Peter I. Cowling

A Survey of Monte Carlo Tree Search Methods

Monte Carlo tree search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling. It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains. This paper is a survey of the literature to date, intended to provide a snapshot of the state of the art after the first five years of MCTS research. We outline the core algorithms derivation, impart some structure on the many variations and enhancements that have been proposed, and summarize the results from the key game and nongame domains to which MCTS methods have been applied. A number of open research questions indicate that the field is ripe for future work.

A Hyperheuristic Approach to Scheduling a Sales Summit

The concept of a hyperheuristic is introduced as an approach that operates at a higher lever of abstraction than current metaheuristic approaches. The hyperheuristic manages the choice of which lower-level heuristic method should be applied at any given time, depending upon the characteristics of the region of the solution space currently under exploration. We analyse the behaviour of several different hyperheuristic approaches for a real-world personnel scheduling problem. Results obtained show the effectiveness of our approach for this problem and suggest wider applicability of hyperheuristic approaches to other problems of scheduling and combinatorial optimisation.

A Memetic Approach to the Nurse Rostering Problem

Constructing timetables of work for personnel in healthcare institutions is known to be a highly constrained and difficult problem to solve. In this paper, we discuss a commercial system, together with the model it uses, for this rostering problem. We show that tabu search heuristics can be made effective, particularly for obtaining reasonably good solutions quickly for smaller rostering problems. We discuss the robustness issues, which arise in practice, for tabu search heuristics. This paper introduces a range of new memetic approaches for the problem, which use a steepest descent improvement heuristic within a genetic algorithm framework. We provide empirical evidence to demonstrate the best features of a memetic algorithm for the rostering problem, particularly the nature of an effective recombination operator, and show that these memetic approaches can handle initialisation parameters and a range of instances more robustly than tabu search algorithms, at the expense of longer solution times. Having presented tabu search and memetic approaches (both with benefits and drawbacks) we finally present an algorithm that is a hybrid of both approaches. This technique produces better solutions than either of the earlier approaches and it is relatively unaffected by initialisation and parameter changes, combining some of the best features of each approach to create a hybrid which is greater than the sum of its component algorithms.

Using real time information for effective dynamic scheduling

Abstract In many production processes real time information may be obtained from process control computers and other monitoring systems, but most existing scheduling models are unable to use this information to effectively influence scheduling decisions in real time. In this paper we develop a general framework for using real time information to improve scheduling decisions, which allows us to trade off the quality of the revised schedule against the production disturbance which results from changing the planned schedule. We illustrate how our framework can be used to select a strategy for using real time information for a single machine scheduling model and discuss how it may be used to incorporate real time information into scheduling the complex production processes of steel continuous caster planning.

MMAC: a new multi-class, multi-label associative classification approach

Building fast and accurate classifiers for large-scale databases is an important task in data mining. There is growing evidence that integrating classification and association rule mining together can produce more efficient and accurate classifiers than traditional classification techniques. In this paper, the problem of producing rules with multiple labels is investigated. We propose a new associative classification approach called multi-class, multi-label associative classification (MMAC). This paper also presents three measures for evaluating the accuracy of data mining classification approaches to a wide range of traditional and multi-label classification problems. Results for 28 different datasets show that the MMAC approach is an accurate and effective classification technique, highly competitive and scalable in comparison with other classification approaches.

MCAR: multi-class classification based on association rule

Summary form only given. Constructing fast, accurate classifiers for large data sets is an important task in data mining and knowledge discovery. In this research paper, a new classification method called multi-class classification based on association rules (MCAR) is presented. MCAR uses an efficient technique for discovering frequent items and employs a rule ranking method which ensures detailed rules with high confidence are part of the classifier. After experimentation with fifteen different data sets, the results indicated that the proposed method is an accurate and efficient classification technique. Furthermore, the classifiers produced are highly competitive with regards to error rate and efficiency, if compared with those generated by popular methods like decision trees, RIPPER and CBA.

An investigation of a hyperheuristic genetic algorithm applied to a trainer scheduling problem

This paper investigates a genetic algorithm based hyperheuristic (hyper-GA) for scheduling geographically distributed training staff and courses. The aim of the hyper-GA is to evolve a good-quality heuristic for each given instance of the problem and use this to find a solution by applying a suitable ordering from a set of low-level heuristics. Since the user only supplies a number of low-level problem-specific heuristics and an evaluation function, the hyperheuristic can easily be reimplemented for a different type of problem, and we would expect it to be robust across a wide range of problem instances. We show that the problem can be solved successfully by a hyper-GA, presenting results for four versions of the hyper-GA as well as a range of simpler heuristics and applying them to five test data set.

Hyperheuristics: Recent Developments

Given their economic importance, there is continuing research interest in providing better and better solutions to real-world scheduling problems. The models for such problems are increasingly complex and exhaustive search for optimal solutions is usually impractical. Moreover, difficulty in accurately modelling the problems means that mathematically “optimal” solutions may not actually be the best possible solutions in practice. Therefore heuristic methods are often used, which do not guarantee optimal or even near optimal solutions. The main goal of heuristics is to produce solutions of acceptable quality in reasonable time. The problem owners often prefer simple, easy to implement heuristic approaches which do not require significant amount of resources for their development and implementation [12]. However, such individual heuristics do not always perform well for the variety of problem instances which may be encountered in practice. There is a wide range of modern heuristics known from the literature which are specifically designed and tuned to solve certain classes of optimisation problems. These methods are based on the partial search of the solution space and often referred as metaheuristics.

Hyperheuristics: A Tool for Rapid Prototyping in Scheduling and Optimisation

The term hyperheuristic was introduced by the authors as a high-level heuristic that adaptively controls several low-level knowledgepoor heuristics so that while using only cheap, easy-to-implement low-level heuristics, we may achieve solution quality approaching that of an expensive knowledge-rich approach. For certain classes of problems, this allows us to rapidly produce effective solutions, in a fraction of the time needed for other approaches, and using a level of expertise common among non-academic IT professionals. Hyperheuristics have been successfully applied by the authors to a real-world problem of personnel scheduling. In this paper, the authors report another successful application of hyperheuristics to a rather different real-world problem of personnel scheduling occuring at a UK academic institution. Not only did the hyperheuristics produce results of a quality much superior to that of a manual solution but also these results were produced within a period of only three weeks due to the savings resulting from using the existing hyperheuristic software framework.

Integration of continuous caster and hot strip mill planning for steel production

In this paper we present a model and a solution approach for integration of steel continuous casters and hot strip mills to provide more responsive steel production at lower unit cost. We describe the production environment and survey existing methods for planning continuous casters and hot strip mills. Since these processes lie at the solid/liquid interface we use ‘virtual’ slabs, corresponding to possible (but not yet cast) solid forms of liquid steel, as a means of communication between hot strip mill and continuous caster. We model the planning problem as a hybrid network. Our model is solved using a combination of mathematical programming and heuristic techniques and we show that the solutions provided are very nearly optimal. The approach which we describe has been implemented at several steel mills worldwide and has demonstrated significant savings. Copyright