Made available in DSpace on 2015-04-11T14:02:36Z (GMT). No. of bitstreams: 1 ricardo.pdf: 2499178 bytes, checksum: 722bfd9fd0d7c53ffddbc4cf6c42eeff (MD5) Previous issue date: 2010-06-01 / With the increasing availability of distance courses and educational software that support the teaching learning, the use of virtual learning environments has been gaining increasing attention from researchers in Artificial Intelligence and Computer Science in Education. This work proposes a distinct use of these environments, creating an educational software based on Multiagent Systems (MAS) to support teaching and learning process of agent oriented programming (AOP), ie, the main idea is to use agents who teach the program agents. Through this approach can guide the student through some areas of the learning process, initially by looking at the most relevant concepts and in the future, interacting more actively with the scenarios that compose the proposed environment. / Com a crescente oferta de cursos à distância e de softwares educacionais que apóiam o processo de ensino e aprendizagem, a utilização de ambientes virtuais de aprendizagem (AVA) vem ganhando cada vez mais atenção por parte dos pesquisadores das áreas de Inteligência Artificial e Informática na Educação. Este trabalho propõe uma utilização diferenciada destes ambientes, criando um software educacional baseado em Sistemas Multiagente (SMA) para apoiar o processo de ensino e aprendizagem da programação orientada a agentes (AOP), ou seja, a idéia principal consiste em utilizar agentes que ensinam a programar agentes. Através desta abordagem é possível guiar o aluno por algumas áreas do processo de aprendizado, inicialmente, observando os conceitos mais relevantes e, futuramente, interagindo de forma mais ativa com os cenários que compõem o ambiente proposto.

Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2016-04-27T12:53:22Z No. of bitstreams: 3 Dissertação - Ericsson Santana Marin - 2013 (1).pdf: 19159669 bytes, checksum: d6cdfd312c164ffbf7fd3f9ef057e9b4 (MD5) Dissertação - Ericsson Santana Marin - 2013 (2).pdf: 3072357 bytes, checksum: cf07b57f01e07d6c3e432eba959e106a (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2016-04-27T12:59:35Z (GMT) No. of bitstreams: 3 Dissertação - Ericsson Santana Marin - 2013 (1).pdf: 19159669 bytes, checksum: d6cdfd312c164ffbf7fd3f9ef057e9b4 (MD5) Dissertação - Ericsson Santana Marin - 2013 (2).pdf: 3072357 bytes, checksum: cf07b57f01e07d6c3e432eba959e106a (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2016-04-27T12:59:35Z (GMT). No. of bitstreams: 3 Dissertação - Ericsson Santana Marin - 2013 (1).pdf: 19159669 bytes, checksum: d6cdfd312c164ffbf7fd3f9ef057e9b4 (MD5) Dissertação - Ericsson Santana Marin - 2013 (2).pdf: 3072357 bytes, checksum: cf07b57f01e07d6c3e432eba959e106a (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2013-02-25 / O propósito desta dissertação é a realização de um estudo sobre redes, mais especificamente das redes sociais, visando à criação de modelos, técnicas e ferramentas para simular a sua geração, produzir o seu mapeamento estrutural gráfico, e viabilizar a realização de buscas nos ambientes que as representam. A geração e visualização de redes, ou grafos, assim como a realização de buscas, compõem um ramo continuamente estudado por diversos profissionais que ingressaram recentemente em uma nova ciência interdisciplinar, enraizada em pesquisas sociológicas e na Teoria dos Grafos: a Ciência das Redes. Alguns resultados provenientes