Learning has been adopted as a general behavioral model for players in repeated games. Learning offers a way that players can adopt to (possibly changing) environment. Learning guarantees high social welfare in many games (including traffic routing as well as online auctions), even when the game or the population of players is dynamically changing. The rate at which the game can change depends on the speed of convergence of the learning algorithm. If players observe all other participants, which such full information feedback classical learning algorithms offer very fast convergence. However, such full information feedback is often not available, and the convergence of classical algorithms with partial feedback is much good. In this talk we develop a black-box approach for learning where the learner observes as feedback only losses of a subset of the actions. The simplicity and black box nature of the approach allows us to use of this faster learning rate as a behavioral assumption in games. Talk based on joint work with Thodoris Lykouris and Karthik Sridharan.
Eva Tardos (Cornell)
Eva Tardos is a Jacob Gould Schurman Professor of Computer Science at Cornell University, was Computer Science department chair 2006-2010. She received her BA and PhD from Eotvos University in Budapest. Tardos’s research interest is algorithms and algorithmic game theory. She is most known for her work on network-flow algorithms, approximation algorithms, and quantifying the efficiency of selfish routing. Her current interest include the effect of learning behavior in games. She has been elected to the National Academy of Engineering, the National Academy of Sciences, the American Academy of Arts and Sciences, and is an external member of the Hungarian Academy of Sciences. She is the recipient of a number of fellowships and awards including the Packard Fellowship, the Goedel Prize, Dantzig Prize, Fulkerson Prize, ETACS prize, and the IEEE Technical Achievement Award. She is editor editor-in-Chief of the Journal of the ACM, and was editor in the past of several other journals including the SIAM Journal of Computing, and Combinatorica, served as problem committee member for many conferences, and was program committee chair for SODA’96, FOCS’05, and EC’13.
More from the Same Authors
2019 : Invited talk: Eva Tardos (Cornell) »
2018 Workshop: Smooth Games Optimization and Machine Learning »
Simon Lacoste-Julien · Ioannis Mitliagkas · Gauthier Gidel · Vasilis Syrgkanis · Eva Tardos · Leon Bottou · Sebastian Nowozin
2016 Poster: Learning in Games: Robustness of Fast Convergence »
Dylan Foster · zhiyuan li · Thodoris Lykouris · Karthik Sridharan · Eva Tardos
2015 Poster: No-Regret Learning in Bayesian Games »
Jason Hartline · Vasilis Syrgkanis · Eva Tardos