A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs

no code implementations • 15 May 2023 • Dirk van der Hoeven, Lukas Zierahn, Tal Lancewicki, Aviv Rosenberg, Nicoló Cesa-Bianchi

We derive a new analysis of Follow The Regularized Leader (FTRL) for online learning with delayed bandit feedback.