mlsanityData to 14 Oct 2026

A Review of Safe Reinforcement Learning: Methods, Theory and Applications

arXiv 2205.10330 ↗First posted 20 May 2022cs.AI cs.LGcited by 181

Not on the map. Why?

Cited by 76 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Reinforcement Learning (RL) has achieved tremendous success in many complex decision-making tasks. However, safety concerns are raised during deploying RL in real-world applications, leading to a growing demand for safe RL algorithms, such as in autonomous driving and robotics scenarios. While safe control has a long history, the study of safe RL algorithms is still in the early stages. To establish a good foundation for future safe RL research, in this paper, we provide a review of safe RL from the perspectives of methods, theories, and applications. Firstly, we review the progress of safe RL from five dimensions and come up with five crucial problems for safe RL being deployed in real-world applications, coined as "2H3W". Secondly, we analyze the algorithm and theory progress from the perspectives of answering the "2H3W" problems. Particularly, the sample complexity of safe RL algorithms is reviewed and discussed, followed by an introduction to the applications and benchmarks of safe RL algorithms. Finally, we open the discussion of the challenging problems in safe RL, hoping to inspire future research on this thread. To advance the study of safe RL algorithms, we release an open-sourced repository containing the implementations of major safe RL algorithms at the link: https://github.com/chauncygu/Safe-Reinforcement-Learning-Baselines.git.

Key facts. Cited by 181 papers in the map (data through 14 Oct 2026). Builds on 141 of its 323 references that are in the map. First posted on arXiv 20 May 2022.

Builds on

141 of 323 references.

References · 141

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2015Continuous control with deep reinforcement learningcited by 3,407
  5. 2015Trust Region Policy Optimizationcited by 2,580
  6. 2021Convex optimizationcited by 2,515
  7. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  8. 2016Concrete Problems in AI Safetycited by 1,642
  9. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  10. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  11. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  12. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
38 more
  1. 2017Constrained Policy Optimizationcited by 983
  2. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  3. 2018Learning Dexterous In-Hand Manipulationcited by 687
  4. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  5. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  6. 2017Safe Reinforcement Learning via Shieldingcited by 449
  7. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  8. 2018Reward Constrained Policy Optimizationcited by 417
  9. 2018AI safety via debatecited by 400
  10. 2019Control Barrier Functions: Theory and Applicationscited by 372
  11. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
  12. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  13. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  14. 2015Recent Advances in Convolutional Neural Networkscited by 360
  15. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 337
  16. 2016Cooperative Inverse Reinforcement Learningcited by 300
  17. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
  18. 2021Unsolved Problems in ML Safetycited by 292
  19. 2019Challenges of Real-World Reinforcement Learningcited by 291
  20. 2018The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systemscited by 277
  21. 2018Learning to Drive in a Daycited by 273
  22. 2019DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Correctionscited by 254
  23. 2018Safe Exploration in Continuous Action Spacescited by 247
  24. 2019Batch Policy Learning under Constraintscited by 244
  25. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 225
  26. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  27. 2020Projection-Based Constrained Policy Optimizationcited by 203
  28. 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 186
  29. 2020FACMAC: Factored Multi-Agent Centralised Policy Gradientscited by 178
  30. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  31. 2015Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approachcited by 170
  32. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 164
  33. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
  34. 2018DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skillscited by 163
  35. 2019Constrained Reinforcement Learning Has Zero Duality Gapcited by 151
  36. 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 145
  37. 2020Parrot: Data-Driven Behavioral Priors for Reinforcement Learningcited by 138
  38. 2020Provably Efficient Safe Exploration via Primal-Dual Policy Optimizationcited by 134

50 most cited of 141 All 141 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 48; 2024: 72; 2025: 46; 2026: 8.

181 papers.

Sort:

By area:

  1. 2024PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preferencecited by 261
  2. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  3. 2024ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agentscited by 133
  4. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
  5. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 93
  6. 2023Diffusion Models for Reinforcement Learning: A Surveycited by 91
  7. 2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 80
  8. 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learningcited by 72
  9. 2023Constrained Decision Transformer for Offline Safe Reinforcement Learningcited by 69
  10. 2023Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agentscited by 69
  11. 2024Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Modelcited by 64
  12. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learningcited by 59
38 more
  1. 2023State-wise Safe Reinforcement Learning: A Surveycited by 55
  2. 2024Enhancing LLM Safety via Constrained Direct Preference Optimizationcited by 49
  3. 2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 44
  4. 2022On the Robustness of Safe Reinforcement Learning under Observational Perturbationscited by 38
  5. 2023Iterative Reachability Estimation for Safe Reinforcement Learningcited by 37
  6. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 36
  7. 2023Safe Offline Reinforcement Learning with Real-Time Budget Constraintscited by 28
  8. 2023Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPscited by 28
  9. 2023Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learningcited by 27
  10. 2023A Survey on Physics Informed Reinforcement Learning: Review and Open Problemscited by 24
  11. 2025Offline Goal-conditioned Reinforcement Learning with Quasimetric Representationscited by 24
  12. 2023Causal Reinforcement Learning: A Surveycited by 23
  13. 2023Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraintscited by 21
  14. 2024Doubly Mild Generalization for Offline Reinforcement Learningcited by 21
  15. 2024Diffusion-Reward Adversarial Imitation Learningcited by 20
  16. 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agentscited by 19
  17. 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learningcited by 18
  18. 2024Offline Reinforcement Learning with OOD State Correction and OOD Action Suppressioncited by 17
  19. 2024Hamilton-Jacobi Reachability in Reinforcement Learning: A Surveycited by 16
  20. 2023A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviorscited by 15
  21. 2023Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilitiescited by 15
  22. 2023Learning Shared Safety Constraints from Multi-task Demonstrationscited by 15
  23. 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learningcited by 15
  24. 2024Off-Policy Primal-Dual Safe Reinforcement Learningcited by 14
  25. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  26. 2023Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersectionscited by 12
  27. 2022Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimizationcited by 11
  28. 2024DDM-Lag : A Diffusion-based Decision-making Model for Autonomous Vehicles with Lagrangian Safety Enhancementcited by 11
  29. 2024A Review of Safe Reinforcement Learning Methods for Modern Power Systemscited by 11
  30. 2023SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agentscited by 10
  31. 2023Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learningcited by 10
  32. 2023Gradient Shaping for Multi-Constraint Safe Reinforcement Learningcited by 10
  33. 2024A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligencecited by 10
  34. 2024Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learningcited by 10
  35. 2024Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learningcited by 10
  36. 2024OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learningcited by 10
  37. 2023State-wise Constrained Policy Optimizationcited by 9
  38. 2024Learning from Sparse Offline Datasets via Conservative Density Estimationcited by 9

50 most cited of 181 All 181 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving
  2. 2025A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety
  3. 2025Skill-based Safe Reinforcement Learning with Risk Planning
  4. 2024A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks
  5. 2024Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
  6. 2026Evaluation Metrics for Safe Reinforcement Learning
  7. 2024Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving
  8. 2023Understanding Reinforcement Learning Algorithms: The Progress from Basic Q-learning to Proximal Policy Optimization