Overview

In adversarial bandits, a learner chooses among actions but observes feedback only for selected actions, while rewards or losses may vary arbitrarily or respond to past choices. The central goal is low regret against a comparator, using methods such as importance-weighted estimates, EXP3, online mirror descent, and follow-the-perturbed-leader. These ideas extend to contextual, linear, kernel, and combinatorial action spaces, as well as settings with delays, constraints, side observations, or switching comparators. A key tension is achieving strong guarantees against adversaries while adapting to stochastic structure, richer feedback, or practical computational limits.

Latest papers

CardsList

62 papers8 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

  1. Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection

    May 28, 2025Qirun Zeng, Eric He, Richard Hoffmann +2Adversarial BanditsMulti-Armed Bandits

  2. Bandit Profit-maximization for Targeted Marketing

    Mar 3, 2024Joon Suk Huh, Ellen Vitercik, Kirthevasan KandasamyAdversarial BanditsDynamic Pricing