mlsanityData to 7 Oct 2026

Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey

arXiv 2404.16879 ↗First posted 22 Apr 2024cs.LG cs.AI cs.ROcited by 3

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning is a powerful technique for developing new robot behaviors. However, typical lack of safety guarantees constitutes a hurdle for its practical application on real robots. To address this issue, safe reinforcement learning aims to incorporate safety considerations, enabling faster transfer to real robots and facilitating lifelong learning. One promising approach within safe reinforcement learning is the use of control barrier functions. These functions provide a framework to ensure that the system remains in a safe state during the learning process. However, synthesizing control barrier functions is not straightforward and often requires ample domain knowledge. This challenge motivates the exploration of data-driven methods for automatically defining control barrier functions, which is highly appealing. We conduct a comprehensive review of the existing literature on safe reinforcement learning using control barrier functions. Additionally, we investigate various techniques for automatically learning the Control Barrier Functions, aiming to enhance the safety and efficacy of Reinforcement Learning in practical robot applications.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 45 of its 70 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

45 of 70 references.

References · 45

  1. 2015Continuous control with deep reinforcement learningcited by 3,279
  2. 2015Trust Region Policy Optimizationcited by 2,503
  3. 2017Constrained Policy Optimizationcited by 928
  4. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  5. 2017Safe Reinforcement Learning via Shieldingcited by 427
  6. 2018Reward Constrained Policy Optimizationcited by 397
  7. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  8. 2019Control Barrier Functions: Theory and Applicationscited by 332
  9. 2019Challenges of Real-World Reinforcement Learningcited by 282
  10. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  11. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 214
  12. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
33 more
  1. 2020Exploration-Exploitation in Constrained MDPscited by 146
  2. 2020Learning to be Safe: Deep RL with a Safety Criticcited by 109
  3. 2017Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learningcited by 97
  4. 2020Learning Control Barrier Functions from Expert Demonstrationscited by 88
  5. 2017Uncertainty-Aware Reinforcement Learning for Collision Avoidancecited by 86
  6. 2021Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificatescited by 71
  7. 2022A Survey on Model-based Reinforcement Learningcited by 65
  8. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 60
  9. 2019Reinforcement Learning with Convex Constraintscited by 57
  10. 2019Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamicscited by 45
  11. 2020Sim2Real Transfer for Reinforcement Learning without Dynamics Randomizationcited by 43
  12. 2016Safe Learning of Regions of Attraction for Uncertain, Nonlinear Systems with Gaussian Processescited by 38
  13. 2021Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violationscited by 36
  14. 2020Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approachcited by 35
  15. 2021Model-based Constrained Reinforcement Learning using Generalized Control Barrier Functioncited by 30
  16. 2019Adaptive Safety with Control Barrier Functionscited by 25
  17. 2020Learning Hybrid Control Barrier Functions from Datacited by 24
  18. 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 24
  19. 2024GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Controlcited by 20
  20. 2020Control Barrier Functions for Unknown Nonlinear Systems using Gaussian Processescited by 19
  21. 2021Learning Robust Output Control Barrier Functions from Safe Expert Demonstrationscited by 19
  22. 2020Learning Barrier Functions for Constrained Motion Planning with Dynamical Systemscited by 17
  23. 2022Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environmentscited by 16
  24. 2019Learning Resilient Behaviors for Navigation Under Uncertaintycited by 11
  25. 2023Online Control Barrier Functions for Decentralized Multi-Agent Navigationcited by 10
  26. 2023Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functionscited by 9
  27. 2021Robust Control Barrier Functions with Sector-Bounded Uncertaintiescited by 8
  28. 2022Learning Differentiable Safety-Critical Control using Control Barrier Functions for Generalization to Novel Environmentscited by 8
  29. 2020Model-Based Generalization Under Parameter Uncertainty Using Path Integral Controlcited by 7
  30. 2022Robust Control Barrier Functions for Nonlinear Control Systems with Uncertainty: A Duality-based Approachcited by 5
  31. 2020Control Barrier Functions for Sampled-Data Systems with Input Delayscited by 2
  32. 2022Gaussian Control Barrier Functions : A Non-Parametric Paradigm to Safetycited by 2
  33. 2023A Data-driven Method for Safety-critical Control: Designing Control Barrier Functions from State Constraintscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signalscited by 2
  2. 2026Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learningcited by 0
  3. 2026Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observationcited by 0