QTRL: Toward Practical Quantum Reinforcement Learning via Quantum-Train

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Chen-Yu, Lin, Chu-Hsuan Abraham, Yang, Chao-Han Huck, Chen, Kuan-Cheng, Hsieh, Min-Hsiu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914861873627136
author Liu, Chen-Yu
Lin, Chu-Hsuan Abraham
Yang, Chao-Han Huck
Chen, Kuan-Cheng
Hsieh, Min-Hsiu
author_facet Liu, Chen-Yu
Lin, Chu-Hsuan Abraham
Yang, Chao-Han Huck
Chen, Kuan-Cheng
Hsieh, Min-Hsiu
contents Quantum reinforcement learning utilizes quantum layers to process information within a machine learning model. However, both pure and hybrid quantum reinforcement learning face challenges such as data encoding and the use of quantum computers during the inference stage. We apply the Quantum-Train method to reinforcement learning tasks, called QTRL, training the classical policy network model using a quantum machine learning model with polylogarithmic parameter reduction. This QTRL approach eliminates the data encoding issues of conventional quantum machine learning and reduces the training parameters of the corresponding classical policy network. Most importantly, the training result of the QTRL is a classical model, meaning the inference stage only requires classical computer. This is extremely practical and cost-efficient for reinforcement learning tasks, where low-latency feedback from the policy model is essential.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06103
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle QTRL: Toward Practical Quantum Reinforcement Learning via Quantum-Train
Liu, Chen-Yu
Lin, Chu-Hsuan Abraham
Yang, Chao-Han Huck
Chen, Kuan-Cheng
Hsieh, Min-Hsiu
Quantum Physics
Quantum reinforcement learning utilizes quantum layers to process information within a machine learning model. However, both pure and hybrid quantum reinforcement learning face challenges such as data encoding and the use of quantum computers during the inference stage. We apply the Quantum-Train method to reinforcement learning tasks, called QTRL, training the classical policy network model using a quantum machine learning model with polylogarithmic parameter reduction. This QTRL approach eliminates the data encoding issues of conventional quantum machine learning and reduces the training parameters of the corresponding classical policy network. Most importantly, the training result of the QTRL is a classical model, meaning the inference stage only requires classical computer. This is extremely practical and cost-efficient for reinforcement learning tasks, where low-latency feedback from the policy model is essential.
title QTRL: Toward Practical Quantum Reinforcement Learning via Quantum-Train
topic Quantum Physics
url https://arxiv.org/abs/2407.06103