mlsanityData to 7 Oct 2026

Robust Shielding for Safe Reinforcement Learning

arXiv 2606.00270 ↗First posted 29 May 2026cs.AI cs.LG cs.LOcited by 2

Not on the map. Why?

Abstract (arXiv)

Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs). However, existing shielding techniques typically assume knowledge of the safety-relevant transition dynamics - a requirement that is seldom met in practice. To address this limitation, we introduce a novel shielding framework for robust MDPs (RMDPs), i.e., MDPs with sets of transition probabilities. We define safety as the satisfaction of a linear temporal logic (LTL) formula with a certain threshold probability under the worst-case transition probabilities of the RMDP. We prove that our shielding framework is both sound and optimal for the RMDP: every policy admissible by the shield is safe, and conversely, every safe RMDP policy is admissible by the shield. We combine our approach with existing sampling methods for learning transition probabilities of MDPs with probably approximately correct (PAC) guarantees. This combination enables the construction of shields for MDPs that, with high confidence, guarantee safety while remaining minimally restrictive. Our experiments show that our shields for learned RMDPs guarantee safety in unknown MDPs while recovering strong expected return as the number of samples increases.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 31 of its 51 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

31 of 51 references.

References · 31

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  3. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  4. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  5. 2017Safe Reinforcement Learning via Shieldingcited by 427
  6. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
  7. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  8. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
  9. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 302
  10. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
  11. 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 140
  12. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 60
19 more
  1. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 49
  2. 2023Safe Reinforcement Learning via Probabilistic Logic Shieldscited by 41
  3. 2021DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learningcited by 34
  4. 2020Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertaintycited by 23
  5. 2022Online Shielding for Reinforcement Learningcited by 19
  6. 2024Robust Markov Decision Processes: A Place Where AI and Formal Methods Meetcited by 18
  7. 2024Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaptioncited by 17
  8. 2022Robust Anytime Learning of Markov Decision Processescited by 16
  9. 2023Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractionscited by 16
  10. 2025Probabilistic Shielding for Safe Reinforcement Learningcited by 12
  11. 2015Faster Statistical Model Checking for Unbounded Temporal Propertiescited by 9
  12. 2023Decision-Making Under Uncertainty: Beyond Probabilitiescited by 8
  13. 2024Safe Reinforcement Learning in Black-Box Environments via Adaptive Shieldingcited by 6
  14. 2024Certifiably Robust Policies for Uncertain Parametric Environmentscited by 6
  15. 2025Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guaranteescited by 6
  16. 2024Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environmentscited by 5
  17. 2024Learning-Based Shielding for Safe Autonomy under Unknown Dynamicscited by 3
  18. 2025Data-Driven Abstraction and Synthesis for Stochastic Systems with Unknown Dynamicscited by 1
  19. 2025Optimization-Based Robust Permissive Synthesis for Interval MDPscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learningcited by 0
  2. 2026Protected Cores Are Not Enough: Certifying AI-Proposed Revisions of Temporal Specificationscited by 0