AlphaRouter: Quantum Circuit Routing with Reinforcement Learning and Tree Search

TL;DR

AlphaRouter is a novel quantum circuit routing method combining reinforcement learning and tree search, significantly reducing routing overhead and improving quantum program efficiency.

Contribution

It introduces a reinforcement learning-based routing algorithm that integrates Monte Carlo Tree Search, outperforming existing methods in minimizing routing overhead.

Findings

AlphaRouter reduces routing overhead by up to 20%.

It outperforms current state-of-the-art routing techniques.

The method enhances quantum program efficiency.

Abstract

Quantum computers have the potential to outperform classical computers in important tasks such as optimization and number factoring. They are characterized by limited connectivity, which necessitates the routing of their computational bits, known as qubits, to specific locations during program execution to carry out quantum operations. Traditionally, the NP-hard optimization problem of minimizing the routing overhead has been addressed through sub-optimal rule-based routing techniques with inherent human biases embedded within the cost function design. This paper introduces a solution that integrates Monte Carlo Tree Search (MCTS) with Reinforcement Learning (RL). Our RL-based router, called AlphaRouter, outperforms the current state-of-the-art routing methods and generates quantum programs with up to $20\%$ less routing overhead, thus significantly enhancing the overall efficiency and feasibility of quantum computing.