Abstract. The European Commission’s eEurope initiative aims to bring every citizen, home, school, business and administration online to create a digitally literate Europe. The value lies not in the objective itself, but in its ability to facilitate the advance of Europe into new ways of living and working. Just as in the first literacy revolution, our lives will change in ways never imagined. The vision of eEurope is underpinned by a technological infrastructure that is now taken for granted. Yet it provides us with the ability to pioneer radical new ways of doing business, of undertaking science, and, of managing our everyday activities. Key to this step change is the development of appropriate mechanisms to automate and improve existing tasks, to anticipate desired actions on our behalf (as human users) and to undertake them, while at the same time enabling us to stay involved and retain as much control as required. For many, these mechanisms are now being realised by agent technologies, which are already providing dramatic and sustained benefits in several business and industry domains, including B2B exchanges, supply chain management, car manufacturing, and so on. While there are many real successes of agent technologies to report, there is still much to be done in research and development for the full benefits to be achieved. This is especially true in the context of environments of pervasive computing devices that are envisaged in coming years. This paper describes the current state-of-the-art of agent technologies and

Since the agent paradigm emerged, agent researchers have faced the challenge of build-ing open societies in which heterogeneous and independently designed entities can work towards similar or different ends. Open societies involve agents that do not necessarily share the same interests, that do not know and might not trust each other, but that can work together and help each other. One of the key omissions in the computational rep-resentation of open societies relates to the need for norms in multi-agent systems, that help to cope with the heterogeneity, the autonomy and the diversity of interests among their members. This also requires agents that can reason about norms because their par-ticipation in a society, rather than predefined, must be voluntary. So, these agents must understand why norms should be adopted and complied with, and why the authority and the power of agents in a society must be respected. This thesis addresses both the in-troduction of norms in systems of autonomous agents, and the modelling of agents that can reason about norms. The thesis makes three main contributions. First, it develops a framework of norma-tive concepts that enables agents to reason about norms and the society in which they participate. Second, it provides the means for agents to identify situations of power, and to use these powers both for the satisfaction of their goals and to understand why the goals of other agents must be satisfied. This is required since agents in an open soci-ety must interact with other agents which are also autonomous, and power represents a means to influence them. Third, this thesis provides models for agents that adopt and comply with norms not as an end, but as the result of a deliberation process in which their goals and motivations are taken into account. This enables agents to voluntarily decide whether participating in a society is important for the achievement of their goals.

Abstract. AOSE methodologies and models borrow various abstractions and concepts from the organization and sociology disciplines. Although they all view multi-agent system as organized society, the organizational abstractions, assumptions, concepts, and models in them are actually used in different ways. It is, therefore desirable to have a systematic way of analyzing and comparing the organizational and social concepts in AOSE. The contribution of this paper is twofold. Firstly, we describe and define the modeling construct levels and the social premises of multi-agent system that should be modeled and analyzed when developing multi-agent system, identify and classify categories of organizational and social concepts in AOSE literature that are used to deal with them from standpoints of organization abstractions. Secondly, we analyze some methodologies and models in AOSE, explain how the organizational and social concepts are used to specify and analyze multi-agent system with various social premises in different levels. 1.

Abstract. In a persistent multi-agent system, it should be possible for new agents to benefit from the accumulated learning of more experienced agents. Parallel reasoning can be applied to the case of newborn animals, and thus the biological literature on social learning may aid in the construction of effective multi-agent systems. Biologists have looked at both the functions of social learning and the mechanisms that enable it. Many researchers have focused on the cognitively complex mechanism of imitation; we will also consider a range of simpler mechanisms that could more easily be implemented in robotic or software agents. Research in artificial life shows that complex global phenomena can arise from simple local rules. Similarly, complex information sharing at the system level may result from quite simple individual learning rules. We demonstrate in simulation that simple mechanisms can outperform imitation in a multi-agent system, and that the effectiveness of any social learning strategy will depend on the agents ’ environment. Our simple mechanisms have obvious advantages in terms of robustness and design costs. Keywords: Multi-agent systems, social learning, imitation, artificial life, biology. 1

