Teaching a Machine to Read Maps with Deep Reinforcement Learning

2017/11/20 by Gino Brunner, Oliver Richter, Brunner, Gino +5
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #I.2.0 #I.2.10 #I.2.6 #I.2.9 #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #Robotics (cs.RO) #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.1711.07479

openalex publication_date 2017/11/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforcement learning agent to read a map in order to find the shortest way out of a random maze it has never seen before. Our system combines several state-of-the-art methods such as A3C and incorporates novel elements such as a recurrent localization cell. Our agent learns to localize itself based on 3D first person images and an approximate orientation angle. The agent generalizes well to bigger mazes, showing that it learned useful localization and navigation capabilities.

Related

• A Critical Investigation of Deep Reinforcement Learning for Navigation
• Learning to Navigate in Complex Environments
• A transformer-based deep reinforcement learning approach to spatial navigation in a partially observable Morris Water Maze
• Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation
• Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments