← Back to all news
arXiv Machine Learning By Alexander W. Goodall, Francesco Belardinelli

Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models

Read the original on arXiv Machine Learning →

The paper presents a recovery‑based shielding framework that guarantees a provable safety lower bound for reinforcement learning in unknown, non‑linear continuous dynamical systems. It combines a backup policy (shield) with the RL agent and uses Gaussian process models to quantify uncertainty and predict safety violations, enabling dynamic recovery to safe trajectories only when needed. The shielded agent’s experience trains the GP models, and policy optimization is performed via internal model‑based sampling, allowing unrestricted exploration and sample‑efficient learning while maintaining strict safety compliance in continuous control tasks.

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.

Related stories

arXiv AI
Aug 21

Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning

arXiv:2608. 19836v1 Announce Type: cross Abstract: Probabilistic shielding is a technique for safe reinforcement learning (RL).

By Astrid Horn Brorholt (Aalborg University, Aalborg, Denmark), Maris F. L. Galesloot (Radboud University, Nijmegen, Netherlands), Nils Jansen (Radboud University, Nijmegen, Netherlands), Kim Guldstrand Larsen (Aalborg University, Aalborg, Denmark), Christian Schilling (Aalborg University, Aalborg, Denmark)
agentsreinforcement-learningsafety
More like this →
arXiv AI
Oct 12

Sampling-Based Safe Reinforcement Learning

Sampling-Based Safe Reinforcement Learning (SBSRL) is a model‑based RL algorithm that enforces safety by jointly constraining a finite set of dynamics samples, approximating a worst‑case optimization over uncertain dynamics. It introduces an exploration strategy that limits epistemic uncertainty, removing the need for explicit exploration bonuses. The authors provide high‑probability safety guarantees and a finite‑time sample complexity bound, and demonstrate safe, efficient exploration in both simulation and real robotic hardware, with extensions to deep‑ensemble implementations for high‑dimensional continuous control.

By Luca Vignola, Bruce D. Lee, Manish Prajapat, Manuel Wendl, Melanie Zeilinger, Andreas Krause, Yarden As
agentsreinforcement-learningroboticssafety
More like this →
arXiv AI
Oct 19

RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning

The paper introduces RecReg, a safe reinforcement learning framework that enforces non‑Markovian regular safety properties through recovery‑based shielding. It provides theoretical foundations and rigorous safety and convergence guarantees in the tabular setting, and demonstrates empirical effectiveness using the MASA‑Safe‑RL library. The authors also outline an extension of RecReg to deep RL with state‑of‑the‑art model‑based methods.

By Alexander W. Goodall, Francesco Belardinelli
agentsreinforcement-learningbenchmarkssafety
More like this →