Near-term quantum hardware can support two-qubit operations only on the
qubits that can interact with each other. Therefore, to execute an arbitrary
quantum circuit on the hardware, compilers have to first perform the task of
qubit routing, i.e., to transform the quantum circuit either by inserting
additional SWAP gates or by reversing existing CNOT gates to satisfy the
connectivity constraints of the target topology. We propose a procedure for
qubit routing that is architecture agnostic and that outperforms other
available routing implementations on various circuit benchmarks. The depth of
the transformed quantum circuits is minimised by utilizing the Monte Carlo tree
search to perform qubit routing, aided by a Graph neural network that evaluates
the value function and action probabilities for each state.

本研究提出了一种基于蒙特卡罗树搜索和图神经网络的量子电路 qubit 路由优化方法，实现了以架构无关的方式，以尽量小的深度进行量子电路执行。

利用图神经网络辅助蒙特卡罗树搜索的量子比特路由

Qubit Routing using Graph Neural Network aided Monte Carlo Tree Search

"Qubit routing" refers to the task of modifying quantum circuits so that they
satisfy the connectivity constraints of a target quantum computer. This
involves inserting SWAP gates into the circuit so that the logical gates only
ever occur between adjacent physical qubits. The goal is to minimise the
circuit depth added by the SWAP gates.
In this paper, we propose a qubit routing procedure that uses a modified
version of the deep Q-learning paradigm. The system is able to outperform the
qubit routing procedures from two of the most advanced quantum compilers
currently available, on both random and realistic circuits, across near-term
architecture sizes.

该论文提出了一种使用改进的深度 Q 学习范例的量子比特路由程序，能够在近期架构大小的随机和现实电路上优于目前两种最先进的量子编译器的比特路由程序。

使用强化学习在量子编译器中执行量子比特路由

Using Reinforcement Learning to Perform Qubit Routing in Quantum  Compilers

This paper addresses the problem of qubit routing in first-generation and
other near-term quantum computers. In particular, it is asserted that the qubit
routing problem can be formulated as a reinforcement learning (RL) problem, and
that this is sufficient, in principle, to discover the optimal qubit routing
policy for any given quantum computer architecture. In order to achieve this,
it is necessary to alter the conventional RL framework to allow combinatorial
action space, and this represents a second contribution of this paper, which is
expected to find additional application, beyond the qubit routing problem
addressed herein. Numerical results are included demonstrating the advantage of
the RL-trained qubit routing policy over using a sorting network.

本文提出了量子计算机中量子比特路由问题的强化学习解决方案，解决此问题的方法是通过将传统的强化学习框架改进，允许离散动作空间，并证明了该方法的优越性，其具有普遍意义。