# Deep-Q Learning with Hybrid Quantum Neural Network on Solving Maze Problems

arXiv: https://arxiv.org/abs/2304.10159 · HTML: https://mlsanity.com/paper/2304.10159/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 8 of 8)

- [Quantum Machine Learning](https://mlsanity.com/paper/1611.09347/) (2016)
- [Supervised quantum machine learning models are kernel methods](https://mlsanity.com/paper/2101.11020/) (2021)
- [Variational Quantum Circuits for Deep Reinforcement Learning](https://mlsanity.com/paper/1907.00397/) (2019)
- [Efficient Learning for Deep Quantum Neural Networks](https://mlsanity.com/paper/1902.10445/) (2019)
- [Quantum Deep Reinforcement Learning for Robot Navigation Tasks](https://mlsanity.com/paper/2202.12180/) (2022)
- [A Hybrid Quantum-Classical Neural Network Architecture for Binary Classification](https://mlsanity.com/paper/2201.01820/) (2022)
- [Variational Quantum Approximate Support Vector Machine with Inference Transfer](https://mlsanity.com/paper/2206.14507/) (2022)
- [QDNN: DNN with Quantum Neural Network Layers](https://mlsanity.com/paper/1912.12660/) (2019)

## Built on by (most cited first, 2 of 2)

- [Quantum Walks-Based Adaptive Distribution Generation with Efficient CUDA-Q Acceleration](https://mlsanity.com/paper/2504.13532/) (2025)
- [Quantum-Embedded Dynamic Security Control using Hybrid Deep Reinforcement Learning](https://mlsanity.com/paper/2512.04095/) (2025)

## Abstract (arXiv)

Quantum computing holds great potential for advancing the limitations of machine learning algorithms to handle higher dimensions of data and reduce overall training parameters in deep learning (DL) models. This study uses a trainable variational quantum circuit (VQC) on a gate-based quantum computing model to investigate the potential for quantum benefit in a model-free reinforcement learning problem. Through a comprehensive investigation and evaluation of the current model and capabilities of quantum computers, we designed and trained a novel hybrid quantum neural network based on the latest Qiskit and PyTorch framework. We compared its performance with a full-classical CNN with and without an incorporated VQC. Our research provides insights into the potential of deep quantum learning to solve a maze problem and, potentially, other reinforcement learning problems. We conclude that reinforcement learning problems can be practical with reasonable training epochs. Moreover, a comparative study of full-classical and hybrid quantum neural networks is discussed to understand these two approaches' performance, advantages, and disadvantages to deep-Q learning problems, especially on larger-scale maze problems larger than 4x4.