Bandit Algorithms

24.7 Exercises 279

of one of the authors on the Pareto-regret frontier for bandits, which characterizes

what tradeoffs are available when it is desirable to have a regret that is unusually

small relative to some specific arms [Lattimore, 2015a].

24.7 Exercises

24.1 Completing the missing steps to prove the inequality in Eq. (24.6).