Bandits in real systems Multi-armed bandit theory [https://en.wikipedia.org/wiki/Multi-armed_bandit] is extremely well-studied in situations where there is a very direct link between actions and rewards. However in many situations where we may wish to deploy these techniques, the choice of an action leads to outcomes in a complex and partially-understood way. For example, choosing the price of a finitely-available product for the following day will result in a semi-predictable sales pattern, and consequent amount of stock left at the end of the day. And choosing some hyper-parameters of a learning method for a period of time will result in a semi-predictable performance improvement of the method. This project will develop techniques for such problems, where there is a (semi-)parameterised model of the world, and sequential decisions must be taken to simultaneously learn the model and optimise outcomes.

I am a Professor of Statistical Learning, and Director of Engagement, in the Department of Mathematics and Statistics at Lancaster University.  I research statistical learning, decision-making, and game theory.  My research on bandit algorithms is used by many of the world's largest companies to balance exploration and exploitation in real time website optimisation. I led the EPSRC/NERC-funded Data Science of the Natural Environment (DSNE) project at Lancaster University, and was a member of the NG-CDI project, funded by an EPSRC Prosperity Partnership with BT. Prior to my position at Lancaster, I was a senior lecturer in the statistics group of the School of Mathematics, University of Bristol, where I was co-director of the EPSRC-funded cross-disciplinary decision-making research group at the University of Bristol. I was also a partner in the ALADDIN project, a large strategic partnership between BAE Systems and EPSRC, and involving researchers from Imperial College, Southampton, Oxford, Bristol and BAE Systems.

• statistical learning
• decision-making
• game theory, particularly learning in games
• reinforcement learning
• stochastic approximation

I am a member of the Scientific Board of the Smith Institute.

I am currently an external examiner for Edinburgh University and Imperial College London. Previously I was an external examiner at the University of Kent at Canterbury and the University of Leicester.

I have held numerous roles at the Royal Statistical Society.  These include elected Council member, member of the long term strategy group, member of the Academic Affairs Advisory Group, and chair of the Applied Probability Section, and member of the Research Section Committee.

I have served on the programme committee of the London Mathematical Society.

I was a member of the Review into Knowledge Exchange in the Mathematical Sciences (aka the Bond Review) and the subsequent Council for the Mathematical Sciences exploration into the establishment of an Academy of Mathematical Sciences.

I have had the privilege to supervise some great students.  The following have finished and moved on:

• Archie Chapman
• Michalis Smyrnakis
• Harriet Mills
• Ben May
• Steve Perkins
• Kevin Lloyd
• Matthew Arnold
• Simon Smith
• Adnane Ez-zizi
• Beki Floyd
• Hannah Julienne
• James Edwards
• Chris Sherfield
• Simon Smith
• Ciara Pike-Burke
• James Grant
• Henry Moss
• Tom Pinder
• Anja Stein

I am always on the lookout for the next good research student. However, note that it is essentially impossible for me to find financial support for students from outside the EU.