Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem

  title={Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem},
  author={Alexandra Carpentier and Andrea Locatelli},
We consider the problem of best arm identification with a fixed budget T , in theK-armed stochastic bandit setting, with arms distribution defined on [0, 1]. We prove that any bandit strategy, for at least one bandit problem characterized by a complexityH , will misidentify the best arm with probability lower bounded by exp ( − T log(K)H ) , whereH is the sum for all sub-optimal arms of the inverse of the squared gaps. Our result disproves formally the general belief coming from results in the… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 4 times over the past 90 days. VIEW TWEETS

From This Paper

Topics from this paper.
15 Citations
19 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 15 extracted citations


Publications referenced by this paper.
Showing 1-10 of 19 references

Similar Papers

Loading similar papers…