Abstract. The paper describes a decentralized peer-to-peer multi-agent learning method based on inductive logic programming and knowledge trading. The method uses first-order logic for model representation. This enables flexible sharing of learned knowledge at different levels of abstraction as well as seamless integration of models created by other agents. A market-inspired mechanism involving knowledge trading is used for inter-agent coordination. This allows for decentralized coordination of learning activity without the need for a central control element. In addition, agents can participate in collaborative learning while pursuing their individual goals and maintaining full control over the disclosure of their private information. Several different types of agents differing in the level and form of knowledge exchange are considered. The mechanism is evaluated using a set of performance criteria on several scenarios in a realistic logistic domain extended with adversary behavior. The results show that using the proposed method agents can collaboratively learn properties of their environment, and consequently significantly improve their operation. 1

Stochastic Diffusion Search (sds) was introduced by Bishop (1989a) as an algorithm to solve pattern matching problems. It relies on many concurrent partial evaluations of candidate solutions by a population of agents and communication between those agents to locate the optimal match to a target pattern in a search space. In subsequent research, several variations on the original algorithmic formulation were proposed. It also became evident that its main principles – partial evaluation and communication between agents – can be employed to problems outside the pattern matching domain. The primary aim of this dissertation is to develop these expansive views further: sds is proposed as a metaheuristic, a generic heuristic procedure for solving problems through search. Furthermore, it is proposed as a challenge to the dominant metaphor in computer science: sequential computation. The thesis proceeds in a structured way by first considering all questions that can be asked about a heuristic procedure like sds: questions of a foundational nature, questions pertaining to mathematical analysis, questions about application domains and questions about physical implementation. It is to the foundational issues that most attention is devoted. Analogies with selective processes in natural and social systems are investigated, as well as analogies with other metaheuristic techniques from artificial intelligence. An attempt is made to categorise potential variants, and to establish what kind of problems sds would be the optimal problem-solving method for. The work aims to provide an expanded but structured understanding of sds, to give guidelines for future work, and to establish how progress in other scientific disciplines can be of use in the study of sds, and vice versa. Preface All sciences characterise the essential nature of the systems they study. These characterisations are invariably qualitative in nature, for they set the terms with which more detailed knowledge can be developed. A. Newell and H. Simon (Newell and Simon, 1976) Cybernetics is the science of defensible metaphors.

Coalition formation in multi-agent systems is a process where agents form coalitions and work together to solve a joint problem via cooperating or coordinating their actions within each coalition. It is important for distributed applications ranging from electronic business to mobile and ubiquitous computing where adaptation to changing resources and environments is crucial. Coalition formation is useful as it may increase the ability of agents to accomplish tasks and achieve their goals. However, in complex real-world environments that agents operate in, the available resources are generally constrained. Agents only have incomplete even inaccurate information about the dynamically changing world. The occurrence of events may require the agents to react in a real-time manner. Agents’ actions may result in uncertain outcomes. These factors inevitably influence the formation process and formation outcome of a coalition. We employ a learning-based two-phased coalition formation approach to help agents form coalitions in complex environments. The approach consists of (1) a two-phase (planning and instantiation) coalition formation model, (2) a two-level (strategic and tactical) learning mechanism, (3) an adaptive, confidence-based negotiation strategy, and

Abstract—In this paper we discuss the notion of situated evolution. Our treatment includes positioning situated evolution on the map of evolutionary processes in terms of time- and space-embeddedness, and the identification of decentralization as an orthogonal property. We proceed with a selected overview of related literature in the categories of our interest. This overview enables us to distill further detailes that distinguish the encountered methods. As it turns out the essential differences can be captured through the mechanics of selection and fertilization. These insights are aggregated into a new model called the Situated Evolution Method, which is then used to provide a fine-grained map of exisiting work. I. BACKGROUND AND OBJECTIVES The background of this paper is a research project1 concerned with a group of robots that operate in a challenging environment and permanently adapt their controllers in order to increase their task performance. Evolution is chosen as the principal method of adaptation, hence evolutionary computing (EC) is expected to supply the technical machinery to enable successful adaptation on-the-fly. This choice draws our attention to evolutionary algorithms, expecting much existing work that can be used to drive the evolutionary mechanics in a group of evolving robots. Looking around in EC soon reveals that there is a large variety of evolutionary algorithms, such as Evolutionary