mlsanityData to 7 Oct 2026

Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics

arXiv 1910.10885 ↗First posted 24 Oct 2019eess.SY cs.LG cs.ROcited by 45

Not on the map. Why?

Abstract (arXiv)

This paper proposes a framework for safe reinforcement learning that can handle stochastic nonlinear dynamical systems. We focus on the setting where the nominal dynamics are known, and are subject to additive stochastic disturbances with known distribution. Our goal is to ensure the safety of a control policy trained using reinforcement learning, e.g., in a simulated environment. We build on the idea of model predictive shielding (MPS), where a backup controller is used to override the learned policy as needed to ensure safety. The key challenge is how to compute a backup policy in the context of stochastic dynamics. We propose to use a tube-based robust NMPC controller as the backup controller. We estimate the tubes using sampled trajectories, leveraging ideas from statistical learning theory to obtain high-probability guarantees. We empirically demonstrate that our approach can ensure safety in stochastic systems, including cart-pole and a non-holonomic particle with random obstacles.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 5; 2023: 9; 2024: 8; 2025: 9; 2026: 4.

45 papers.

Sort:

By area:

  1. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 77
  2. 2022Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environmentscited by 54
  3. 2021Safe Reinforcement Learning Using Advantage-Based Interventioncited by 45
  4. 2021Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learningcited by 43
  5. 2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 42
  6. 2023Safe Reinforcement Learning via Probabilistic Logic Shieldscited by 41
  7. 2022Learning Control Policies for Stochastic Systems with Reach-avoid Guaranteescited by 21
  8. 2022Online Shielding for Reinforcement Learningcited by 19
  9. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 19
  10. 2021Shielding Atari Games with Bounded Presciencecited by 14
  11. 2021Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learningcited by 13
  12. 2023Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approachcited by 13
33 more
  1. 2021SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interactioncited by 12
  2. 2022Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarioscited by 12
  3. 2023Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learningcited by 11
  4. 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learningcited by 11
  5. 2021Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shieldingcited by 9
  6. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functionscited by 8
  7. 2021MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerancecited by 7
  8. 2023Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approachcited by 7
  9. 2023Risk-Aware Reinforcement Learning through Optimal Transport Theorycited by 7
  10. 2021Scalable Synthesis of Verified Controllers in Deep Reinforcement Learningcited by 5
  11. 2021Uniformly Conservative Exploration in Reinforcement Learningcited by 3
  12. 2024Learning safety critics via a non-contractive binary bellman operatorcited by 3
  13. 2024Learning Control Barrier Functions and their application in Reinforcement Learning: A Surveycited by 3
  14. 2023Control invariant set enhanced safe reinforcement learning: improved sampling efficiency, guaranteed stability and robustnesscited by 2
  15. 2021Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-Interactioncited by 1
  16. 2023Control invariant set enhanced reinforcement learning for process control: improved sampling efficiency and guaranteed stabilitycited by 1
  17. 2024Who Plays First? Optimizing the Order of Play in Stackelberg Games with Many Robotscited by 1
  18. 2024Myopically Verifiable Probabilistic Certificates for Safe Control and Learningcited by 1
  19. 2025Accelerated Learning with Linear Temporal Logic using Differentiable Simulationcited by 1
  20. 2026Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Modelscited by 1
  21. 2022Safe Control and Learning Using Generalized Action Governorcited by 0
  22. 2023Shared Information-Based Safe And Efficient Behavior Planning For Connected Autonomous Vehiclescited by 0
  23. 2024Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learningcited by 0
  24. 2024Collaborative State Fusion in Partially Known Multi-agent Environmentscited by 0
  25. 2025Risk-Aware Safe Reinforcement Learning for Control of Stochastic Linear Systemscited by 0
  26. 2025Guided by Guardrails: Control Barrier Functions as Safety Instructors for Robotic Learningcited by 0
  27. 2025Efficient Dynamic Shielding for Parametric Safety Specificationscited by 0
  28. 2025Hierarchical Reinforcement Learning with Low-Level MPC for Multi-Agent Controlcited by 0
  29. 2025How Well Do Latent World Models Understand Partially Observable Safety Constraints?cited by 0
  30. 2025Approximating Safety Feedback Without a Safety Oracle via Model Predictive Controlcited by 0
  31. 2026Safe-Support Q-Learning: Learning without Unsafe Explorationcited by 0
  32. 2026Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systemscited by 0
  33. 2026Decentralized Safe Multi-Agent Reinforcement Learning via Predictive Shieldingcited by 0