← Back to all news
arXiv Machine Learning By Nicol\`o Cesa-Bianchi, Matteo Papini

m-Set Adversarial Bandits with Winner Feedback

Read the original on arXiv Machine Learning →

The paper presents upper and lower bounds on the regret for m‑set adversarial bandits across various utilities—winner reward or sum of rewards—and feedback models, including winner index, winner reward, sum of rewards, and their combinations. By comparing these results to standard bounds for combinatorial and MNL bandits, the authors demonstrate that small changes in the setting can dramatically affect learning rates. The main technical contribution is the derivation of information‑theoretic lower bounds, and synthetic experiments validate the theoretical findings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 1

On the Complexity of Preference-Based Bandits

The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.

By Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY)
reinforcement-learning
More like this →