A simple multi-armed bandit algorithm with optimal variation-bounded regret
published: Aug. 2, 2011, recorded: July 2011, views: 4641
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.
We pose the question of whether it is possible to design a simple, linear-time algorithm for the basic multi-armed bandit problem in the adversarial setting which has a regret bound of O(√QlogT), where Q is the total quadratic variation of all the arms.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !