Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Cooperative multi-agent systems (MAS) are finding applications in a wide variety of domains, including sensor networks, robotics, distributed control, collaborative decision support systems, and data mining. A cooperative MAS consists of a group of autonomous agents that interact with one another in order to optimize a global performance measure. A central challenge in cooperative MAS research is to design distributed coordination policies. Designing optimal distributed coordination policies offline is usually not feasible for large-scale complex multi-agent systems, where 10s to 1000s of agents are involved, there is limited communication bandwidth and communication delay between agents, agents have only limited partial views of the whole system, etc. This infeasibility is either due to a prohibitive cost to build an accurate decision model, or a dynamically evolving environment, or the intractable computation complexity. This thesis develops a multi-agent reinforcement learning paradigm to allow agents to effectively learn and adapt coordination policies in complex cooperative domains without explicitly building the complete decision models. With multi-agent reinforcement learning (MARL), agents explore the environment through trial and error, adapt their behaviors to the dynamics of the uncertain and evolving environment, and improve their performance through experiences. To achieve the scalability of MARL and ensure the global performance, the MARL paradigm developed in this thesis restricts the learning of each agent to using information locally observed or received from local interactions with a limited number of agents (i.e., neighbors) in the system and exploits non-local interaction information to coordinate the learning processes of agents. This thesis develops new MARL algorithms for agents to learn effectively with limited observations in multi-agent settings and introduces a low-overhead supervisory control framework to collect and integrate non-local information into the learning process of agents to coordinate their learning. More specifically, the contributions of already completed aspects of this thesis are as follows: Multi-Agent Learning with Policy Prediction: This thesis introduces the concept of policy prediction and augments the basic gradient-based learning algorithm to achieve two properties: best-response learning and convergence. The convergence property of multi-agent learning with policy prediction is proven for a class of static games under the assumption of full observability. MARL Algorithm with Limited Observability: This thesis develops PGA-APP, a practical multi-agent learning algorithm that extends Q-learning to learn stochastic policies. PGA-APP combines the policy gradient technique with the idea of policy prediction. It allows an agent to learn effectively with limited observability in complex domains in presence of other learning agents. The empirical results demonstrate that PGA-APP outperforms state-of-the-art MARL techniques in both benchmark games. MARL Application in Cloud Computing: This thesis illustrates how MARL can be applied to optimizing online distributed resource allocation in cloud computing. Empirical results show that the MARL approach performs reasonably well, compared to an optimal solution, and better than a centralized myopic allocation approach in some cases. A General Paradigm for Coordinating MARL: This thesis presents a multi-level supervisory control framework to coordinate and guide the agents' learning process. This framework exploits non-local information and introduces a more global view to coordinate the learning process of individual agents without incurring significant overhead and exploding their policy space. Empirical results demonstrate that this coordination significantly improves the speed, quality and likelihood of MARL convergence in large-scale, complex cooperative multi-agent systems. An Agent Interaction Model: This thesis proposes a new general agent interaction model. This interaction model formalizes a type of interactions among agents, called {\em joint-even-driven} interactions, and define a measure for capturing the strength of such interactions. Formal analysis reveals the relationship between interactions between agents and the performance of individual agents and the whole system. Self-Organization for Nearly-Decomposable Hierarchy: This thesis develops a distributed self-organization approach, based on the agent interaction model, that dynamically form a nearly decomposable hierarchy for large-scale multi-agent systems. This self-organization approach is integrated into supervisory control framework to automatically evolving supervisory organizations to better coordinating MARL during the learning process. Empirically results show that dynamically evolving supervisory organizations can perform better than static ones. Automating Coordination for Multi-Agent Learning: We tailor our supervision framework for coordinating MARL in ND-POMDPs. By exploiting structured interaction in ND-POMDPs, this tailored approach distributes the learning of the global joint policy among supervisors and employs DCOP techniques to automatically coordinate distributed learning to ensure the global learning performance. We prove that this approach can learn a globally optimal policy for ND-POMDPs with a property called groupwise observability.

