regret bound in a earlier paper on combinatorial bandits with linear rewards. We apply our CMAB framework to two new applications, probabilistic maximum coverage and social influence maximization, both having nonlinear reward structures. In particular, application to social influence maximization requires our extension on probabilistically triggered arms.