mlsanityData to 14 Oct 2026

MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding

arXiv 1910.12639 ↗First posted 25 Oct 2019eess.SY cs.AI cs.MAcited by 20

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks. However, a policy learned in simulation often fails to guarantee even simple safety properties such as obstacle avoidance. To ensure safety, we propose multi-agent model predictive shielding (MAMPS), an algorithm that provably guarantees safety for an arbitrary learned policy. In particular, it operates by using the learned policy as often as possible, but instead uses a backup policy in cases where it cannot guarantee the safety of the learned policy. Using a multi-agent simulation environment, we show how MAMPS can achieve good performance while ensuring safety.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 3; 2023: 1; 2024: 6; 2025: 3; 2026: 1.

20 papers.

Sort:

By area:

  1. 2021Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificatescited by 74
  2. 2021Multi-Agent Constrained Policy Optimisationcited by 35
  3. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 32
  4. 2022Online Shielding for Reinforcement Learningcited by 22
  5. 2022Distributed Reinforcement Learning for Robot Teams: A Reviewcited by 16
  6. 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learningcited by 15
  7. 2021Shielding Atari Games with Bounded Presciencecited by 14
  8. 2022Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarioscited by 13
  9. 2024Compositional Shielding and Reinforcement Learning for Multi-Agent Systemscited by 8
  10. 2025Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARLcited by 6
  11. 2021Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spacescited by 5
  12. 2024A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Taskscited by 5
8 more
  1. 2021Reinforcement Learning with Formal Performance Metrics for Quadcopter Attitude Control under Non-nominal Contextscited by 3
  2. 2024Safe Reinforcement Learning for Power System Control: A Reviewcited by 3
  3. 2024Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learningcited by 1
  4. 2025Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamicscited by 1
  5. 2025Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Reviewcited by 1
  6. 2021Safe Learning of Uncertain Environmentscited by 0
  7. 2023Shared Information-Based Safe And Efficient Behavior Planning For Connected Autonomous Vehiclescited by 0
  8. 2026Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filteringcited by 0