Matches in SemOpenAlex for { <https://semopenalex.org/work/W2939627158> ?p ?o ?g. }
- W2939627158 abstract "Multi-armed a simple but very powerful framework for algorithms that make decisions over time under uncertainty. An enormous body of work has accumulated over the years, covered in several books and surveys. This book provides a more introductory, textbook-like treatment of the subject. Each chapter tackles a particular line of work, providing a self-contained, teachable technical introduction and a brief review of the further developments; many of the chapters conclude with exercises. The book is structured as follows. The first four chapters are on IID rewards, from the basic model to impossibility results to Bayesian priors to Lipschitz rewards. The next three chapters cover adversarial rewards, from the full-feedback version to adversarial to extensions with linear rewards and combinatorially structured actions. Chapter 8 is on contextual bandits, a middle ground between IID and adversarial in which the change in reward distributions is completely explained by observable contexts. The last three chapters cover connections to economics, from learning in repeated games to with supply/budget constraints to exploration in the presence of incentives. The appendix provides sufficient background on concentration and KL-divergence. The chapters on bandits with similarity information, bandits with knapsacks and bandits and agents can also be consumed as standalone surveys on the respective topics." @default.
- W2939627158 created "2019-04-25" @default.
- W2939627158 creator A5058550942 @default.
- W2939627158 date "2019-04-15" @default.
- W2939627158 modified "2023-09-27" @default.
- W2939627158 title "Introduction to Multi-Armed Bandits" @default.
- W2939627158 cites W1094752974 @default.
- W2939627158 cites W1487320471 @default.
- W2939627158 cites W1506859583 @default.
- W2939627158 cites W1518788040 @default.
- W2939627158 cites W1520045492 @default.
- W2939627158 cites W1521084402 @default.
- W2939627158 cites W1529039634 @default.
- W2939627158 cites W1552364668 @default.
- W2939627158 cites W1553290137 @default.
- W2939627158 cites W1556834409 @default.
- W2939627158 cites W1570963478 @default.
- W2939627158 cites W157259654 @default.
- W2939627158 cites W1575658237 @default.
- W2939627158 cites W1589928278 @default.
- W2939627158 cites W1625390266 @default.
- W2939627158 cites W1631797562 @default.
- W2939627158 cites W165458731 @default.
- W2939627158 cites W1659045240 @default.
- W2939627158 cites W1668488459 @default.
- W2939627158 cites W1699297496 @default.
- W2939627158 cites W172143579 @default.
- W2939627158 cites W1735261864 @default.
- W2939627158 cites W1761637522 @default.
- W2939627158 cites W1835900096 @default.
- W2939627158 cites W1861050369 @default.
- W2939627158 cites W1861297722 @default.
- W2939627158 cites W1882177676 @default.
- W2939627158 cites W1900560890 @default.
- W2939627158 cites W1911551976 @default.
- W2939627158 cites W1973991804 @default.
- W2939627158 cites W1974144574 @default.
- W2939627158 cites W1979352993 @default.
- W2939627158 cites W1982971964 @default.
- W2939627158 cites W1987292194 @default.
- W2939627158 cites W1988716172 @default.
- W2939627158 cites W1988790447 @default.
- W2939627158 cites W1989274820 @default.
- W2939627158 cites W2004001705 @default.
- W2939627158 cites W2008737310 @default.
- W2939627158 cites W2009551863 @default.
- W2939627158 cites W2009979684 @default.
- W2939627158 cites W2010189695 @default.
- W2939627158 cites W2012731843 @default.
- W2939627158 cites W2017154601 @default.
- W2939627158 cites W2023599408 @default.
- W2939627158 cites W2028404160 @default.
- W2939627158 cites W2029241234 @default.
- W2939627158 cites W2034184818 @default.
- W2939627158 cites W2039522160 @default.
- W2939627158 cites W2041264641 @default.
- W2939627158 cites W2044439361 @default.
- W2939627158 cites W2044493620 @default.
- W2939627158 cites W2046934276 @default.
- W2939627158 cites W2049337234 @default.
- W2939627158 cites W2049934117 @default.
- W2939627158 cites W2053578961 @default.
- W2939627158 cites W2057050711 @default.
- W2939627158 cites W2058879737 @default.
- W2939627158 cites W2061753713 @default.
- W2939627158 cites W2066298059 @default.
- W2939627158 cites W2068490100 @default.
- W2939627158 cites W2072459156 @default.
- W2939627158 cites W2073107347 @default.
- W2939627158 cites W2073242866 @default.
- W2939627158 cites W2073384958 @default.
- W2939627158 cites W2073826257 @default.
- W2939627158 cites W2077902449 @default.
- W2939627158 cites W2083562271 @default.
- W2939627158 cites W2086170941 @default.
- W2939627158 cites W2093825590 @default.
- W2939627158 cites W2096355537 @default.
- W2939627158 cites W2096382242 @default.
- W2939627158 cites W2096678000 @default.
- W2939627158 cites W2097477220 @default.
- W2939627158 cites W2097487180 @default.
- W2939627158 cites W2098258765 @default.
- W2939627158 cites W2099111195 @default.
- W2939627158 cites W2101379030 @default.
- W2939627158 cites W2102588075 @default.
- W2939627158 cites W2103715332 @default.
- W2939627158 cites W2105066050 @default.
- W2939627158 cites W2106887613 @default.
- W2939627158 cites W2108114251 @default.
- W2939627158 cites W2108746281 @default.
- W2939627158 cites W2108817391 @default.
- W2939627158 cites W2109345727 @default.
- W2939627158 cites W2111241577 @default.
- W2939627158 cites W2111957769 @default.
- W2939627158 cites W2112420033 @default.
- W2939627158 cites W2112788936 @default.
- W2939627158 cites W2112794046 @default.
- W2939627158 cites W2113690490 @default.
- W2939627158 cites W2113719870 @default.
- W2939627158 cites W2115276154 @default.