This paper presents results from an experimental computer simulated stock market. In this market artificial intelligence algorithms take on the role of traders. They make predictions about the future, and buy and sell stock as indicated by their expectations of future risk and return. Prices are set endogenously to clear the market. Time series from this market are analyzed from the standpoint of well-known empirical features in real markets. The simulated market is able to replicate several of these phenomenon, including fundamental and technical predictability, volatility persistence, and leptokurtosis. Moreover, agent behavior is shown to be consistent with these features, in that they condition on the variables that are found to be significant in the time series tests. Agents are also able to collectively learn a homogeneous rational expectations equilibrium for certain parameters giving both time series and individual forecast values

Building blocks are a ubiquitous feature at all levels of human understanding, from perception through science and innovation. Genetic algorithms are designed to exploit this prevalence. A new, more robust class of genetic algorithms, cohort genetic algorithms (cGA's), provides substantial advantages in exploring search spaces for building blocks while exploiting building blocks already found. To test these capabilities, a new, general class of test functions, the hyperplane-defined functions (hdf's), has been designed. Hdf's offer the means of tracing the origin of each advance in performance; at the same time hdf's are resistant to reverse engineering, so that algorithms cannot be designed to take advantage of the characteristics of particular examples. Keywords Building blocks, chromosome-like strings, crossover, fitness, genetic algorithms, schema, search spaces, robustness, selection, test functions. 1 Introduction The "building block thesis" holds that most of what w...

We present an agent-based computational economics (ACE) model of the wholesale "sh market in Marseille. Two of the stylized facts of that market are high loyalty of buyers to sellers, and persistent price dispersion, although it is every day the same population of sellers and buyers that meets in the same market hall. In our ACE model, sellers decide on quantities to supply, prices to ask, and how to treat loyal customers, while buyers decide which sellers to visit, and which prices to accept. Learning takes place through reinforcement. The model explains both stylized facts price dispersion and high loyalty. In a coevolutionary process, buyers learn to become loyal as sellers learn to o!er higher utility to loyal buyers, while these sellers, in turn, learn to o!er higher utility to loyal buyers as they happen to realize higher gross revenues from loyal buyers. The model also explains the e!ect of heterogeneity of the buyers. We analyze how this leads to subtle di!erences in the shopping patterns of the di!erent types of buyers, and how this is

The current implementation of the Neo-Darwinian model of evolution typically assumes that the set of possible phenotypes is organized into a highly symmetric and regular space equipped with a notion of distance, for example, a Euclidean vector space. Recent computational work on a biophysical genotype-phenotype model based on the folding of RNA sequences into secondary structures suggests a rather different picture. If phenotypes are organized according to genetic accessibility, the resulting space lacks a metric and is formalized by an unfamiliar structure, known as a pretopology. Patterns of phenotypic evolution -- such as punctuation, irreversibility, modularity -- result naturally from the properties of this space. The classical framework, however, addresses these patterns by exclusively invoking natural selection on suitably imposed fitness landscapes. We propose to extend the explanatory level for phenotypic evolution from fitness considerations alone to include the topological st...

The explicit investigation of anticipations in relation to adaptive behavior is a recent approach. This chapter first provides psychological background that motivates and inspires the study of anticipations in the adaptive behavior field. Next, a basic framework for the study of anticipations in adaptive behavior is suggested. Different anticipatory mechanisms are identified and characterized. First fundamental distinctions are drawn between implicit anticipatory behavior, payoff anticipatory behavior, sensory anticipatory behavior, and state anticipatory behavior. A case study allows further insights into the drawn distinctions.

This paper documents our investigation into various heuristic methods to solve the vehicle routing problem with time windows (VRPTW) to near optimal solutions. The objective of the VRPTW is to serve a number of customers within predefined time windows at minimum cost (in terms of distance travelled), without violating the capacity and total trip time constraints for each vehicle. Combinatorial optimisation problems of this kind are non-polynomial-hard (NP-hard) and are best solved by heuristics. The heuristics we are exploring here are mainly third-generation artificial intelligent (AI) algorithms, namely simulated annealing (SA), Tabu search (TS) and genetic algorithm (GA). Based on the original SA theory proposed by Kirkpatrick and the work by Thangiah, we update the cooling scheme and develop a fast and efficient SA heuristic. One of the variants of Glover's TS, strict Tabu, is evaluated and first used for VRPTW, with the help of both recency and frequency measures. Our GA implementation, unlike Thangiah's genetic sectoring heuristic, uses intuitive integer string representation and incorporates several new crossover operations and other advanced techniques such as hybrid hill-climbing and adaptive mutation scheme. We applied each of the heuristics developed to Solomon's 56 VRPTW 100-customer instances, and yielded 18 solutions better than or equivalent to the best solution ever published for these problems. This paper is also among the first to document the implementation of all the

The paper analyses recent developments of a number of memory-based metaheuristics such as taboo search, scatter search, genetic algorithms and ant colonies. It shows that the implementations of these general solving methods are more and more similar. So, a unified presentation is proposed under the name of Adaptive Memory Programming (AMP). A number of methods recently developed for the quadratic assignment, vehicle routing and graph colouring problems are reviewed and presented under the adaptive memory programming point of view. AMP presents a number of interesting aspects such as a high parallelization potential and the ability of dealing with real and dynamic applications.

In this paper a methodology for feature selection for the handwritten digit string recognition is proposed. Its novelty lies in the use of a multi-objective genetic algorithm where sensitivity analysis and neural network are employed to allow the use of a representative database to evaluate tness and the use of a validation database to identify the subsets of selected features that provide a good generalization. Some advantages of this approach include the ability to accommodate multiple criteria such as number of features and accuracy of the classier, as well as the capacity to deal with huge databases in order to adequately represent the pattern recognition problem. Comprehensive experiments on the NIST SD19 demonstrate the feasibility of the proposed methodology.

The identi cation, design, and implementation of strategies for cooperation is a central research issue in the eld of Distributed Arti cial Intelligence (DAI). We propose a novel approach tothe construction of cooperation strategies for a group of problem solvers based on the Genetic Programming (GP) paradigm. GPs are a class of adaptive algorithms used to evolve solution structures that optimize a given evaluation criterion. Our approach is based on designing a representation for cooperation strategies that can be manipulated by GPs. We present results from experiments in the predator-prey domain, whichhas been extensively studied as a easy-to-describe but di cult-to-solve cooperation problem domain. The key aspect of our approach isthe minimalreliance on domain knowledge and human intervention in the construction of good cooperation strategies. Promising comparison results withprior systems lend credence to the viabilityofthis approach. Topic areas: Evolutionary computation, cooperation strategies 1

Abstract not found