Model-based RL in ATARI games

This report describes the implementation of the world model reinforcement learning algorithm to gauge its performance against traditional reinforcement learning algorithms like deep Q-learning. The algorithm will be tested in different Atari Environments, some of which pose great difficultly due to...

Full description

Saved in:

Bibliographic Details
Main Author:	Akarapu, Bharadwaj
Other Authors:	Zinovi Rabinovich
Format:	Final Year Project
Language:	English
Published:	Nanyang Technological University 2021
Subjects:	Engineering::Computer science and engineering
Online Access:	https://hdl.handle.net/10356/148080
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-148080
record_format	dspace
spelling	sg-ntu-dr.10356-1480802021-04-22T13:06:00Z Model-based RL in ATARI games Akarapu, Bharadwaj Zinovi Rabinovich School of Computer Science and Engineering zinovi@ntu.edu.sg Engineering::Computer science and engineering This report describes the implementation of the world model reinforcement learning algorithm to gauge its performance against traditional reinforcement learning algorithms like deep Q-learning. The algorithm will be tested in different Atari Environments, some of which pose great difficultly due to the smaller signals in the observation frames. Specific modifications were required to tailor the world model for each of the different environments. Bachelor of Engineering (Computer Science) 2021-04-22T13:06:00Z 2021-04-22T13:06:00Z 2021 Final Year Project (FYP) Akarapu, B. (2021). Model-based RL in ATARI games. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148080 https://hdl.handle.net/10356/148080 en SCSE20-0485 application/pdf Nanyang Technological University
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	Engineering::Computer science and engineering
spellingShingle	Engineering::Computer science and engineering Akarapu, Bharadwaj Model-based RL in ATARI games
description	This report describes the implementation of the world model reinforcement learning algorithm to gauge its performance against traditional reinforcement learning algorithms like deep Q-learning. The algorithm will be tested in different Atari Environments, some of which pose great difficultly due to the smaller signals in the observation frames. Specific modifications were required to tailor the world model for each of the different environments.
author2	Zinovi Rabinovich
author_facet	Zinovi Rabinovich Akarapu, Bharadwaj
format	Final Year Project
author	Akarapu, Bharadwaj
author_sort	Akarapu, Bharadwaj
title	Model-based RL in ATARI games
title_short	Model-based RL in ATARI games
title_full	Model-based RL in ATARI games
title_fullStr	Model-based RL in ATARI games
title_full_unstemmed	Model-based RL in ATARI games
title_sort	model-based rl in atari games
publisher	Nanyang Technological University
publishDate	2021
url	https://hdl.handle.net/10356/148080
_version_	1698713707686658048

Model-based RL in ATARI games

Similar Items