Home > Research > Publications & Outputs > A reinforcement learning hyper-heuristic for th...

Research

Associated organisational units

Electronic data

  • CEC2020

    Accepted author manuscript, 907 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

A reinforcement learning hyper-heuristic for the optimisation of flight connections

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

A reinforcement learning hyper-heuristic for the optimisation of flight connections. / Pylyavskyy, Yaroslav; Kheiri, Ahmed; Ahmed, Leena.
IEEE Congress on Evolutionary Computation (IEEE CEC). IEEE, 2020. 9185803.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Pylyavskyy, Y, Kheiri, A & Ahmed, L 2020, A reinforcement learning hyper-heuristic for the optimisation of flight connections. in IEEE Congress on Evolutionary Computation (IEEE CEC)., 9185803, IEEE, 2020 IEEE Congress on Evolutionary Computation, CEC 2020, Virtual, Glasgow, United Kingdom, 19/07/20. https://doi.org/10.1109/CEC48606.2020.9185803

APA

Pylyavskyy, Y., Kheiri, A., & Ahmed, L. (2020). A reinforcement learning hyper-heuristic for the optimisation of flight connections. In IEEE Congress on Evolutionary Computation (IEEE CEC) Article 9185803 IEEE. https://doi.org/10.1109/CEC48606.2020.9185803

Vancouver

Pylyavskyy Y, Kheiri A, Ahmed L. A reinforcement learning hyper-heuristic for the optimisation of flight connections. In IEEE Congress on Evolutionary Computation (IEEE CEC). IEEE. 2020. 9185803 Epub 2020 Jul 24. doi: 10.1109/CEC48606.2020.9185803

Author

Pylyavskyy, Yaroslav ; Kheiri, Ahmed ; Ahmed, Leena. / A reinforcement learning hyper-heuristic for the optimisation of flight connections. IEEE Congress on Evolutionary Computation (IEEE CEC). IEEE, 2020.

Bibtex

@inproceedings{02a77e913f854977bbeea7f98574479d,
title = "A reinforcement learning hyper-heuristic for the optimisation of flight connections",
abstract = "Many combinatorial computational problems have been effectively solved by means of hyper-heuristics. In this study, we focus on a problem proposed by Kiwi.com and solve this problem by implementing a Reinforcement Learning (RL) hyperheuristic algorithm. Kiwi.com proposed a real-world NP-hard minimisation problem associated with air travelling services. The problem shares some characteristics with several TSP variants, such as time-dependence and time-windows that make the problem more complex in comparison to the classical TSP. In this work, we evaluate our proposed RL method on kiwi.com problem and compare its results statistically with common random-based hyper-heuristic approaches. The empirical results show that RL method achieves the best performance between the tested selection hyper-heuristics. Another significant achievement of RL is that better solutions were found compared to the best known solutions in several problem instances.",
author = "Yaroslav Pylyavskyy and Ahmed Kheiri and Leena Ahmed",
year = "2020",
month = sep,
day = "3",
doi = "10.1109/CEC48606.2020.9185803",
language = "English",
booktitle = "IEEE Congress on Evolutionary Computation (IEEE CEC)",
publisher = "IEEE",
note = "2020 IEEE Congress on Evolutionary Computation, CEC 2020 ; Conference date: 19-07-2020 Through 24-07-2020",

}

RIS

TY - GEN

T1 - A reinforcement learning hyper-heuristic for the optimisation of flight connections

AU - Pylyavskyy, Yaroslav

AU - Kheiri, Ahmed

AU - Ahmed, Leena

PY - 2020/9/3

Y1 - 2020/9/3

N2 - Many combinatorial computational problems have been effectively solved by means of hyper-heuristics. In this study, we focus on a problem proposed by Kiwi.com and solve this problem by implementing a Reinforcement Learning (RL) hyperheuristic algorithm. Kiwi.com proposed a real-world NP-hard minimisation problem associated with air travelling services. The problem shares some characteristics with several TSP variants, such as time-dependence and time-windows that make the problem more complex in comparison to the classical TSP. In this work, we evaluate our proposed RL method on kiwi.com problem and compare its results statistically with common random-based hyper-heuristic approaches. The empirical results show that RL method achieves the best performance between the tested selection hyper-heuristics. Another significant achievement of RL is that better solutions were found compared to the best known solutions in several problem instances.

AB - Many combinatorial computational problems have been effectively solved by means of hyper-heuristics. In this study, we focus on a problem proposed by Kiwi.com and solve this problem by implementing a Reinforcement Learning (RL) hyperheuristic algorithm. Kiwi.com proposed a real-world NP-hard minimisation problem associated with air travelling services. The problem shares some characteristics with several TSP variants, such as time-dependence and time-windows that make the problem more complex in comparison to the classical TSP. In this work, we evaluate our proposed RL method on kiwi.com problem and compare its results statistically with common random-based hyper-heuristic approaches. The empirical results show that RL method achieves the best performance between the tested selection hyper-heuristics. Another significant achievement of RL is that better solutions were found compared to the best known solutions in several problem instances.

U2 - 10.1109/CEC48606.2020.9185803

DO - 10.1109/CEC48606.2020.9185803

M3 - Conference contribution/Paper

BT - IEEE Congress on Evolutionary Computation (IEEE CEC)

PB - IEEE

T2 - 2020 IEEE Congress on Evolutionary Computation, CEC 2020

Y2 - 19 July 2020 through 24 July 2020

ER -