paper

Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation

arXiv:2310.10250

Abstract

This work addresses the challenge of navigating expansive spaces with sparse rewards through Reinforcement Learning (RL). Using topological maps, we elevate elementary actions to object-oriented macro actions, enabling a simple Deep Q-Network (DQN) agent to solve otherwise practically impossible environments.

Extended Abstract, Northern Lights Deep Learning Conference 2024, 3 pages, 2 figures

Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation · wovepaper