153 citations · 1.2k across the 73 of their papers we have counts for
Showing 2016 · math.STShow all
2 papers · 2 filters
math.ST2016★ 57 cited
On Explore-Then-Commit Strategies
Aurélien Garivier, Emilie Kaufmann, Tor Lattimore
We study the problem of minimising regret in two-armed bandit problems with Gaussian rewards. Our objective is to use this simple setting to illustrate that strategies based on an…
math.ST2016★ 55 cited
Refined Lower Bounds for Adversarial Bandits
Sébastien Gerchinovitz, Tor Lattimore
We provide new lower bounds on the regret that must be suffered by adversarial bandit algorithms. The new results show that recent upper bounds that either (a) hold with high-proba…