I present a new approach to evolutionary search called novelty search, wherein only behavioral novelty is rewarded, thereby abstracting evolution as a search for novel forms. This new approach contrasts with the traditional approach of rewarding progress towards the objective through an objective function. Although they are designed to light a path to the objective, objective functions can instead deceive search into converging to dead ends called local optima. As a significant problem in evolutionary computation, deception has inspired many techniques designed to mitigate it. However, nearly all such methods are still ultimately susceptible to deceptive local optima because they still measure progress with respect to the objective, which this dissertation will show is often a broken compass. Furthermore, although novelty search completely abandons the objective, it counterintuitively often outperforms methods that search directly for the objective in deceptive tasks and can induce evolutionary dynamics closer in spirit to natural evolution. The main contributions are to (1) introduce novelty search, an example of an effective search method that is not guided by actively measuring or encouraging objective progress; (2) validate novelty search by applying it to biped locomotion; (3) demonstrate novelty search’s benefits for evolvability (i.e. the ability of an organism to further evolve) in a variety of domains; (4) introduce an extension of novelty search called minimal criteria novelty search that brings a new abstraction of natural evolution to evolutionary computation (i.e. evolution as a search for many ways of iii meeting the minimal criteria of life); (5) present a second extension of novelty search called novelty search with local competition that abstracts evolution instead as a process driven towards diversity with competition playing a subservient role; and (6) evolve a diversity of functional virtual creatures in a single run as a culminating application of novelty search with local competition. Overall these contributions establish novelty search as an important new research direction for the field of evolutionary computation.

Artificial intelligence has traditionally been approached through centralized architectures and optimization of specific metrics on large datasets. However, the frontiers of fields spanning cognitive science, biology, physics, and computer science suggest that intelligence is better understood as a multi-scale, decentralized, emergent phenomenon. As such, scaling up approaches that mirror the natural world may be one of the next big advances in AI. This thesis presents Coralai, a framework for efficiently simulating the emergence of diverse artificial life ecosystems integrated with modular physics. The key innovations of Coralai include: 1) Hosting diverse Neural Cellular Automata organisms in the same simulation that can interact and evolve; 2) Allowing user-defined physics and weather that organisms adapt to and can utilize to enact environmental changes; 3) Hardware-acceleration using Taichi, PyTorch, and HyperNEAT, enabling interactive evolution of ecosystems with 500k evolved parameters on a grid of 1m+ 16-channel physics-governed cells, all in real-time on a laptop. Initial experiments with Coralai demonstrate the emergence of diverse ecosystems of organisms that employ a variety of strategies to compete for resources in dynamic environments. Key observations include competing mobile and sessile organisms, organisms that exploit environmental niches like dense energy sources, and cyclic dynamics of greedy dominance out-competed by resilience.

No description available.

En el ámbito de la Vida Artificial, el termino de agentes virtuales autónomos (AVA) es utilizado para definir personajes que habitan en un mundo virtual 3D, y cuya apariencia y comportamiento intentan imitar las de seres vivientes reales, con la intención de crear la ilusión de que ellos también lo son. Pero para que un personaje virtual resulte convincente, no solo debe parecer real, sino también comportarse de manera real. El presente trabajo hace un aporte al desarrollo de sistemas de animación del comportamiento para AVAs, enfocándose principalmente en la animación de humanos virtuales autónomos; presentando un marco general de simulacion para la incorporacion de tecnicas computacionales que faliciten el desarrollo de simulaciones de actores virtuales, a la vez que introduce un nuevo esquema de animacion del comportamiento, el cual incorpora diferentes modulos que intentan emular el proceso cognitivo que genera la toma de desiciones. La integracion de los elentos graficos y el sistema de control de comportamiento desarrollado dan origen a la generacion de simulaciones donde humanos virtuales exhiben comportamientos realistas, basados en objetivos, y motivados por parametros emocionales, estados internos, y conocimiento sobre el entorno y sobre si mismos. / One of the most exciting topics in Computer Graphics is the realistic animation of the behavior of virtual agents. In this field (also known as Artificial Life), the challenge is to create a behavioral system for the virtual agents so that they behave as realistic as possible. To this aim, a number of different techniques have been applied during the last few years. Among them, the most powerful and appealing ones seem to be those based on Artifcial Intelligence (AI) techniques. After all, most of the AI techniques (such as neural networks or expert systems) are based on the idea of reproducing the structure and behavior of the human brain. Consequently, they are optimal candidates to be applied to this goal. This work is focused on describing a general framework for simulating the behavior of virtual actors evolving within a virtual 3D world, and achive realistically to simulate the mental processes of those virtual agents and the application of some well-known AI techniques to this purpose. In particular, we explore some of these techniques and discuss how can they be successfully applied to tackle this issue. For each technique, a discussion about how can it be applied to perform specific tasks is given. We also describe how can some mental processes such as memory, reasonning, recognition, perception and others be realistically simulated by using a carefully chosen combination of these techniques.

This thesis is a contribution to the formalisation of the notion of an agent within the class of finite multivariate Markov chains. In accordance with the literature agents are are seen as entities that act, perceive, and are goaldirected. We present a new measure that can be used to identify entities (called i-entities). The intuition behind this is that entities are spatiotemporal patterns for which every part makes every other part more probable. The measure, complete local integration (CLI), is formally investigated within the more general setting of Bayesian networks. It is based on the specific local integration (SLI) which is measured with respect to a partition. CLI is the minimum value of SLI over all partitions. Upper bounds are constructively proven and a possible lower bound is proposed. We also prove a theorem that shows that completely locally integrated spatiotemporal patterns occur as blocks in specific partitions of the global trajectory. Conversely we can identify partitions of global trajectories for which every block is completely locally integrated. These global partitions are the finest partitions that achieve a SLI less or equal to their own SLI. We also establish the transformation behaviour of SLI under permutations of the nodes in the Bayesian network. We then go on to present three conditions on general definitions of entities. These are most prominently not fulfilled by sets of random variables i.e. the perception-action loop, which is often used to model agents, is too restrictive a setting. We instead propose that any general entity definition should in effect specify a subset of the set of all spatiotemporal patterns of a given multivariate Markov chain. Any such definition will then define what we call an entity set. The set of all completely locally integrated spatiotemporal patterns is one example of such a set. Importantly the perception-action loop also naturally induces such an entity set. We then propose formal definitions of actions and perceptions for arbitrary entity sets. We show that these are generalisations of notions defined for the perception-action loop by plugging the entity-set of the perception-action loop into our definitions. We also clearly state the properties that general entity-sets have but the perception-action loop entity set does not. This elucidates in what way we are generalising the perception-action loop. Finally we look at some very simple examples of bivariate Markov chains. We present the disintegration hierarchy, explain it via symmetries, and calculate the i-entities. Then we apply our definitions of perception and action to these i-entities.

Made available in DSpace on 2014-06-11T19:25:29Z (GMT). No. of bitstreams: 0 Previous issue date: 2006-10-30Bitstream added on 2014-06-13T18:28:51Z : No. of bitstreams: 1 junqueira_lhp_me_mar_prot.pdf: 265340 bytes, checksum: daf69a1d10690f402ce7b118240d49da (MD5) / É antiga a preocupação do ser humano com as questões relacionadas ao conhecimento, incluindo as discussões sobre a sua origem, seu aprendizado, sobre a nossa capacidade de utiliza-lo e sobre as características específicas da cognição humana. Essa preocupação remonta aos antigos filósofos gregos (2.500 A.C.), desenvolvendo-se posteriormente a partir da abordagem da Epistemologia, originária da Filosofia ocidental, e mais recentemente a partir do Funcionalismo, pertencente aos estudos em Filosofia da Mente e em Ciência Cognitiva. Essa última abordagem, em particular, contribuiu para o surgimento de programas de pesquisas que procuram entender o funcionamento da mente humana com a ajuda do computador. A Ciência Cognitiva possui fortes ligações com as pesquisas em Inteligência Artificial, e ambas vem se desenvolvendo desde a década de 1950. Mais recentemente, a partir da década de 1980, uma nova área de estudos surgiu, formada por pesquisas em Vida Artificial, que trabalha com a possibilidade de síntese de entidades vivas, por meios artificiais, e desde então vem chamando a atenção de pesquisadores interessados no estudo da cognição. Enquanto a Ciência Cognitiva tem ligações estreitas com a Filosofia e a Psicologia, a Vida Artificial tem uma forte inspiração na Biologia. Neste trabalho, procuramos investigar o encontro entre essas disciplinas, e seus programas de pesquisas, considerando as possibilidades de contribuição para o estudo da cognição humana, a partir de uma abordagem conjunta entre essas áreas. / It is na old thing the human concern about knowledge related questions, including discussions on its origin, its learning, about our capacity to utilize it and about specific characteristics of the human cognition. That concern remounts to the ancient greek philosophers (2.500 B.C.), developing itself later from the approach of Epistemology, originated in the occidental Philosophy, and more recently from the Functionalism, that makes part of the studies of Philosophy of Mind and of Cognitive Science. This last approach, particularly, contributed to appearing of research programs that try to understand the function of the human mind with the help of the computer. The Cognitive Science has strong relation with research in Artificial Intelligence, and both areas have been growing since the 1950 decade. More recently, from the decade 1980 on, a new area of atudies appeared, formed by researches in Artificial Life, that work with the possibility of synthesis of alive entities, by artificial means, and sice then has been attracting the attention of researchers interested in the study of Cognition. While Cognitive Science has strict relations with the Philosophy and the Psychology, Artifiical life has a strong inspiration in the Biology. In this work, we tried to investigate the meeting between these subjects, and their research programs, considering the possibilities of the contribution to the study of the human cognition, by means of an integrated approach of these areas.

This diploma thesis brings an integral view at cognitive processes connected with artificial intelligence systems, and makes a comparison with the processes observed in nature, including human being. A historical background helps us to look at the whole issue from a certain point of view. The main axis of interest comes after the historical overview and includes the following: environment -- stimulations -- processing -- reflection in the cognitive system -- reaction to stimulation; I balance the approach and the limited potential of the human being against the machine (or artificial intelligence). In the last part, there are introduced two projects that have been already implemented in the inteligent transport systems, and their potential for the further expansion and development is shown here. The main emphasis is placed on the coherence between each part of this thesis and cognitive processes, and on the relation and the mutual dependence of these processes.

