mlsanityData to 7 Oct 2026

Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function

arXiv 2103.01556 ↗First posted 2 Mar 2021cs.RO cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Model information can be used to predict future trajectories, so it has huge potential to avoid dangerous region when implementing reinforcement learning (RL) on real-world tasks, like autonomous driving. However, existing studies mostly use model-free constrained RL, which causes inevitable constraint violations. This paper proposes a model-based feasibility enhancement technique of constrained RL, which enhances the feasibility of policy using generalized control barrier function (GCBF) defined on the distance to constraint boundary. By using the model information, the policy can be optimized safely without violating actual safety constraints, and the sample efficiency is increased. The major difficulty of infeasibility in solving the constrained policy gradient is handled by an adaptive coefficient mechanism. We evaluate the proposed method in both simulations and real vehicle experiments in a complex autonomous driving collision avoidance task. The proposed method achieves up to four times fewer constraint violations and converges 3.36 times faster than baseline constrained RL approaches.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 11 of its 26 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

11 of 26 references.

References · 11

  1. 2015Trust Region Policy Optimizationcited by 2,503
  2. 2016Concrete Problems in AI Safetycited by 1,582
  3. 2017Constrained Policy Optimizationcited by 928
  4. 2018Reward Constrained Policy Optimizationcited by 397
  5. 2019Control Barrier Functions: Theory and Applicationscited by 332
  6. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
  7. 2018Learning-based Model Predictive Control for Safe Explorationcited by 116
  8. 2020Numerically Stable Dynamic Bicycle Model for Discrete-time Controlcited by 15
  9. 2019Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraintscited by 12
  10. 2020Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Criticcited by 12
  11. 2021Feasibility Enhancement of Constrained Receding Horizon Control Using Generalized Control Barrier Functioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 8; 2023: 7; 2024: 4; 2025: 3; 2026: 3.

30 papers.

Sort:

By area:

  1. 2022Physics-Informed Machine Learning: A Survey on Problems, Methods and Applicationscited by 88
  2. 2022Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environmentscited by 54
  3. 2022Reachability Constrained Reinforcement Learningcited by 52
  4. 2022Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Modelcited by 44
  5. 2021Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safetycited by 30
  6. 2021Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learningcited by 25
  7. 2023A Survey on Physics Informed Reinforcement Learning: Review and Open Problemscited by 22
  8. 2024Hamilton-Jacobi Reachability in Reinforcement Learning: A Surveycited by 11
  9. 2023Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guaranteescited by 9
  10. 2023Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidancecited by 8
  11. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functionscited by 8
  12. 2023Gaussian Max-Value Entropy Search for Multi-Agent Bayesian Optimizationcited by 7
18 more
  1. 2021Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learningcited by 4
  2. 2023Feasible Policy Iteration for Safe Reinforcement Learningcited by 4
  3. 2026How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?cited by 4
  4. 2021Model Free Barrier Functions via Implicit Evading Maneuverscited by 3
  5. 2021Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehiclescited by 3
  6. 2022Safe Inverse Reinforcement Learning via Control Barrier Functioncited by 3
  7. 2023Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environmentscited by 3
  8. 2024Learning Control Barrier Functions and their application in Reinforcement Learning: A Surveycited by 3
  9. 2022Improve Generalization of Driving Policy at Signalized Intersections with Adversarial Learningcited by 2
  10. 2023Control invariant set enhanced safe reinforcement learning: improved sampling efficiency, guaranteed stability and robustnesscited by 2
  11. 2022Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Mergingcited by 1
  12. 2024Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systemscited by 1
  13. 2024Act Better by Timing: A timing-Aware Reinforcement Learning for Autonomous Drivingcited by 1
  14. 2026Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learningcited by 1
  15. 2022Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learningcited by 0
  16. 2025Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategiescited by 0
  17. 2025Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-lane Scenarioscited by 0
  18. 2026Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learningcited by 0