Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret

Details Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret

2011-07-20

arxiv.org/abs/1107.4042v1

Mathematics

Optimization and Control

Scientific paper

In this paper we consider the problem of learning the optimal policy for the uncontrolled restless bandit problem. In this problem only the state of the selected arm can be observed, the state transitions are independent of control and the transition law is unknown. We propose a learning algorithm which gives logarithmic regret uniformly over time with respect to the optimal finite horizon policy with known transition law under some assumptions on the transition probabilities of the arms and the structure of the optimal stationary policy for the infinite horizon average reward problem.

Affiliated with

Also associated with

No associations

Rating

Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret 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 Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-36196