Terrain is a key aspect of a game to help immerse the player in the virtual environment. Producing such content can however be quite challenging for a designer since landscapes need to satisfy the game’s visual and playable needs. This paper presents a way to generate different terrain features through the control of software agents to help aid the design process. An artifact was developed which enabled the terrain features to be evaluated in combination with each other. While the features themselves performed well in isolation there would be a few issues depending on how these were integrated.

No description available.

A Bayesian network approach to self-organization and learning is introduced for use with intelligent agents. Bayesian networks, with the help of influence diagrams, are employed to create a decision-theoretic intelligent agent. Influence diagrams combine both Bayesian networks and utility theory. In this research, an intelligent agent is modeled by its belief, preference, and capabilities attributes. Each agent is assumed to have its own belief about its environment. The belief aspect of the intelligent agent is accomplished by a Bayesian network. The goal of an intelligent agent is said to be the preference of the agent and is represented with a utility function in the decision theoretic intelligent agent. Capabilities are represented with a set of possible actions of the decision-theoretic intelligent agent. Influence diagrams have utility nodes and decision nodes to handle the preference and capabilities of the decision-theoretic intelligent agent, respectively. Learning is accomplished by Bayesian networks in the decision-theoretic intelligent agent. Bayesian network learning methods are discussed intensively in this paper. Because intelligent agents will explore and learn the environment, the learning algorithm should be implemented online. None of the existent Bayesian network learning algorithms has online learning. Thus, an online Bayesian network learning method is proposed to allow the intelligent agent learn during its exploration. Self-organization of the intelligent agents is accomplished because each agent models other agents by observing their behavior. Agents have belief, not only about environment, but also about other agents. Therefore, an agent takes its decisions according to the model of the environment and the model of the other agents. Even though each agent acts independently, they take the other agents behaviors into account to make a decision. This permits the agents to organize themselves for a common task. To test the proposed intelligent agent's learning and self-organizing abilities, Windows application software is written to simulate multi-agent systems. The software, IntelliAgent, lets the user design decision-theoretic intelligent agents both manually and automatically. The software can also be used for knowledge discovery by employing Bayesian network learning a database. Additionally, we have explored a well-known herding problem to obtain sound results for our intelligent agent design. In the problem, a dog tries to herd a sheep to a certain location, i.e. a pen. The sheep tries to avoid the dog by retreating from the dog. The herding problem is simulated using the IntelliAgent software. Simulations provided good results in terms of the dog's learning ability and its ability to organize its actions according to the sheep's (other agent) behavior. In summary, a decision-theoretic approach is applied to the self-organization and learning problems in intelligent agents. Software was written to simulate the learning and self-organization abilities of the proposed agent design. A user manual for the software and the simulation results are presented. This research is supported by the Office of Naval Research with the grant number N00014-98-1-0779. Their financial support is greatly appreciated. / Ph. D.

