# Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

## TL;DR

This paper introduces SAVN, a meta-reinforcement learning approach enabling a visual navigation agent to adapt autonomously to new environments without explicit supervision, significantly improving success rates in unseen scenes.

## Contribution

The paper presents a novel self-adaptive visual navigation method using meta-learning that allows agents to generalize better to unseen environments without explicit supervision.

## Key findings

- Major improvements in success rate in novel scenes
- Enhanced SPL scores for visual navigation
- Effective self-supervised adaptation demonstrated

## Abstract

Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. As we learn a task, we keep learning about it while performing the task. What we learn and how we learn it varies during different stages of learning. Learning how to learn and adapt is a key property that enables us to generalize effortlessly to new settings. This is in contrast with conventional settings in machine learning where a trained model is frozen during inference. In this paper we study the problem of learning to learn at both training and test time in the context of visual navigation. A fundamental challenge in navigation is generalization to unseen scenes. In this paper we propose a self-adaptive visual navigation method (SAVN) which learns to adapt to new environments without any explicit supervision. Our solution is a meta-reinforcement learning approach where an agent learns a self-supervised interaction loss that encourages effective navigation. Our experiments, performed in the AI2-THOR framework, show major improvements in both success rate and SPL for visual navigation in novel scenes. Our code and data are available at: https://github.com/allenai/savn .