das pesquisas desta ciência subverteram conceitos previamente definidos, e apresentaram características reveladoras sobre o universo social interconectado. Dentre eles destacam-se a desmistificação dos seis graus de separação com a comprovação do fenômeno do "mundo pequeno". Tais revelações inserem-se particularmente no estudo das redes sociais, mas demonstraram ser uma característica onipresente nas demais redes pesquisadas pelos cientistas. Consequentemente, as pesquisas sobre redes sociais principiaram o estudo sobre redes de forma mais geral, produzindo inúmeros trabalhos sobre o tema. Dentro deste contexto, a aplicação Fluzz, engendrada sob os alicerces dos Sistemas Multiagentes e dos princípios da contemporânea Ciência das Redes, é introduzida para prover ferramentas de visualização e de simulação da geração de redes sociais, baseadas nos modelos já propostos na literatura e em um novo modelo concebido nesta obra. Para o processo de busca, agentes de software capazes de atuar de forma distribuída e paralela, foram implementados utilizando-se de diversas abordagens intrínsecas à Inteligência Artificial, como Algoritmo de Dijkstra, Otimização por Colônia de Formigas e Algoritmos Genéticos. Tais agentes foram projetados para maximizar a probabilidade de influência entre os indivíduos das redes sociais, contribuindo para o aumento da atividade de conexão, de interação, e consequentemente de cooperação entre os mesmos. / O propósito desta dissertação é a realização de um estudo sobre redes, mais especificamente das redes sociais, visando à criação de modelos, técnicas e ferramentas para simular a sua geração, produzir o seu mapeamento estrutural gráfico, e viabilizar a realização de buscas nos ambientes que as representam. A geração e visualização de redes, ou grafos, assim como a realização de buscas, compõem um ramo continuamente estudado por diversos profissionais que ingressaram recentemente em uma nova ciência interdisciplinar, enraizada em pesquisas sociológicas e na Teoria dos Grafos: a Ciência das Redes. Alguns resultados provenientes das pesquisas desta ciência subverteram conceitos previamente definidos, e apresentaram características reveladoras sobre o universo social interconectado. Dentre eles destacam-se a desmistificação dos seis graus de separação com a comprovação do fenômeno do "mundo pequeno". Tais revelações inserem-se particularmente no estudo das redes sociais, mas demonstraram ser uma característica onipresente nas demais redes pesquisadas pelos cientistas. Consequentemente, as pesquisas sobre redes sociais principiaram o estudo sobre redes de forma mais geral, produzindo inúmeros trabalhos sobre o tema. Dentro deste contexto, a aplicação Fluzz, engendrada sob os alicerces dos Sistemas Multiagentes e dos princípios da contemporânea Ciência das Redes, é introduzida para prover ferramentas de visualização e de simulação da geração de redes sociais, baseadas nos modelos já propostos na literatura e em um novo modelo concebido nesta obra. Para o processo de busca, agentes de software capazes de atuar de forma distribuída e paralela, foram implementados utilizando-se de diversas abordagens intrínsecas à Inteligência Artificial, como Algoritmo de Dijkstra, Otimização por Colônia de Formigas e Algoritmos Genéticos. Tais agentes foram projetados para maximizar a probabilidade de influência entre os indivíduos das redes sociais, contribuindo para o aumento da atividade de conexão, de interação, e consequentemente de cooperação entre os mesmos.

