# Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

arXiv: https://arxiv.org/abs/2310.12567 · HTML: https://mlsanity.com/paper/2310.12567/

## 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 (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Responsive Safety in Reinforcement Learning by PID Lagrangian Methods](https://mlsanity.com/paper/2007.03964/) (2020)
- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021)
- [Projection-Based Constrained Policy Optimization](https://mlsanity.com/paper/2010.03152/) (2020)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [A Review of Safe Reinforcement Learning: Methods, Theory and Applications](https://mlsanity.com/paper/2205.10330/) (2022)
- [Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning](https://mlsanity.com/paper/2206.08686/) (2022)
- [AI Safety Gridworlds](https://mlsanity.com/paper/1711.09883/) (2017)
- [SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles](https://mlsanity.com/paper/2206.09682/) (2022)
- [Constrained Update Projection Approach to Safe Policy Optimization](https://mlsanity.com/paper/2209.07089/) (2022)
- [Constrained Policy Optimization via Bayesian World Models](https://mlsanity.com/paper/2201.09802/) (2022)
- [safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics](https://mlsanity.com/paper/2109.06325/) (2021)
- [Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability](https://mlsanity.com/paper/2209.08025/) (2022)
- [Multi-Agent Constrained Policy Optimisation](https://mlsanity.com/paper/2110.02793/) (2021)
- [Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks](https://mlsanity.com/paper/2212.05727/) (2022)
- [CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning](https://mlsanity.com/paper/2202.07565/) (2022)
- [Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning](https://mlsanity.com/paper/2112.07701/) (2021)

## Built on by (most cited first, 30 of 143)

- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond](https://mlsanity.com/paper/2405.03520/) (2024)
- [SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models](https://mlsanity.com/paper/2311.08370/) (2023)
- [SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning](https://mlsanity.com/paper/2503.03480/) (2025)
- [A Survey of Embodied Learning for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2408.11537/) (2024)
- [Constrained Reinforcement Learning with Smoothed Log Barrier Function](https://mlsanity.com/paper/2403.14508/) (2024)
- [Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization](https://mlsanity.com/paper/2503.18130/) (2025)
- [A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety](https://mlsanity.com/paper/2505.17342/) (2025)
- [Probabilistic Shielding for Safe Reinforcement Learning](https://mlsanity.com/paper/2503.07671/) (2025)
- [LTL-Constrained Policy Optimization with Cycle Experience Replay](https://mlsanity.com/paper/2404.11578/) (2024)
- [A Review of Safe Reinforcement Learning Methods for Modern Power Systems](https://mlsanity.com/paper/2407.00304/) (2024)
- [Embedding Safety into RL: A New Take on Trust Region Methods](https://mlsanity.com/paper/2411.02957/) (2024)
- [Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective](https://mlsanity.com/paper/2501.03562/) (2025)
- [State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning](https://mlsanity.com/paper/2503.20613/) (2025)
- [One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2508.01561/) (2025)
- [Safe Multi-agent Reinforcement Learning with Natural Language Constraints](https://mlsanity.com/paper/2405.20018/) (2024)
- [Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning](https://mlsanity.com/paper/2412.08794/) (2024)
- [Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks](https://mlsanity.com/paper/2503.20844/) (2025)
- [PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2508.02159/) (2025)
- [Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding](https://mlsanity.com/paper/2405.18180/) (2024)
- [Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium](https://mlsanity.com/paper/2411.15036/) (2024)
- [HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents](https://mlsanity.com/paper/2503.08241/) (2025)
- [Improving Policy Optimization via varepsilon-Retrain](https://mlsanity.com/paper/2406.08315/) (2024)
- [Safety through feedback in Constrained RL](https://mlsanity.com/paper/2406.19626/) (2024)
- [Learning Conservative Neural Control Barrier Functions from Offline Data](https://mlsanity.com/paper/2505.00908/) (2025)
- [Designing Latent Safety Filters using Pre-Trained Vision Models](https://mlsanity.com/paper/2509.14758/) (2025)
- [V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions](https://mlsanity.com/paper/2512.10822/) (2025)
- [How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?](https://mlsanity.com/paper/2602.02924/) (2026)
- [Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization](https://mlsanity.com/paper/2402.15197/) (2024)
- [A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions](https://mlsanity.com/paper/2508.09128/) (2025)

## 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.