Computer Science – Learning
Scientific paper
2011-12-08
Computer Science
Learning
9 pages, 1 figure
Scientific paper
We consider the multi-armed bandit problems in which a player aims to accrue reward by sequentially playing a given set of arms with unknown reward statistics. In the classic work, policies were proposed to achieve the optimal logarithmic regret order for some special classes of light-tailed reward distributions, e.g., Auer et al.'s UCB1 index policy for reward distributions with finite support. In this paper, we extend Auer et al.'s UCB1 index policy to achieve the optimal logarithmic regret order for all light-tailed (or equivalently, locally sub-Gaussian) reward distributions defined by the (local) existence of the moment-generating function.
Liu Keqin
Zhao Qing
No associations
LandOfFree
Extended UCB Policy for Multi-Armed Bandit with Light-Tailed Reward Distributions does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Extended UCB Policy for Multi-Armed Bandit with Light-Tailed Reward Distributions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Extended UCB Policy for Multi-Armed Bandit with Light-Tailed Reward Distributions will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-547431