Graduate Thesis Or Dissertation
 

Auxiliary Tasks for Efficient Learning of Point-Goal Navigation

Public Deposited

Contenu téléchargeable

Télécharger le fichier PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/c821gs704

Descriptions

Attribute NameValues
Creator
Abstract
  • Top-performing approaches to embodied AI tasks like point-goal navigation often rely on training agents via reinforcement learning over tens of millions (or even billions) of experiential steps – learning neural agents that map directly from visual observations to actions. In this work, we question whether these extreme training durations are necessary or if they are simply due to the difficulty of learning visual representations purely from task reward. We examine the task of point-goal navigation in photorealistic environments and introduce three auxiliary tasks that encourage learned representations to capture key elements of the task – local scene geometry, transition dynamics of the environment, and progress towards the goal. Importantly, these can be evaluated independent of task performance and provide strong supervision for representation learning. Our auxiliary tasks are simple to implement and rely on supervision already present in simulators commonly used for point-goal navigation. Applying our auxiliary losses to agents from prior works, we observe a >4× improvement in sample efficiency – in 17 million steps, our augmented agents outperforms state-of-the-art agents trained for 72 million steps.
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Déclaration de droits
Publisher
Peer Reviewed
Language

Des relations

Parents:

This work has no parents.

Dans Collection:

Articles

La vignette Titre Date de téléchargement Visibilité actes
file details DesaiSaurabhSatish2022.pdf 2021-12-14 Public Télécharger