Made available in DSpace on 2016-08-17T14:53:07Z (GMT). No. of bitstreams: 1 Jaclason Machado Veras.pdf: 1682090 bytes, checksum: 035fe122eaaac20d2dba05af3e7eab78 (MD5) Previous issue date: 2010-02-26 / This work proposes a general modeling for an educational software which will serve to verify the knowledge of geometry of fourth grade students of elementary school. The Virtual-Taneb will be based on Basic Education Evaluation System (SAEB) which is an evaluative instrument used in Brazil originated from the guidelines of the National Assessment of Educational Progress (NAEP), which is currently applied manually by written tests. One of the motivations for developing this tool was to reduce the delivery time of obtained results through the resolution of written tests, obeying Basic Education Courseworks. Another motivation was the inclusion of the Item Response Theory (IRT) as an educational evaluation quantifier and qualifier, allowing a statistical analysis from items such as central elements of tests, since the need to monitor the development process of educational evaluation systems. However, there are factors that suppress the use of IRT on a large scale, such as customizing each application and the mathematical complexity of the methods involved. This prototype of educational software will be applied to elementary schools in the State of Maranhão, Brazil. It will be adapted to the cognitive level of students through the inclusion of recourses from the area of Artificial Intelligence and besides it will enable an effective analysis of students knowledge using the IRT on the responses made. Virtual-Taneb will provide some benefits to the Brazilian society, as to favor a long-term reduction of economic investment in the evaluation process, resulting in improvements for present and future generations. Another benefit is the adequation possibility of this software to other evaluation systems, as an example, the International Program of Students Assessment (PISA), the National Examination of High School (ENEM), Prova Brasil, among others. In the future, though the adaptation of the Virtual-Taneb software, there will be the possibility of adding other subjects to the test. / Esse trabalho propõe uma modelagem geral para um software educacional que atuará na verificação do conhecimento de geometria de alunos da quarta série do ensino fundamental. O Virtual-TANEB estará baseado no Sistema de Avaliação da Educação Básica (SAEB) que é um instrumento avaliativo usado no Brasil originado a partir das diretrizes do National Assessment of Educational Progress (NAEP), que, atualmente, é aplicado de forma manual por meio de cadernos de provas. Uma das motivações para o desenvolvimento dessa ferramenta foi reduzir o tempo de entrega dos resultados obtidos, através da resolução dos cadernos de provas, obedecendo à Matriz Curricular da Educação Básica. Outra motivação foi a inclusão da Teoria da Resposta ao Item (TRI) como quantificadora e qualificadora da avaliação educacional, permitindo uma análise estatística a partir de itens como elementos centrais da prova, visto a necessidade de acompanhar o processo de evolução dos sistemas de avaliação educacional. Porém, existem fatores que suprimem a utilização da TRI em larga escala, tais como: a personalização de cada aplicação e a complexidade matemática dos métodos envolvidos. Este protótipo de software educacional será aplicado às escolas do ensino fundamental no Estado do Maranhão, Brasil. Ele se adaptará ao nível cognitivo dos alunos através da inclusão de recursos provenientes da área de Inteligência Artificial e, além disso, possibilitará uma análise mais efetiva do conhecimento dos alunos usando a TRI sobre as respostas efetuadas. O Virtual-TANEB irá proporcionar alguns benefícios para a sociedade, como favorecer a longo prazo a redução de investimento econômico no processo de avaliação, resultando em melhorias para gerações presentes e futuras. Outro beneficio é a adequação desse software a outros sistemas de avaliação, por exemplo, Programa Internacional de Avaliação de Alunos (PISA), Exame Nacional do Ensino Médio (ENEM), Prova Brasil, dentre outros. No futuro, mediante uma adaptação no software Virtual-TANEB, haverá a possibilidade de realizar a inclusão de outras disciplinas à prova.

