Biological development is a remarkably complex process. A single cell, in an appropriate environment, contains su#cient information to generate a variety of di#erentiated cell types, whose spatial and temporal dynamics interact to form detailed morphological patterns. While several di#erent physical and chemical processes play an important role in the development of an organism, the locus of control is the cell's gene regulatory network.

This dissertation concerns the principles and techniques for scalable evolutionary computation to achieve better solutions for larger problems with more computational resources. It suggests that many of the limitations of existent evolutionary algorithms, such as premature convergence, stagnation, loss of diversity, lack of reliability and efficiency, are derived from the fundamental convergent evolution model, the oversimplified “survival of the fittest” Darwinian evolution model. Within this model, the higher the fitness the population achieves, the more the search capability is lost. This is also the case for many other conventional search techniques. The main result of this dissertation is the introduction of a novel sustainable evolution model, the Hierarchical Fair Competition (HFC) model, and corresponding five sustainable evolutionary algorithms (EA) for evolutionary search. By maintaining individuals in hierarchically organized fitness levels and keeping evolution going at all fitness levels, HFC transforms the conventional convergent evolutionary computation model into a sustainable search framework by ensuring a continuous supply and incorporation of low-level building blocks and by culturing and maintaining building blocks of intermediate levels with its

We review the applications of artificial life (ALife), the creation of synthetic life on computers to study, simulate, and understand living systems. The definition and features of ALife are shown by application studies. ALife application fields treated include robot control, robot manufacturing, practical robots, computer graphics, natural phenomenon modeling, entertainment, games, music, economics, Internet, information processing, industrial design, simulation software, electronics, security, data mining, and telecommunications. In order to show the status of ALife application research, this review primarily features a survey of about 180 ALife application articles rather than a selected representation of a few articles. Evolutionary computation is the most popular method for designing such applications, but recently swarm intelligence, artificial immune network, and agent-based modeling have also produced results. Applications were initially restricted to the robotics

A key property for the effectiveness of stochastic search techniques, including evolutionary algorithms, is the existence of a positive correlation between the form and the quality of candidate solutions. In this paper, we show that when the ordering of genomic symbols in a genetic algorithm is completely independent of the fitness function and therefore free to evolve along the candidate solutions it encodes, the resulting genomes self-organize into self-similar structures that favor this key stochastic search property.

This paper introduces a metric that measures symmetry in tree graphs, which allows for a statistical characterization of GP solutions by their architectural “shapes. ” A case study is given that applies this metric to 80.4 million trees to identify trends in GP runs. Results provide a first quantitative look at the dynamics of symmetry breaking.

Modular robotic systems offer potential advantages as versatile, fault-tolerant, cost-effective platforms for space exploration, but a sufficiently mature system is not yet available. We discuss the possible applications of such a system, and present prototype hardware intended as a step in the right direction. We also present elements of an automated design and optimization framework aimed at making modular robots easier to design and use, and discuss the results of applying the system to a gait optimization problem. Finally, we discuss the potential near-term applications of modular robotics to terrestrial robotics research. 1.

Abstract. Evolutionary algorithms typically use direct encodings, where each element of the phenotype is specified independently in the genotype. Because direct encodings have difficulty evolving modular and symmetric phenotypes, some researchers use indirect encodings, wherein one genomic element can influence multiple parts of a phenotype. We have previously shown that Hyper-NEAT, an indirect encoding, outperforms FT-NEAT, a direct-encoding control, on many problems, especially as the regularity of the problem increases. However, HyperNEAT is no panacea; it had difficulty accounting for irregularities in problems. In this paper, we propose a new algorithm, a Hybridized Indirect and Direct encoding (HybrID), which discovers the regularity of a problem with an indirect encoding and accounts for irregularities via a direct encoding. In three different problem domains, HybrID outperforms HyperNEAT in most situations, with performance improvements as large as 40%. Our work suggests that hybridizing indirect and direct encodings can be an effective way to improve the performance of evolutionary algorithms.

The Age-Layered Population Structure (ALPS) paradigm is a novel metaheuristic for overcoming premature convergence by running multiple instances of a search algorithm simultaneously. When the ALPS paradigm was first introduceditwascombinedwithagenerationalEvolutionaryAlgorithm(EA)and the ALPS-EA was shown to work significantly better than a basic EA. Here we describe a version of ALPS with a steady-state EA, which is well suited for use in situations in which the synchronization constraints of a generational model are not desired. To demonstrate the effectiveness of our version of ALPS we compare it against a basic steady-state EA (BEA) in two test problems and find that itoutperforms theBEAinbothcases.