Breeding Programs Optimization with Reinforcement Learning

TL;DR

This paper explores the application of reinforcement learning to optimize crop breeding programs, demonstrating improved genetic gains over traditional methods through simulated experiments with real maize genomic data.

Contribution

It introduces RL-based methods for crop breeding optimization and provides a new benchmarking suite for evaluating such algorithms.

Findings

RL outperforms standard practices in genetic gain

Benchmark suite enables systematic evaluation of RL in breeding

Simulated results with real genomic data validate approach

Abstract

Crop breeding is crucial in improving agricultural productivity while potentially decreasing land usage, greenhouse gas emissions, and water consumption. However, breeding programs are challenging due to long turnover times, high-dimensional decision spaces, long-term objectives, and the need to adapt to rapid climate change. This paper introduces the use of Reinforcement Learning (RL) to optimize simulated crop breeding programs. RL agents are trained to make optimal crop selection and cross-breeding decisions based on genetic information. To benchmark RL-based breeding algorithms, we introduce a suite of Gym environments. The study demonstrates the superiority of RL techniques over standard practices in terms of genetic gain when simulated in silico using real-world genomic maize data.