Dragonfly: a modular deep reinforcement learning library

Dragonfly is a deep reinforcement learning library focused on modularity, in order to ease experimentation and developments. It relies on a json serialization that allows to swap building blocks and perform parameter sweep, while minimizing code maintenance. Some of its features are specifically designed for CPU-intensive environments, such as numerical simulations. Its performance on standard agents using common benchmarks compares favorably with the literature.

@article{viquerat2025_2505.03778,
  title={ Dragonfly: a modular deep reinforcement learning library },
  author={ Jonathan Viquerat and Paul Garnier and Amirhossein Bateni and Elie Hachem },
  journal={arXiv preprint arXiv:2505.03778},
  year={ 2025 }
}