Collaborative Filtering bases its effectiveness as a recommender system on ratings about a set of items provided by a set of users. In our perspective, an agent behaves as a member of a group would do (the agent implicitly belongs to the same "culture" of the group) without extra-effort or direct interaction. In this paper, we introduce the concept of Implicit Culture and propose a general architecture for Systems for Implicit Culture Support. We show how Collaborative Filtering can be considered as an instance of our architecture, and finally, we consider the related work. 1. INTRODUCTION Given the problem of information overload, the building of recommender systems is a mayor issue. Collaborative Filtering (see [4] for a recent reference) demonstrated to be an effective approach from an applicative point of view. However, the ideas underlying Collaborative Filtering have a greater scope than filtering itself. In this paper we capture those ideas in the notion of Implicit Culture an...

. An on-going project investigating group formation, stereotyping and cultural evolution using an artificial society is outlined. Agents culturally interact by exchanging behavioural rules and cultural markers. They economically interact by playing games of the Prisoners Dilemma. The mode of game play is novel because agents apply stochastic repeated game strategies not to individuals but to subjectively stereotyped groups (based on cultural makers). Agents consequently treat stereotyped groups as single players with whom they are involved in an on-going game of iterated PD. It is envisaged that such cultural processes may display a form of "second order emergence" [11] in which agents come to recognise the cultural groupings that have emerged within the society. Some initial experimental results are presented with tentative observations. 1 Introduction In complex social worlds, individuals are required to interact with many strangers using limited knowledge and bounded rationality. ...

Agents' autonomy and incoming agents can prevent a multi-agent system from fulfilling its requirements. Given a group of autonomous agents acting in an environment it should be useful to exploit information about their actions in order to improve the single agent's knowledge and behavior, and guarantee the realization of the requirements. In this paper, we introduce the concept of implicit culture and propose a general architecture for Systems for Implicit Culture Support (SICS). We show how it is possible to use a SICS to guarantee the persistence of the multi-agent system 's requirements; we present some existing systems that can be considered as instances of our architecture; and finally, we consider the related work. Keywords--- Agents, multi-agent systems, implicit culture, behaviors, actions. I. Introduction Different methodologies are used for the requirements modeling of a multi-agent system. For instance, in [1] the authors describe the system in terms of roles and interact...

. A growing body of researchers from the social and computer sciences are using computational experimentation in a highly exploratory way. The work done in this area is less "simulation" and more "construction". By analogy with artificial intelligence and artificial life, this synthetic approach has become known as artificial societies. It is argued that artificial societies can aid memetic theory building ultimately producing theories and hypotheses that can be tested in the real world. A set of methodologies loosely based on the Popperian (Popper 1968) conception of theory refutation through the falsification of hypotheses and consequent theory development is presented. This process occurs within a deductive system (the artificial society) which due to it's complexity requires empirical investigations to refute hypotheses and generate theory. Current work (Hales 1998c) involving construction and experimentation with an artificial society in order to aid the building of meme theory ar...

Conformant planning is the problem of nding a sequence of actions that is guaranteed to achieve the goal for any possible initial state and nondeterministic behavior of the planning domain. In this paper we present a new approach to conformant planning. We propose an algorithm that returns the set of all conformant plans of minimal length if the problem admits a solution, otherwise it returns with failure. Our work is based on the planning via model checking paradigm, and relies on symbolic techniques such as Binary Decision Diagrams to compactly represent and eciently analyze the planning domain. The algorithm, called cmbp, has been implemented in the mbp planner. cmbp is strictly more expressive than the state of the art conformant planner cgp. Furthermore, an experimental evaluation suggests that cmbp is able to deal with uncertainties more eciently than cgp.

Abstract not found