EvoTorch: Scalable Evolutionary Computation in Python
This provides a tool for researchers and practitioners in AI, robotics, and optimization to handle modern computational demands, though it is incremental as it builds on existing frameworks.
The authors tackled the need for scalable and practical evolutionary algorithm implementations by developing EvoTorch, a Python library that supports high-dimensional optimization with GPU and parallelization capabilities, built on PyTorch for seamless integration.
Evolutionary computation is an important component within various fields such as artificial intelligence research, reinforcement learning, robotics, industrial automation and/or optimization, engineering design, etc. Considering the increasing computational demands and the dimensionalities of modern optimization problems, the requirement for scalable, re-usable, and practical evolutionary algorithm implementations has been growing. To address this requirement, we present EvoTorch: an evolutionary computation library designed to work with high-dimensional optimization problems, with GPU support and with high parallelization capabilities. EvoTorch is based on and seamlessly works with the PyTorch library, and therefore, allows the users to define their optimization problems using a well-known API.