arXiv Machine Learning June 2, 2026 By Bernd Frauenknecht, Devdutt Subhasish, Artur Eisele, Friedrich Solowjow, Sebastian Trimpe

All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2606. 01363v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) infers information about the environment from a learned dynamics model and bears the potential to address open problems such as data efficient and safe learning in robotics.

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 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

Jun 10

SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration

arXiv:2606. 10228v1 Announce Type: cross Abstract: Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains.

By Kaustubh Mani, Yann Pequignot, Vincent Mai, Liam Paull

agents reinforcement-learning safety

arXiv Machine Learning

Aug 11

Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics

arXiv:2604. 26836v3 Announce Type: replace Abstract: Predictive safety filters (PSFs) leverage model predictive control to enforce constraint satisfaction during deep reinforcement learning (RL) exploration, yet their reliance on first-principles models or Gaussian processes limits scalability and broader applicability.

By Bernd Frauenknecht, Lukas Kesper, Daniel Mayfrank, Henrik Hose, Sebastian Trimpe

reinforcement-learning benchmarks safety

arXiv AI

Jul 17

RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences

arXiv:2607. 14180v1 Announce Type: cross Abstract: World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset.

By Logan Mondal Bhamidipaty, Mykel Kochenderfer, Subramanian Ramamoorthy

reinforcement-learning fine-tuning safety

Hugging Face Trending Papers

Jul 8

Safe Reinforcement Learning using Ideas from Model Predictive Control

Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics. A persistent challenge, however, is ensuring strict, hard safety constraints during the active learning phase.

agents reinforcement-learning robotics safety

arXiv AI

Jun 8

Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning

arXiv:2606. 06976v1 Announce Type: new Abstract: Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions.

By Yijin Zhou, Linqian Zeng, Xiaoya Lu, Wenyuan Xie, Dongrui Liu, Junchi Yan, Jing Shao

llms agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Safe Exploration via Policy Priors

SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration

Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics

RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences

Safe Reinforcement Learning using Ideas from Model Predictive Control

Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning