arXiv Machine Learning June 2, 2026 By Gianmarco Genalti, Achraf Azize, Vianney Perchet

Online Packet Scheduling with Deadlines and Learning

Read the original on arXiv Machine Learning →

arXiv:2606. 00835v1 Announce Type: new Abstract: Network routers that enforce Quality-of-Service (QoS) guarantees must decide, at every clock cycle, which expiring packet of information to transmit, even when the value of the packet is unknown until it is processed.

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 9

Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret

arXiv:2606. 09668v1 Announce Type: new Abstract: Contextual queueing bandits provide a framework for learning to schedule heterogeneous jobs under unknown context-dependent service rates.

By Seoungbin Bae, Dabeen Lee

arXiv Machine Learning

Sep 15

Toward Optimal Switching Regret for Multi-Armed Bandits with Oblivious Adversary

arXiv:2609.13547v1 Announce Type: new Abstract: We study switching regret in adversarial multi-armed bandits, where the learner competes with an arm sequence that changes at most $S$ times. When $S$...

By Mengxiao Zhang

safety

arXiv Machine Learning

Aug 3

Parameter-Free Heavy-Tailed Bandits

arXiv:2607. 29460v1 Announce Type: new Abstract: Heavy-tailed distributions arise naturally in sequential decision-making problems such as financial investment, online advertising, and network management, where rare but extreme outcomes can dominate performance.

By Gianmarco Genalti, Alberto Maria Metelli

arXiv Machine Learning

Jun 29

Learning in Markovian bandits with non-observable states and constrained decision epochs

arXiv:2606. 27448v1 Announce Type: new Abstract: This paper studies the problem of regret minimization in Markovian bandits with \emph{non-observable states} and possibly \emph{constrained} decision epochs.

By Thomas Hira, Victor Boone, Urtzi Ayesta, Ina Maria Verloop

reinforcement-learning benchmarks safety

arXiv Machine Learning

Jul 14

Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards

arXiv:2112. 06362v5 Announce Type: replace Abstract: We consider the problem of scheduling in multi-class, parallel-server queuing systems with uncertain rewards from job-server assignments.

By Jung-hun Kim, Milan Vojnovic

reinforcement-learning efficiency

arXiv Machine Learning

4d ago

Learning When to Update: A Near-Optimal Timing Bandit Approach

arXiv:2609.37932v1 Announce Type: new Abstract: Systems operating in dynamic environments require timely updates to sustain performance. For resource-intensive systems such as machine learning models...

By Qiulin Lin, Junyan Su, Liyuan Wang, Minghua Chen

reinforcement-learning

One email a morning, machine-written

Related stories

Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret

Toward Optimal Switching Regret for Multi-Armed Bandits with Oblivious Adversary

Parameter-Free Heavy-Tailed Bandits

Learning in Markovian bandits with non-observable states and constrained decision epochs

Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards

Learning When to Update: A Near-Optimal Timing Bandit Approach