Exponential Weights
Abstract
We already saw an application of exponential weights to linear and quadratic bandits in Chapter 7. The same abstract algorithm can also be used for convex bandits but the situation is more complicated. Throughout this chapter we assume the losses are bounded and there is no noise:
Fields of Study & Subjects
Advanced Bandit Algorithms Research
Optimization and Search Problems
Reinforcement Learning in Robotics
Publication details
- Journal / source
- Cambridge University Press eBooks
- Pages
- 94–117
- Publication date
- 7 March 2026
- Language
- EN
- Document type
- Book chapter