This paper describes a system for the evolution and co-evolution of virtual creatures that compete in physically simulated three-dimensional worlds. Pairs of individuals enter one-on-one contests in which they contend to gain control of a common resource. The winners receive higher relative fitness scores allowing them to survive and reproduce. Realistic dynamics simulation including gravity, collisions, and friction, restricts the actions to physically plausible behaviors. The morphology of these creatures and the neural systems for controlling their muscle forces are both genetically determined, and the morphology and behavior can adapt to each other as they evolve simultaneously. The genotypes are structured as directed graphs of nodes and connections, and they can efficiently but flexibly describe instructions for the development of creatures ’ bodies and control systems with repeating or recursive components. When simulated evolutions are performed with populations of competing creatures, interesting and diverse strategies and counter-strategies emerge. 1

This tutorial covers the canonical genetic algorithm as well as more experimental forms of genetic algorithms, including parallel island models and parallel cellular genetic algorithms. The tutorial also illustrates genetic search byhyperplane sampling. The theoretical foundations of genetic algorithms are reviewed, include the schema theorem as well as recently developed exact models of the canonical genetic algorithm.

Evolutionary computation has started to receive significant attention during the last decade, although the origins can be traced back to the late 1950s. This article surveys the history as well as the current state of this rapidly growing field. We describe the purpose, the general structure and the working principles of different approaches, including genetic algorithms (GA) (with links to genetic programming (GP) and classifier systems (CS)), evolution strategies (ES), and evolutionary programming (EP), by analysis and comparison of their most important constituents (i.e., representations, variation operators, reproduction and selection mechanism). Finally, we give a brief overview on the manifold of application domains, although this necessarily must remain incomplete.

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...

In the typical genetic algorithm experiment, the fitness function is constructed to be independent of the contents of the population to provide a consistent objective measure. Such objectivity entails significant knowledge about the environment which suggests either the problem has previously been solved or other non-evolutionary techniques may be more efficient. Furthermore, for many complex tasks an independent fitness function is either impractical or impossible to provide. In this paper, we demonstrate that competitive fitness functions, i.e. fitness functions that are dependent on the constituents of the population, can provide a more robust training environment than independent fitness functions. We describe three differing methods for competitive fitness, and discuss their respective advantages.

To successfully apply evolutionary algorithms to the solution of increasingly complex problems, we must develop effective techniques for evolving solutions in the form of interacting coadapted subcomponents. One of the major difficulties is finding computational extensions to our current evolutionary paradigms that will enable such subcomponents to “emerge ” rather than being hand designed. In this paper, we describe an architecture for evolving such subcomponents as a collection of cooperating species. Given a simple stringmatching task, we show that evolutionary pressure to increase the overall fitness of the ecosystem can provide the needed stimulus for the emergence of an appropriate number of interdependent subcomponents that cover multiple niches, evolve to an appropriate level of generality, and adapt as the number and roles of their fellow subcomponents change over time. We then explore these issues within the context of a more complicated domain through a case study involving the evolution of artificial neural networks.

This thesis addresses situated, embodied agents interacting in complex domains. It focuses on two problems: 1) synthesis and analysis of intelligent group behavior, and 2) learning in complex group environments. Basic behaviors, control laws that cluster constraints to achieve particular goals and have the appropriate compositional properties, are proposed as effective primitives for control and learning. The thesis describes the process of selecting such basic behaviors, formally specifying them, algorithmically implementing them, and empirically evaluating them. All of the proposed ideas are validated with a group of up to 20 mobile robots using a basic behavior set consisting of: safe--wandering, following, aggregation, dispersion, and homing. The set of basic behaviors acts as a substrate for achieving more complex high--level goals and tasks. Two behavior combination operators are introduced, and verified by combining subsets of the above basic behavior set to implement collective flocking, foraging, and docking. A methodology is introduced for automatically constructing higher--level behaviors

Niching methods extend genetic algorithms to domains that require the location and maintenance of multiple solutions. Such domains include classification and machine learning, multimodal function optimization, multiobjective function optimization, and simulation of complex and adaptive systems. This study presents a comprehensive treatment of niching methods and the related topic of population diversity. Its purpose is to analyze existing niching methods and to design improved niching methods. To achieve this purpose, it first develops a general framework for the modelling of niching methods, and then applies this framework to construct models of individual niching methods, specifically crowding and sharing methods. Using a constructed model of crowding, this study determines why crowding methods over the last two decades have not made effective niching methods. A series of tests and design modifications results in the development of a highly effective form of crowding, called determin...

Many seemingly different problems in artificial intelligence, symbolic processing, and machine learning can be viewed as requiring discovery of a computer program that produces some desired output for particular inputs. When viewed in this way, the process of solving these problems becomes equivalent to searching a space of possible computer programs for a most fit individual computer program. The new genetic programming paradigm described herein provides a way to search for this most fit individual computer program. In this new genetic programming paradigm, populations of computer programs are genetically bred using the Darwinian principle of survival of the fittest and using a genetic crossover (recombination) operator appropriate for genetically mating computer programs. In this paper, the process of formulating and solving problems using this new paradigm is illustrated using examples from various areas.

This paper discusses the feasibility of applying evolutionary methods to automatically generating controllers for physical mobile robots. We overview the state of the art in the field, describe some of the main approaches, discuss the key challenges, unanswered problems, and some promising directions. 1 Introduction This paper is concerned with the distant goal of automated synthesis of robot controllers. Specifically, we focus on the problems of evolving controllers for physically embodied and embedded systems that deal with all of the noise and uncertainly present in the world. We will also address some systems that evolve both the morphology and the controller of a robot. Within the scope of this paper we define morphology as the physical, embodied characteristics of the robot, such as its mechanics and sensor organization. Given that definition, the only examples of evolving both morphology and control exist in simulation. Evolutionary methods for automated hardware design are an ...