Can't Stop is a jeopardy stochastic game played on an octagonal game board with four six-sided dice. Optimal strategies have been computed for some simplified versions of Can't Stop by employing retrograde analysis and value iteration combined with Newton's method. These computations result in databases that map game positions to optimal moves. Solving the original game, however, is infeasible with current techniques and technology. This paper describes the creation of heuristic strategies for solitaire Can't Stop by generalizing an existing heuristic and using genetic algorithms to optimize the generalized parameters. The resulting heuristics are easy to use and outperform the original heuristic by 19%. Results of the genetic algorithm are compared to the known optimal results for smaller versions of Can't Stop, and data is presented showing the relative insensitivity of the particular genetic algorithm used to the balance between reduced noise and increased population diversity.

Our aim in this paper is to analyse the phenotypic effects (evolvability) of diverse coding conversion operators in an instance of the states based evolutionary algorithm (SEA). Since the representation of solutions or the selection of the best encoding during the optimization process has been proved to be very important for the efficiency of evolutionary algorithms (EAs), we will discuss a strategy of coupling more than one representation and different procedures of conversion from one coding to another during the search. Elsewhere, some EAs try to use multiple representations (SM-GA, SEA, etc.) in intention to benefit from the characteristics of each of them. In spite of those results, this paper shows that the change of the representation is also a crucial approach to take into consideration while attempting to increase the performances of such EAs. As a demonstrative example, we use a two states SEA (2-SEA) which has two identical search spaces but different coding conversion operators. The results show that the way of changing from one coding to another and not only the choice of the best representation nor the representation itself is very advantageous and must be taken into account in order to well-desing and improve EAs execution.

We recently reported that the simple genetic algorithm (SGA) is capable of performing a remarkable form of sublinear computation which has a straightforward connection with the general problem of interacting attributes in data-mining. In this paper we explain how the SGA can leverage this computational proficiency to perform efficient adaptation on a broad class of fitness functions. Based on the relative ease with which a practical fitness function might belong to this broad class, we submit a new hypothesis about the workings of genetic algorithms. We explain why our hypothesis is superior to the building block hypothesis, and, by way of empirical validation, we present the results of an experiment in which the use of a simple mechanism called clamping dramatically improved the performance of an SGA with uniform crossover on large, randomly generated instances of the MAX 3-SAT problem.

I argue that data becomes temporarily interesting by itself to some self-improving, but computationally limited, subjective observer once he learns to predict or compress the data in a better way, thus making it subjectively simpler and more beautiful. Curiosity is the desire to create or discover more non-random, non-arbitrary, regular data that is novel and surprising not in the traditional sense of Boltzmann and Shannon but in the sense that it allows for compression progress because its regularity was not yet known. This drive maximizes interestingness, the first derivative of subjective beauty or compressibility, that is, the steepness of the learning curve. It motivates exploring infants, pure mathematicians, composers, artists, dancers, comedians, yourself, and (since 1990) artificial systems.

Auctions are markets with strict regulations governing the information available to traders in the market and the possible actions they can take. Since well designed auctions achieve desirable economic outcomes, they have been widely used in solving real-world optimization problems, and in structuring stock or futures exchanges. Auctions also provide a very valuable testing-ground for economic theory, and they play an important role in computer-based control systems. Auction mechanism design aims to manipulate the rules of an auction in order to achieve specific goals. Economists traditionally use mathematical methods, mainly game theory, to analyze auctions and design new auction forms. However, due to the high complexity of auctions, the mathematical models are typically simplified to obtain results, and this makes it difficult to apply results derived from such models to market environments in the real world. As a result, researchers are turning to empirical approaches. This report aims to survey the theoretical and empirical approaches to designing auction mechanisms and trading strategies with more weights on empirical ones, and build the foundation for further research in the field.

