Abstract | In this paper we describe the evolution of a discrete-time recurrent neural network to control a real mobile robot. In all our experiments the evolutionary procedure is carried out entirely on the physical robot without human intervention. We showthat the autonomous development of a set of behaviors for locating a battery charger and periodically returning to it can be achieved by lifting constraints in the design of the robot/environment interactions that were employed in a preliminary experiment. The emergent homing behavior is based on the autonomous development ofaninternal neural topographic map (which is not pre-designed) that allows the robot to choose the appropriate trajectory as function of location and remaining energy.

It is appealing to consider hybrids of neural-network learning algorithms with evolutionary search procedures, simply because Nature has so successfully done so. In fact, computational models of learning and evolution offer theoretical biology new tools for addressing questions about Nature that have dogged that field since Darwin [Belew, 1990]. The concern of this paper, however, is strictly artificial: Can hybrids of connectionist learning algorithms and genetic algorithms produce more efficient and effective algorithms than either technique applied in isolation? The paper begins with a survey of recent work (by us and others) that combines Holland's Genetic Algorithm (GA) with connectionist techniques and delineates some of the basic design problems these hybrids share. This analysis suggests the dangers of overly literal representations of the network on the genome (e.g., encoding each weight explicitly). A preliminary set of experiments that use the GA to find unusual but successf...

This article reviews the growing body of scientific work in Artificial Chemistry. First, common motivations and fundamental concepts are introduced. Second, current research activities are discussed along three application dimensions: modelling, information processing and optimization. Finally, common phenomena among the different systems are summarized. It is argued here that Artificial Chemistries are "the right stuff" for the study of pre-biotic and bio-chemical evolution, and they provide a productive framework for questions regarding the origin and evolution of organizations in general. Furthermore, Artificial Chemistries have a broad application range to practical problems as shown in this review.

This paper proposes a method of visualizing and measuring evolution in Artificial Life simulations. The evolving population of agents is treated as a dynamical system. The proposed method is inspired by the notion of trajectory. This paper provides examples of tracking of trajectories of evolutionary system in the spaces of genotypes, strategies and some global characteristics. Visualization similar to bifurcation diagram is used to represent results of series of simulations.

The effects of differing dispersal distances on the evolution of virulence in parasites was explored through the use of a configuration model. Both hosts and parasites were individually represented on a two-dimensional surface. Each parasite had a "gene" for virulence that determined the amount of energy the parasite removed from its host in a single time step. When a parasite reproduced, its offspring was placed near to, or far away from the parent depending on a dispersal distance parameter. The offspring's virulence was also mutated slightly at reproduction. Distance of dispersal had a small but statistically significant, positive effect on the evolution of the parasite's virulence. That is, those parasites that were forced to disperse their offspring further away, evolved a higher level of virulence than the parasites that dispersed their offspring locally. Introduction There is a growing interest in the application of evolutionary theory to disease control and treatment [ Ewald,...

Evolutionary computation is a rapidly expanding field of research with a long history. Much of that history remains unknown to most practitioners and researchers. This paper offers a review of selected foundational efforts in evolutionary computation. A brief initial overview of the essential components of evolutionary algorithms is presented, followed by a review of early research in artificial life, evolving programs, and evolvable hardware. Comments on theoretical developments and future developments conclude the review.

A computer based simulation with artificial adaptive agents for predicting secondary structure from the protein hydrophobicity ffl [34] Accurate Gen. Lander: An Experiment in ffl NeuroGenetic Cntr. [149] adaptation Characterizing the ffl abilities of a class of gen. based machine learning alg. [45] ffl in dynamic environments through a minimal probability of exploration [125] adaptive A computer based simulation with artificial ffl agents for predicting secondary structure from the protein hydrophobicity [Abstract] [15] -- A hierarchical classifier syst. implementing a motivationally autonomous ffl animat [40] -- Computer simulations of ffl behavior in animats [98] -- Darwinian ffl simulated annealing [99] -- Extended classifiers for simulation of ffl behavior [114] -- From animals to animats: everything you wanted to know about the simulation of ffl behaviour [19] -- Fuzzy Q-learning and evol. strategy for ffl fuzzy cntr. [115] -- Simulation of ffl behavior in animats: Review and pr...