Harnessing deep reinforcement learning to construct time-dependent optimal fields for quantum control dynamics. Issue 39 (21st September 2022)

• Record Type: Journal Article
• Authors: Gao, Yuanqi; Wang, Xian; Yu, Nanpeng; Wong, Bryan M.
• Is Part Of: Physical chemistry chemical physics. Volume 24:Issue 39(2022)
• Page Start: 24012
• Page End: 24020
• Publication Date: 2022-09-21
• Subjects: Chemistry, Physical and theoretical -- Periodicals; 541.3
• DOI: 10.1039/d2cp02495k
• Languages: English
• ISSNs: 1463-9076

Abstract

Abstract : Deep reinforcement learning can be used as an efficient artificial intelligence approach to control time-dependent quantum dynamical systems. Abstract : We present an efficient deep reinforcement learning (DRL) approach to automatically construct time-dependent optimal control fields that enable desired transitions in dynamical chemical systems. Our DRL approach gives impressive performance in constructing optimal control fields, even for cases that are difficult to converge with existing gradient-based approaches. We provide a detailed description of the algorithms and hyperparameters as well as performance metrics for our DRL-based approach. Our results demonstrate that DRL can be employed as an effective artificial intelligence approach to efficiently and autonomously design control fields in quantum dynamical chemical systems.