arXiv Machine Learning June 15, 2026 By Christoph Bauschmann, Setareh Maghsudi

Graph Structured Combinatorial Semi-Bandit with Nonlinear Reward Associations through Separable Signals

Read the original on arXiv Machine Learning →

arXiv:2606. 14650v1 Announce Type: new Abstract: The identification of optimal structures within vast arrays of interconnected data necessitates significant sampling- and computational effort.

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.

reinforcement-learning

arXiv Machine Learning

Jun 2

Evaluating and Learning Robust Bandit Policies Under Uncertain Causal Mechanisms

arXiv:2508. 02812v3 Announce Type: replace Abstract: Causal graphical models can encode large amounts structural knowledge, both from the background knowledge of domain experts and the structural knowledge discovered from randomized experiments or observational data.

By Katherine Avery, Chinmay Pendse, David Jensen

reinforcement-learning

arXiv AI

Jun 29

The Minimal Search Space for Conditional Causal Bandits

arXiv:2502. 06577v3 Announce Type: replace-cross Abstract: Causal knowledge can be used to support decision-making problems.

By Francisco N. F. Q. Simoes, Itai Feigenbaum, Mehdi Dastani, Thijs van Ommen

reinforcement-learning

arXiv AI

Jul 20

Information-Directed Sampling for Causal Bandits

arXiv:2607. 15577v1 Announce Type: cross Abstract: Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions.

By Muhammad Qasim Elahi, Murat Kocaoglu, Mahsa Ghasemi

reinforcement-learning

arXiv AI

Jul 13

Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

arXiv:2607. 09015v1 Announce Type: cross Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing.

By Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi, Vijaykrishnan Narayanan

llms reinforcement-learning benchmarks

arXiv AI

3d ago

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

arXiv Machine Learning

Jul 8

No-Regret Gaussian Process Optimization of Time-Varying Functions

arXiv:2512. 00517v3 Announce Type: replace-cross Abstract: Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings.

By Eliabelle Mauduit, Elo\"ise Berthier, Andrea Simonetto

reinforcement-learning

One email a morning, machine-written

Related stories

Evaluating and Learning Robust Bandit Policies Under Uncertain Causal Mechanisms

The Minimal Search Space for Conditional Causal Bandits

Information-Directed Sampling for Causal Bandits

Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing

On the Complexity of Preference-Based Bandits

No-Regret Gaussian Process Optimization of Time-Varying Functions