CropGym: a Reinforcement Learning Environment for Crop Management
This work addresses environmental sustainability in agriculture through AI, but it is incremental as it applies existing methods to a new domain-specific problem.
The authors tackled the problem of reducing environmental impact from nitrogen fertilizers by creating a reinforcement learning environment, CropGym, where an agent trained with Proximal Policy Optimization outperformed baseline agents in optimizing fertilization management.
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.