Memory-Based Deep Reinforcement Learning for Quantum Control With Partial Observations

doi:10.1109/TETCI.2025.3631693

Memory-Based Deep Reinforcement Learning for Quantum Control With Partial Observations

2025-11-28

0

PRE

AI

DOI：10.1109/TETCI.2025.3631693

Original

Original request for help

Save

Abstract

En 中文

Deep reinforcement learning (DRL) has gained increasing attention in quantum physics, especially for quantum control problems, as it effectively handles high dimensionality and complex dynamics. However, many existing DRL-based quantum control methods assume full observability of quantum states, which tends to be impractical due to the massive state copies required for precise quantum measurements. To address this, we model quantum control under partial observations and introduce a memory-based DRL (MDRL) method that efficiently handles such scenarios. The proposed MDRL comprises two key components: a memory-based exploration strategy and a memory-based reward scheme. Specifically, the agent is equipped with a biology-inspired brain to memorize information derived from partial observations, including whether an episode is successful and the number of steps spent on a successful episode. The exploration strategy leverages the memorized information to guide interactions with the quantum system, while the reward scheme assigns appropriate rewards, together enabling the agent to learn an effective control strategy. The effectiveness of MDRL is verified by three examples, i.e., one-qubit state control, two-qubit state control, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$T_{x}$</tex-math></inline-formula> gate design. Numerical results demonstrate that MDRL outperforms several representative DRL algorithms for quantum control.

Keywords:

Deep reinforcement learning

quantum control

partial observations

exploration strategy

reward design

Memory-Based Deep Reinforcement Learning for Quantum Control With Partial Observations

Abstract

Journal

Organization