no code implementations • NeurIPS 2016 • Zohar S. Karnin
In these generalizations, additional structure is known in advance, causing the task of verifying the optimality of a candidate to be easier than discovering the best arm.
no code implementations • NeurIPS 2016 • Zohar S. Karnin, Oren Anava
Our main result is a regret guarantee that scales with the variation parameter of the environment, without requiring any prior knowledge about it whatsoever.