Evolutionary dispersal of ecological species via Multi-Agent Deep Reinforcement Learning

Wonhyung Choi, Inkyung Ahn,
Evolutionary dispersal of ecological species via Multi-Agent Deep Reinforcement Learning,
Ecological Complexity,
Volume 64,
2025,
101146,
ISSN 1476-945X,
https://doi.org/10.1016/j.ecocom.2025.101146.
(https://www.sciencedirect.com/science/article/pii/S1476945X25000315)
Abstract: Understanding species dynamics in heterogeneous environments is essential for ecosystem studies. Traditional models assumed homogeneous habitats; however, recent approaches incorporate spatial and temporal variability, highlighting the importance of species migration. We adopt starvation-driven diffusion (SDD) models as a nonlinear diffusion approach to describe species dispersal based on local resource conditions, which has been shown to offer advantages for species survival. However, accurate prediction remains challenging due to model simplifications. This study uses Multi-Agent Reinforcement Learning (MARL) with Deep Q-Networks (DQN) to simulate single-species and predator–prey interactions, incorporating SDD-type rewards. Our simulations reveal evolutionary dispersal strategies, providing insights into species dispersal mechanisms and validating traditional mathematical models.
Keywords: Evolutionary dispersal; Predator–prey interactions; Multi-agent deep reinforcement learning; Starvation-driven diffusions; Ideal free distribution