We analyze the effect of different genetic encodings used for evolving three-dimensional agents with physical morphologies. The complex phenotypes used in such systems often require nontrivial encodings. Different encodings used in Framsticks--a system for evolving three-dimensional agents--are presented. These include a low-level direct mapping and two higher-level encodings: one recurrent and one developmental. Quantitative results are presented from three simple optimization tasks (passive height, active height, and locomotion speed). The low-level encoding produced solutions of lower fitness than the two higher-level encodings under similar conditions. Results from recurrent and developmental encodings had similar fitness values but displayed qualitative differences. Desirable advantages and some drawbacks of more complex encodings are established.

Abstract. In this paper we describe our attempt to create a nature-like simulation model of artificial creatures. The model includes physical simulation of creatures, their interaction with the environment, their neural network control, and both directed and open-ended evolution. We describe a complex, three-dimensional simulation system, where various fitness criteria can be selected for evolving species, and a spontaneous evolution can be run. The work is still being developed, and we hope to make it a realistic model capable of producing real-life phenomena through an open-ended evolution in a life-like world of stick creatures.

Abstract.A three-dimensional virtual world simulation is described, where evolution takes place and it is possible to investigate behaviors of creatures in real-time. Bodies of these creatures are made of sticks, and their brains are built from artificial neurons. There are no constraints on topology and complexity of neural networks, as well as on the size of morphology. The model is inspired by biology, so energetic issues such as energy gains and losses are also considered. The evolutionary process can be guided by some pre-defined criteria, however, it is possible to mimic spontaneous evolution when the fitness is defined as the life span of the organisms. Interactions in the virtual world are discussed (including the possibility of worldwide-distributed simulation), and the results of so-far experiments are presented.

No abstract

In this article, results of the automation of an abductive procedure are reported. This work is a continuation of our earlier research [21], where a general scheme of the procedure has been proposed. Here, a more advanced system developed to generate and evaluate abductive hypotheses is introduced. Abductive hypotheses have been generated by the implementation of the Synthetic Tableau Method. Before the evaluation, the set of hypotheses has undergone several reduction phases. To assess usefulness of abductive hypotheses in the reduced set, several criteria have been employed. The evaluation of efficiency of the hypotheses has been provided by the multi-criteria dominance relation. To comprehend the abductive procedure and the evaluation process more extensively, analyses have been conducted on a number of artificially generated abductive problems.