2019 TutORial: Recent Advances in Multiarmed Bandits for Sequential Decision Making
Given by Shipra Agrawal at the 2019 INFORMS Annual Meeting in Seattle, WA.
This tutorial discusses some recent advances in sequential decision making models that build upon the basic multi-armed bandit (MAB) setting to greatly expand its purview. Specifically, it discusses progress in algorithm design and analysis techniques for three models: (a) Contextual bandits, (b) Combinatorial bandits, and (c) Bandits with long-term constraints and non-additive rewards, along with applications in several domains such as online advertising, recommendation systems, crowdsourcing, healthcare, network routing, assortment optimization, revenue management, and resource allocation.
Видео 2019 TutORial: Recent Advances in Multiarmed Bandits for Sequential Decision Making канала INFORMS
This tutorial discusses some recent advances in sequential decision making models that build upon the basic multi-armed bandit (MAB) setting to greatly expand its purview. Specifically, it discusses progress in algorithm design and analysis techniques for three models: (a) Contextual bandits, (b) Combinatorial bandits, and (c) Bandits with long-term constraints and non-additive rewards, along with applications in several domains such as online advertising, recommendation systems, crowdsourcing, healthcare, network routing, assortment optimization, revenue management, and resource allocation.
Видео 2019 TutORial: Recent Advances in Multiarmed Bandits for Sequential Decision Making канала INFORMS
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Multi-Armed Bandits: A Cartoon Introduction - DCBA #1CS885 Lecture 8b: Bayesian and Contextual BanditsThompson sampling, one armed bandits, and the Beta distributionThompson Sampling for Learning in Online Decision MakingContextual Bandit: from Theory to Applications. - Vernade - Workshop 3 - CEB T1 201926: Resampling methods (bootstrapping)Contextual Bandit Personalization: Is A/B Testing Dead? | Exponea Experts Explain (Robert Lacok)Best Multi-Armed Bandit Strategy? (feat: UCB Method)Player Modeling via Multi-Armed Bandits - FDG 2020Class 12 "Invitation and Reply writing, Format, Tips, Examples, Doubts Clearing"Reinforcement Learning: Thompson Sampling & The Multi Armed Bandit Problem - Part 01Online Learning and Bandits (Part 1)The Contextual Bandits ProblemPersonalizing Explainable Recommendations with Multi-objective Contextual BanditsLecture 16 | Adversarial Examples and Adversarial TrainingBayesian Bandit ExplorerHow to Win Slot Machines - Intro to Deep Learning #13Why You Should NOT Learn Machine Learning!Thompson Sampling : Data Science ConceptsWayfair Data Science Explains It All: Multi-Armed Bandits