EvoJAX: A Hardware-accelerated Toolkit for Neuroevolution

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY-SA

Source arXiv

Neural and Evolutionary Computing

EvoJAX: A Hardware-accelerated Toolkit for Neuroevolution

EvoJAX: Hardware-Accelerated Neuroevolution

Evolutionary computation has been shown to be a highly effective method for training neural networks, particularly when employed at scale on a single cluster of processors.

Recent work has 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 topof the jax library, our toolkit enables neuroevolution algorithms to work with neural networks running in parallel across multiple tpu/gpus.

Our toolkit 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.

We believe our toolkit can significantly shorten the iteration time of conducting experiments for researchers working with evolutionary computation.

Authors

Yujin Tang, Yingtao Tian, David Ha

◐ Recommended Follows

◐ Latest Activity