Game-solving algorithms using no-regret learners achieve non-asymptotic optimality guarantees for pure exploration in exponential family bandits.
Unimodal bandits: Regret lower bounds and optimal algorithms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.