garage - A toolkit for reproducible reinforcement learning research
A toolkit and library for developing, evaluating, and reproducing reinforcement learning algorithms.
What is garage - A toolkit for reproducible reinforcement learning research?
Garage is an open-source toolkit and accompanying library for developing, evaluating, and reproducing reinforcement learning algorithms. It provides a wide range of modular components like neural network models, samplers, and replay buffers, alongside implementations of state-of-the-art algorithms, to streamline the RL research process.
Reinforcement learning researchers and practitioners who need a reliable, reproducible, and well-tested framework for experimenting with and benchmarking RL algorithms.
Developers choose garage for its strong focus on reproducibility, comprehensive testing suite, support for multiple deep learning frameworks (PyTorch and TensorFlow), and its collection of pre-built, high-performance algorithm implementations that are kept up-to-date.
Overview
A toolkit for reproducible reinforcement learning research.
Use Cases
Best For
- Implementing and benchmarking new reinforcement learning research ideas.
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
