During Michaelmas Term, OxTalks will be moving to a new platform (full details are available on the Staff Gateway).
For now, continue using the current page and event submission process (freeze period dates to be advised).
If you have any questions, please contact halo@digital.ox.ac.uk
Multi-armed bandits are a mathematical framework for studying sequential decision-making problems with partial feedback. Recommendation, personalization, hyperparameter tuning, and clinical trials are examples of application areas that use this framework. In this talk, I will introduce some basic algorithms for solving bandit problems and show applications of these algorithms to digital markets.