Deep reinforcement learning for optimal experimental design in biology

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.

Automated summary

The field of optimal experimental design utilizes mathematical techniques to identify experiments with maximal information content. In this study, a reinforcement learning technique is applied to achieve optimal experimental design for maximizing confidence in model parameter estimates. Results demonstrate that reinforcement learning outperforms other algorithms, such as one-step ahead optimization and model predictive control, in inferring bacterial growth parameters in a simulated chemostat. Moreover, reinforcement learning is shown to be robust to parametric uncertainty, as it can be trained over a distribution of parameters.