Neural Algorithms for Graph Navigation

Aaron Zweig, Nesreen Ahmed, Theodore L. Willke, Guixiang Ma

Keywords: Reinforcement Learning, Graph Neural Network

TL;DR: Meta-learning on RL graph environments using external graph-shaped memory and local entropy priors

Abstract: The application of deep reinforcement learning (RL) to graph learning and meta-learning admits challenges from both topics. We consider the task of one-shot, partially observed graph navigation, acknowledging and addressing the difficulties of partially observed graph environments. In this work, we present a framework for graph meta-learning, and we propose an agent equipped with external memory and local action priors adapted to the underlying graphs. We demonstrate the efficacy of our framework through partially-observed navigation on synthetic graphs, as well as application to partially-observed navigation on 3D meshes, showing substantially improvement in one-shot performance over baseline agents.