ERA

Download the full-sized PDF of Game-independent AI agents for playing Atari 2600 console  gamesDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R3134Q

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Graduate Studies and Research, Faculty of

Collections

This file is in the following collections:

Theses and Dissertations

Game-independent AI agents for playing Atari 2600 console games Open Access

Descriptions

Other title
Subject/Keyword
Artificial Intelligence
Atari 2600
Tree Search
Games
Reinforcement Learning
UCT
Sarsa Lambda
Type of item
Thesis
Degree grantor
University of Alberta
Author or creator
Naddaf, Yavar
Supervisor and department
Michael Bowling (Computing Science)
Examining committee member and department
Richard Sutton (Computing Science)
Sean Gouglas (Computing Science)
Vadim Bulitko (Computing Science)
Department
Department of Computing Science
Specialization

Date accepted
2010-04-13T19:43:34Z
Graduation date
2010-06
Degree
Master of Science
Degree level
Master's
Abstract
This research focuses on developing AI agents that play arbitrary Atari 2600 console games without having any game-specific assumptions or prior knowledge. Two main approaches are considered: reinforcement learning based methods and search based methods. The RL-based methods use feature vectors generated from the game screen as well as the console RAM to learn to play a given game. The search-based methods use the emulator to simulate the consequence of actions into the future, aiming to play as well as possible by only exploring a very small fraction of the state-space. To insure the generic nature of our methods, all agents are designed and tuned using four specific games. Once the development and parameter selection is complete, the performance of the agents is evaluated on a set of 50 randomly selected games. Significant learning is reported for the RL-based methods on most games. Additionally, some instances of human-level performance is achieved by the search-based methods.
Language
English
DOI
doi:10.7939/R3134Q
Rights
License granted by Yavar Naddaf (naddaf@cs.ualberta.ca) on 2010-04-13T17:44:42Z (GMT): Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of the above terms. The author reserves all other publication and other rights in association with the copyright in the thesis, and except as herein provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.
Citation for previous publication

File Details

Date Uploaded
Date Modified
2014-04-29T15:04:20.648+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 1169404
Last modified: 2015:10:12 10:30:25-06:00
Filename: Naddaf_Yavar_Spring_2010.pdf
Original checksum: 7baa338afb82ceaee96c8542b457b6b3
Well formed: false
Valid: false
Status message: Lexical error offset=1159307
Page count: 77
Activity of users you follow
User Activity Date