# Safe Multi-Agent Reinforcement Learning through Decentralized Multiple Control Barrier Functions

arXiv: https://arxiv.org/abs/2103.12553 · HTML: https://mlsanity.com/paper/2103.12553/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2021.

## Built on by (most cited first, 10 of 10)

- [A Survey on Physics Informed Reinforcement Learning: Review and Open Problems](https://mlsanity.com/paper/2309.01909/) (2023)
- [Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2304.06281/) (2023)
- [Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving](https://mlsanity.com/paper/2405.18209/) (2024)
- [Provably Learning Nash Policies in Constrained Markov Potential Games](https://mlsanity.com/paper/2306.07749/) (2023)
- [Safe Multi-agent Reinforcement Learning with Natural Language Constraints](https://mlsanity.com/paper/2405.20018/) (2024)
- [Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL](https://mlsanity.com/paper/2504.15425/) (2025)
- [Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning](https://mlsanity.com/paper/2311.00063/) (2023)
- [A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions](https://mlsanity.com/paper/2508.09128/) (2025)
- [Robust and Safe Multi-Agent Reinforcement Learning with Communication for Autonomous Vehicles: From Simulation to Hardware](https://mlsanity.com/paper/2506.00982/) (2025)
- [Distributed Direct Preference Optimization](https://mlsanity.com/paper/2605.20696/) (2026)

## Abstract (arXiv)

Multi-Agent Reinforcement Learning (MARL) algorithms show amazing performance in simulation in recent years, but placing MARL in real-world applications may suffer safety problems. MARL with centralized shields was proposed and verified in safety games recently. However, centralized shielding approaches can be infeasible in several real-world multi-agent applications that involve non-cooperative agents or communication delay. Thus, we propose to combine MARL with decentralized Control Barrier Function (CBF) shields based on available local information. We establish a safe MARL framework with decentralized multiple CBFs and develop Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to Multi-Agent Deep Deterministic Policy Gradient with decentralized multiple Control Barrier Functions (MADDPG-CBF). Based on a collision-avoidance problem that includes not only cooperative agents but obstacles, we demonstrate the construction of multiple CBFs with safety guarantees in theory. Experiments are conducted and experiment results verify that the proposed safe MARL framework can guarantee the safety of agents included in MARL.