Fractional Moments on Bandit Problems

Details Fractional Moments on Bandit Problems Fractional Moments on Bandit Problems

2012-02-14

arxiv.org/abs/1202.3750v1

Computer Science

Learning

Scientific paper

Reinforcement learning addresses the dilemma between exploration to find profitable actions and exploitation to act according to the best observations already made. Bandit problems are one such class of problems in stateless environments that represent this explore/exploit situation. We propose a learning algorithm for bandit problems based on fractional expectation of rewards acquired. The algorithm is theoretically shown to converge on an eta-optimal arm and achieve O(n) sample complexity. Experimental results show the algorithm incurs substantially lower regrets than parameter-optimized eta-greedy and SoftMax approaches and other low sample complexity state-of-the-art techniques.

Affiliated with

Also associated with

No associations

Rating

Fractional Moments on Bandit Problems 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 Fractional Moments on Bandit Problems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fractional Moments on Bandit Problems will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-90624