mlsanityData to 7 Oct 2026

Safe Multi-Agent Reinforcement Learning via Shielding

arXiv 2101.11196 ↗First posted 27 Jan 2021cs.LG cs.FLcited by 60

Not on the map. Why?

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.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 9 of its 25 references that are in the map. First posted on arXiv 27 Jan 2021.

Builds on

9 of 25 references.

References · 9

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  2. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  3. 2017Safe Reinforcement Learning via Shieldingcited by 427
  4. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 301
  5. 2018A Survey and Critique of Multiagent Deep Reinforcement Learningcited by 173
  6. 2018Omega-Regular Objectives in Model-Free Reinforcement Learningcited by 74
  7. 2019Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learningcited by 74
  8. 2020Cautious Reinforcement Learning with Logical Constraintscited by 44
  9. 2018CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learningcited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 15; 2024: 12; 2025: 13; 2026: 9.

60 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 30
  3. 2022Learning Control Policies for Stochastic Systems with Reach-avoid Guaranteescited by 21
  4. 2022Online Shielding for Reinforcement Learningcited by 19
  5. 2023Compositional Policy Learning in Stochastic Control Systems with Formal Guaranteescited by 12
  6. 2025A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safetycited by 12
  7. 2023Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learningcited by 11
  8. 2025Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advancescited by 11
  9. 2022Correct-by-Construction Runtime Enforcement in AI -- A Surveycited by 10
  10. 2024Independent Learning in Constrained Markov Potential Gamescited by 10
  11. 2021Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shieldingcited by 9
  12. 2023Safe Deep Reinforcement Learning by Verifying Task-Level Propertiescited by 9
38 more
  1. 2023SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agentscited by 9
  2. 2024Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Drivingcited by 9
  3. 2023Provably Learning Nash Policies in Constrained Markov Potential Gamescited by 7
  4. 2024Safe Multi-agent Reinforcement Learning with Natural Language Constraintscited by 7
  5. 2024Compositional Shielding and Reinforcement Learning for Multi-Agent Systemscited by 7
  6. 2023Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specificationscited by 6
  7. 2024Safe Reinforcement Learning in Black-Box Environments via Adaptive Shieldingcited by 6
  8. 2021Model-Free Learning of Safe yet Effective Controllerscited by 5
  9. 2022Learning a Shield from Catastrophic Action Effects: Never Repeat the Same Mistakecited by 5
  10. 2023Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Surveycited by 5
  11. 2023Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challengescited by 5
  12. 2024Safe and Robust Reinforcement Learning: Principles and Practicecited by 4
  13. 2025Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARLcited by 4
  14. 2022Logic-based Reward Shaping for Multi-Agent Reinforcement Learningcited by 3
  15. 2023Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanismcited by 3
  16. 2023Safety Shielding under Delayed Observationcited by 3
  17. 2023Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learningcited by 3
  18. 2024Learning Control Barrier Functions and their application in Reinforcement Learning: A Surveycited by 3
  19. 2025The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomycited by 3
  20. 2022SAFER: Safe Collision Avoidance using Focused and Efficient Trajectory Search with Reinforcement Learningcited by 2
  21. 2023Approximate Shielding of Atari Agents for Safe Explorationcited by 2
  22. 2023Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learningcited by 2
  23. 2025HypRL: Reinforcement Learning of Control Policies for Hyperpropertiescited by 2
  24. 2025Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Surveycited by 2
  25. 2026Shields to Guarantee Probabilistic Safety in MDPscited by 2
  26. 2026Robust Shielding for Safe Reinforcement Learningcited by 2
  27. 2026TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learningcited by 2
  28. 2022Resilient robot teams: a review integrating decentralised control, change-detection, and learningcited by 1
  29. 2024Anytime-Constrained Equilibria in Polynomial Timecited by 1
  30. 2024Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learningcited by 1
  31. 2025Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamicscited by 1
  32. 2022Data Valuation for Offline Reinforcement Learningcited by 0
  33. 2023Safe Multi-agent Learning via Trapping Regionscited by 0
  34. 2023Experiments with Detecting and Mitigating AI Deceptioncited by 0
  35. 2024Safety-Aware Multi-Agent Learning for Dynamic Network Bridgingcited by 0
  36. 2024Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learningcited by 0
  37. 2025Scalable Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantee: A Constrained Mean-Field Reinforcement Learning Approachcited by 0
  38. 2025Follow the STARs: Dynamic ω-Regular Shielding of Learned Policiescited by 0

50 most cited of 60 All 60 (JSON)