It's-A-Me, Quantum Mario: Scalable Quantum Reinforcement Learning with Multi-Chip Ensembles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Junghoon Justin, Tseng, Huan-Hsin, Yoo, Shinjae, Chen, Samuel Yen-Chi, Cha, Jiook
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908511852560384
author Park, Junghoon Justin
Tseng, Huan-Hsin
Yoo, Shinjae
Chen, Samuel Yen-Chi
Cha, Jiook
author_facet Park, Junghoon Justin
Tseng, Huan-Hsin
Yoo, Shinjae
Chen, Samuel Yen-Chi
Cha, Jiook
contents Quantum reinforcement learning (QRL) promises compact function approximators with access to vast Hilbert spaces, but its practical progress is slowed by NISQ-era constraints such as limited qubits and noise accumulation. We introduce a multi-chip ensemble framework using multiple small Quantum Convolutional Neural Networks (QCNNs) to overcome these constraints. Our approach partitions complex, high-dimensional observations from the Super Mario Bros environment across independent quantum circuits, then classically aggregates their outputs within a Double Deep Q-Network (DDQN) framework. This modular architecture enables QRL in complex environments previously inaccessible to quantum agents, achieving superior performance and learning stability compared to classical baselines and single-chip quantum models. The multi-chip ensemble demonstrates enhanced scalability by reducing information loss from dimensionality reduction while remaining implementable on near-term quantum hardware, providing a practical pathway for applying QRL to real-world problems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00713
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle It's-A-Me, Quantum Mario: Scalable Quantum Reinforcement Learning with Multi-Chip Ensembles
Park, Junghoon Justin
Tseng, Huan-Hsin
Yoo, Shinjae
Chen, Samuel Yen-Chi
Cha, Jiook
Quantum Physics
Artificial Intelligence
Quantum reinforcement learning (QRL) promises compact function approximators with access to vast Hilbert spaces, but its practical progress is slowed by NISQ-era constraints such as limited qubits and noise accumulation. We introduce a multi-chip ensemble framework using multiple small Quantum Convolutional Neural Networks (QCNNs) to overcome these constraints. Our approach partitions complex, high-dimensional observations from the Super Mario Bros environment across independent quantum circuits, then classically aggregates their outputs within a Double Deep Q-Network (DDQN) framework. This modular architecture enables QRL in complex environments previously inaccessible to quantum agents, achieving superior performance and learning stability compared to classical baselines and single-chip quantum models. The multi-chip ensemble demonstrates enhanced scalability by reducing information loss from dimensionality reduction while remaining implementable on near-term quantum hardware, providing a practical pathway for applying QRL to real-world problems.
title It's-A-Me, Quantum Mario: Scalable Quantum Reinforcement Learning with Multi-Chip Ensembles
topic Quantum Physics
Artificial Intelligence
url https://arxiv.org/abs/2509.00713