![]() |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Machine Learning Seminar Series | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Date: | April 3, 2006 |
| Time: | 3:00 PM - 4:30 PM |
| Location: | 1305 Newell-Simon Hall |
| Speaker: | Rakesh Vohra, Northwestern University |
| Title: | Calibration, Regret and Learning in Games |
| Abstract: | This talk will be a survey of the connections between calibration (a measure of the accuracy of a probability forecast), regret (a measure of how well a decision rule performs which in Wodsworth's words: `looks before and after and pines for what is not') and the question of learning in games (will boundedly rational players in repeated play of a game converge to ones favorite equilibrium of the game?). |