Evolving large phenotypes remains nowadays a problem due to the combinatorial explosion of the search space. Seeking better scalability and inspired by the development of biological systems several indirect genetic encodings have been proposed. Here two different developmental mechanisms are compared. The first, developed for hardware implementations, relies on simple mechanisms inspired upon gene regulation and cell differentiation. The second, inspired by Cellular Automata, is an Artificial Embryogeny system based on cell-chemistry. This paper analyses the scalability and robustness to phenotypic faults of these two systems, with a direct encoding strategy used for comparison.

Abstract. Recently, a small number of papers have appeared in which the authors implement stochastic search algorithms, such as evolutionary computation, to generate game content, such as levels, rules and weapons. We propose a taxonomy of such approaches, centring on what sort of content is generated, how the content is represented, and how the quality of the content is evaluated. The relation between search-based and other types of procedural content generation is described, as are some of the main research challenges in this new field. The paper ends with some successful examples of this approach. 1

For computer-automated design systems to scale to complex designs they must be able to produce designs that exhibit the characteristics of modularity, regularity and hierarchy – characteristics that are found both in man-made and natural designs. Here we claim that these characteristics are enabled by implementing the attributes of combination, control-flow and abstraction in the representation. To support this claim we use an evolutionary algorithm to evolve solutions to different sizes of a table design problem using five different representations, each with different combinations of modularity, regularity and hierarchy enabled and show that the best performance happens when all three of these attributes are enabled. We also define metrics for modularity, regularity and hierarchy in design encodings and demonstrate that high fitness values are achieved with high values of modularity, regularity and hierarchy and that there is a positive correlation between increases in fitness and increases in the measured values of modularity, regularity and hierarchy.

This paper introduces a continuous model for Multi-cellular Developmental Design. The cells are fixed on a 2D grid and exchange ”chemicals ” with their neighbors during the growth process. The quantity of chemicals that a cell produces, as well as the differentiation value of the cell in the phenotype, are controlled by a Neural Network (the genotype) that takes as inputs the chemicals produced by the neighboring cells at the previous time step. In the proposed model, the number of iterations of the growth process is not pre-determined, but emerges during evolution: only organisms for which the growth process stabilizes give a phenotype (the stable state), others are declared nonviable. The optimization of the controller is done using the NEAT algorithm, that optimizes both the topology and the weights of the Neural Networks. Though each cell only receives local information from its neighbors, the experimental results of the proposed approach on the ’flags ’ problems (the phenotype must match a given 2D pattern) are almost as good as those of a direct regression approach using the same model with global information. Moreover, the resulting multi-cellular organisms exhibit almost perfect self-healing characteristics.

To increase the evolvability of larger search spaces, several indirect encoding strategies have been proposed. Among these, multicellular developmental systems are believed to offer great potential for the evolution of general, scalable and self-repairing organisms. In this paper we reinforce this view, presenting the results achieved by such a model and comparing it against direct encoding. Extra effort has been made to make this comparison both general and meaningful. Embryonal stages, a generic method showing increased evolvability and which can be applied to any developmental model, are introduced. Development with embryonal stages implement what we refer to as direct ‘Neutral Complexification’: a direct genotype complexification mechanisms by neutral duplications of expressed genes. Results show that, even for high complexity evolutionary targets, the developmental model proves more scalable. The model also shows emergent self-repair, which is used to produce highly resilient organisms. 1 1

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.

We introduce a model of cellular growth that generates neurocontrollers capable of guiding simple simulated agents in a harvesting task. The morphogenesis of the neurocontroller is itself controlled by an evolved artificial neural network. The neural network operates only on local variables and chemical concentrations and is thought as a flexible model of a gene regulatory system and cell metabolism. The model is designed in order to increase the evolvability of the growth mechanism, which constitutes a serious issue in artificial embryogeny. Also, to increase the flexibility of development, organisms are grown in embryonal stages, which allow an incremental refinement of development. Neurocontrollers are organized in horizontal layers, with vertical input and output pathways. Within the same layer, neurons can have only local connections. On one side this limits the information needed for routing and on the other makes the system easy to implement in hardware. Results show that the system is capable of developing appropriate neurocontrollers in most of the evolutionary runs.

Adaptive representations allow evolution to explore the space of phenotypes by choosing the most suitable set of genotypic parameters. Although such an approach is believed to be efficient on complex problems, few empirical studies have been conducted in such domains. In this paper, three neural network representations, a direct encoding, a complexifying encoding, and an implicit encoding capable of adapting the genotype-phenotype mapping are compared on Nothello, a complex game playing domain from the AAAI General Game Playing Competition. Implicit encoding makes the search more efficient and uses several times fewer parameters. Random mutation leads to highly structured phenotypic variation that is acquired during the course of evolution rather than built into the representation itself. Thus, adaptive representations learn to become evolvable, and furthermore do so in a way that makes search efficient on difficult coevolutionary problems.

Abstract. It has been suggested that evolving developmental programs instead of direct genotype-phenotype mappings may increase the scalability of Genetic Algorithms. Many of these Artificial Embryogeny (AE) models have been proposed and their evolutionary properties are being investigated. One of these properties concerns the fault-tolerance of at least a particular class of AE, which models the development of artificial multicellular organisms. It has been shown that such AE evolves designs capable of recovering phenotypic faults during development, even if faulttolerance is not selected for during evolution. This type of adaptivity is clearly very interesting both for theoretical reasons and possible robotic applications. In this paper we provide empirical evidence collected from a multicellular AE model showing a subtle relationship between evolution and development. These results explain why developmental fault-tolerance necessarily emerges during evolution. 1

Abstract—Procedural content generation (PCG) is an increasingly important area of technology within modern human-computer interaction (HCI) design. Personalization of user experience via affective and cognitive modeling, coupled with real-time adjustment of the content according to user needs and preferences are important steps towards effective and meaningful PCG. Games, Web 2.0, interface and software design are amongst the most popular applications of automated content generation. The paper provides a taxonomy of PCG algorithms and introduces a framework for PCG driven by computational models of user experience. This approach, which we call Experience-Driven Procedural Content Generation (EDPCG), is generic and applicable to various subareas of HCI. We employ games as an indicative example of rich HCI and complex affect elicitation, and demonstrate the approach’s effectiveness via dissimilar successful studies.