qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation

Stan Van Der Linde; Willem De Kok; Tariq Bontekoe; Sebastian Feld

doi:10.1109/QCE57702.2023.10179

qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation

Stan Van Der Linde, Willem De Kok, Tariq Bontekoe^*, Sebastian Feld

^*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

44 Downloads (Pure)

Abstract

Compiling a quantum circuit for specific quantum hardware is a challenging task. Moreover, current quantum computers have severe hardware limitations. To make the most use of the limited resources, the compilation process should be optimized. To improve currents methods, Reinforcement Learning (RL), a technique in which an agent interacts with an environment to learn complex policies to attain a specific goal, can be used. In this work, we present qgym, a software framework derived from the OpenAI gym, together with environments that are specifically tailored towards quantum compilation. The goal of qgym is to connect the research fields of Artificial Intelligence (AI) with quantum compilation by abstracting parts of the process that are irrelevant to either domain. It can be used to train and benchmark RL agents and algorithms in highly customizable environments.

Original language	English
Title of host publication	Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023
Editors	Hausi Muller, Yuri Alexev, Andrea Delgado, Greg Byrd
Publisher	IEEE
Pages	26-30
Number of pages	5
ISBN (Electronic)	9798350343236
DOIs	https://doi.org/10.1109/QCE57702.2023.10179
Publication status	Published - 2023
Event	4th IEEE International Conference on Quantum Computing and Engineering, QCE 2023 - Bellevue, United States Duration: 17 Sept 2023 → 22 Sept 2023

Publication series

Name	Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023
Volume	2

Conference

Conference	4th IEEE International Conference on Quantum Computing and Engineering, QCE 2023
Country/Territory	United States
City	Bellevue
Period	17/09/23 → 22/09/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Quantum Compilation
Qubit Mapping
Qubit Routing
Reinforcement Learning
Scheduling

Access to Document

10.1109/QCE57702.2023.10179

qgym_A_Gym_for_Training_and_Benchmarking_RL-Based_Quantum_CompilationFinal published version, 410 KB

Cite this

Van Der Linde, S., De Kok, W., Bontekoe, T., & Feld, S. (2023). qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation. In H. Muller, Y. Alexev, A. Delgado, & G. Byrd (Eds.), Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023 (pp. 26-30). (Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023; Vol. 2). IEEE. https://doi.org/10.1109/QCE57702.2023.10179

Van Der Linde, Stan ; De Kok, Willem ; Bontekoe, Tariq et al. / qgym : A Gym for Training and Benchmarking RL-Based Quantum Compilation. Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023. editor / Hausi Muller ; Yuri Alexev ; Andrea Delgado ; Greg Byrd. IEEE, 2023. pp. 26-30 (Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023).

@inproceedings{8161caa9c33f41a8929797bcadf87fd5,

title = "qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation",

abstract = "Compiling a quantum circuit for specific quantum hardware is a challenging task. Moreover, current quantum computers have severe hardware limitations. To make the most use of the limited resources, the compilation process should be optimized. To improve currents methods, Reinforcement Learning (RL), a technique in which an agent interacts with an environment to learn complex policies to attain a specific goal, can be used. In this work, we present qgym, a software framework derived from the OpenAI gym, together with environments that are specifically tailored towards quantum compilation. The goal of qgym is to connect the research fields of Artificial Intelligence (AI) with quantum compilation by abstracting parts of the process that are irrelevant to either domain. It can be used to train and benchmark RL agents and algorithms in highly customizable environments.",

keywords = "Quantum Compilation, Qubit Mapping, Qubit Routing, Reinforcement Learning, Scheduling",

author = "{Van Der Linde}, Stan and {De Kok}, Willem and Tariq Bontekoe and Sebastian Feld",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 4th IEEE International Conference on Quantum Computing and Engineering, QCE 2023 ; Conference date: 17-09-2023 Through 22-09-2023",

year = "2023",

doi = "10.1109/QCE57702.2023.10179",

language = "English",

series = "Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023",

publisher = "IEEE",

pages = "26--30",

editor = "Hausi Muller and Yuri Alexev and Andrea Delgado and Greg Byrd",

booktitle = "Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023",

address = "United States",

}

Van Der Linde, S, De Kok, W, Bontekoe, T & Feld, S 2023, qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation. in H Muller, Y Alexev, A Delgado & G Byrd (eds), Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023. Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023, vol. 2, IEEE, pp. 26-30, 4th IEEE International Conference on Quantum Computing and Engineering, QCE 2023, Bellevue, United States, 17/09/23. https://doi.org/10.1109/QCE57702.2023.10179

qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation. / Van Der Linde, Stan; De Kok, Willem; Bontekoe, Tariq et al.
Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023. ed. / Hausi Muller; Yuri Alexev; Andrea Delgado; Greg Byrd. IEEE, 2023. p. 26-30 (Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023; Vol. 2).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - qgym

T2 - 4th IEEE International Conference on Quantum Computing and Engineering, QCE 2023

AU - Van Der Linde, Stan

AU - De Kok, Willem

AU - Bontekoe, Tariq

AU - Feld, Sebastian

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2023

Y1 - 2023

N2 - Compiling a quantum circuit for specific quantum hardware is a challenging task. Moreover, current quantum computers have severe hardware limitations. To make the most use of the limited resources, the compilation process should be optimized. To improve currents methods, Reinforcement Learning (RL), a technique in which an agent interacts with an environment to learn complex policies to attain a specific goal, can be used. In this work, we present qgym, a software framework derived from the OpenAI gym, together with environments that are specifically tailored towards quantum compilation. The goal of qgym is to connect the research fields of Artificial Intelligence (AI) with quantum compilation by abstracting parts of the process that are irrelevant to either domain. It can be used to train and benchmark RL agents and algorithms in highly customizable environments.

AB - Compiling a quantum circuit for specific quantum hardware is a challenging task. Moreover, current quantum computers have severe hardware limitations. To make the most use of the limited resources, the compilation process should be optimized. To improve currents methods, Reinforcement Learning (RL), a technique in which an agent interacts with an environment to learn complex policies to attain a specific goal, can be used. In this work, we present qgym, a software framework derived from the OpenAI gym, together with environments that are specifically tailored towards quantum compilation. The goal of qgym is to connect the research fields of Artificial Intelligence (AI) with quantum compilation by abstracting parts of the process that are irrelevant to either domain. It can be used to train and benchmark RL agents and algorithms in highly customizable environments.

KW - Quantum Compilation

KW - Qubit Mapping

KW - Qubit Routing

KW - Reinforcement Learning

KW - Scheduling

UR - http://www.scopus.com/inward/record.url?scp=85180006693&partnerID=8YFLogxK

U2 - 10.1109/QCE57702.2023.10179

DO - 10.1109/QCE57702.2023.10179

M3 - Conference contribution

AN - SCOPUS:85180006693

T3 - Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023

SP - 26

EP - 30

BT - Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023

A2 - Muller, Hausi

A2 - Alexev, Yuri

A2 - Delgado, Andrea

A2 - Byrd, Greg

PB - IEEE

Y2 - 17 September 2023 through 22 September 2023

ER -

Van Der Linde S, De Kok W, Bontekoe T, Feld S. qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation. In Muller H, Alexev Y, Delgado A, Byrd G, editors, Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023. IEEE. 2023. p. 26-30. (Proceedings - 2023 IEEE International Conference on Quantum Computing and Engineering, QCE 2023). doi: 10.1109/QCE57702.2023.10179

qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this