no code implementations • 13 Mar 2020 • Luchen Li, Ignacio Albert-Smet, Aldo A. Faisal
Our aim is to establish a framework where reinforcement learning (RL) of optimizing interventions retrospectively allows us a regulatory compliant pathway to prospective clinical testing of the learned policies in a clinical deployment.
no code implementations • 17 May 2019 • Luchen Li, Matthieu Komorowski, Aldo A. Faisal
Health-related data is noisy and stochastic in implying the true physiological states of patients, limiting information contained in single-moment observations for sequential clinical decision making.
no code implementations • 29 May 2018 • Luchen Li, Matthieu Komorowski, Aldo A. Faisal
We capture this situation with partially observable Markov decision process, in which an agent optimises its actions in a belief represented as a distribution of patient states inferred from individual history trajectories.
no code implementations • 24 Nov 2015 • Romy Lorenz, Ricardo P Monti, Ines R Violante, Aldo A. Faisal, Christoforos Anagnostopoulos, Robert Leech, Giovanni Montana
Bayesian optimization has been proposed as a practical and efficient tool through which to tune parameters in many difficult settings.