Målet med den här datorbaserade filosofiska utredningen inom kognitionsvetenskap är att utforska intentionalitet i kollektiva beteenden hos artificiella svärmar. Två definitioner av intentionalitet utforskades; som representationer hos agenter och som observerbara attribut hos agenter, även kallat intentional stance. För den representativa definitionen användes en modell av kollektiv intentionalitet som integrerar två olika ståndpunkter, singularståndpunkten och pluralståndpunkten av kollektiv intentionalitet. Modellen har fem villkor för intentionalitet enligt SharedPlans. Genom att använda Belief-Desire-Intention-modellen för intelligenta agenter operationaliserades villkoren till möjliga representationer. En implementation av en målinriktad artificiell svärm i NetLogo analyserades genom att studera hur väl den uppfyllde de operationaliserade villkoren. Fyra av fem villkor var uppfyllda. Flera simuleringar med olika hastighet genomfördes även under observation. Dessa visade att processen kunde delas upp i tre faser med olika egenskaper. Den utforskande fasen hade gemensam intentionalitet centrerad till ett fåtal aktiva individer. Beslutsfasen hade individuella intentioner som kunde stå i konflikt med varandra medan gemensamma intentioner strävade mot samma mål. I flyttfasen var de individuella intentionerna att förhålla sig till varandra, vilket fick gruppen att upplevas som en enhet med intentionen att flytta gruppen. Resultaten visade att intentionalitet kan observeras och analyseras hos den här artificiella svärmen. Däremot har svärmen inte kollektiv intentionalitet utifrån båda ståndpunkterna.

Die Arbeit fragt nach dem aktuellen Bild des Menschen im westlichen Denken anhand des Leitfadens der Philosophie des Organischen von Helmuth Plessner. Dabei handelt es sich um eine acht Jahrzehnte zurückliegende philosophische Bestrebung, die, wie sich zeigen lässt, befruchtende Impulse in aktuelle Debatten und Theorien im Umkreis des Komplexes homo / humanitas einbringen kann. Plessner Werk »Die Stufen des Organischen und der Mensch.Einführung in die philosophische Anthropologie« (1928) fragt, was das organische Lebewesen Mensch sei – in methodischer Absicht. Zur Beantwortung der Frage wird zunächst das organische Leben, beginnend beim Einzeller, hinführend zum Menschen, untersucht. Das Ergebnis ist aber nicht das Endziel der Untersuchung, sondern Ausgangspunkt und Grundlage der philosophischen Anthropologie, welche Plessner als eine Hermeneutik entwirft und zum Fundament der Geisteswissenschaften erheben möchte. Plessner fand die Notwendigkeit dazu in der Ideengeschichte vor, die bereits zu seiner Zeit an einen Punkt gelangt war, an dem die Naturwissenschaften Leitfunktion übernommen hatten. »Philosophische Anthropologie« ist der Name eines interdisziplinären Programms im Dienste der Geisteswissenschaften (als einer Wissenschaft mit fundierter Deutungskompetenz). Die »Philosophie des Organischen« ist dieses Programmes Kern. Im ersten Teil Arbeit wird davon gehandelt, wie es zur Trennung in Geistes- und Naturwissenschaften kam, dem von Plessner so bezeichneten »cartesianische Alternativprinzip«. Es wird sich zeigen, dass Plessner mit seiner Analyse den Schlüssel zum Verständnis der Unvereinbarkeit von Geistes- und Naturwissenschaften gefunden hat – und damit den Schlüssel zur Überwindung dieses Dualismus. Um die Herausforderungen an ein ganzheitliches Menschenbild geht es im weiteren Verlauf. Die Arbeit stellt kurz die für Plessners Philosophie relevante Lebensphilosophie und die Phänomenologie, welche er als »hermeneutische Deskriptionsmethode« einsetzt, vor. Die »Philosophie des Organischen« gipfelt im Begriff der »exzentrischen Positionalität« und mündet in drei daraus ableitbaren »anthropologischen Grundgesetzen«. Im Anschluss wird zum Thema »Philosophische Anthropologie« übergeleitet. Diese ist fundiert durch die Philosophie des Organischen, welche somit die Funktion eines Bindeglieds übernimmt. In einem pluralistischen Dialog mit den Wissenschaften kommt es nun darauf an, die Gesetze der belebten Materie durchzuhalten, die jenseits des empiristischen Weltmodells liegen. Eine der zahlreichen daran anknüpfbaren Anwendungen findet die Arbeit abschließend in einer Auseinandersetzung mit dem Begriff der »Lebendigkeit« im Zusammenhang mit der Erforschung künstlicher Intelligenz. Es zeigt sich, dass die offenbar unreflektiert vollzogene Annäherung der Begriffe »Intelligenz« und »Lebendigkeit« unzulässig ist.

No description available.