mlsanityData to 13 Oct 2026

Compositional Shielding and Reinforcement Learning for Multi-Agent Systems

arXiv 2410.10460 ↗First posted 14 Oct 2024cs.LO cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning has emerged as a powerful tool for obtaining high-performance policies. However, the safety of these policies has been a long-standing issue. One promising paradigm to guarantee safety is a shield, which shields a policy from making unsafe actions. However, computing a shield scales exponentially in the number of state variables. This is a particular concern in multi-agent systems with many agents. In this work, we propose a novel approach for multi-agent shielding. We address scalability by computing individual shields for each agent. The challenge is that typical safety specifications are global properties, but the shields of individual agents only ensure local properties. Our key to overcome this challenge is to apply assume-guarantee reasoning. Specifically, we present a sound proof rule that decomposes a (global, complex) safety specification into (local, simple) obligations for the shields of the individual agents. Moreover, we show that applying the shields during reinforcement learning significantly improves the quality of the policies obtained for a given training budget. We demonstrate the effectiveness and scalability of our multi-agent shielding framework in two case studies, reducing the computation time from hours to seconds and achieving fast learning convergence.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Builds on 12 of its 33 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

12 of 33 references.

References · 12

  1. 2017Proximal Policy Optimization Algorithmscited by 14,592
  2. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 910
  3. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  4. 2017Safe Reinforcement Learning via Shieldingcited by 431
  5. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 60
  6. 2023Safe Reinforcement Learning via Probabilistic Logic Shieldscited by 41
  7. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 31
  8. 2019MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shieldingcited by 17
  9. 2013What is Decidable about Partially Observable Markov Decision Processes with ω-Regular Objectivescited by 14
  10. 2022Correct-by-Construction Runtime Enforcement in AI -- A Surveycited by 10
  11. 2023Shielded Reinforcement Learning for Hybrid Systemscited by 8
  12. 2024Efficient Shield Synthesis via State-Space Transformationcited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Shields to Guarantee Probabilistic Safety in MDPscited by 2
  2. 2026Easy-to-Use Shielding for Reinforcement Learningcited by 1
  3. 2026COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Managementcited by 0
  4. 2026Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learningcited by 0
  5. 2026Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learningcited by 0
  6. 2026Decentralized Safe Multi-Agent Reinforcement Learning via Predictive Shieldingcited by 0
  7. 2026VACS: Value-Aligned Compositional Shielding for Multi-Agent Reasoningcited by 0