AI & ML
Safe Reinforcement Learning with Hard Constraints: Policy Gradient Methods with Intersample Guarantees
arXiv cs.SY0 views
arXiv:2611.21987v1 Announce Type: new 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.
Source:https://arxiv.org/abs/2611.21987PreviousFirst-Order Model-Free Policy Gradient for Undiscounted LQR with Global Optimality and Convergence GuaranteesNextPS-HalluBench: Taxonomy-Driven Benchmarking of LLM Hallucinations in Power Systems
Related posts

Parallels Desktop review
0TechRadar
How Far Behind Are Open Weights, Measured
0dev.to
Claude was trained on protein sequences at scale
0Hacker News
Pretraining vs post-training: one apple problem, four learning signals
0dev.to Beginners
Bitcoin Recovery Expert USA: Professional Crypto Asset Recovery with META TECH RETRIEVE PRO
0dev.to Beginners
Hugging Face Switches Its Inference Providers to OpenRouter Routing
0dev.to OpenSource