The air transportation system has grown significantly during the past few decades. The demand for air travel has increased tremendously as compared to the increase in the supply. The air transportation system can be divided into four subsystems: airports, airlines, air traffic control, and passengers, each of them having different interests. These subsystems interact in a very complex way resulting in various phenomena. On the airport side, there is excessive flight demand during the peak hours that frequently exceeds the airport capacity resulting in serious flight delays. These delays incur costs to the airport, passengers, and airlines. The air traffic pattern is also affected by the characteristics of the air transportation network. The current network structure of most major airlines in United States is a hub-and-spoke network. The airports are interested in reducing congestion, especially during the peak time. The airlines act as direct demand to the airport and as the supplier to the passengers. They sometimes compete with other airlines on certain routes and sometimes they collaborate to maximize revenue. The flight schedule of airlines directly affects the travel demand. The flight schedule that minimizes the schedule delay of passengers in directed and connected flights will attract more passengers. The important factors affecting the airline revenue include ticket price, departure times, frequency, and aircraft type operated on each route. The revenue generated from airline depends also on the behavior of competing airlines, and their flight schedules. The passengers choose their flight based on preferred departure times, offered ticket prices, and willingness of airlines to minimize delay and cost. Hence, all subsystems of air transportation system are inter-connected to each other, meaning, strategy of each subsystem directly affects the performance of other subsystems. This interaction between the subsystems makes it more difficult to analyze the air transportation system. Traditionally, analytical top-down approach has been used to analyze the air transportation problem. In top-down approach, a set of objectives is defined and each subsystem is fixed in the overall scheme. On the other hand, in a bottom-up approach, many issues are addressed simultaneously and each individual system has greater autonomy to make decisions, communicate and to interact with one another to achieve their goals when considering complex air transportation system. Therefore, it seems more appropriate to approach the complex air traffic congestion and airline competition problems using a bottom-up approach. In this research, an agent-based model for the air transportation system has been developed. The developed model considers each subsystem as an independent type of agent that acts based on its local knowledge and its interaction with other agents. The focus of this research is to analyze air traffic congestion and airline competition in a hub-and-spoke network. The simulation model developed is based on evolutionary computation. It seems that the only way for analyzing emergent phenomenon (such as air traffic congestion) is through the development of simulation models that can simulate the behavior of each agent. In the agent-based model developed in this research, agents that represent airports can increase capacity or significantly change landing fee policy, while the agents that represent airlines learn all the time, change their markets, fare structure, flight frequencies, and flight schedules. Such a bottom-up approach facilitates a better understanding of the complex nature of congestion and gains more insights into the competition in air transportation, hence making it easier to understand, predict and control the overall performance of the complex air transportation system. / Ph. D.

Tesis por compendio / [EN] Multi-Agent Systems (MAS), Argumentation and Automated Planning are three lines of investigations within the field of Artificial Intelligence (AI) that have been extensively studied over the last years. A MAS is a system composed of multiple intelligent agents that interact with each other and it is used to solve problems whose solution requires the presence of various functional and autonomous entities. Multi-agent systems can be used to solve problems that are difficult or impossible to resolve for an individual agent. On the other hand, Argumentation refers to the construction and subsequent exchange (iteratively) of arguments between a group of agents, with the aim of arguing for or against a particular proposal. Regarding Automated Planning, given an initial state of the world, a goal to achieve, and a set of possible actions, the goal is to build programs that can automatically calculate a plan to reach the final state from the initial state. The main objective of this thesis is to propose a model that combines and integrates these three research lines. More specifically, we consider a MAS as a team of agents with planning and argumentation capabilities. In that sense, given a planning problem with a set of objectives, (cooperative) agents jointly construct a plan to satisfy the objectives of the problem