Curriculum-based Deep Reinforcement Learning for Quantum Control

TL;DR

This paper introduces a curriculum-based deep reinforcement learning method that improves quantum control by sequentially training on tasks of increasing difficulty, leading to more efficient and precise control strategies.

Contribution

It presents a novel curriculum-based deep reinforcement learning approach for quantum control, enabling better performance and fewer control pulses compared to existing methods.

Findings

Enhanced control performance for quantum systems

Fewer control pulses needed for optimal strategies

Effective transfer of knowledge between tasks

Abstract

Deep reinforcement learning has been recognized as an efficient technique to design optimal strategies for different complex systems without prior knowledge of the control landscape. To achieve a fast and precise control for quantum systems, we propose a novel deep reinforcement learning approach by constructing a curriculum consisting of a set of intermediate tasks defined by a fidelity threshold. Tasks among a curriculum can be statically determined using empirical knowledge or adaptively generated with the learning process. By transferring knowledge between two successive tasks and sequencing tasks according to their difficulties, the proposed curriculum-based deep reinforcement learning (CDRL) method enables the agent to focus on easy tasks in the early stage, then move onto difficult tasks, and eventually approaches the final task. Numerical simulations on closed quantum systems and open quantum systems demonstrate that the proposed method exhibits improved control performance for quantum systems and also provides an efficient way to identify optimal strategies with fewer control pulses.