mlsanityData to 14 Oct 2026

Learning Conservative Neural Control Barrier Functions from Offline Data

arXiv 2505.00908 ↗First posted 1 May 2025cs.LG cs.FL cs.ROcited by 5

On the map: Offline RL and imitation learning from data → Safe offline RL

also in 1 more
Abstract (arXiv)

Safety filters, particularly those based on control barrier functions, have gained increased interest as effective tools for safe control of dynamical systems. Existing correct-by-construction synthesis algorithms for such filters, however, suffer from the curse-of-dimensionality. Deep learning approaches have been proposed in recent years to address this challenge. In this paper, we add to this set of approaches an algorithm for training neural control barrier functions from offline datasets. Such functions can be used to design constraints for quadratic programs that are then used as safety filters. Our algorithm trains these functions so that the system is not only prevented from reaching unsafe states but is also disincentivized from reaching out-of-distribution ones, at which they would be less reliable. It is inspired by Conservative Q-learning, an offline reinforcement learning algorithm. We call its outputs Conservative Control Barrier Functions (CCBFs). Our empirical results demonstrate that CCBFs outperform existing methods in maintaining safety while minimally affecting task performance. Source code is available at https://github.com/tabz23/CCBF.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data. Builds on 34 of its 41 references that are in the map. First posted on arXiv 1 May 2025.

Builds on

34 of 41 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model19 Jan
  2. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learning15 Jun
  3. 2021Constraints Penalized Q-learning for Safe Offline Reinforcement Learning19 Jul
  4. 2020Learning Control Barrier Functions from Expert Demonstrations7 Apr

Other references · 30

  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  2. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  3. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  4. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  5. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,241
  6. 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 840
  7. 2019Behavior Regularized Offline Reinforcement Learningcited by 662
  8. 2019Control Barrier Functions: Theory and Applicationscited by 372
  9. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
  10. 2017Count-Based Exploration with Neural Density Modelscited by 257
  11. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 201
  12. 2022Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methodscited by 151
18 more
  1. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  2. 2021Uncertainty Weighted Actor-Critic for Offline Reinforcement Learningcited by 126
  3. 2021Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functionscited by 94
  4. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 88
  5. 2024Agile But Safe: Learning Collision-Free High-Speed Legged Locomotioncited by 73
  6. 2022COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimationcited by 71
  7. 2020Classification with Rejection Based on Cost-sensitive Classificationcited by 55
  8. 2025Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysiscited by 45
  9. 2023How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systemscited by 44
  10. 2022When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learningcited by 31
  11. 2022Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Controlcited by 28
  12. 2021Learning Robust Output Control Barrier Functions from Safe Expert Demonstrationscited by 20
  13. 2023In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution Statescited by 16
  14. 2021Verification and Synthesis of Control Barrier Functionscited by 13
  15. 2015Some Applications of Polynomial Optimization in Operations Research and Real-Time Decision Makingcited by 11
  16. 2022Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Drivingcited by 10
  17. 2023Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theorycited by 6
  18. 2025Estimating Control Barriers from Offline Datacited by 3

Built on by

Cited by year (2026 to 14 Oct)

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

5 papers.

  1. 2025Designing Latent Safety Filters using Pre-Trained Vision Modelscited by 5
  2. 2026Safe Control using Learned Safety Filters and Adaptive Conformal Inferencecited by 2
  3. 2025Learning Neural Control Barrier Functions from Expert Demonstrations using Inverse Constraint Learningcited by 1
  4. 2026CrossSafe: Towards Cross-Embodiment Latent Safety Filterscited by 0
  5. 2026Safe Reinforcement Learning with Receding-Horizon Safety Critic and Differentiable Action Shieldscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions
  2. 2025Explicit Control Barrier Function-based Safety Filters and their Resource-Aware Computation
  3. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
  4. 2023Safe Neural Control for Non-Affine Control Systems with Differentiable Control Barrier Functions
  5. 2025Learning State-Action Control Barrier Functions for Model-Free Control under Constraints
  6. 2024Disturbance Observer-based Control Barrier Functions with Residual Model Learning for Safe Reinforcement Learning
  7. 2024Practical Considerations for Discrete-Time Implementations of Continuous-Time Control Barrier Function-Based Safety Filters
  8. 2026CAPSULE: Control-Theoretic Action Perturbations for Safe Uncertainty-Aware Reinforcement Learning