# Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehicles

arXiv: https://arxiv.org/abs/2605.16894 · HTML: https://mlsanity.com/paper/2605.16894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multi-agent reinforcement learning, one of 15 directions in Deep reinforcement learning methods.
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 16 May 2026.

## Placed in

- Deep reinforcement learning methods / [Multi-agent reinforcement learning](https://mlsanity.com/deeprl/multi-agent-reinforcement-learning/)

## Builds on (most cited first, 19 of 19)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks](https://mlsanity.com/paper/1903.08792/) (2019)
- [A predictive safety filter for learning-based control of constrained nonlinear dynamical systems](https://mlsanity.com/paper/1812.05506/) (2018)
- [Reward (Mis)design for Autonomous Driving](https://mlsanity.com/paper/2104.13906/) (2021)
- [Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning](https://mlsanity.com/paper/2001.08726/) (2020)
- [Model-free Deep Reinforcement Learning for Urban Autonomous Driving](https://mlsanity.com/paper/1904.09503/) (2019)
- [Learning for Safety-Critical Control with Control Barrier Functions](https://mlsanity.com/paper/1912.10099/) (2019)
- [Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1902.00089/) (2019)
- [Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion](https://mlsanity.com/paper/2308.12517/) (2023)
- [Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Merge](https://mlsanity.com/paper/1709.02066/) (2017)
- [A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards](https://mlsanity.com/paper/2409.15780/) (2024)
- [Barrier Functions Inspired Reward Shaping for Reinforcement Learning](https://mlsanity.com/paper/2403.01410/) (2024)
- [Episodic Learning for Safe Bipedal Locomotion with Control Barrier Functions and Projection-to-State Safety](https://mlsanity.com/paper/2105.01697/) (2021)
- [SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning](https://mlsanity.com/paper/2408.07644/) (2024)
- [A Real-Time Control Barrier Function-Based Safety Filter for Motion Planning with Arbitrary Road Boundary Constraints](https://mlsanity.com/paper/2505.02395/) (2025)
- [A Learning-Based Control Barrier Function for Car-Like Robots: Toward Less Conservative Collision Avoidance](https://mlsanity.com/paper/2411.08999/) (2024)
- [TTCBF: A Truncated Taylor Control Barrier Function for High-Order Safety Constraints](https://mlsanity.com/paper/2601.15196/) (2026)

## Abstract (arXiv)

Reinforcement Learning (RL) uses rewards to guide learning, yet reward design is typically hand-crafted using heuristics that can be difficult to tune. We propose a Control Barrier Function (CBF)-informed reward design for Multi-Agent RL (MARL) that converts CBF constraint values under joint MARL actions into a reward signal that explicitly guides safe learning. We compare against two heuristic reward baselines in a four-way multi-lane intersection with connected and automated vehicles. Results show that our method achieves the highest task performance and is less sensitive to reward hyperparameters, yielding consistently strong performance across the tested hyperparameter range. Code for reproducing the experimental results and a video demonstration are available at https://github.com/bassamlab/SigmaRL.