while they defeasibly reason about the environmental conditions so as to provide a stronger guarantee of success of the plan at execution time. Therefore, the goal is to use the planning knowledge to build a plan while agents beliefs about the impact of unexpected environmental conditions is used to select the plan which is less likely to fail at execution time. Thus, the system is intended to return collaborative plans that are more robust and adapted to the circumstances of the execution environment. In this thesis, we designed, built and evaluated a model of argumentation based on defeasible reasoning for planning cooperative multi-agent system. The designed system is independent of the domain, thus demonstrating the ability to solve problems in different application contexts. Specifically, the system has been tested in context sensitive domains such as Ambient Intelligence as well as with problems used in the International Planning Competitions. / [ES] Dentro de la Inteligencia Artificial (IA), existen tres ramas que han sido ampliamente estudiadas en los últimos años: Sistemas Multi-Agente (SMA), Argumentación y Planificación Automática. Un SMA es un sistema compuesto por múltiples agentes inteligentes que interactúan entre sí y se utilizan para resolver problemas cuya solución requiere la presencia de diversas entidades funcionales y autónomas. Los sistemas multiagente pueden ser utilizados para resolver problemas que son difíciles o imposibles de resolver para un agente individual. Por otra parte, la Argumentación consiste en la construcción y posterior intercambio (iterativamente) de argumentos entre un conjunto de agentes, con el objetivo de razonar a favor o en contra de una determinada propuesta. Con respecto a la Planificación Automática, dado un estado inicial del mundo, un objetivo a alcanzar, y un conjunto de acciones posibles, el objetivo es construir programas capaces de calcular de forma automática un plan que permita alcanzar el estado final a partir del estado inicial. El principal objetivo de esta tesis es proponer un modelo que combine e integre las tres líneas anteriores. Más específicamente, nosotros consideramos un SMA como un equipo de agentes con capacidades de planificación y argumentación. En ese sentido, dado un problema de planificación con un conjunto de objetivos, los agentes (cooperativos) construyen conjuntamente un plan para resolver los objetivos del problema y, al mismo tiempo, razonan sobre la viabilidad de los planes, utilizando como herramienta de diálogo la Argumentación. Por tanto, el objetivo no es sólo obtener automáticamente un plan solución generado de forma colaborativa entre los agentes, sino también utilizar las creencias de los agentes sobre la información del contexto para razonar acerca de la viabilidad de los planes en su futura etapa de ejecución. De esta forma, se pretende que el sistema sea capaz de devolver planes colaborativos más robustos y adaptados a las circunstancias del entorno de ejecución. En esta tesis se diseña, construye y evalúa un modelo de argumentación basado en razonamiento defeasible para un sistema de planificación cooperativa multiagente. El sistema diseñado es independiente del dominio, demostrando así la capacidad de resolver problemas en diferentes contextos de aplicación. Concretamente el sistema se ha evaluado en dominios sensibles al contexto como es la Inteligencia Ambiental y en problemas de las competiciones internacionales de planificación. / [CA] Dins de la intel·ligència artificial (IA), hi han tres branques que han sigut àmpliament estudiades en els últims anys: Sistemes Multi-Agent (SMA), Argumentació i Planificació Automàtica. Un SMA es un sistema compost per múltiples agents intel·ligents que interactúen entre si i s'utilitzen per a resoldre problemas la solución dels quals requereix la presència de diverses entitats funcionals i autònomes. Els sistemes multiagente poden ser utilitzats per a resoldre problemes que són difícils o impossibles de resoldre per a un agent individual. D'altra banda, l'Argumentació consistiex en la construcció i posterior intercanvi (iterativament) d'arguments entre un conjunt d'agents, amb l'objectiu de raonar a favor o en contra d'una determinada proposta. Respecte a la Planificació Automàtica, donat un estat inicial del món, un objectiu a aconseguir, i un conjunt d'accions possibles, l'objectiu és construir programes capaços de calcular de forma automàtica un pla que permeta aconseguir l'estat final a partir de l'estat inicial. El principal objectiu d'aquesta tesi és proposar un model que combine i integre les tres línies anteriors. Més específicament, nosaltres considerem un SMA com un equip d'agents amb capacitats de planificació i argumentació. En aquest sentit, donat un problema de planificació amb un conjunt d'objectius, els agents (cooperatius) construeixen conjuntament un pla per a resoldre els objectius del problema i, al mateix temps, raonen sobre la viabilitat dels plans, utilitzant com a ferramenta de diàleg l'Argumentació. Per tant, l'objectiu no és només obtindre automàticament un pla solució generat de forma col·laborativa entre els agents, sinó també utilitzar les creences dels agents