A VNS-based hyper-heuristic with adaptive computational budget of local search

Hsiao, Ping-Che; Chiang, Tsung-Che; Fu, Li‐Chen

doi:10.1109/cec.2012.6252969

Cited by 17 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both for the total and the individual domains the table shows points and rank. From the original competition, these include the winner GIHH (Misir et al 2011), VNS-TW (Hsiao, Chiang, and Fu 2012), and an original entry based on reinforcement learning (Larose 2011).…”

Section: Comparison Against Other Methodsmentioning

confidence: 99%

“…A streamlined version of this algorithm was published by Adriaensen and Nowé (2016). The following places in the competition were taken by a self-adaptive variable neighbourhood search (Hsiao, Chiang, and Fu 2012), and an algorithm using cycles of diversification and intensification (Larose 2011). Extensions to the framework have been provided later (Ochoa et al 2012b), including several additional domains (Adriaensen, Ochoa, and Nowé 2015).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Large-State Reinforcement Learning for Hyper-Heuristics

Kletzander

Musliu

2023

AAAI

View full text Add to dashboard Cite

Hyper-heuristics are a domain-independent problem solving approach where the main task is to select effective chains of problem-specific low-level heuristics on the fly for an unseen instance. This task can be seen as a reinforcement learning problem, however, the information available to the hyper-heuristic is very limited, usually leading to very limited state representations. In this work, for the first time we use the trajectory of solution changes for a larger set of features for reinforcement learning in the novel hyper-heuristic LAST-RL (Large-State Reinforcement Learning). Further, we introduce a probability distribution for the exploration case in our epsilon-greedy policy that is based on the idea of Iterated Local Search to increase the chance to sample good chains of low-level heuristics. The benefit of the collaboration of our novel components is shown on the academic benchmark of the Cross Domain Heuristic Challenge 2011 consisting of six different problem domains. Our approach can provide state-of-the-art results on this benchmark where it outperforms recent hyper-heuristics based on reinforcement learning, and also demonstrates high performance on a benchmark of complex real-life personnel scheduling domains.

show abstract

Section: Comparison Against Other Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Large-State Reinforcement Learning for Hyper-Heuristics

Kletzander

Musliu

2023

AAAI

View full text Add to dashboard Cite

show abstract

“… Turky et al (2020) proposes a two-stage hyper-heuristic to control the local search and its operators; the framework is used for two combinatorial optimization problems. Hsiao, Chiang & Fu (2012) proposes a hyper-heuristic based on variable neighbourhood search, where local search is used and tested for four combinatorial optimization problems. Soria-Alcaraz et al (2016) designs a hyper-heuristic based on an iterated local search algorithm for a course timetabling problem.…”

Section: Related Workmentioning

confidence: 99%

Nested Markov chain hyper-heuristic (NMHH): a hybrid hyper-heuristic framework for single-objective continuous problems

Bándi,

Gaskó

2024

PeerJ Computer Science

View full text Add to dashboard Cite

This article introduces a new hybrid hyper-heuristic framework that deals with single-objective continuous optimization problems. This approach employs a nested Markov chain on the base level in the search for the best-performing operators and their sequences and simulated annealing on the hyperlevel, which evolves the chain and the operator parameters. The novelty of the approach consists of the upper level of the Markov chain expressing the hybridization of global and local search operators and the lower level automatically selecting the best-performing operator sequences for the problem. Numerical experiments conducted on well-known benchmark functions and the comparison with another hyper-heuristic framework and six state-of-the-art metaheuristics show the effectiveness of the proposed approach.

show abstract

“…Regarding the development of hyper-heuristics, the field of study is relatively new, with an increase in publications on this subject over the last three-four years [20]. There are several methods available, such as approaches based on genetic programming [21], graphbased [22], VNS-based [23], ant-based [24], tabu search-based [25], greedy selection-based [26], GA-based [27], simulated annealing-based [28], and reinforcement learning-based [29]. Those are several relevant examples that initiated the domain in various directions.…”

Section: State Of the Artmentioning

confidence: 99%

HyperDE: An Adaptive Hyper-Heuristic for Global Optimization

Manescu,

Dumitrescu

2023

Algorithms

View full text Add to dashboard Cite

In this paper, a novel global optimization approach in the form of an adaptive hyper-heuristic, namely HyperDE, is proposed. As the naming suggests, the method is based on the Differential Evolution (DE) heuristic, which is a well-established optimization approach inspired by the theory of evolution. Additionally, two other similar approaches are introduced for comparison and validation, HyperSSA and HyperBES, based on Sparrow Search Algorithm (SSA) and Bald Eagle Search (BES), respectively. The method consists of a genetic algorithm that is adopted as a high-level online learning mechanism, in order to adjust the hyper-parameters and facilitate the collaboration of a homogeneous set of low-level heuristics with the intent of maximizing the performance of the search for global optima. Comparison with the heuristics that the proposed methodologies are based on, along with other state-of-the-art methods, is favorable.

show abstract

A VNS-based hyper-heuristic with adaptive computational budget of local search

Cited by 17 publications

References 23 publications

Large-State Reinforcement Learning for Hyper-Heuristics

Large-State Reinforcement Learning for Hyper-Heuristics

Nested Markov chain hyper-heuristic (NMHH): a hybrid hyper-heuristic framework for single-objective continuous problems

HyperDE: An Adaptive Hyper-Heuristic for Global Optimization

Contact Info

Product

Resources

About