{"id":67,"date":"2021-02-22T13:50:37","date_gmt":"2021-02-22T13:50:37","guid":{"rendered":"https:\/\/meetings.informs.org\/wordpress\/anaheim2021\/?page_id=67"},"modified":"2021-10-11T20:01:02","modified_gmt":"2021-10-11T20:01:02","slug":"tutorials","status":"publish","type":"page","link":"https:\/\/meetings.informs.org\/wordpress\/anaheim2021\/tutorials\/","title":{"rendered":"TutORials"},"content":{"rendered":"\n
\n
\n
\n
\n \n
\n
\n

The\u00a0TutORials in Operations Research<\/em> series is published annually by INFORMS as an introduction to emerging and classical subfields of operations research and management science. These chapters are designed to be accessible for all constituents of the INFORMS community, including current students, practitioners, faculty, and researchers. The publication allows readers to keep pace with new developments in the field and serves as augmenting material for a selection of the tutorial presentations offered at the INFORMS Annual Meeting.<\/p>\n

All attendees receive free access to the INFORMS 2021 TutORials in Operations Research<\/em>\u00a0online content concurrently with the meeting. Registrants of the 2021 INFORMS Annual Meeting have online access to the 2021 chapters, written by select presenters, beginning on October 24, 2021.<\/p> <\/div>\n<\/div>\n <\/div>\n

\n <\/div>\n <\/div>\n <\/div>\n
\n
\n
\n \n
\n
\n

SUNDAY<\/strong> 7:45-9:15am PDT – Virtual<\/h3> <\/div>\n<\/div>\n\n
\n
\n

Learning and Information in Stochastic Networks and Queues<\/h3>\n

We review the role of information and learning in the stability and optimization of queueing systems. In recent years, techniques from supervised learning, online learning and reinforcement learning have been applied to queueing systems supported by the increasing role of information in decision making. We present observations and new results that help rationalize the application of these areas to queueing systems. We prove that the MaxWeight policy is an application of Blackwell\u2019s Approachability Theorem. This connects queueing theoretic results with adversarial learning. We then discuss the requirements of statistical learning for service parameter estimation. As an example, we show how queue size regret can be bounded when applying a perceptron algorithm to classify service. Next, we discuss the role of state information in improved decision making. Here we contrast the roles of epistemic information (information on uncertain parameters) and aleatoric information (information on an uncertain state). Finally, we review recent advances in the theory of reinforcement learning and queueing, as well as provide discussion of current research challenges.<\/p>\n

Authors: Neil Walton,\u00a0Kuang Xu<\/span><\/p> <\/div>\n<\/div>\n\n

\n \n