Deep Reinforcement Learning Conditioned on the Natural Language

Xu, Yunqiu

Deep Reinforcement Learning Conditioned on the Natural Language

Xu, Yunqiu

Permalink

Publication Type:: Thesis
Issue Date:: 2022

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download contents and abstractAdobe PDF (286.23 kB)

Adobe PDF

Download thesisAdobe PDF (13.36 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Xu, Yunqiu
dc.date.accessioned	2022-09-12T04:47:10Z
dc.date.available	2022-09-12T04:47:10Z
dc.date.issued	2022
dc.identifier.uri	http://hdl.handle.net/10453/161756
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	In recent years, the advances of deep reinforcement learning and language representation learning lead to increasing research interest in the language-conditional reinforcement learning. In this research, we aim at designing language-conditional RL agent that is capable of handling the major challenges, including state representation learning, reasoning, generalization, low sample efficiency and large action space.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/161756/2/02whole.pdf
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	au.edu.uts.lib/ppc
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Deep Reinforcement Learning Conditioned on the Natural Language	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

In recent years, the advances of deep reinforcement learning and language representation learning lead to increasing research interest in the language-conditional reinforcement learning. In this research, we aim at designing language-conditional RL agent that is capable of handling the major challenges, including state representation learning, reasoning, generalization, low sample efficiency and large action space.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/161756