# CropGym: a Reinforcement Learning Environment for Crop Management

arXiv: https://arxiv.org/abs/2104.04326 · HTML: https://mlsanity.com/paper/2104.04326/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 32 references that are in the map.
- First posted on arXiv 9 Apr 2021.

## Builds on (most cited first, 3 of 3)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)

## Built on by (most cited first, 21 of 21)

- [Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations](https://mlsanity.com/paper/2204.10394/) (2022)
- [gym-DSSAT: a crop model turned into a Reinforcement Learning environment](https://mlsanity.com/paper/2207.03270/) (2022)
- [Optimizing Crop Management with Reinforcement Learning and Imitation Learning](https://mlsanity.com/paper/2209.09991/) (2022)
- [The New Agronomists: Language Models are Experts in Crop Management](https://mlsanity.com/paper/2403.19839/) (2024)
- [A SWAT-based Reinforcement Learning Framework for Crop Management](https://mlsanity.com/paper/2302.04988/) (2023)
- [Machine Learning aided Crop Yield Optimization](https://mlsanity.com/paper/2111.00963/) (2021)
- [WOFOSTGym: A Crop Simulator for Learning Annual and Perennial Crop Management Strategies](https://mlsanity.com/paper/2502.19308/) (2025)
- [Learning-based agricultural management in partially observable environments subject to climate variability](https://mlsanity.com/paper/2401.01273/) (2024)
- [BVR Gym: A Reinforcement Learning Environment for Beyond-Visual-Range Air Combat](https://mlsanity.com/paper/2403.17533/) (2024)
- [Current applications and potential future directions of reinforcement learning-based Digital Twins in agriculture](https://mlsanity.com/paper/2406.08854/) (2024)
- [A Comparative Study of Deep Reinforcement Learning for Crop Production Management](https://mlsanity.com/paper/2411.04106/) (2024)
- [To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement Learning](https://mlsanity.com/paper/2501.12823/) (2025)
- [Power and accountability in reinforcement learning applications to environmental policy](https://mlsanity.com/paper/2205.10911/) (2022)
- [An Online Optimization-Based Decision Support Tool for Small Farmers in India: Learning in Non-stationary Environments](https://mlsanity.com/paper/2311.17277/) (2023)
- [AgGym: An agricultural biotic stress simulation environment for ultra-precision management planning](https://mlsanity.com/paper/2409.00735/) (2024)
- [A Learned Simulation Environment to Model Plant Growth in Indoor Farming](https://mlsanity.com/paper/2212.03155/) (2022)
- [CROPS: A Deployable Crop Management System Over All Possible State Availabilities](https://mlsanity.com/paper/2411.06034/) (2024)
- [Opportunities of Reinforcement Learning in South Africa's Just Transition](https://mlsanity.com/paper/2411.15145/) (2024)
- [Towards Fully Automated Decision-Making Systems for Greenhouse Control: Challenges and Opportunities](https://mlsanity.com/paper/2503.21640/) (2025)
- [BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management](https://mlsanity.com/paper/2509.19846/) (2025)
- [Technical Report on the Turba Fertilizer Machine Learning Stack in Morocco](https://mlsanity.com/paper/2610.05949/) (2026)

## Abstract (arXiv)

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.