CVAILGRODec 3, 2018

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

arXiv:1812.00971v2255 citationsHas Code
Originality Highly original
AI Analysis

This addresses the challenge of generalization in visual navigation for AI agents, representing a novel approach rather than an incremental improvement.

The paper tackles the problem of generalization to unseen scenes in visual navigation by proposing a self-adaptive method (SAVN) that learns to adapt during both training and test time, resulting in major improvements in success rate and SPL in novel scenes.

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 .

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes