Deep reinforcement learning for optimal experimental design in biology.

ABSTRACT: The field of optimal experimental design uses mathematical techniques to determine experiments that are maximally informative from a given experimental setup. Here we apply a technique from artificial intelligence-reinforcement learning-to the optimal experimental design task of maximizing confidence in estimates of model parameter values. We show that a reinforcement learning approach performs favourably in comparison with a one-step ahead optimisation algorithm and a model predictive controller for the inference of bacterial growth parameters in a simulated chemostat. Further, we demonstrate the ability of reinforcement learning to train over a distribution of parameters, indicating that this approach is robust to parametric uncertainty.

SUBMITTER: Treloar NJ 

PROVIDER: S-EPMC9721483 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature