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

Avatar
Poster
Voice is AI-generated
Connected to paperThis paper is a preprint and has not been certified by peer review

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

Authors

Simon Hakenes, Tobias Glasmachers

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.

Follow Us on

0 comments

Add comment