sobre la informació del context per a raonar sobre la viabilitat dels plans en la seua futura etapa d'execució. D'aquesta manera, es pretén que el sistema siga capaç de tornar plans col·laboratius més robustos i adaptats a les circumstàncies de l'entorn d'execució. En aquesta tesi es dissenya, construeix i avalua un model d'argumentació basat en raonament defeasible per a un sistema de planificació cooperativa multiagent. El sistema dissenyat és independent del domini, demostrant així la capacitat de resoldre problemes en diferents contextos d'aplicació. Concretament el sistema s'ha avaluat en dominis sensibles al context com és la inte·ligència Ambiental i en problemes de les competicions internacionals de planificació. / Pajares Ferrando, S. (2016). Defeasible Argumentation for Cooperative Multi-Agent Planning [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/60159 / Compendio

Recent events have probably lead us to wonder why people make decisions that seem to be irrational, and that go against any easily understandable logic. The fact that these decisions are emotionally driven often explains what, at first glance, does not have a plausible explanation. Evidence has been found that proves that emotions and other affective characteristics guide decisions beyond a purely rational deliberation. Understanding the way emotions take place, the way emotions change, and/or the way emotions influence behavior, has traditionally been a concern of several fields including psychology and neurology. Moreover, other sciences such as behavioral economics, artificial intelligence, and in general, all sciences that aim to understand, explain, or simulate human behavior, acknowledge the important role of affective characteristics in this task. Specifically, artificial intelligence uses psychological findings in order to create agents that simulate human behavior. Nevertheless, individual research efforts in modeling affective characteristics are often overlapped, short of integration, and they lack of a common conceptual system. This deprives individual researches of the exchange and cooperation's inherent benefits, and makes the task of computationally simulating affective characteristics more difficult. Although much individual effort has been put in classifying, formalizing and modeling emotions and emotion theories on some fields, recognized researchers of emotions' and affective processes' modeling report that a common formal language, an informal conceptual system, and a general purpose affective agent architecture will greatly improve the interdisciplinary exchange and the intradisciplinary coordination. The research literature proposes a wide amount of affective models that deal with some of: relationship between emotions and cognition, relationship between emotions and behavior, emotions and their evolutionary account, emotions for appraising situations, emotion regulation, etc. These models are useful tools for addressing particular emotion-related issues. Furthermore, computational approaches that are based on particular psychological theories have also been proposed. They often address domain specific issues starting from a specific psychological theory. In such solutions, the absence of a common conceptual system and/or platform, makes difficult the feedback between psychological theories and computational approaches. This thesis systematizes and formalizes affect-related theories, what can benefit the interdisciplinary exchange, the intradisciplinary coordination, and hence, allows the improvement of involved disciplines. Specifically this thesis makes the following contributions: (1) a theoretical framework that includes the main processes and concepts that a model of an affective agent with practical reasoning should have; (2) a general-purpose affective agent architecture that shares the concepts of the proposed theoretical framework; (3) an implementation-independent formal language for designing affective agents that have the proposed architecture; and (4) a specific agent language for implementing affective agents which is an extension of a BDI language. Some studies with human participants have helped to validate the contributions of this thesis. They include classical games of game theory, and an study with 300 participants, which have provided the necessary information to evaluate the contributions. The validation has been performed in three directions: determine whether the proposed computational approach represents better the human behavior than traditional computational approaches; determine whether this approach allows to improve psychological theories used by default; and determine whether the proposed affective agents' behavior is closer to human behavior than the behavior of a purely rational agent. / Probablemente algunos eventos recientes nos han conducido a preguntarnos por qué las personas toman decisiones aparentemente irracionales y en contra de alguna lógica fácilmente comprensible. El hecho de que estas decisiones estén bajo la influencia de las emociones a menudo explica lo que, a primera vista, parece no tener una explicación aceptable. En este sentido, se han encontrado evidencias que