Game-solving algorithms using no-regret learners achieve non-asymptotic optimality guarantees for pure exploration in exponential family bandits.
Thresholding Bandit for Dose-ranging: The Impact of Monotonicity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We analyze the sample complexity of the thresholding bandit problem, with and without the assumption that the mean values of the arms are increasing. In each case, we provide a lower bound valid for any risk $\delta$ and any $\delta$-correct algorithm; in addition, we propose an algorithm whose sample complexity is of the same order of magnitude for small risks. This work is motivated by phase 1 clinical trials, a practically important setting where the arm means are increasing by nature, and where no satisfactory solution is available so far.
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Non-Asymptotic Pure Exploration by Solving Games
Game-solving algorithms using no-regret learners achieve non-asymptotic optimality guarantees for pure exploration in exponential family bandits.