In this paper we introduce chain multi-agent causal models which are an extension of causal Bayesian networks to a multi-agent setting. Instead of 1 single agent modeling the entire domain, there are several agents organised in a chain, each modeling non-disjoint subsets of the domain. Every agent has a causal model over the variables in his domain, determined by an acyclic causal diagram and a...

Research on agent communication languages has typically taken the speech acts paradigm as its starting point. Despite their manifest attractions, speech-act models of communication have several serious disadvantages as a foundation for communication in artificial agent systems. In particular, it has proved to be extremely difficult to give a satisfactory semantics to speech-act based agent comm...

Agent-oriented methodologies and related modeling techniques have become a priority for the development of large scale agent-based systems. Several methodologies have been proposed for the development of multiagent systems (MAS). For the most part, these methodologies remain incomplete: they are either an extension of object-oriented methodologies or an extension of knowledge-based methodologie...

In this paper, an extension of a formalized model of affective decision making is presented, based on the informally described I-PEFiC model. This extension manages that the actions agents undertake have an effect on other agents. The agents change their perceptions and beliefs about other agents if actions are taken. Further, the anger level of the agents is simulated. Simulation experiments s...

Reinforcement Learning has been used for a number of years in single agent environments. This article reports on our investigation of Reinforcement Learning techniques in a multi-agent and adversarial environment with continuous observable state information. Our framework for evaluating algorithms is two-player hexagonal grid soccer. We introduce an extension to Prioritized Sweeping that allows...

. In this paper we address the problem of collective norms, and discuss two action logics for that purpose. The first action logic is based on the action modality Ei, where expressions of the form Eip are read as ‘agent brings about (sees to it) that ’. This operator relates an agent with the effects of his action, and abstracts away details of the specific actions. We will show that this abstr...

This paper introduces an architecture-centric object-oriented design method for MAS (Multi-Agent Systems) using the extended UML (Unified Modeling Language). The UML extension is based on design principles that are derived from characteristics of MAS and concept of software architecture which helps to design reusable and wellstructured multi-agent architecture. The extension allows one to use o...