mlsanityData to 14 Oct 2026

Safety-Constrained Reinforcement Learning for MDPs

arXiv 1510.05880 ↗First posted 20 Oct 2015cs.SE cs.SY eess.SYcited by 33

Not on the map. Why?

Abstract (arXiv)

We consider controller synthesis for stochastic and partially unknown environments in which safety is essential. Specifically, we abstract the problem as a Markov decision process in which the expected performance is measured using a cost function that is unknown prior to run-time exploration of the state space. Standard learning approaches synthesize cost-optimal strategies without guaranteeing safety properties. To remedy this, we first compute safe, permissive strategies. Then, exploration is constrained to these strategies and thereby meets the imposed safety requirements. Exploiting an iterative learning procedure, the resulting policy is safety-constrained and optimal. We show correctness and completeness of the method and discuss the use of several heuristics to increase its scalability. Finally, we demonstrate the applicability by means of a prototype implementation.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Oct 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 5; 2023: 5; 2024: 10; 2025: 2; 2026: 6.

33 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 181
  2. 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 96
  3. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  4. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 56
  5. 2022Safe Reinforcement Learning for Legged Locomotioncited by 35
  6. 2022COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checkingcited by 19
  7. 2021Reinforcement Learning with Almost Sure Constraintscited by 11
  8. 2021Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report)cited by 9
  9. 2024Thresholded Lexicographic Ordered Multiobjective Reinforcement Learningcited by 8
  10. 2024Certifiably Robust Policies for Uncertain Parametric Environmentscited by 7
  11. 2023Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Surveycited by 5
  12. 2022Shielding in Resource-Constrained Goal POMDPscited by 4
21 more
  1. 2023Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penaltiescited by 4
  2. 2024Personalized Reinforcement Learning with a Budget of Policiescited by 4
  3. 2023The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedbackcited by 3
  4. 2021Learning to Act Safely with Limited Exposure and Almost Sure Certaintycited by 2
  5. 2024Shielded Deep Reinforcement Learning for Complex Spacecraft Taskingcited by 2
  6. 2024Federated Reinforcement Learning with Constraint Heterogeneitycited by 2
  7. 2024Reinforcement Learning for Sustainable Energy: A Surveycited by 2
  8. 2025Compositional shield synthesis for safe reinforcement learning in partial observabilitycited by 2
  9. 2026Robust Probabilistic Shielding for Safe Offline Reinforcement Learningcited by 2
  10. 2026Shields to Guarantee Probabilistic Safety in MDPscited by 2
  11. 2024Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learningcited by 1
  12. 2026Robust Parameter Learning for Uncertain MDPscited by 1
  13. 2021Safe Learning of Uncertain Environmentscited by 0
  14. 2023Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guaranteescited by 0
  15. 2023Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effectscited by 0
  16. 2024Safe Online Convex Optimization with Multi-Point Feedbackcited by 0
  17. 2024A Safety-Oriented Self-Learning Algorithm for Autonomous Driving: Evolution Starting from a Basic Modelcited by 0
  18. 2025Constrained Reinforcement Learning for the Dynamic Inventory Routing Problem under Stochastic Supply and Demandcited by 0
  19. 2026COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Managementcited by 0
  20. 2026COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenancecited by 0
  21. 2026SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventionscited by 0