Kollektives Handeln ist erforderlich um nachhaltige Entwicklungspfade in gekoppelten sozial-ökologischen Systemen zu erschließen, fernab von gefährlichen Kippelementen. Ohne anderen Modellierungsprinzipien ihren Nutzen abzuerkennen, schlägt diese Dissertation die Agent-Umwelt Schnittstelle als die mathematische Grundlage für das Modellieren sozial-ökologischer Systeme vor. Zuerst erweitert diese Arbeit eine Methode aus der Literatur der statistischen Physik über Lerndynamiken, um einen deterministischen Grenzübergang von etablierten Verstärkungslernalgorithmen aus der Forschung zu künstlicher Intelligenz herzuleiten. Die resultierenden Lerndynamiken zeigen eine große Bandbreite verschiedener dynamischer Regime wie z.B. Fixpunkte, Grenzzyklen oder deterministisches Chaos. Zweitens werden die hergeleiteten Lerngleichungen auf eine neu eingeführte Umwelt, das Ökologisches Öffentliches Gut, angewendet,. Sie modelliert ein gekoppeltes sozial-ökologisches Dilemma und erweitert damit etablierte soziale Dilemmaspiele um ein ökologisches Kippelement. Bekannte theoretische und empirische Ergebnisse werden reproduziert und neuartige, qualitativ verschiedene Parameterregime aufgezeigt, darunter eines, in dem diese belohnungsoptimierenden Lern-Agenten es vorziehen, gemeinsam unter einem Kollaps der Umwelt zu leiden, als in einer florierenden Umwelt zu kooperieren. Drittens stellt diese Arbeit das Optimierungsparadigma der Lern-Agenten in Frage. Die drei Entscheidungsparadimen ökonomischen Optimierung, Nachhaltigkeit und Sicherheit werden systematisch miteinander verglichen, während sie auf das Management eines umweltlichen Kippelements angewendet werden. Es wird gezeigt, dass kein Paradigma garantiert, Anforderungen anderer Paradigmen zu erfüllen, sowie dass das Fehlen eines Meisterparadigmas von besonderer Bedeutung für das Klimasystem ist, da dieses sich am Rand zwischen Parameterbereichen befinden kann, wo ökonomische Optimierung weder nachhaltig noch sicher wird. / Collective action is required to enter sustainable development pathways in coupled social-ecological systems, safely away from dangerous tipping elements. Without denying the usefulness of other model design principles, this thesis proposes the agent-environment interface as the mathematical foundation for the design of social-ecological system models. First, this work refines techniques from the statistical physics literature on learning dynamics to derive a deterministic limit of established reinforcement learning algorithms from artificial intelligence research. Illustrations of the resulting learning dynamics reveal a wide range of different dynamical regimes, such as fixed points, periodic orbits and deterministic chaos. Second, the derived multi-state learning equations are applied to a newly introduced environment, the Ecological Public Good. It models a coupled social-ecological dilemma, extending established repeated social dilemma games by an ecological tipping element. Known theoretical and empirical results are reproduced and novel qualitatively different parameter regimes are discovered, including one in which these reward-optimizing agents prefer to collectively suffer in environmental collapse rather than cooperating in a prosperous environment. Third, this thesis challenges the reward optimizing paradigm of the learning equations. It presents a novel formal comparison of the three decision paradigms of economic optimization, sustainability and safety for the governance of an environmental tipping element. It is shown that no paradigm guarantees fulfilling requirements imposed by another paradigm. Further, the absence of a master paradigm is shown to be of special relevance for governing the climate system, since the latter may reside at the edge between parameter regimes where economic welfare optimization becomes neither sustainable nor safe.

Les sujets discutés dans cette thèses’inscrivent dans le cadre général des systèmesinterconnectés. Nous abordons les réseauxmulti-agent qui ont des tâches coopératives etnous proposons un nouveau protocole deconsensus qui comporte des retards et desagents anticipatifs. Nous étudions lesconditions pour lesquelles un réseau organiséconformément au protocole proposé atteint leconsensus. Nous dérivons également desrésultats théoriques valables pour une classeplus générale de systèmes. Ces résultatsconcernent le cas des racines multiples surl’axe des imaginaires, situation qui peutcorrespondre aux réseaux avec une topologiechangeante.Dans notre approche, nous discutonsséparément le cas des racines multiples àl’origine et racines multiples sur l’axe desimaginaires sauf l’origine. Un autre résultatimportant comporte un nouveau modèle pourun réseau génétique qui fonctionne comme unmultiplexeur. Ce circuit innovant utilise troisentrées pour commander deux signaux desortie. Nous effectuons une analyse destabilité pour le modèle proposé et nousdémontrons que son point d’équilibre estunique et stable. Pour valider ce réseaugénétique, nous étudions également le modèlestochastique dérivé du modèle déterministe. / This thesis discusses diverse types ofinterconnected systems through networks. Weaddress networks of agents with cooperativetasks and propose a new consensus protocolwith delays and anticipatory agents. We studythe consensus reaching conditions for networksorganized under the proposed model.Moreover, we derive some theoretical results,which can apply to a more general class ofsystems, concerning stability issues when theconsidered system has multiple imaginaryroots. In terms of networks, this situation cancorrespond to the case of switching topologynetworks, when the network can even bedisconnected at some point.We separately discuss the case of zerocharacteristic roots, and roots laying on theimaginary axis, except the origin. Finally, wepropose a gene network model with afunctionality similar to a multiplexer circuit.Thus, we control two outputs with three inputsignals, and we carry out a stability analysis.We prove the uniqueness and the stability ofthe network steady states, and validate thecontinuous and deterministic model with astochastic model.

