Download the full-sized PDF of The Role of Information in Online LearningDownload the full-sized PDF



Permanent link (DOI):


Export to: EndNote  |  Zotero  |  Mendeley


This file is in the following communities:

Graduate Studies and Research, Faculty of


This file is in the following collections:

Theses and Dissertations

The Role of Information in Online Learning Open Access


Other title
regret analysis
online learning
machine learning
partial monitoring
Type of item
Degree grantor
University of Alberta
Author or creator
Bartók, Gábor
Supervisor and department
Szepesvári, Csaba (Computing Science)
Examining committee member and department
Schuurmans, Dale (Computing Science)
Greiner, Russel (Computing Science)
Bowling, Michael (Computing Science)
Gombay, Edit (Mathematical and Statistical Sciences)
Ben-David, Shai (Computer Science, University of Waterloo)
Department of Computing Science

Date accepted
Graduation date
Doctor of Philosophy
Degree level
In a partial-monitoring game a player has to make decisions in a sequential manner. In each round, the player suffers some loss that depends on his decision and an outcome chosen by an opponent, after which he receives "some" information about the outcome. The goal of the player is to keep the sum of his losses as low as possible. This problem is an instance of online learning: By choosing his actions wisely the player can figure out important bits about the opponent's strategy that, in turn, can be used to select actions that will have small losses. Surprisingly, up to now, very little is known about this fundamental online learning problem. In this thesis, we investigate this problem. In particular, we investigate to what extent the information received influences the best achievable cumulative loss suffered by an optimal player. We present algorithms that have theoretical guarantees for achieving low cumulative loss, and prove their optimality by providing matching, algorithm independent lower bounds. Our new algorithms represent new ways of handling the exploration-exploitation trade-off, while some of the lower bound proofs introduce novel proof techniques.
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 these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before 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
Gábor Bartók, Dávid Pál, and Csaba Szepesvári. Toward a classification of finite partial-monitoring games. In ALT'10, pages 224–238, 2010.Gábor Bartók, Dávid Pál, and Csaba Szepesvári. Minimax regret of finite partial-monitoring games in stochastic environments. In COLT 2011, Proceedings of the 24th Annual Conference on Learning Theory, Budapest, Hungary, July 9–11, 2011, 2011.Gábor Bartók, Navid Zolghadr, and Csaba Szepesvári. An adaptive algorithm for finite stochastic partial monitoring. In ICML, 2012.

File Details

Date Uploaded
Date Modified
Audit Status
Audits have not yet been run on this file.
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 1228437
Last modified: 2015:10:12 15:35:29-06:00
Filename: Bartok_Gabor_Fall2012.pdf
Original checksum: 9128402a1cce8942f09f15f973580a90
Well formed: true
Valid: true
Status message: Too many fonts to report; some fonts omitted. Total fonts = 1444
Page count: 140
Activity of users you follow
User Activity Date