Hierarchical Integration of Deep Reinforcement Learning with a Pursuit Behavioral Model for Robust and Interpretable Navigation

Abstract

Integrating theoretical models into machine learning models holds immense potential for constructing efficient, robust, and interpretable models. Here, we propose a hybrid architecture that hierarchically integrates a biological pursuit model into deep reinforcement learning. This approach enables seamless acceleration-mode switching and geometrically reasonable action selection, demonstrating our hierarchical predator agents realized efficient navigation in a predator-prey environment. Interestingly, our results have commonalities with group hunting behaviors observed in nature, suggesting the potential application of our model as a tool for providing new insights into biology.