d3rlpy
A Python library for offline deep reinforcement learning with support for state-of-the-art algorithms and user-friendly APIs.
What is d3rlpy?
d3rlpy is an offline deep reinforcement learning library that enables training RL agents using pre-existing datasets without requiring online environment interaction. It solves the problem of applying RL in domains where real-time interaction is costly or impossible, such as robotics and healthcare. The library supports both offline and online RL algorithms through a unified API.
Machine learning practitioners and researchers working on reinforcement learning projects, particularly those focused on offline RL, robotics, or data-driven control systems.
Developers choose d3rlpy for its comprehensive support of state-of-the-art offline RL algorithms, user-friendly API that abstracts deep learning complexities, and unique features like distributional Q functions and distributed training capabilities.
Overview
An offline deep reinforcement learning library
Use Cases
Best For
- Training RL agents with pre-collected datasets in robotics applications
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.
