Search Strategies for Self-Driving Laboratories with Pending Experiments

Abstract

Self-driving laboratories (SDLs) consist of multiple stations that perform material synthesis and characterisation tasks. To minimize station downtime and maxi- mize experimental throughput, it is practical to run experiments in asynchronous parallel, in which multiple experiments are being performed at once in differ- ent stages. Asynchronous parallelization of experiments, however, introduces delayed feedback (i.e. “pending points”), which is known to reduce Bayesian optimizer performance. Here, we build a simulator for a multi-stage SDL and com- pare optimization strategies for dealing with delayed feedback and asynchronous parallelized operation. Using data from [1], we build a ground truth Bayesian optimization simulator from 177 previously run experiments for maximizing the conductivity of functional coatings. We then compare search strategies such as naive expected improvement, 4-mode exploration as proposed by the original authors and asynchronous batching. We evaluate their performance in terms of number of stages, and short, medium and long-term optimization performance. Our simulation results showcase the trade-off between the asynchronous parallel operation and delayed feedback.