EvoJAX: Hardware-Accelerated Neuroevolution

Abstract

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

GECCO 2022. Project website at https://github.com/google/evojax

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Population Based Training of Neural Networks
• L2 Regularization versus Batch and Weight Normalization
• How Does Learning Rate Decay Help Modern Neural Networks?
• Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
• Learning to Predict Without Looking Ahead: World Models Without Forward Prediction