%0 Generic %1 slivkins2019introduction %A Slivkins, Aleksandrs %D 2019 %K 2019 arxiv book reinforcement-learning tutorial %T Introduction to Multi-Armed Bandits %U http://arxiv.org/abs/1904.07272 %X Multi-armed bandits 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. The chapters are as follows: stochastic bandits, lower bounds; Bayesian bandits and Thompson Sampling; Lipschitz Bandits; full Feedback and adversarial costs; adversarial bandits; linear costs and semi-bandits; contextual Bandits; bandits and games; bandits with knapsacks; bandits and incentives.

@misc{slivkins2019introduction, abstract = {Multi-armed bandits 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. The chapters are as follows: stochastic bandits, lower bounds; Bayesian bandits and Thompson Sampling; Lipschitz Bandits; full Feedback and adversarial costs; adversarial bandits; linear costs and semi-bandits; contextual Bandits; bandits and games; bandits with knapsacks; bandits and incentives.}, added-at = {2020-01-02T14:20:43.000+0100}, author = {Slivkins, Aleksandrs}, biburl = {https://www.bibsonomy.org/bibtex/2736edd7b45a0d848af1140377a687424/analyst}, description = {[1904.07272] Introduction to Multi-Armed Bandits}, interhash = {8545af4f759cefec44a4f80391f93890}, intrahash = {736edd7b45a0d848af1140377a687424}, keywords = {2019 arxiv book reinforcement-learning tutorial}, note = {cite arxiv:1904.07272Comment: The manuscript is complete, but comments are very welcome! To be published with Foundations and Trends in Machine Learning}, timestamp = {2021-03-12T19:42:30.000+0100}, title = {Introduction to Multi-Armed Bandits}, url = {http://arxiv.org/abs/1904.07272}, year = 2019 }