Quantum computation has a strong implication for advancing the current
limitation of machine learning algorithms to deal with higher data dimensions
or reducing the overall training parameters for a deep neural network model.
Based on a gate-based quantum computer, a parameterized quantum circuit was
designed to solve a model-free reinforcement learning problem with the deep-Q
learning method. This research has investigated and evaluated its potential.
Therefore, a novel PQC based on the latest Qiskit and PyTorch framework was
designed and trained to compare with a full-classical deep neural network with
and without integrated PQC. At the end of the research, the research draws its
conclusion and prospects on developing deep quantum learning in solving a maze
problem or other reinforcement learning problems.

本研究旨在探究基于门型量子计算机的参数量子电路，通过集成最新的 Qiskit 和 PyTorch 框架，与纯经典深度神经网络进行比较，评估其在模型非自由强化学习问题中的潜力，以及在解决迷宫问题或其他强化学习问题方面、深度量子学习的前景。

混合量子神经网络的深度强化学习

Deep Reinforcement Learning Using Hybrid Quantum Neural Network

Among different quantum algorithms, PQC for QML show promises on near-term
devices. To facilitate the QML and PQC research, a recent python library called
TorchQuantum has been released. It can construct, simulate, and train PQC for
machine learning tasks with high speed and convenient debugging supports.
Besides quantum for ML, we want to raise the community's attention on the
reversed direction: ML for quantum. Specifically, the TorchQuantum library also
supports using data-driven ML models to solve problems in quantum system
research, such as predicting the impact of quantum noise on circuit fidelity
and improving the quantum circuit compilation efficiency.
This paper presents a case study of the ML for quantum part. Since estimating
the noise impact on circuit reliability is an essential step toward
understanding and mitigating noise, we propose to leverage classical ML to
predict noise impact on circuit fidelity. Inspired by the natural graph
representation of quantum circuits, we propose to leverage a graph transformer
model to predict the noisy circuit fidelity. We firstly collect a large dataset
with a variety of quantum circuits and obtain their fidelity on noisy
simulators and real machines. Then we embed each circuit into a graph with gate
and noise properties as node features, and adopt a graph transformer to predict
the fidelity.
Evaluated on 5 thousand random and algorithm circuits, the graph transformer
predictor can provide accurate fidelity estimation with RMSE error 0.04 and
outperform a simple neural network-based model by 0.02 on average. It can
achieve 0.99 and 0.95 R$^2$ scores for random and algorithm circuits,
respectively. Compared with circuit simulators, the predictor has over 200X
speedup for estimating the fidelity.

使用 TorchQuantum Python 库中的图形变换模型，利用机器学习方法预测噪声对电路保真度的影响，可以在估计精度和速度方面胜过传统的电路模拟器。