CropGym: a Reinforcement Learning Environment for Crop Management

---

Abstract

Nitrogen fertilizers have a detrimental effect on the environment, which can be reduced by optimizing fertilizer management strategies. We implement an OpenAI Gym environment where a reinforcement learning agent can learn fertilization management policies using process-based crop growth models and identify policies with reduced environmental impact. In our environment, an agent trained with the Proximal Policy Optimization algorithm is more successful at reducing environmental impacts than the other baseline agents we present.

Download full text in pdf format

Published as:
H. Overweg, H. N. C. Berghuijs, I. N. Athanasiadis, CropGym: a Reinforcement Learning Environment for Crop Management, Computing Research Repository, AIMOCC 2021 Workshop at 9th Int'l Conf Learning Representations (ICLR 2021), 2021, doi:10.48550/arXiv.2104.04326.

---

You might also enjoy (View all publications)

• BloomBench: A Multi-Species Benchmark for Evaluating the Generalization of Fruit Tree Phenology Models
• Corn yield estimation under extreme climate stress with knowledge-encoded deep learning
• Causal machine learning methods for understanding land use and land cover change

---