Show simple item record

dc.contributor.authorDaskalakis, Constantinos
dc.contributor.authorDeckelbaum, Alan T.
dc.contributor.authorKim, Anthony
dc.date.accessioned2012-09-21T15:32:49Z
dc.date.available2012-09-21T15:32:49Z
dc.date.issued2011-01
dc.identifier.issn1071-9040
dc.identifier.urihttp://hdl.handle.net/1721.1/73097
dc.description.abstractWe propose a new no-regret learning algorithm. When used against an adversary, our algorithm achieves average regret that scales as O (1/√T) with the number T of rounds. This regret bound is optimal but not rare, as there are a multitude of learning algorithms with this regret guarantee. However, when our algorithm is used by both players of a zero-sum game, their average regret scales as O (ln T/T), guaranteeing a near-linear rate of convergence to the value of the game. This represents an almost-quadratic improvement on the rate of convergence to the value of a game known to be achieved by any no-regret learning algorithm, and is essentially optimal as we show a lower bound of Ω (1/T). Moreover, the dynamics produced by our algorithm in the game setting are strongly-uncoupled in that each player is oblivious to the payoff matrix of the game and the number of strategies of the other player, has limited private storage, and is not allowed funny bit arithmetic that can trivialize the problem; instead he only observes the performance of his strategies against the actions of the other player and can use private storage to remember past played strategies and observed payoffs, or cumulative information thereof. Here, too, our rate of convergence is nearly-optimal and represents an almost-quadratic improvement over the best previously known strongly-uncoupled dynamics.en_US
dc.description.sponsorshipNational Science Foundation (U.S.) (CAREER Award CCF-0953960)en_US
dc.language.isoen_US
dc.publisherSociety for Industrial and Applied Mathematicsen_US
dc.relation.isversionofhttp://dl.acm.org/citation.cfm?id=2133057en_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.sourceSIAMen_US
dc.titleNear-optimal no-regret algorithms for zero-sumen_US
dc.typeArticleen_US
dc.identifier.citationConstantinos Daskalakis, Alan Deckelbaum, and Anthony Kim. 2011. Near-optimal no-regret algorithms for zero-sum games. In Proceedings of the Twenty-Second Annual ACM-SIAM Symposium on Discrete Algorithms (SODA '11). SIAM 235-254. SIAM ©2011en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mathematicsen_US
dc.contributor.mitauthorDaskalakis, Constantinos
dc.contributor.mitauthorDeckelbaum, Alan T.
dc.relation.journalProceedings of the Twenty-Second Annual ACM-SIAM Symposium on Discrete Algorithms (SODA '11)en_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-5451-0490
mit.licensePUBLISHER_POLICYen_US
mit.metadata.statusComplete


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record