mlsanityData to 7 Oct 2026

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

arXiv 2306.04026 ↗First posted 6 Jun 2023cs.LG cs.AI cs.ROcited by 5

Not on the map. Why?

Abstract (arXiv)

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/

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 58 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

33 of 58 references.

References · 33

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  5. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  6. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  7. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  8. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
  9. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  10. 2018Reward Constrained Policy Optimizationcited by 397
  11. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  12. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 302
21 more
  1. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
  2. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  3. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  4. 2018Safe Exploration in Continuous Action Spacescited by 237
  5. 2022Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methodscited by 148
  6. 2023Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learningcited by 116
  7. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 113
  8. 2020Learning Stable Deep Dynamics Modelscited by 110
  9. 2020Conservative Safety Critics for Explorationcited by 107
  10. 2018The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systemscited by 87
  11. 2022Safe Reinforcement Learning by Imagining the Near Futurecited by 67
  12. 2021Introduction to Neural Network Verificationcited by 63
  13. 2022Safe Control Under Input Limits with Neural Control Barrier Functionscited by 27
  14. 2022Learning Safe, Generalizable Perception-based Hybrid Control with Certificatescited by 24
  15. 2022Neuro-Symbolic Verification of Deep Neural Networkscited by 21
  16. 2022Lyapunov Design for Robust and Efficient Robotic Reinforcement Learningcited by 20
  17. 2021Safe Continuous Control with Constrained Model-Based Policy Optimizationcited by 17
  18. 2022SABLAS: Learning Safe Control for Black-box Dynamical Systemscited by 17
  19. 2021Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximationcited by 16
  20. 2020Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approachcited by 10
  21. 2021Safe Value Functionscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functionscited by 8
  2. 2025Learning Conservative Neural Control Barrier Functions from Offline Datacited by 4
  3. 2026Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous Drivingcited by 0
  4. 2026No Free Checker: A Survey of Verifiers for Robot Policiescited by 0
  5. 2026LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentialscited by 0