|Bandit Algorithms (Cambridge University Press)|
|Friday, 02 October 2020|
Decision-making in the face of uncertainty is a significant challenge in machine learning, and the multi-armed bandit model is a commonly used framework to address it. This comprehensive and rigorous introduction examines all the major settings, including stochastic, adversarial, and Bayesian frameworks. Tor Lattimore and Csaba Szepesvári focus on both mathematical intuition and carefully worked proofs.
Linear bandits receive special attention as one of the most useful models in applications, while other chapters are dedicated to combinatorial bandits, ranking, non-stationary problems, Thompson sampling and pure exploration.
Author: Tor Lattimore and Csaba Szepesvári
For more Book Watch just click.
Book Watch is I Programmer's listing of new books and is compiled using publishers' publicity material. It is not to be read as a review where we provide an independent assessment. Some, but by no means all, of the books in Book Watch are eventually reviewed.
To have new titles included in Book Watch contact BookWatch@i-programmer.info