pith. sign in

arxiv: 2306.04026 · v4 · pith:P2CVPWCDnew · submitted 2023-06-06 · 💻 cs.LG · cs.AI· cs.RO

Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory

classification 💻 cs.LG cs.AIcs.RO
keywords controlfunctionsvaluelearningpoliciessafetheoryverification
0
0 comments X
read the original abstract

Guaranteeing safe behaviour of reinforcement learning (RL) policies poses significant challenges for safety-critical applications, despite RL's generality and scalability. To address this, we propose a new approach to apply verification methods from control theory to learned value functions. By analyzing task structures for safety preservation, we formalize original theorems that establish links between value functions and control barrier functions. Further, we propose novel metrics for verifying value functions in safe control tasks and practical implementation details to improve learning. Our work presents a novel method for certificate learning, which unlocks a diversity of verification techniques from control theory for RL policies, and marks a significant step towards a formal framework for the general, scalable, and verifiable design of RL-based control systems. Code and videos are available at this https url: https://rl-cbf.github.io/

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous Driving

    cs.AI 2026-05 unverdicted novelty 5.0

    Uncertainty-triggered expert advice with temporal regulation and shared replay buffer improves success rate by 5-7% over IQN baseline in CARLA unsignalized intersection tasks.