arXiv Machine Learning July 30, 2026 By Nicolas Gutowski, Fabien Chhel, Alexandre Letard, Sylvain Lamprier

Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection

Read the original on arXiv Machine Learning →

arXiv:2607. 26273v1 Announce Type: new Abstract: We consider a stochastic multi-objective bandit problem where, at each round, the agent selects a slate of $k$ arms and observes their $d$-dimensional reward vectors under semi-bandit feedback.

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.

arXiv Machine Learning

Aug 6

Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation

arXiv:2608. 04333v1 Announce Type: new Abstract: Large language model (LLM) configuration evaluation is challenging due to limited evaluation budgets, varying costs, and multiple competing objectives.

By Bo Xue, Zhi Hong, Jiayi Li, Yuanyu Wan, Ji Cheng, Shuang Qiu

llms reinforcement-learning

arXiv Machine Learning

Jun 30

Optimal Regret for Single Index Bandits

arXiv:2605. 09454v2 Announce Type: replace-cross Abstract: We study the $\textit{single-index bandit}$ problem, where rewards depend on an unknown one-dimensional projection of high-dimensional contexts through an unknown reward function.

By Devdan Dey, Sujoy Bhore, Avishek Ghosh

reinforcement-learning

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

Sep 22

The Role of Coordinates in Pareto Regret for Adversarial Multi-Objective Bandits

arXiv:2609. 23092v1 Announce Type: new Abstract: Adversarial multi-objective bandits hold the potential to help us optimize choices (arms) whose reward is a multidimensional vector chosen by an adversary and whose performance is measured by Pareto regret.

By Changkun Guan, Mengfan Xu

safety

arXiv Machine Learning

Jul 16

Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation

arXiv:2607. 13686v1 Announce Type: new Abstract: We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation.

By Hao Qin, Chicheng Zhang

reinforcement-learning benchmarks

arXiv AI

3d ago

Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivit

arXiv:2609. 38659v1 Announce Type: cross Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers.

By Kaixuan Ji, Qiwei Di, Qingyue Zhao, Heyang Zhao, Quanquan Gu

One email a morning, machine-written

Related stories

Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation

Optimal Regret for Single Index Bandits

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

The Role of Coordinates in Pareto Regret for Adversarial Multi-Objective Bandits

Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation

Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivit