A reinforcement learning approach to resource allocation in genomic selection

TL;DR

This paper introduces a reinforcement learning-based method for optimizing resource allocation in genomic selection, aiming to improve genetic gain in plant breeding through automated decision-making.

Contribution

It develops a novel RL algorithm formulated as an MDP with an integer linear program and value function approximation for efficient resource allocation in genomic selection.

Findings

Enhanced genetic gain demonstrated in case study

Effective RL-based resource allocation outperforms traditional methods

Method reduces complexity of state space in decision process

Abstract

Genomic selection (GS) is a technique that plant breeders use to select individuals to mate and produce new generations of species. Allocation of resources is a key factor in GS. At each selection cycle, breeders are facing the choice of budget allocation to make crosses and produce the next generation of breeding parents. Inspired by recent advances in reinforcement learning for AI problems, we develop a reinforcement learning-based algorithm to automatically learn to allocate limited resources across different generations of breeding. We mathematically formulate the problem in the framework of Markov Decision Process (MDP) by defining state and action spaces. To avoid the explosion of the state space, an integer linear program is proposed that quantifies the trade-off between resources and time. Finally, we propose a value function approximation method to estimate the action-value function and then develop a greedy policy improvement technique to find the optimal resources. We demonstrate the effectiveness of the proposed method in enhancing genetic gain using a case study with realistic data.