mlsanityData to 14 Oct 2026

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

arXiv 2310.12567 ↗First posted 19 Oct 2023cs.AI cs.LGcited by 143

Not on the map. Why?

Cited by 91 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input. Additionally, we offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms. This comprehensive library can serve as a validation tool for the research community. By introducing this benchmark, we aim to facilitate the evaluation and comparison of safety performance, thus fostering the development of reinforcement learning for safer, more reliable, and responsible real-world applications. The website of this project can be accessed at https://sites.google.com/view/safety-gymnasium.

Key facts. Cited by 143 papers in the map (data through 14 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 19 Oct 2023.

Builds on

24 of 45 references.

References · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  5. 2017Constrained Policy Optimizationcited by 983
  6. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  7. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  8. 2020dm_control: Software and Tasks for Continuous Controlcited by 375
  9. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
  10. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 290
  11. 2020Projection-Based Constrained Policy Optimizationcited by 203
  12. 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 186
12 more
  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 181
  2. 2022Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learningcited by 119
  3. 2017AI Safety Gridworldscited by 110
  4. 2022SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehiclescited by 66
  5. 2022Constrained Update Projection Approach to Safe Policy Optimizationcited by 58
  6. 2022Constrained Policy Optimization via Bayesian World Modelscited by 57
  7. 2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 50
  8. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 36
  9. 2021Multi-Agent Constrained Policy Optimisationcited by 35
  10. 2022Evaluating Model-free Reinforcement Learning toward Safety-critical Taskscited by 22
  11. 2022CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learningcited by 20
  12. 2021Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learningcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 34; 2025: 45; 2026: 62.

143 papers.

Sort:

By area:

  1. 2024PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preferencecited by 261
  2. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  3. 2023SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Modelscited by 76
  4. 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learningcited by 72
  5. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 35
  6. 2024Constrained Reinforcement Learning with Smoothed Log Barrier Functioncited by 15
  7. 2025Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularizationcited by 14
  8. 2025A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safetycited by 13
  9. 2025Probabilistic Shielding for Safe Reinforcement Learningcited by 12
  10. 2024LTL-Constrained Policy Optimization with Cycle Experience Replaycited by 11
  11. 2024A Review of Safe Reinforcement Learning Methods for Modern Power Systemscited by 11
  12. 2024Embedding Safety into RL: A New Take on Trust Region Methodscited by 10
38 more
  1. 2025Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspectivecited by 10
  2. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 8
  3. 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learningcited by 8
  4. 2024Safe Multi-agent Reinforcement Learning with Natural Language Constraintscited by 7
  5. 2024Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learningcited by 7
  6. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  7. 2025PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learningcited by 7
  8. 2024Safe Reinforcement Learning in Black-Box Environments via Adaptive Shieldingcited by 6
  9. 2024Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibriumcited by 6
  10. 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agentscited by 6
  11. 2024Improving Policy Optimization via varepsilon-Retraincited by 5
  12. 2024Safety through feedback in Constrained RLcited by 5
  13. 2025Learning Conservative Neural Control Barrier Functions from Offline Datacited by 5
  14. 2025Designing Latent Safety Filters using Pre-Trained Vision Modelscited by 5
  15. 2025V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functionscited by 5
  16. 2026How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?cited by 5
  17. 2024Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimizationcited by 4
  18. 2025A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functionscited by 4
  19. 2025World Model Robustness via Surprise Recognitioncited by 4
  20. 2026Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policiescited by 4
  21. 2024Feasibility Consistent Representation Learning for Safe Reinforcement Learningcited by 3
  22. 2024Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approachcited by 3
  23. 2024FOSP: Fine-tuning Offline Safe Policy through World Modelscited by 3
  24. 2024Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuningcited by 3
  25. 2024Towards Fast Safe Online Reinforcement Learning via Policy Finetuningcited by 3
  26. 2024Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimationcited by 3
  27. 2025Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigationcited by 3
  28. 2025Central Path Proximal Policy Optimizationcited by 3
  29. 2025Optimistic Exploration for Risk-Averse Constrained Reinforcement Learningcited by 3
  30. 2025Safe In-Context Reinforcement Learningcited by 3
  31. 2025Provably Optimal Reinforcement Learning under Safety Filteringcited by 3
  32. 2026Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Controlcited by 3
  33. 2026Improving Feasibility via Fast Autoencoder-Based Projectionscited by 3
  34. 2024DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learningcited by 2
  35. 2024RobocupGym: A challenging continuous control benchmark in Robocupcited by 2
  36. 2024Vision-driven UAV River Following: Benchmarking with Safe Reinforcement Learningcited by 2
  37. 2025On the Design of Safe Continual RL Methods for Control of Nonlinear Systemscited by 2
  38. 2025A2Perf: Real-World Autonomous Agents Benchmarkcited by 2

50 most cited of 143 All 143 (JSON)