mlsanityData to 7 Oct 2026

Safe Reinforcement Learning in Constrained Markov Decision Processes

arXiv 2008.06626 ↗First posted 15 Aug 2020cs.LG cs.AI cs.ROcited by 109

Not on the map. Why?

Abstract (arXiv)

Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision processes under unknown safety constraints. Specifically, we take a stepwise approach for optimizing safety and cumulative reward. In our method, the agent first learns safety constraints by expanding the safe region, and then optimizes the cumulative reward in the certified safe region. We provide theoretical guarantees on both the satisfaction of the safety constraint and the near-optimality of the cumulative reward under proper regularity assumptions. In our experiments, we demonstrate the effectiveness of SNO-MDP through two experiments: one uses a synthetic data in a new, openly-available environment named GP-SAFETY-GYM, and the other simulates Mars surface exploration by using real observation data.

Key facts. Cited by 109 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 14; 2023: 22; 2024: 24; 2025: 16; 2026: 23.

109 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2024Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Modelcited by 62
  3. 2023State-wise Safe Reinforcement Learning: A Surveycited by 48
  4. 2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 42
  5. 2022Near-Optimal Sample Complexity Bounds for Constrained MDPscited by 36
  6. 2021Context-Aware Safe Reinforcement Learning for Non-Stationary Environmentscited by 33
  7. 2021Safe Reinforcement Learning with Linear Function Approximationcited by 33
  8. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  9. 2023Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithmscited by 27
  10. 2021Safe Pontryagin Differentiable Programmingcited by 25
  11. 2024ActSafe: Active Exploration with Safety Constraints for Reinforcement Learningcited by 22
  12. 2023Survival Instinct in Offline Reinforcement Learningcited by 20
38 more
  1. 2025Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Drivingcited by 19
  2. 2022Evaluating Model-free Reinforcement Learning toward Safety-critical Taskscited by 18
  3. 2024Distributionally Robust Constrained Reinforcement Learning under Strong Dualitycited by 15
  4. 2022Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimizationcited by 14
  5. 2021Safe Exploration by Solving Early Terminated MDPcited by 13
  6. 2022Safe Linear Bandits over Unknown Polytopescited by 13
  7. 2023Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learningcited by 13
  8. 2021Lyapunov Barrier Policy Optimizationcited by 12
  9. 2026BAGEN: Are LLM Agents Budget-Aware?cited by 12
  10. 2022Near-Optimal Multi-Agent Learning for Safe Coverage Controlcited by 11
  11. 2023Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learningcited by 11
  12. 2021Safe Policy Optimization with Local Generalized Linear Function Approximationscited by 10
  13. 2023Provably Safe Reinforcement Learning with Step-wise Violation Constraintscited by 10
  14. 2023Directional Optimism for Safe Linear Banditscited by 8
  15. 2022Provable Safe Reinforcement Learning with Binary Feedbackcited by 7
  16. 2023Gradient Shaping for Multi-Constraint Safe Reinforcement Learningcited by 7
  17. 2024Thresholded Lexicographic Ordered Multiobjective Reinforcement Learningcited by 7
  18. 2022SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisitioncited by 6
  19. 2022SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Criticscited by 6
  20. 2022Risk Verification of Stochastic Systems with Neural Network Controllerscited by 6
  21. 2023Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Ratecited by 6
  22. 2024Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guaranteecited by 6
  23. 2026Safe Exploration via Policy Priorscited by 6
  24. 2023Fairness and Sequential Decision Making: Limits, Lessons, and Opportunitiescited by 5
  25. 2023Reduced Policy Optimization for Continuous Control with Hard Constraintscited by 5
  26. 2024Safe Reinforcement Learning for Constrained Markov Decision Processes with Stochastic Stopping Timecited by 5
  27. 2024Safety through feedback in Constrained RLcited by 5
  28. 2024Efficient Policy Evaluation with Safety Constraint for Reinforcement Learningcited by 5
  29. 2023Safe Reinforcement Learning with Dead-Ends Avoidance and Recoverycited by 4
  30. 2024Long-term Safe Reinforcement Learning with Binary Feedbackcited by 4
  31. 2024Confident Natural Policy Gradient for Local Planning in qπ-realizable Constrained MDPscited by 4
  32. 2025Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategiescited by 4
  33. 2025Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Dualitycited by 4
  34. 2021Learning to Be Cautiouscited by 3
  35. 2023Provable Reset-free Reinforcement Learning by No-Regret Reductioncited by 3
  36. 2023Physical Deep Reinforcement Learning Towards Safety Guaranteecited by 3
  37. 2024Feasibility Consistent Representation Learning for Safe Reinforcement Learningcited by 3
  38. 2024Flipping-based Policy for Chance-Constrained Markov Decision Processescited by 3

50 most cited of 109 All 109 (JSON)