# EvoJAX: Hardware-Accelerated Neuroevolution

arXiv: https://arxiv.org/abs/2202.05008 · HTML: https://mlsanity.com/paper/2202.05008/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2022.

## Built on by (most cited first, 29 of 29)

- [Discovering Evolution Strategies via Meta-Black-Box Optimization](https://mlsanity.com/paper/2211.11260/) (2022)
- [evosax: JAX-based Evolution Strategies](https://mlsanity.com/paper/2212.04180/) (2022)
- [Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization](https://mlsanity.com/paper/2304.03995/) (2023)
- [Evolutionary Reinforcement Learning: A Survey](https://mlsanity.com/paper/2303.04150/) (2023)
- [QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration](https://mlsanity.com/paper/2308.03665/) (2023)
- [JaxPruner: A concise library for sparsity research](https://mlsanity.com/paper/2304.14082/) (2023)
- [Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities](https://mlsanity.com/paper/2501.06572/) (2025)
- [minimax: Efficient Baselines for Autocurricula in JAX](https://mlsanity.com/paper/2311.12716/) (2023)
- [EvoTorch: Scalable Evolutionary Computation in Python](https://mlsanity.com/paper/2302.12600/) (2023)
- [CAX: Cellular Automata Accelerated in JAX](https://mlsanity.com/paper/2410.02651/) (2024)
- [Evolving Populations of Diverse RL Agents with MAP-Elites](https://mlsanity.com/paper/2303.12803/) (2023)
- [Rethinking Population-assisted Off-policy Reinforcement Learning](https://mlsanity.com/paper/2305.02949/) (2023)
- [Evolutionary Optimization of Physics-Informed Neural Networks: Advancing Generalizability by the Baldwin Effect](https://mlsanity.com/paper/2312.03243/) (2023)
- [Scale-PINN: Learning Efficient Physics-Informed Neural Networks Through Sequential Correction](https://mlsanity.com/paper/2602.19475/) (2026)
- [Neuroevolution of Physics-Informed Neural Nets: Benchmark Problems and Comparative Results](https://mlsanity.com/paper/2212.07624/) (2022)
- [NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications](https://mlsanity.com/paper/2311.02394/) (2023)
- [Enabling Population-Level Parallelism in Tree-Based Genetic Programming for GPU Acceleration](https://mlsanity.com/paper/2501.17168/) (2025)
- [Kozax: Flexible and Scalable Genetic Programming in JAX](https://mlsanity.com/paper/2502.03047/) (2025)
- [gfnx: Fast and Scalable Library for Generative Flow Networks in JAX](https://mlsanity.com/paper/2511.16592/) (2025)
- [Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability](https://mlsanity.com/paper/2306.00045/) (2023)
- [Stein Variational Evolution Strategies](https://mlsanity.com/paper/2410.10390/) (2024)
- [Higher-order mutual information reveals synergistic sub-networks for multi-neuron importance](https://mlsanity.com/paper/2211.00416/) (2022)
- [Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces](https://mlsanity.com/paper/2601.01082/) (2026)
- [Curiosity creates Diversity in Policy Search](https://mlsanity.com/paper/2212.03530/) (2022)
- [Evolution of Collective AI Beyond Individual Optimization](https://mlsanity.com/paper/2412.02085/) (2024)
- [Ludax: A GPU-Accelerated Domain Specific Language for Board Games](https://mlsanity.com/paper/2506.22609/) (2025)
- [Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search](https://mlsanity.com/paper/2603.19563/) (2026)
- [FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games](https://mlsanity.com/paper/2607.06514/) (2026)
- [On Scaling Coordinate-Based Neuroevolution: The Quadtree Bottleneck in ES-HyperNEAT](https://mlsanity.com/paper/2608.24480/) (2026)

## Abstract (arXiv)

Evolutionary computation has been shown to be a highly effective method for training neural networks, particularly when employed at scale on CPU clusters. Recent work have also showcased their effectiveness on hardware accelerators, such as GPUs, but so far such demonstrations are tailored for very specific tasks, limiting applicability to other domains. We present EvoJAX, a scalable, general purpose, hardware-accelerated neuroevolution toolkit. Building on top of the JAX library, our toolkit enables neuroevolution algorithms to work with neural networks running in parallel across multiple TPU/GPUs. EvoJAX achieves very high performance by implementing the evolution algorithm, neural network and task all in NumPy, which is compiled just-in-time to run on accelerators. We provide extensible examples of EvoJAX for a wide range of tasks, including supervised learning, reinforcement learning and generative art. Since EvoJAX can find solutions to most of these tasks within minutes on a single accelerator, compared to hours or days when using CPUs, our toolkit can significantly shorten the iteration cycle of evolutionary computation experiments. EvoJAX is available at https://github.com/google/evojax