Decision-making in the face of uncertainty is a significant challenge in machine learning,
and the multi-armed bandit model is a commonly used framework to address it. This …

Multi-armed bandits a simple but very powerful framework for algorithms that make
decisions over time under uncertainty. An enormous body of work has accumulated over the …

Self-play, where the algorithm learns by playing against itself without requiring any direct
supervision, has become the new weapon in modern Reinforcement Learning (RL) for …

In a multi-armed bandit (MAB) problem a gambler needs to choose at each round of play
one of K arms, each characterized by an unknown reward distribution. Reward realizations …

We introduce a new model of stochastic bandits with adversarial corruptions which aims to
capture settings where most of the input follows a stochastic pattern but some fraction of it …

A major research direction in contextual bandits is to develop algorithms that are
computationally efficient, yet support flexible, general-purpose function approximation …

In two-player competitive sports, such as boxing and fencing, athletes often demonstrate
efficient and tactical movements during a competition. In this paper, we develop a learning …

Boltzmann exploration is a classic strategy for sequential decision-making under
uncertainty, and is one of the most standard tools in Reinforcement Learning (RL). Despite …

In online advertising markets, advertisers often purchase ad placements through bidding in
repeated auctions based on realized viewer information. We study how budget-constrained …

We study the stochastic multi-armed bandits problem in the presence of adversarial
corruption. We present a new algorithm for this problem whose regret is nearly optimal …