Universal Successor Features Based Deep Reinforcement Learning for Navigation

About this item

Title

Universal Successor Features Based Deep Reinforcement Learning for Navigation

Content partner

The University of Auckland Library

Collection

ResearchSpace@Auckland

Description

This thesis outlines a research work on modelling a novel approach for robot navigation by using an advanced Deep Reinforcement Learning (DRL) algorithm. Visual navigation is a core problem in the robotics and machine vision. Previous research used map-based, map-building or map-less navigation strategies. The first two approaches were favoured in the past, however, they essentially depend on the accurate mapping of the environment and a careful human-guided training phase, which overall limi...

Read more

Format

Research paper

Research format

Thesis

Thesis level

Masters

Date created

2019

Creator

Siriwardhana, Shamane (Pallek Kankanamalage)

URL

http://hdl.handle.net/2292/46457

What is the copyright status of this item?

Share, Modify

See below for specifics about how you may use this item.

More Information

The University of Auckland Library has this to say about the rights status of this item:

Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher.

You can learn more about the rights status of this item at:

• https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm
• http://creativecommons.org/licenses/by-nc-sa/3.0/nz/
• https://creativecommons.org/licenses/by-sa/3.0/nz
• http://purl.org/eprint/accessRights/OpenAccess

What can I do with this item?

You must always check with The University of Auckland Library to confirm the specific terms of use, but this is our understanding:

Non-infringing use

NZ Copyright law does not prevent every use of a copyright work. You should consider what you can and cannot do with a copyright work.

Share it

This item is suitable for copying and sharing with others, without further permission.

Modify it

This item is suitable for modifying, remixing and building upon, without further permission.

No commercial use

You may not use this item commercially.