# CRAX: Fast Safe Reinforcement Learning Benchmarking

arXiv: https://arxiv.org/abs/2606.20376 · HTML: https://mlsanity.com/paper/2606.20376/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 31 of its 53 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [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)
- [Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark](https://mlsanity.com/paper/2310.12567/) (2023)
- [CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee](https://mlsanity.com/paper/2011.05869/) (2020)
- [Learning to Walk in the Real World with Minimal Human Effort](https://mlsanity.com/paper/2002.08550/) (2020)
- [AI Safety Gridworlds](https://mlsanity.com/paper/1711.09883/) (2017)
- [Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning](https://mlsanity.com/paper/2402.16801/) (2024)
- [MuJoCo Playground](https://mlsanity.com/paper/2502.08844/) (2025)
- [Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation](https://mlsanity.com/paper/2202.06558/) (2022)
- [Penalized Proximal Policy Optimization for Safe Reinforcement Learning](https://mlsanity.com/paper/2205.11814/) (2022)
- [VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning](https://mlsanity.com/paper/2207.03530/) (2022)
- [JaxMARL: Multi-Agent RL Environments and Algorithms in JAX](https://mlsanity.com/paper/2311.10090/) (2023)
- [Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX](https://mlsanity.com/paper/2306.09884/) (2023)
- [XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX](https://mlsanity.com/paper/2312.12044/) (2023)
- [safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics](https://mlsanity.com/paper/2109.06325/) (2021)
- [A Survey of Constraint Formulations in Safe Reinforcement Learning](https://mlsanity.com/paper/2402.02025/) (2024)
- [Direct Behavior Specification via Constrained Reinforcement Learning](https://mlsanity.com/paper/2112.12228/) (2021)
- [Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark](https://mlsanity.com/paper/2103.15332/) (2021)
- [A Clean Slate for Offline Reinforcement Learning](https://mlsanity.com/paper/2504.11453/) (2025)
- [HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents](https://mlsanity.com/paper/2503.08241/) (2025)

## Built on by (most cited first, 2 of 2)

- [Evaluation Metrics for Safe Reinforcement Learning](https://mlsanity.com/paper/2609.15315/) (2026)
- [Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning](https://mlsanity.com/paper/2610.05569/) (2026)

## Abstract (arXiv)

Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have been central to progress in RL, existing 3D physics-based safety benchmarks remain computationally slow, limiting large-scale experimentation and rapid prototyping. To address this gap, we propose CRAX (Constrained RL Accelerated with JAX). Built on top of the MuJoCo XLA (MJX) physics engine, CRAX leverages vectorized operations and hardware acceleration, yielding up to 200x faster training over comparable CPU-based safety benchmarks. The benchmark features eight tasks spanning three difficulty levels and multiple agent morphologies. Evaluating seven popular safe RL methods, we find that none dominates across tasks, and that learning safe policies from pixels remains largely unsolved.