Curriculum Learning for Vision-and-Language Navigation

11/14/2021
by   Jiwen Zhang, et al.
5

Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. To tackle this issue, we propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. We develop the principle of curriculum design and re-arrange the benchmark Room-to-Room (R2R) dataset to make it suitable for curriculum training. Experiments show that our method is model-agnostic and can significantly improve the performance, the generalizability, and the training efficiency of current state-of-the-art navigation agents without increasing model complexity.

READ FULL TEXT

page 4

page 8

research
08/02/2020

Curriculum Learning with a Progression Function

Curriculum Learning for Reinforcement Learning is an increasingly popula...
research
03/02/2020

Multi-View Learning for Vision-and-Language Navigation

Learning to navigate in a visual environment following natural language ...
research
02/14/2022

One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones

We study the problem of developing autonomous agents that can follow hum...
research
03/06/2023

Robustness of Utilizing Feedback in Embodied Visual Navigation

This paper presents a framework for training an agent to actively reques...
research
11/29/2017

Curriculum Q-Learning for Visual Vocabulary Acquisition

The structure of curriculum plays a vital role in our learning process, ...
research
03/30/2022

ESNI: Domestic Robots Design for Elderly and Disabled People

Our paper focuses on the research of the possibility for speech recognit...
research
07/19/2021

Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning

We present a novel approach that improves the performance of reverberant...

Please sign up or login with your details

Forgot password? Click here to reset