The pace of progress in the fields of Evolutionary Computation and Machine Learning is currently limited -- in the former field, by the improbability of making advantageous extensions to evolutionary algorithms when their capacity for adaptation is poorly understood, and in the latter by the difficulty of finding effective semi-principled reductions of hard real-world problems to relatively simple optimization problems. In this paper we explain why a theory which can accurately explain the simple genetic algorithm's remarkable capacity for adaptation has the potential to address both these limitations. We describe what we believe to be the impediments -- historic and analytic -- to the discovery of such a theory and highlight the negative role that the building block hypothesis (BBH) has played. We argue based on experimental results that a fundamental limitation which is widely believed to constrain the SGA's adaptive ability (and is strongly implied by the BBH) is in fact illusionary and does not exist. The SGA therefore turns out to be more powerful than it is currently thought to be. We give conditions under which it becomes feasible to numerically approximate and study the multivariate marginals of the search distribution of an infinite population SGA over multiple generations even when its genomes are long, and explain why this analysis is relevant to the riddle of the SGA's remarkable adaptive abilities.

When genetic algorithms are used to evolve decision trees, key tree quality parameters can be recursively computed and re-used across generations of partially similar decision trees. Simply storing instance indices at leaves is enough for fitness to be piecewise computed in a lossless fashion. We show the derivation of the (substantial) expected speed-up on two bounding case problems and trace the attractive property of lossless fitness inheritance to the divide-and-conquer nature of decision trees. The theoretical results are supported by experimental evidence.

This paper presents several types of evolutionary algorithms (EAs) used for global optimization on real domains. The interest has been focused on multimodal problems, where the difficulties of a premature convergence usually occurs. First the standard genetic algorithm (SGA) using binary encoding of real values and its unsatisfactory behavior with multimodal problems is briefly reviewed together with some improvements of fighting premature convergence. Two types of real encoded methods based on differential operators are examined in detail: the differential evolution (DE), a very modern and effective method firstly published by R. Storn and K. Price, and the simplified real-coded differential genetic algorithm SADE proposed by the authors. In addition, an improvement of the SADE method, called CERAF technology, enabling the population of solutions to escape from local extremes, is examined. All methods are tested on an identical set of objective functions and a systematic comparison based on a reliable methodology is presented. It is confirmed that real coded methods generally exhibit better behavior on real domains than the binary algorithms, even when extended by several improvements. Furthermore, the positive influence of the differential operators due to their possibility of self-adaptation is demonstrated. From the reliability point of view, it seems that the real encoded differential algorithm, improved by the technology described in this paper, is a universal and reliable method capable of solving all proposed test problems.

This paper presents comparison of several stochastic optimization algorithms developed by authors in their previous works for the solution of some problems arising in Civil Engineering. The introduced optimization methods are: the integer augmented simulated annealing (IASA), the real-coded augmented simulated annealing (RASA) [10], the differential evolution (DE) in its original fashion developed by R. Storn and K. Price[15] and simplified real-coded differential genetic algorithm (SADE) [6]. Each of these methods was developed for some specific optimization problem; namely the Chebychev trial polynomial problem, the so called type 0 function and two engineering problems - the reinforced concrete beam layout and the periodic unit cell problem respectively. Detailed and extensive numerical tests were performed to examine the stability and efficiency of proposed algorithms. The results of our experiments suggest that the performance and robustness of RASA, IASA and SADE methods are comparable, while the DE algorithm performs slightly worse. This fact together with a small number of internal parameters promotes the SADE method as the most robust for practical use.

When a considerable number of mutations have no effects on fitness values, the fitness landscape is said neutral. In order to study the interplay between neutrality, which exists in many real-world applications, and performances of metaheuristics, it is useful to design landscapes which make it possible to tune precisely neutral degree distribution. Even though many neutral landscape models have already been designed, none of them are general enough to create landscapes with specific neutral degree distributions. We propose three steps to design such landscapes: first using an algorithm we construct a landscape whose distribution roughly fits the target one, then we use a simulated annealing heuristic to bring closer the two distributions and finally we affect fitness values to each neutral network. Then using this new family of fitness landscapes we are able to highlight the interplay between deceptiveness and neutrality.