prueban que las emociones y otras características afectivas condicionan las decisiones más allá de una deliberación meramente racional. Entender cómo las emociones tienen lugar, cómo cambian y cómo influyen en el comportamiento, ha sido tradicionalmente de interés para muchos campos de investigación, incluyendo la psicología y la neurología. Además, otras ciencias como la economía conductual o la inteligencia artificial reconocen el importante papel de las características afectivas en esta tarea. Específicamente, la inteligencia artificial utiliza los resultados obtenidos en psicología para crear agentes que simulan el comportamiento humano. Sin embargo, a menudo los esfuerzos individuales de investigación en el modelado del afecto se solapan, carecen de la suficiente integración y de un sistema conceptual común. Esto limita a las investigaciones individuales para disponer de los beneficios que ofrecen el intercambio y la cooperación, y hace más compleja la tarea de simular los procesos afectivos. Las emociones y teorías relacionadas han sido clasificadas, formalizadas y modeladas. No obstante, reconocidos investigadores argumentan que un lenguaje formal común, un sistema conceptual informal y una arquitectura de agentes de propósito general, mejorarán significativamente el intercambio interdisciplinar y la coordinación intradisciplinar. En la literatura se propone una amplia cantidad de modelos afectivos que modelan: la relación entre las emociones y la cognición, la relación entre las emociones y el comportamiento, las emociones para evaluar las situaciones, la regulación de emociones, etc. Estos modelos son herramientas útiles para abordar aspectos particulares relacionados con las emociones. Además, se han realizado propuestas computacionales que abordan aspectos específicos sobre la base de teorías psicológicas específicas. En éstas soluciones, la ausencia de una plataforma y/o sistema conceptual dificulta la retroalimentación entre las teorías psicológicas y las propuestas computacionales. Esta tesis sistematiza y formaliza teorías relacionadas con el afecto, lo cual beneficia el intercambio interdisciplinar y la coordinación intradisciplinar, y por tanto, permite el desarrollo de las disciplinas correspondientes. Específicamente esta tesis realiza las siguientes contribuciones: (1) una plataforma teórica que incluye los conceptos y procesos principales que debería poseer un modelo de agentes afectivos con razonamiento práctico; (2) una arquitectura de agentes de propósito general que comparte los conceptos de la plataforma teórica propuesta; (3) un lenguaje formal independiente de la implementación, para diseñar agentes afectivos que poseen la arquitectura propuesta; y (4) un lenguaje de agentes específico para implementar agentes afectivos el cual es un extensión de un lenguaje BDI. Algunos estudios con participantes humanos han ayudado a validar las contribuciones de esta tesis. Estos incluyen juegos clásicos de teoría de juegos y un estudio con 300 participantes, los cuales han proporcionado la información necesaria para evaluar las contribuciones. La validación se ha realizado en tres direcciones: determinar si la propuesta computacional que se ha realizado representa mejor el comportamiento humano que propuestas computacionales tradicionales; determinar si esta propuesta permite mejorar las teorías psicológicas empleadas por defecto; y determinar si el comportamiento de los agentes afectivos propuestos se acerca más al comportamiento humano que el compor / Probablement alguns esdeveniments recents ens han conduït a preguntar-nos per què les persones prenen decisions que aparentment són irracionals i que van en contra d'algun tipus de lògica fàcilment comprensible. El fet que aquestes decisions estiguin sota la influència de les emocions sovint explica el que, a primera vista, sembla no tenir una explicació acceptable. En aquest sentit, s'han trobat evidències que proven que les emocions i altres característiques afectives condicionen les decisions més enllà d'una deliberació merament racional. Entendre com les emocions tenen lloc, com canvien i com influeixen en el comportament, ha estat tradicionalment d'interès per a molts camps d'investigació, incloent la psicologia i la neurologia. A més, altres ciències com l'economia conductual, la intel·ligència artificial i, en general, totes les ciències que intenten entendre, explicar o simular el comportament humà, reconeixen l'important paper de les característiques afectives en aquesta tasca. Específicament, la intel·ligència artificial utilitza els resultats obtinguts en psicologia per crear agents que simulen el comportament humà. No obstant això, sovint els esforços individuals d'investigació en el modelatge de l'afecte es solapen, no tenen la suficient integració ni compten amb un sistema conceptual comú. Això limita a les investigacions individuals, que no poden disposar dels beneficis que ofereixen l'intercanvi i la cooperació, i fa més complexa la tasca de simular els processos afectius. Les emocions i teories relacionades han estat classificades, formalitzades i modelades. No obstant això reconeguts investigadors argumenten que un llenguatge formal