Skyline Identification in Multi-Armed Bandits

Modal Bandits

Analyses of multi-armed bandits primarily presume that the value of an arm is its expected reward. We introduce a theory for multi-armed bandits where the values are the modes of the reward distributions.

Multiple Identifications in Multi-Armed Bandits

We study the problem of identifying the top m arms in a multi-armed bandit game. Our proposed solution relies on a new algorithm based on successive rejects of the seemingly bad arms, and successive accepts of the good ones. This algorithmic contribution allows to tackle other multiple identifications settings that were previously out of reach. In particular we show that this idea of successive...

Habilitation À Diriger Des Recherches De L'université Paris-est Agrégation Pac-bayésienne Et Bandits À Plusieurs Bras Pac-bayesian Aggregation and Multi-armed Bandits

Generic Exploration and K-armed Voting Bandits

We study a stochastic online learning scheme with partial feedback where the utility of decisions is only observable through an estimation of the environment parameters. We propose a generic pure-exploration algorithm, able to cope with various utility functions from multi-armed bandits settings to dueling bandits. The primary application of this setting is to offer a natural generalization of ...

The Epoch-Greedy Algorithm for Contextual Multi-armed Bandits

We present Epoch-Greedy, an algorithm for contextual multi-armed bandits (also known as bandits with side information). Epoch-Greedy has the following properties: 1. No knowledge of a time horizon T is necessary. 2. The regret incurred by Epoch-Greedy is controlled by a sample complexity bound for a hypothesis class. 3. The regret scales asO(T S) or better (sometimes, much better). Here S is th...