
Conte aos seus amigos sobre este item:
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems - Foundations and Trends (R) in Machine Learning
Sebastien Bubeck
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems - Foundations and Trends (R) in Machine Learning
Sebastien Bubeck
Mathematically, a multi-armed bandit is defined by the payoff process associated with each option. In this book, the focus is on two extreme cases in which the analysis of regret is particularly simple and elegant: independent and identically distributed payoffs and adversarial payoffs.
138 pages
Mídia | Livros Paperback Book (Livro de capa flexível e brochura) |
Lançado | 12 de dezembro de 2012 |
ISBN13 | 9781601986269 |
Editoras | now publishers Inc |
Páginas | 138 |
Dimensões | 234 × 159 × 8 mm · 204 g |
Idioma | English |