Mike Preuss

Sequential parameter optimization

Sequential parameter optimization is a heuristic that combines classical and modern statistical techniques to improve the performance of search algorithms. To demonstrate its flexibility, three scenarios are discussed: (1) no experience how to choose the parameter setting of an algorithm is available, (2) a comparison with other algorithms is needed, and (3) an optimization algorithm has to be applied effectively and efficiently to a complex real-world optimization problem. Although sequential parameter optimization relies on enhanced statistical techniques such as design and analysis of computer experiments, it can be performed algorithmically and requires basically the specification of the relevant algorithms parameters

Experimental Methods for the Analysis of Optimization Algorithms

In operations research and computer science it is common practice to evaluate the performance of optimization algorithms on the basis of computational results, and the experimental approach should follow accepted principles that guarantee the reliability and reproducibility of results. However, computational experiments differ from those in other sciences, and the last decade has seen considerable methodological research devoted to understanding the particular features of such experiments and assessing the related statistical methods. This book consists of methodological contributions on different scenarios of experimental analysis. The first part overviews the main issues in the experimental analysis of algorithms, and discusses the experimental cycle of algorithm development; the second part treats the characterization by means of statistical distributions of algorithm performance in terms of solution quality, runtime and other measures; and the third part collects advanced methods from experimental design for configuring and tuning algorithms on a specific class of instances with the goal of using the least amount of experimentation. The contributor list includes leading scientists in algorithm design, statistical design, optimization and heuristics, and most chapters provide theoretical background and are enriched with case studies. This book is written for researchers and practitioners in operations research and computer science who wish to improve the experimental assessment of optimization algorithms and, consequently, their design.

A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft

This paper presents an overview of the existing work on AI for real-time strategy (RTS) games. Specifically, we focus on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research. We describe the specific AI challenges posed by RTS games, and overview the solutions that have been explored to address them. Additionally, we also present a summary of the results of the recent StarCraft AI competitions, describing the architectures used by the participants. Finally, we conclude with a discussion emphasizing which problems in the context of RTS game AI have been solved, and which remain open.

Exploratory landscape analysis

Exploratory Landscape Analysis subsumes a number of techniques employed to obtain knowledge about the properties of an unknown optimization problem, especially insofar as these properties are important for the performance of optimization algorithms. Where in a first attempt, one could rely on high-level features designed by experts, we approach the problem from a different angle here, namely by using relatively cheap low-level computer generated features. Interestingly, very few features are needed to separate the BBOB problem groups and also for relating a problem to high-level, expert designed features, paving the way for automatic algorithm selection.

Multiobjective exploration of the StarCraft map space

This paper presents a search-based method for generating maps for the popular real-time strategy (RTS) game StarCraft. We devise a representation of StarCraft maps suitable for evolutionary search, along with a set of fitness functions based on predicted entertainment value of those maps, as derived from theories of player experience. A multiobjective evolutionary algorithm is then used to evolve complete StarCraft maps based on the representation and selected fitness functions. The output of this algorithm is a Pareto front approximation visualizing the tradeoff between the several fitness functions used, and where each point on the front represents a viable map. We argue that this method is useful for both automatic and machine-assisted map generation, and in particular that the Pareto fronts are excellent design support tools for human map designers.

Multimodal Optimization by Means of a Topological Species Conservation Algorithm

Any evolutionary technique for multimodal optimization must answer two crucial questions in order to guarantee some success on a given task: How to most unboundedly distinguish between the different attraction basins and how to most accurately safeguard the consequently discovered solutions. This paper thus aims to present a novel technique that integrates the conservation of the best successive local individuals (as in the species conserving genetic algorithm) with a topological subpopulations separation (as in the multinational genetic algorithm) instead of the common but problematic radius-triggered manner. A special treatment for offspring integration, a more rigorous control on the allowed number and uniqueness of the resulting seeds, and a more efficient fitness evaluations budget management further augment a previously suggested naïve combination of the two algorithms. Experiments have been performed on a series of benchmark test functions, including a problem from engineering design. Comparison is primarily conducted to show the significant performance difference to the naïve combination; also the related radius-dependent conserving algorithm is subsequently addressed. Additionally, three more multimodal evolutionary methods, being either conceptually close, competitive as radius-based strategies, or recent state-of-the-art are also taken into account. We detect a clear advantage of three of the six algorithms that, in the case of our method, probably comes from the proper topological separation into subpopulations according to the existing attraction basins, independent of their locations in the function landscape. Additionally, an investigation of the parameter independence of the method as compared to the radius-compelled algorithms is systematically accomplished.

Towards multiobjective procedural map generation

A search-based procedural content generation (SBPCG) algorithm for strategy game maps is proposed. Two representations for strategy game maps are devised, along with a number of objectives relating to predicted player experience. A multiobjective evolutionary algorithm is used for searching the space of maps for candidates that satisfy pairs of these objectives. As the objectives are inherently partially conflicting, the algorithm generates Pareto fronts showing how these objectives can be balanced. Such fronts are argued to be a valuable tool for designers looking to balance various design needs. Choosing appropriate points (manually or automatically) on the Pareto fronts, maps can be found that exhibit good map design according to specified criteria, and could either be used directly in e.g. an RTS game or form the basis for further human design.

The 2009 Simulated Car Racing Championship

In this paper, we overview the 2009 Simulated Car Racing Championship-an event comprising three competitions held in association with the 2009 IEEE Congress on Evolutionary Computation (CEC), the 2009 ACM Genetic and Evolutionary Computation Conference (GECCO), and the 2009 IEEE Symposium on Computational Intelligence and Games (CIG). First, we describe the competition regulations and the software framework. Then, the five best teams describe the methods of computational intelligence they used to develop their drivers and the lessons they learned from the participation in the championship. The organizers provide short summaries of the other competitors. Finally, we summarize the championship results, followed by a discussion about what the organizers learned about 1) the development of high-performing car racing controllers and 2) the organization of scientific competitions.

Effects of scale-free and small-world topologies on binary coded self-adaptive CEA

In this paper we investigate the properties of CEAs with populations structured as Watts–Strogatz small-world graphs and Albert–Barabasi scale-free graphs as problem solvers, using several standard discrete optimization problems as a benchmark. The EA variants employed include self-adaptation of mutation rates. Results are compared with the corresponding classical panmictic EA showing that topology together with self-adaptation drastically influences the search.

Capabilities of EMOA to detect and preserve equivalent pareto subsets

Recent works in evolutionary multiobjective optimization suggest to shift the focus from solely evaluating optimization success in the objective space to also taking the decision space into account. They indicate that this may be a) necessary to express the users requirements of obtaining distinct solutions (distinct Pareto set parts or subsets) of similar quality (comparable locations on the Pareto front) in real-world applications, and b) a demanding task for the currently most commonly used algorithms.We investigate if standard EMOA are able to detect and preserve equivalent Pareto subsets and develop an own special purpose EMOA that meets these requirements reliably.