Learning a Mixture of Search Heuristics

Epstein, Susan L.; Petrovic, Smiljana

doi:10.1007/978-3-642-21434-9_5

Cited by 3 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A generalization of this item selection is the basis of the rationale behind this approach. Furthermore, the advantages of mixing heuristics have previously been discussed in detail for various optimization and search problems [27,58].…”

Section: Discussionmentioning

confidence: 99%

A Feature-Independent Hyper-Heuristic Approach for Solving the Knapsack Problem

et al. 2021

View full text Add to dashboard Cite

Recent years have witnessed a growing interest in automatic learning mechanisms and applications. The concept of hyper-heuristics, algorithms that either select among existing algorithms or generate new ones, holds high relevance in this matter. Current research suggests that, under certain circumstances, hyper-heuristics outperform single heuristics when evaluated in isolation. When hyper-heuristics are selected among existing algorithms, they map problem states into suitable solvers. Unfortunately, identifying the features that accurately describe the problem state—and thus allow for a proper mapping—requires plenty of domain-specific knowledge, which is not always available. This work proposes a simple yet effective hyper-heuristic model that does not rely on problem features to produce such a mapping. The model defines a fixed sequence of heuristics that improves the solving process of knapsack problems. This research comprises an analysis of feature-independent hyper-heuristic performance under different learning conditions and different problem sets.

show abstract

Section: Discussionmentioning

confidence: 99%

A Feature-Independent Hyper-Heuristic Approach for Solving the Knapsack Problem

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Automatic design of optimization algorithms is thoroughly studied in [26] from multiple perspectives. For example, in [34] a survey on automatic parameter setting is given while in [23] a learning system for the coordination of heuristics in the context of constrained optimization is presented. In [5] the use of reinforcement learning for online parameter tuning of stochastic local search algorithms is shown.…”

Section: Introductionmentioning

confidence: 99%