My research is in the field of statistical machine learning. I am particularly interested in sequential decision making problems, where the goal is to learn to make optimal decisions by sequentially interacting with an unknown environment. Some examples of problems I have worked on include variants of the multi-armed bandit, online learning, and reinforcement learning problems.
For further details of my research please see my personal website.
Johnson E, Pike-Burke C, Rebeschini P, Optimal convergence rate for exact policy mirror descent in discounted Markov decision processes, Neural Information Processing Systems (NeurIPS 2023)
Robert A, Pike-Burke C, Faisal A, Sample complexity of goal-conditioned hierarchical reinforcement learning, Neural Information Processing Systems (NeurIPS 2023)
et al., 2023, Delayed feedback in kernel bandits, 40th International Conference on Machine Learning, ML Research Press, Pages:34779-34792, ISSN:2640-3498
et al., 2023, Trading-off payments and accuracy in online classification with paid stochastic experts, 40th International Conference on Machine Learning, ML Research Press, Pages:34809-34830, ISSN:2640-3498
Howson B, Pike-Burke C, Filippi S, 2023, Delayed feedback in generalised linear bandits revisited, Artificial Intelligence and Statistics s (AISTATS 2023), PMLR, Pages:1-25, ISSN:2640-3498