CropGym: a Reinforcement Learning Environment for Crop Management

CropGym is a highly configurable Python Gymnasium environment to conduct Reinforcement Learning (RL) research for crop management. CropGym is built around PCSE, a well established python library that includes implementations of a variety of crop simulation models. CropGym follows standard gym conventions and enables daily interactions between an RL agent and a crop model.

Installation

Examples

Use Cases

Citing CropGym

If you use CropGym in your publications, please cite us following this Bibtex entry

@article{cropgym,
  title={Nitrogen management with reinforcement learning and crop growth models},
  volume={2},
  DOI={10.1017/eds.2023.28},
  journal={Environmental Data Science},
  publisher={Cambridge University Press},
  author={Kallenberg, Michiel G.J. and Overweg, Hiske and van Bree, Ron and Athanasiadis, Ioannis N.},
  year={2023},
  pages={e34}
}

Contact

Indices and tables