Gautron, RomainPadrón, Emilio J.Preux, PhilippeBigot, JulienMaillard, Odalric-AmbrymHoogenboom, GerritTeigny, Julien2026-04-292026-04-292023-02R. Gautron, E. J Padrón, P. Preux, J. Bigot, O.-A. Maillard, G. Hoogenboom, and J. Teigny, "Learning Crop Management by Reinforcement: gym-DSSAT", proceedings of the 2nd AAAI Workshop on AI for Agriculture and Food Systems (AIAFS 2023), 2023, Washington DC, United States / Onlinehttps://hdl.handle.net/2183/48133M. de Castro, R. R. Osorio, Y. Torres and D. R. Llanos, "Accelerating Scientific Model Optimization with a Pipelined FPGA-Based Differential Evolution Engine", 2025 IEEE 33rd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), Fayetteville, AR, USA, 2025, pp. 283-283, doi: 10.1109/FCCM62733.2025.00055.[Abstract]: We introduce gym-DSSAT, a gym environment for crop management tasks, that is easy to use for training Rein- forcement Learning (RL) agents. gym-DSSAT is based on DSSAT, a state-of-the-art mechanistic crop growth simulator. We modify DSSAT so that an external software agent can in- teract with it to control the actions performed in a crop field during a growing season. The RL environment provides pre- defined decision problems without having to manipulate the complex crop simulator. We report encouraging preliminary results on a use case of nitrogen fertilization for maize. This work opens up opportunities to explore new sustainable crop management strategies with RL, and provides RL researchers with an original set of challenging tasks to investigate.eng© 2023Reinforcement learningCrop managementSimulatorDSSATconference outputopen access