<p>Autonomous systems are often deployed in dynamic environments and are challenged with unexpected changes (novelties) in the environments where they receive novel data that was not seen during training. Given the uncertainty, they should be able to operate without (or with limited) human intervention and they are expected to (1) Adapt to such changes while still being effective and efficient in performing their multiple tasks. The system should be able to provide continuous availability of its critical functionalities. (2) Make informed decisions independently from any central authority. (3) Be Cognitive: learns the new context, its possible actions, and be rich in knowledge discovery through mining and pattern recognition. (4) Be Reflexive: reacts to novel unknown data as well as to security threats without terminating on-going critical missions. These characteristics combine to create the workflow of autonomous decision-making process in multi-agent environments (i.e.,) any action taken by the system must go through these characteristic models to autonomously make an ideal decision based on the situation. </p> <p><br></p> <p>In this dissertation, we propose novel learning-based models to enhance the decision-making process in autonomous multi-agent systems where agents are able to detect novelties (i.e., unexpected changes in the environment), and adapt to it in a timely manner. For this purpose, we explore two complex and highly dynamic domains </p> <p>(1) Transportation Networks (e.g., Ridesharing application): where we develop AdaPool: a novel distributed diurnal-adaptive decision-making framework for multi-agent autonomous vehicles using model-free deep reinforcement learning and change point detection. (2) Multi-agent games (e.g., Monopoly): for which we propose a hybrid approach that combines deep reinforcement learning (for frequent but complex decisions) with a fixed-policy approach (for infrequent but straightforward decisions) to facilitate decision-making and it is also adaptive to novelties. (3) Further, we present a domain agnostic approach for decision making without prior knowledge in dynamic environments using Bootstrapped DQN. Finally, to enhance security of autonomous multi-agent systems, (4) we develop a machine learning based resilience testing of address randomization moving target defense. Additionally, to further  improve the decision-making process, we present (5) a novel framework for multi-agent deep covering option discovery that is designed to accelerate exploration (which is the first step of decision-making for autonomous agents), by identifying potential collaborative agents and encouraging visiting the under-represented states in their joint observation space. </p>

Formation control in multi-agent systems represents a groundbreaking intersection of various research fields with lots of emerging applications in various technologies. The realm of space exploration also can benefit significantly from formation control, facilitating a wide range of functions from astronomical observations, and climate monitoring to enhancing telecommunications, and on-orbit servicing and assembly. In this thesis, we present a novel 3D formation control scheme for directed graphs in a leader-follower configuration, achieving (almost) global convergence to the desired shape. Specifically, we introduce three controlled variables representing bispherical coordinates that uniquely describe the formation in 3D. Acyclic triangulated directed graphs (a class of minimally acyclic persistent graphs) are used to model the inter-agent sensing topology, while the agents’ dynamics are governed by the single-integrator model and 2nd order nonlinear version representing spacecraft formation flight. The analysis demonstrates that the proposed decentralized robust formation controller using prescribed performance control ensures (almost) global asymptotic stability while avoiding potential shape ambiguities in the final formation. Furthermore, the control laws are implementable in arbitrarily oriented local coordinate frames of follower agents using only low-cost onboard vision sensors, making them suitable for practical applications. Formation maneuvering and collision avoidance among agents are also addressed which play crucial