Memory-Augmented Reinforcement Learning for Image-Goal Navigation

Citations Over TimeTop 1% of 2022 papers

Abstract

In this work, we present a memory-augmented approach for image-goal navigation. Earlier attempts, including RL-based and SLAM-based approaches have either shown poor generalization performance, or are heavily-reliant on pose/depth sensors. Our method is based on an attention-based end-to-end model that leverages an episodic memory to learn to navigate. First, we train a state-embedding network in a self-supervised fashion, and then use it to embed previously-visited states into the agent's memory. Our navigation policy takes advantage of this information through an attention mechanism. We validate our approach with extensive evaluations, and show that our model establishes a new state of the art on the challenging Gibson dataset. Furthermore, we achieve this impressive performance from RGB input alone, without access to additional information such as position or depth, in stark contrast to related work.

Related Papers

• → A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Platform(2022)15 cited
• → Embedding as a modeling problem(1998)167 cited
• → Performance of distributed multi-agent multi-state reinforcement spectrum management using different exploration schemes(2013)13 cited
• → Cost-Efficient Reinforcement Learning for Optimal Trade Execution on Dynamic Market Environment(2022)2 cited
• → Chapter 5: The Generalization of Relations and the Dependence of Generalization on Analysis and Abstraction(2021)1 cited