AboutI am a research scientist at DeepMind in London, working mostly on algorithms for sequential decision making.
For the last few years I've spent a lot of time working on bandits. Csaba and I are in the process of completing a book on bandits to be published by Cambridge University Press. You can download the book for free here.
You can contact me at email@example.com.
- February 2019: Csaba and I are back at adversarial partial monitoring. This time using minimax duality and Bayesian regret analysis. The paper features a minimax theorem for finite-action partial monitoring and a generalisation of Russo and Van Roy's information-theoretic analysis for Bayesian regret. These are applied to a variety of problems, including finite-armed bandits, cops and robbers and finite-action partial monitoring. Preprint is here.