具有待处理实验的自主驾驶实验室搜索策略
Search Strategies for Self-driving Laboratories with Pending Experiments
AI总结：
针对自主驾驶实验室异步并行实验中的待处理实验导致贝叶斯优化性能下降问题，本文基于177个真实实验构建多阶段SDL模拟器，比较多种搜索策略在不同延迟和维度下的表现，揭示并行操作与延迟反馈的权衡。
摘要：
自主驾驶实验室（SDL）由执行材料合成和表征任务的多个工位组成。为最大限度减少工位停机时间并最大化实验通量，采用异步并行方式运行实验是切实可行的，即多个实验同时在不同阶段进行。然而，实验的异步并行化会引入延迟反馈（即“待处理实验”），已知这会降低贝叶斯优化器的性能。本文构建了一个多阶段SDL模拟器，并比较了用于处理延迟反馈和异步并行操作的优化策略。利用来自真实SDL的数据，我们基于此前运行的177个实验构建了真值贝叶斯优化模拟器，用于最大化功能涂层的电导率。随后比较了期望改进、带噪期望改进、4模式探索和随机采样等搜索策略，并根据延迟量和问题维度评估其性能。仿真结果展示了异步并行操作与延迟反馈之间的权衡。
英文摘要：
Self-driving laboratories (SDLs) consist of multiple stations that perform material synthesis and characterisation tasks. To minimize station downtime and maximize experimental throughput, it is practical to run experiments in asynchronous parallel, in which multiple experiments are being performed at once in different stages. Asynchronous parallelization of experiments, however, introduces delayed feedback (i.e. "pending experiments"), which is known to reduce Bayesian optimiser performance. Here, we build a simulator for a multi-stage SDL and compare optimisation strategies for dealing with delayed feedback and asynchronous parallelized operation. Using data from a real SDL, we build a ground truth Bayesian optimisation simulator from 177 previously run experiments for maximizing the conductivity of functional coatings. We then compare search strategies such as expected improvement, noisy expected improvement, 4-mode exploration and random sampling. We evaluate their performance in terms of amount of delay and problem dimensionality. Our simulation results showcase the trade-off between the asynchronous parallel operation and delayed feedback.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
