Knapsack based Optimal Policies for Budget-Limited Multi-Armed Bandits

Details Knapsack based Optimal Policies for Budget-Limited Multi-Armed Bandits Knapsack based Optimal Policies for Budget-Limited Multi-Armed Bandits

2012-04-09

arxiv.org/abs/1204.1909v1

Computer Science

Artificial Intelligence

Scientific paper

In budget-limited multi-armed bandit (MAB) problems, the learner's actions are costly and constrained by a fixed budget. Consequently, an optimal exploitation policy may not be to pull the optimal arm repeatedly, as is the case in other variants of MAB, but rather to pull the sequence of different arms that maximises the agent's total reward within the budget. This difference from existing MABs means that new approaches to maximising the total reward are required. Given this, we develop two pulling policies, namely: (i) KUBE; and (ii) fractional KUBE. Whereas the former provides better performance up to 40% in our experimental settings, the latter is computationally less expensive. We also prove logarithmic upper bounds for the regret of both policies, and show that these bounds are asymptotically optimal (i.e. they only differ from the best possible regret by a constant factor).

Affiliated with

Also associated with

No associations

Rating

Knapsack based Optimal Policies for Budget-Limited Multi-Armed Bandits 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 Knapsack based Optimal Policies for Budget-Limited Multi-Armed Bandits, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Knapsack based Optimal Policies for Budget-Limited Multi-Armed Bandits will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-652152