Machine learning-based optimal control for colloidal self-assembly

Andres Lizano-Villalobos

doi:10.1002/aic.70389

Machine learning-based optimal control for colloidal self-assembly

2026-04-08

0

PRE

AI

A

Andres Lizano-Villalobos

DOI：10.1002/aic.70389

Original

Original request for help

Save

Abstract

En 中文

Achieving precise control of colloidal self-assembly into specific patterns remains a longstanding challenge due to the complex process dynamics. Recently, machine learning-based state representation and reinforcement learning-based control strategies have started to accumulate popularity in the field, showing great potential as an automatable and generalizable approach to producing patterned colloidal assembly. In this work, we proposed a machine learning-based optimal control framework, combining unsupervised learning and graph convolutional neural network for state representation with deep reinforcement learning-based optimal control policy calculation, to provide a data-driven control strategy that can potentially be generalized to other many-body self-assembly systems. With Brownian Dynamics simulations, we demonstrated its superior performance as compared to traditional order parameter-based state description, and its efficacy in obtaining ordered two-dimensional spherical colloidal self-assembly in an electric field-mediated system with an actual success rate of 97%.

Keywords:

colloidal self-assembly

deep Q-learning

graph convolutional neural network

machine learning

optimal control

Machine learning-based optimal control for colloidal self-assembly

Abstract

Journal

Organization