roles in the safety of space operations. Finally, we validate our formation control approach by simulation studies. / Formationskontroll i system med flera agenter representerar en banbrytande skärningspunkt av olika forskningsområden med massor av nya tillämpningar inom olika teknologier. Rymdutforskningens rike kan också dra stor nytta av formationskontroll, underlättar ett brett utbud av funktioner från astronomiska observationer och klimat övervakning för att förbättra telekommunikation och service och montering i omloppsbana. I denna avhandling presenterar vi ett nytt 3D-formationskontrollschema för riktade grafer i en ledare-följare-konfiguration, vilket uppnår (nästan) global konvergens till önskad form. Specifikt introducerar vi tre kontrollerade variabler som representerar bisfäriska koordinater som unikt beskriver formationen i 3D. Acykliska triangulerade riktade grafer (en klass av minimalt acykliska beständiga grafer) används för att modellera avkänningstopologin mellan agenter, medan agenternas dynamik styrs av singelintegratormodellen och 2:a ordningen olinjär version som representerar rymdfarkostbildningsflygning. Analysen visar att den föreslagna decentraliserade robusta formationskontrollanten använder föreskriven prestanda kontroll säkerställer (nästan) global asymptotisk stabilitet samtidigt som potentiell form undviks oklarheter i den slutliga formationen. Dessutom är kontrolllagarna implementerbara i godtyckligt orienterade lokala koordinatramar för efterföljare som endast använder lågkostnad ombord visionsensorer, vilket gör dem lämpliga för praktiska tillämpningar. Formationsmanövrering och undvikande av kollisioner mellan agenter tas också upp som spelar avgörande roller i säkerheten vid rymdoperationer. Slutligen validerar vi vår strategi för formningskontroll genom simuleringsstudier

[pt] O compartilhamento e o gerenciamento de dados pessoais são atividades desafiadoras devido à grande quantidade de dados gerados, carregados e digitalizados por cidadãos para utilizar serviços, online ou não. Esse desafio afeta não apenas os cidadãos, mas também os controladores e processadores de dados, que são responsáveis pela segurança, privacidade, anonimato e uso de dados fundados em bases legais e no propósito inicial quando os dados foram solicitados. Nesse cenário, a proteção e regulamentação dedados entram em cena para organizar esse ambiente, propondo direitos e deveres aos agentes envolvidos. No entanto, cada país é livre para criar e empregar sua própria regulamentação de dados, como o GDPR na União Europeia e a LGPD no Brasil. Portanto, embora o objetivo seja proteger os cidadãos, as regulamentações podem apresentar regras diferentes com base em sua jurisdição. Nesse cenário, as ontologias surgem para identificar as entidades e relacionamentos e mostrá-los em um nível de abstração elevado, facilitando o alinhamento das ontologias com diferentes regulamentações. Para isso, desenvolvemos um meta modelo baseado em ontologias da GDPR para possibilitar a representação da LGPD com foco na base legal do consentimento. Além disso, propusemos o GoDReP (Geraçãod e Cenários de Regulamentação de Dados) para permitir que os atores representem a interpretação de sua legislação em um cenário de aplicação específico. Apresentamos então três cenários diferentes para exercitar a aplicação do GoDReP. Além disso, nesta tese, também propomos uma arquitetura de sistema multiagente normativo e inteligente (RegulAI) para representar os direitos e obrigações apresentados pela regulamentação de dados pessoais, bem como o processo de tomada de decisão dos agentes.Por fim, desenvolvemos um estudo de caso aplicando o RegulAI no cenário de open banking. / [en] Sharing and managing personal data are challenging due to the massive amount of data generated, uploaded, and digitalized, informed by data subjects to utilize services, online or not. This challenge disrespects not only the data subjects, but also data controllers and processors, which are responsible for security, privacy, anonymity, and data usage under the legal basis applied and the initial purpose when the data were required. In this scenario, data protection and regulation take place to organize this environment proposing rights and duties to the involved agents. However, each