[Ml-stat-talks] Marty Zinkevich talk, Mon, 11/15, 3pm, CS402

Robert Schapire schapire at CS.Princeton.EDU
Wed Nov 10 11:23:05 EST 2010


Marty Zinkevich will give a talk this Monday, November 15, at 3pm in CS 
room 402.

------------------------------------------------------------------------

Solving Unsolvable Games
Martin Zinkevich, Yahoo! Research
Monday, November 15, 3pm
Computer Science Building, room 402

http://martin.zinkevich.org/lemonade

I will discuss the 2010 Lemonade Stand Competition, where nine teams 
competed in a three-player symmetric, constant sum, unsolvable game.  A 
game is unsolvable if there is an equilibrium A for Alice, an 
equilibrium B for Belle, and an equilibrium C for Carly, where if every 
player plays her part of her equilibrium, then the resulting combined 
play is not in equilibrium.  Moreover, in this game, the "safe" strategy 
guarantees a very small fraction of the total utility (the team that 
played the safe strategy came in last).  On the other hand, simple 
strategies, such as choosing a fixed strategy for a few rounds, and then 
moving randomly if the utility obtained is not above the average, came 
in near the top.  These simple strategies benefit from some of the more 
sophisticated strategies that learned to cooperate.  This competition 
has been successful in its short-term goal of building a publicly 
available library of intelligent agents.  The long-term goal of this 
competition is to help scientists develop a new language of describing 
intelligent behavior, that can be used in understanding human 
experiments, designing theoretical models of intelligence, and building 
more general intelligent agents in the future.


Martin Zinkevich is a Senior Research Scientist at Yahoo! Research.  He 
received his PhD in computer science at Carnegie Mellon in 2004.  He 
works on both applied and theoretical large scale machine learning and 
game theory applied to advertising, antispam, and poker.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20101110/0393f43d/attachment.html>


More information about the Ml-stat-talks mailing list