Thompson Sampling for the Duelling Bandits Problem
published: May 28, 2013, recorded: September 2012, views: 3314
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
In surprisingly many situations, absolute rewards are not available (or nonstationary) while relative preferences are easy to collect (or stable). This variation of the bandit problem is known at the duelling bandits (or, dueling bandits in the US; see http://www.cs.cornell.edu/people/tj/publications/yue_etai_09a.pdf). My talk will cover our preliminary work developing a Thompson sam piing algorithm for the duelling (or dueling) bandit problem.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !