# Safe Multi-Agent Reinforcement Learning via Shielding

arXiv: https://arxiv.org/abs/2101.11196 · HTML: https://mlsanity.com/paper/2101.11196/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 27 Jan 2021.

## Builds on (most cited first, 9 of 9)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1610.03295/) (2016)
- [A Survey and Critique of Multiagent Deep Reinforcement Learning](https://mlsanity.com/paper/1810.05587/) (2018)
- [Omega-Regular Objectives in Model-Free Reinforcement Learning](https://mlsanity.com/paper/1810.00950/) (2018)
- [Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning](https://mlsanity.com/paper/1909.07299/) (2019)
- [Cautious Reinforcement Learning with Logical Constraints](https://mlsanity.com/paper/2002.12156/) (2020)
- [CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1809.05188/) (2018)

## Built on by (most cited first, 30 of 61)

- [A Review of Safe Reinforcement Learning: Methods, Theory and Applications](https://mlsanity.com/paper/2205.10330/) (2022)
- [Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2408.09675/) (2024)
- [Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees](https://mlsanity.com/paper/2210.05308/) (2022)
- [Online Shielding for Reinforcement Learning](https://mlsanity.com/paper/2212.01861/) (2022)
- [Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees](https://mlsanity.com/paper/2312.01456/) (2023)
- [A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety](https://mlsanity.com/paper/2505.17342/) (2025)
- [Correct-by-Construction Runtime Enforcement in AI -- A Survey](https://mlsanity.com/paper/2208.14426/) (2022)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2304.06281/) (2023)
- [SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents](https://mlsanity.com/paper/2308.02594/) (2023)
- [Independent Learning in Constrained Markov Potential Games](https://mlsanity.com/paper/2402.17885/) (2024)
- [Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding](https://mlsanity.com/paper/2112.11490/) (2021)
- [Safe Deep Reinforcement Learning by Verifying Task-Level Properties](https://mlsanity.com/paper/2302.10030/) (2023)
- [Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving](https://mlsanity.com/paper/2405.18209/) (2024)
- [Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey](https://mlsanity.com/paper/2404.16879/) (2024)
- [Compositional Shielding and Reinforcement Learning for Multi-Agent Systems](https://mlsanity.com/paper/2410.10460/) (2024)
- [Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications](https://mlsanity.com/paper/2306.06808/) (2023)
- [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)
- [Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding](https://mlsanity.com/paper/2405.18180/) (2024)
- [Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL](https://mlsanity.com/paper/2504.15425/) (2025)
- [Model-Free Learning of Safe yet Effective Controllers](https://mlsanity.com/paper/2103.14600/) (2021)
- [Learning a Shield from Catastrophic Action Effects: Never Repeat the Same Mistake](https://mlsanity.com/paper/2202.09516/) (2022)
- [Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey](https://mlsanity.com/paper/2304.12090/) (2023)
- [Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges](https://mlsanity.com/paper/2305.10091/) (2023)
- [Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning](https://mlsanity.com/paper/2311.00063/) (2023)
- [Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism](https://mlsanity.com/paper/2306.14055/) (2023)
- [Safe and Robust Reinforcement Learning: Principles and Practice](https://mlsanity.com/paper/2403.18539/) (2024)
- [A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions](https://mlsanity.com/paper/2508.09128/) (2025)
- [Logic-based Reward Shaping for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2206.08881/) (2022)

## Abstract (arXiv)

Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the learning process.Unfortunately, current MARL methods do not have safety guarantees. Therefore, we present two shielding approaches for safe MARL. In centralized shielding, we synthesize a single shield to monitor all agents' joint actions and correct any unsafe action if necessary. In factored shielding, we synthesize multiple shields based on a factorization of the joint state space observed by all agents; the set of shields monitors agents concurrently and each shield is only responsible for a subset of agents at each step.Experimental results show that both approaches can guarantee the safety of agents during learning without compromising the quality of learned policies; moreover, factored shielding is more scalable in the number of agents than centralized shielding.