country is free to create and employ its data regulation, e.g., GDPR in European Union and LGPD in Brazil. Therefore, although the goal is to protect the data subjects, the regulations can present different rules based on their jurisdiction. In this scenario, ontologies emerge to identify the entities and relationships to show them at a high abstraction level, facilitating ontology alignment with different regulations. To do so, we developed a metamodel based on GDPR ontologies to enable the LGPD representation focused on the consent legal basis. Moreover, we proposed GoDReP (Generation of Data Regulation Plots) to allow actors to represent their law s interpretation in a specific application scenario. As a result, we set three scenarios to exercise the GoDReP application. Moreover, in this thesis, we also propose an intelligent normative multiagent system architecture (RegulAI) to represent the personal data regulation rights and obligations, as well as the agent s decision-making process. Finally, we developed a use case applying RegulAI in the open banking scenario.

<p dir="ltr">Current artificial intelligence (AI) systems are proficient at tasks in a closed-world setting where the rules are often rigid. However, in real-world applications, the environment is usually open and dynamic. In this work, we investigate the effects of such dynamic environments on AI systems and develop ways to mitigate those effects. Central to our exploration is the concept of \textit{novelties}. Novelties encompass structural changes, unanticipated events, and environmental shifts that can confound traditional AI systems. We categorize novelties based on their representation, anticipation, and impact on agents, laying the groundwork for systematic detection and adaptation strategies. We explore novelties in the context of stochastic games. Decision-making in stochastic games exercises many aspects of the same reasoning capabilities needed by AI agents acting in the real world. A multi-agent stochastic game allows for infinitely many ways to introduce novelty. We propose an extension of the deep reinforcement learning (DRL) paradigm to develop agents that can detect and adapt to novelties in these environments. To address the sample efficiency challenge in DRL, we introduce a hybrid approach that combines fixed-policy methods with traditional DRL techniques, offering enhanced performance in complex decision-making tasks. We present a novel method for detecting anticipated novelties in multi-agent games, leveraging information theory to discern patterns indicative of collusion among players. Finally, we introduce DABLER, a pioneering deep reinforcement learning architecture that dynamically adapts to changing environmental conditions through broad learning approaches and environment recognition. Our findings underscore the importance of developing AI systems equipped to navigate the uncertainties of the open world, offering promising pathways for advancing AI research and application in real-world settings.</p>

Les systèmes complexes, naturels et artificiels, ont reçu récemment une attention renouvelée : les systèmes naturels, notamment biologiques, du fait de la nécessité de les appréhender dans une démarche systémique ; les systèmes artificiels, du fait de la dématérialisation de l'ordinateur amorcée avec l'informatique ubiquitaire. L'art, de son côté, explore depuis toujours le détournement des dernières avancées scientifiques et technologiques pour la création d'oeuvres singulières. Le travail mené depuis dix ans se situe à la croisée de ces chemins, dans le cadre unificateur des systèmes multi-agents. Je me suis intéressé plus particulièrement à l'interaction homme-machine dans le contexte de l'informatique ambiante, dans l'idée d'une construction automatique et d'une régulation dynamique de systèmes d'interaction. Ce travail est alimenté par la recherche menée dans le cadre de la simulation à base d'agents, aussi bien du point de vue des concepts et outils développés, que du point de vue de l'inspiration tirée des mécanismes d'auto-organisation et de régulation des systèmes étudiés. L'art fournit quant à lui un cadre expérimental original par la mise en scène métaphorique, dans des performances numériques interactives, des situations étudiées.