Material Detail

Multiarmed Bandits With Limited Expert Advice

Multiarmed Bandits With Limited Expert Advice

This video was recorded at 27th Annual Conference on Learning Theory (COLT), Barcelona 2014. We consider the problem of minimizing regret in the setting of advice-efficient multiarmed bandits with expert advice. We give an algorithm for the setting of K arms and N experts out of which we are allowed to query and use only M experts' advice in each round, which has a regret bound of O(min{K,M}NMT√) after T rounds. We also prove that any algorithm for this problem must have expected regret at least Ω(min{K,M}NMT√), thus showing that our upper bound is nearly tight. This solves the COLT 2013 open problem of Seldin et al. (2013).

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.