Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation

Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e.g., television) using only visual observations. A key challenge for current deep reinforcement learning models lies in the requirements for a large amount of training data. It is exceedingly e...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Juncheng, Wang, Xin, Tang, Siliang, Shi, Haizhou, Wu, Fei, Zhuang, Yueting, Wang, William Yang
Format: Conference Proceeding
Language:English
Subjects:
Generators
Learning (artificial intelligence)
Navigation
Robots
Task analysis
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e.g., television) using only visual observations. A key challenge for current deep reinforcement learning models lies in the requirements for a large amount of training data. It is exceedingly expensive to construct sufficient 3D synthetic environments annotated with the target object information. In this paper, we focus on visual navigation in the low-resource setting, where we have only a few training environments annotated with object information. We propose a novel unsupervised reinforcement learning approach to learn transferable meta-skills (e.g., bypass obstacles, go straight) from unannotated environments without any supervisory signals. The agent can then fast adapt to visual navigation through learning a high-level master policy to combine these meta-skills, when the visual-navigation-specified reward is provided. Experimental results show that our method significantly outperforms the baseline by 53.34% relatively on SPL, and further qualitative analysis demonstrates that our method learns transferable motor primitives for visual navigation.
ISSN:2575-7075
DOI:10.1109/CVPR42600.2020.01214