Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation

TL;DR

This paper introduces an unsupervised reinforcement learning method for embodied agents to acquire transferable meta-skills in visual navigation, reducing the need for annotated training environments and enabling fast adaptation.

Contribution

It presents a novel unsupervised approach to learn transferable meta-skills for visual navigation without supervision, improving performance in low-resource settings.

Findings

Outperforms baseline by 53.34% on SPL in AI2-THOR environments.

Learns transferable motor primitives for navigation.

Enables fast adaptation to new visual navigation tasks.

Abstract

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. Evaluation in the AI2-THOR environments shows 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.