arXiv · 2611.21987
Safe Reinforcement Learning with Hard Constraints: Policy Gradient Methods with Intersample Guarantees
Abstract
We develop a policy-gradient (PG) reinforcement learning (RL) framework with hard inter-sample control barrier function (CBF)-based safety constraints for nonlinear sampled-data systems. We first design a class of stochastic policies with support truncated to sampling-period-dependent safe control sets, that guarantee safety-by-construction at sampling instants. We then propose a model-free PG algorithm that searches over the class of safe-by-design policies and establish sufficient conditions on sampling-period such that any action sampled from safe control sets remains safe throughout the sampling interval, providing inter-sample guarantees. We further establish finite-time convergence and sample complexity guarantees for the proposed PG algorithm and characterize its global optimality under gradient dominance. Finally, we illustrate inter-sample safety guarantees on a safe quadrotor navigation environment.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Vipul K. Sharma, S. Sivaranjani. 2026-11-16. Safe Reinforcement Learning with Hard Constraints: Policy Gradient Methods with Intersample Guarantees. https://searcharxiv.com/abs/2611.21987
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.