comú, un sistema conceptual informal i una arquitectura d'agents de propòsit general, milloraran significativament l'intercanvi interdisciplinar i la coordinació intradisciplinar. En la literatura es proposa una àmplia quantitat de models afectius que modelen: la relació entre les emocions i la cognició, la relació entre les emocions i el comportament, les emocions per avaluar les situacions, la regulació d'emocions, etc. Aquests models són eines útils per abordar aspectes particulars relacionats amb les emocions. A més, s'han realitzat propostes computacionals que aborden aspectes específics sobre la base de teories psicològiques específiques. En aquestes solucions, l'absència d'una plataforma i/o sistema conceptual dificulta la retroalimentació entre les teories psicològiques i les propostes computacionals. Aquesta tesi sistematitza i formalitza teories relacionades amb l'afecte, la qual cosa beneficia l'intercanvi interdisciplinar i la coordinació intradisciplinar, i per tant, permet el desenvolupament de les disciplines corresponents. Específicament aquesta tesi realitza les següents contribucions: (1) una plataforma teòrica que inclou els conceptes i processos principals que hauria de posseir un model d'agents afectius amb raonament pràctic; (2) una arquitectura d'agents de propòsit general que comparteix els conceptes de la plataforma teòrica proposta; (3) un llenguatge formal independent de la implementació, per dissenyar agents afectius que posseeixen l'arquitectura proposada; i (4) un llenguatge d'agents específic per implementar agents afectius el qual és un extensió d'un llenguatge BDI. Alguns estudis amb participants humans han ajudat a validar les contribucions d'aquesta tesi. Aquests inclouen jocs clàssics de teoria de jocs i un estudi amb 300 participants, els quals han proporcionat la informació necessària per avaluar les contribucions. La validació s'ha realitzat en tres direccions: determinar si la proposta computacional que s'ha realitzat representa millor el comportament humà que propostes computacionals tradicionals; determinar si aquesta proposta permet millorar les teories psicològiques emprades per defecte; i determinar si el comportament dels agents afectius proposats s'acosta més al / Alfonso Espinosa, B. (2017). Agents with Affective Traits for Decision-Making in Complex Environments [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/90497

One of the major planning problems faced by medium and large manufacturing enterprises is the distribution of production over various (production) facilities. The need for cross-facility capacity management is most evident in the high-tech industries having capital-intensive equipment and short technology life cycle. There have been solutions proposed in the literature that are based on the lagragian decomposition method which separate the overall multiple product problem into a number of single product problems. We believe that multi-agent systems, given their distributed problem solving approach can be used to solve this problem, in its entirety, more effectively. According to other researchers who have worked in this field, auction theoretic mechanisms are a good way to solve complex production planning problems. This research study develops a multi-agent system and negotiation protocol based on combinatorial auction framework to solve the given multi-facility planning problem. The output of this research is a software library, which can be used as a multi-agent system model of the multi-product, multi-facility capacity allocation problem. The negotiation protocol for the agents is based on an iterative combinatorial auction framework which can be used for making allocation decisions in this environment in real-time. A simulator based on this library is created to validate the multi-agent model as well as the auction theoretic framework for different scenarios in the problem domain. The planning software library is created using open source standards so that it can be seamlessly integrated with scheduling library being developed as a part of the Advanced Planning and Scheduling (APS) system project or any other software suite which might require this functionality. The research contribution of this study is in terms of a new multi-agent architecture for an Advanced Planning and Control (APS) system as well as a novel iterative combinatorial auction mechanism which can be used as an agent negotiation protocol within this architecture. The theoretical concepts introduced by this research are implemented in the MultiPlanner production planning tool which can be used for generating master production plans for manufacturing enterprises. The validation process carried out on both the iterative combinatorial framework and the agent-based production planning methodology demonstrate that the proposed solution strategies can be used for integrated decision making in the multi-product, multi-facility production planning domain. Also, the software tool developed as part of this research is a robust, platform independent tool which can be used by manufacturing enterprises to make relevant production planning decisions. / Master of Science

No description available.