Probabilistic and Parametric Learning Combinations of Local Job Shop Scheduling Rules

Crowston, Wallace B. S.; Glover, Fred; Thompson, Gerald L.; Trawick, Jack D

doi:10.21236/ad0600965

Cited by 72 publications

(38 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Note that hyper-heuristic research has been undertaken for a number of years although the term "hyper-heuristics" is relatively new. The roots of such work can be traced back to the 1960' s (Fisher andThompson 1963, Crowston et al 1963) and throughout the 1980' s and 1990' s (Mockus 1989, Kitano 1990, Hart, Ross and Nelson 1998. This section gives a short overview of relevant hyper-heuristic methods.…”

Section: Hyper-heuristics: An Overviewmentioning

confidence: 99%

A simulated annealing hyper-heuristic methodology for flexible decision support

et al. 2011

View full text Add to dashboard Cite

Abstract. One of the main motivations for investigating hyper-heuristic methodologies is to provide a more general search framework than is currently available. Most of the current search techniques represent approaches that are largely adapted for specific search problems (and, in some cases, even specific problem instances). There are many real-world scenarios where the development of such bespoke systems is entirely appropriate. However, there are other situations where it would be beneficial to have methodologies which are more generally applicable to more problems. One of our motivating goals is to underpin the development of more flexible search methodologies that can be easily and automatically employed on a broader range of problems than is currently possible. Almost all the heuristics that have appeared in the literature have been designed and selected by humans. In this paper, we investigate a simulated annealing hyper-heuristic methodology which operates on a search space of heuristics and which employs a stochastic heuristic selection strategy and a short-term memory. The generality and performance of the proposed algorithm is demonstrated over a large number of benchmark data sets drawn from three very different and difficult (NP-hard) problems: nurse rostering, university course timetabling and onedimensional bin packing. Experimental results show that the proposed hyper-heuristic is able to achieve significant performance improvements over a recently proposed tabu search hyper-heuristic without lowering the level of generality. We also show that our hyper-heuristic is capable of producing competitive results against bespoke meta-heuristics methods for these problems. In some cases, the simulated annealing hyper-heuristic has even obtained considerable improvements over some of the current best problem-specific meta-heuristic approaches. The contribution of this paper is to present a method which can be readily (and automatically) applied to very different problems whilst still being able to produce results on benchmark problems which are competitive with bespoke human designed tailor made algorithms for those problems.

show abstract

Section: Hyper-heuristics: An Overviewmentioning

confidence: 99%

A simulated annealing hyper-heuristic methodology for flexible decision support

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Thus, meta-heuristics may have different performances on different problem domains or even on different instances of the same problem. In order to overcome these dependencies, automated search techniques have emerged [8][9][10], and now are often generically called hyper-heuristics. Hyper-heuristics take the search process one level higher to the space of heuristics.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Generalizing Hyper-heuristics via Apprenticeship Learning

Asta

Özcan

Parkes

et al. 2013

Evolutionary Computation in Combinatorial Optimization

View full text Add to dashboard Cite

Abstract. An apprenticeship-learning-based technique is used as a hyperheuristic to generate heuristics for an online combinatorial problem. It observes and learns from the actions of a known-expert heuristic on small instances, but has the advantage of producing a general heuristic that works well on other larger instances. Specifically, we generate heuristic policies for online bin packing problem by using expert near-optimal policies produced by a hyper-heuristic on small instances, where learning is fast. The "expert" is a policy matrix that defines an index policy, and the apprenticeship learning is based on observation of the action of the expert policy together with a range of features of the bin being considered, and then applying a k-means classification. We show that the generated policy often performs better than the standard best-fit heuristic even when applied to instances much larger than the training set.

show abstract

“…One of the rare theoretical studies reveal that mixing move acceptance within a selection hyper-heuristic framework could yield a better running time on some benchmark functions [36]. Machine learning techniques, such as reinforcement learning and learning classifier systems have been used as a component of selection hyper-heuristics since the early ideas have emerged [23]. In this study, we propose a multi-stage selection hyper-heuristic, hybridizing two simple move acceptance methods, which is significantly improved by the use of a machine learning technique, namely tensor analysis [40].…”

Section: Introductionmentioning

confidence: 99%

A tensor-based selection hyper-heuristic for cross-domain heuristic search

Asta

Özcan

2015

Information Sciences

View full text Add to dashboard Cite

Hyper-heuristics have emerged as automated high level search methodologies that manage a set of low level heuristics for solving computationally hard problems. A generic selection hyper-heuristic combines heuristic selection and move acceptance methods under an iterative single point-based search framework. At each step, the solution in hand is modified after applying a selected heuristic and a decision is made whether the new solution is accepted or not. In this study, we represent the trail of a hyper-heuristic as a third order tensor. Factorization of such a tensor reveals the latent relationships between the low level heuristics and the hyper-heuristic itself. The proposed learning approach partitions the set of low level heuristics into two equal subsets where heuristics in each subset are associated with a separate move acceptance method. Then a multi-stage hyper-heuristic is formed and while solving a given problem instance, heuristics are allowed to operate only in conjunction with the associated acceptance method at each stage. To the best of our knowledge, this is the first time tensor analysis of the space of heuristics is used as a data science approach to improve the performance of a hyper-heuristic in the prescribed manner. The empirical results across six different problem domains from a benchmark indeed indicate the success of the proposed approach.

show abstract

Probabilistic and Parametric Learning Combinations of Local Job Shop Scheduling Rules

Cited by 72 publications

References 0 publications

A simulated annealing hyper-heuristic methodology for flexible decision support

A simulated annealing hyper-heuristic methodology for flexible decision support

Generalizing Hyper-heuristics via Apprenticeship Learning

A tensor-based selection hyper-heuristic for cross-domain heuristic search

Contact Info

Product

Resources

About