arXiv Machine Learning June 2, 2026 By Tim van Erven, Jack Mayo, Julia Olkhovskaya, Chen-Yu Wei

An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction

Read the original on arXiv Machine Learning →

arXiv:2508. 11931v3 Announce Type: replace Abstract: We present an oracle-efficient, near-optimal algorithm for linear contextual bandits with adversarial losses and stochastic action sets, only requiring a linear optimization oracle for the action sets in each round.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jul 7

Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions

arXiv:2607. 02891v1 Announce Type: new Abstract: Many online decision-making problems involve both round-specific feasible actions and drifting reward models: eligible ad impressions, feasible prices, and available treatments can change over time, while user preferences, demand curves, and patient responses may evolve.

By Zihao Hu, Yuan Yao, Jiheng Zhang, Zhengyuan Zhou

reinforcement-learning benchmarks

arXiv Machine Learning

Jul 23

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.

By Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du

reinforcement-learning

arXiv Machine Learning

Jun 16

Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach

arXiv:2602. 06404v2 Announce Type: replace Abstract: We study distributed adversarial bandits, where $N$ agents cooperate to minimize the global average loss while observing only their own local losses.

By Hao Qiu, Mengxiao Zhang, Nicol\`o Cesa-Bianchi

agents reinforcement-learning safety

arXiv Machine Learning

6d ago

An Efficient Near-Optimal Algorithm for Adversarial $m$-Set Bandits

arXiv:2608. 12231v1 Announce Type: new Abstract: We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items.

By Francesco Bacchiocchi, Tommaso Cesari, Roberto Colomboni

safety

arXiv Machine Learning

Jun 29

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits

arXiv:2602. 09456v2 Announce Type: replace Abstract: We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression.

By Hao Qin, Chicheng Zhang

reinforcement-learning

arXiv Machine Learning

Jul 1

A Complete Characterization of Learnability for Adversarial Noisy Bandits

arXiv:2605. 09200v2 Announce Type: replace Abstract: We study adversarial noisy bandits given a known function class $\mathcal{F}$.

By Steve Hanneke, Kun Wang

reinforcement-learning safety

Related stories

Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach

An Efficient Near-Optimal Algorithm for Adversarial $m$-Set Bandits

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits

A Complete Characterization of Learnability for Adversarial Noisy Bandits