A Multi-Armed Bandit Hyper-Heuristic

被引：8

作者：

Ferreira, Alexandre Silvestre ^{[1
]}

Goncalves, Richard Aderbal ^{[2
]}

Ramirez Pozo, Aurora Trinidad ^{[1
]}

机构：

[1] Univ Fed Parana, Dept Comp Sci, Curitiba, Parana, Brazil

[2] State Univ Ctr Oeste, Dept Comp Sci, Guarapuava, Brazil

来源：

2015 BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS 2015) | 2015年

关键词：

Hyper-Heuristic; Multi-Armed Bandit; Combinatorial Optimization;

D O I：

10.1109/BRACIS.2015.31

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Hyper-heuristics are search methods that aim to solve optimization problems by selecting or generating heuristics. Selection hyper-heuristics choose from a pool of heuristics a good one to be applied at the current stage of the optimization process. The selection mechanism is the main part of a selection hyperheuristic and have a great impact on its performance. In this paper a deterministic selection mechanism based on the concepts of the Multi-Armed Bandit (MAB) problem is proposed. The proposed approach is integrated into the HyFlex framework and is compared to twenty other hyper-heuristics using the methodology adapted by the CHeSC 2011 Challenge. The results obtained were good and comparable to those attained by the best hyper-heuristics. Therefore, it is possible to affirm that the use of a MAB mechanism as a selection method in a hyper-heuristic is a promising approach.

引用

页码：13 / 18

页数：6

共 50 条

[21] ON MULTI-ARMED BANDIT PROBLEM WITH NUISANCE PARAMETER
孙嘉阳
Science China Mathematics, 1986, (05) : 464 - 475
[22] Multi-armed bandit algorithms and empirical evaluation
Vermorel, J
Mohri, M
MACHINE LEARNING: ECML 2005, PROCEEDINGS, 2005, 3720 : 437 - 448
[23] Sustainable Cooperative Coevolution with a Multi-Armed Bandit
De Rainville, Francois-Michel
Sebag, Michele
Gagne, Christian
Schoenauer, Marc
Laurendeau, Denis
GECCO'13: PROCEEDINGS OF THE 2013 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2013, : 1517 - 1524
[24] Characterizing Truthful Multi-Armed Bandit Mechanisms
Babaioff, Moshe
Sharma, Yogeshwer
Slivkins, Aleksandrs
10TH ACM CONFERENCE ON ELECTRONIC COMMERCE - EC 2009, 2009, : 79 - 88
[25] Identifying Outlier Arms in Multi-Armed Bandit
Zhuang, Honglei
Wang, Chi
Wang, Yifan
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[26] ON MULTI-ARMED BANDIT PROBLEM WITH NUISANCE PARAMETER
孙嘉阳
ScienceinChina,SerA., 1986, Ser.A.1986 (05) : 464 - 475
[27] Robust control of the multi-armed bandit problem
Caro, Felipe
Das Gupta, Aparupa
ANNALS OF OPERATIONS RESEARCH, 2022, 317 (02) : 461 - 480
[28] Achieving Privacy in the Adversarial Multi-Armed Bandit
Tossou, Aristide C. Y.
Dimitrakakis, Christos
THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2653 - 2659
[29] Generic Outlier Detection in Multi-Armed Bandit
Ban, Yikun
He, Jingrui
KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 913 - 923
[30] Anytime Algorithms for Multi-Armed Bandit Problems
Kleinberg, Robert
PROCEEDINGS OF THE SEVENTHEENTH ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, 2006, : 928 - 936

← 1 2 3 4 5 →