arXiv AI July 17, 2026 By Mattie Fellows, Clarisse Wibault, Uljad Berdica, Johannes Forkel, Maike Osborne, Jakob N. Foerster

Fully Offline Reinforcement Learning

Read the original on arXiv AI →

arXiv:2505. 22442v3 Announce Type: replace-cross Abstract: Offline RL (ORL) promises safe and sample-efficient deployment but existing methods rely on undocumented online interactions for hyperparameter tuning and lack reliable fully offline estimates of initial online performance.

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 AI.

reinforcement-learning

arXiv Machine Learning

Jun 17

Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach

arXiv:2510. 19528v2 Announce Type: replace-cross Abstract: We investigate the fundamental problem of leveraging offline data to accelerate online reinforcement learning - a direction with strong potential but limited theoretical grounding.

By Sebastian Reboul, H\'el\`ene Halconruy

reinforcement-learning fine-tuning

arXiv Machine Learning

4d ago

From Static Policies to Adaptive Priors in Offline Reinforcement Learning

arXiv:2609.35880v1 Announce Type: new Abstract: Offline reinforcement learning (RL) has traditionally focused on learning policies for direct deployment under conservative objectives, where uncertain...

By Tianwei Ni, Vineet Jain, Akash Karthikeyan, Pierre-Luc Bacon

reinforcement-learning fine-tuning

arXiv AI

Jun 2

Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief

arXiv:2606. 00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets.

By Hongqiang Lin, Pengfei Wang, Nenggan Zheng

reinforcement-learning benchmarks

arXiv AI

Jun 16

Safe Exploration via Policy Priors

arXiv:2601. 19612v3 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.

By Manuel Wendl, Yarden As, Manish Prajapat, Anton Pollak, Stelian Coros, Andreas Krause

agents reinforcement-learning benchmarks safety

arXiv AI

Jul 14

Active Offline-to-Online Reinforcement Learning

arXiv:2607. 11720v1 Announce Type: cross Abstract: Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction.

By Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai

reinforcement-learning fine-tuning

arXiv AI

Jul 7

The Three Regimes of Offline-to-Online Reinforcement Learning

arXiv:2510. 01460v4 Announce Type: replace-cross Abstract: Offline-to-online reinforcement learning (RL) has emerged as a practical paradigm that leverages offline datasets for pretraining and online interactions for fine-tuning.

By Lu Li, Tianwei Ni, Yihao Sun, Pierre-Luc Bacon

reinforcement-learning fine-tuning

One email a morning, machine-written

Related stories

Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach

From Static Policies to Adaptive Priors in Offline Reinforcement Learning

Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief

Safe Exploration via Policy Priors

Active Offline-to-Online Reinforcement Learning

The Three Regimes of Offline-to-Online Reinforcement Learning