Characterising agents' behaviours: selecting goal strategies based on attributes

Authors:
José Cascalho;Luis Antunes;Milton Corrêa;Helder Coelho
Affiliations:
Departamento de Ciências da Educação, Universidade dos Açores, Angra do Heroismo, Portugal;Departamento de Informática, Faculdade de Ciências da Universidade de Lisboa, Lisboa, Portugal;Coordenação da Ciência da Computação e Laboratório Nacional de Computação Científica, Petrópolis, RJ, Brasil;Departamento de Informática, Faculdade de Ciências da Universidade de Lisboa, Lisboa, Portugal
Venue:
CIA'06 Proceedings of the 10th international conference on Cooperative Information Agents
Year:
2006

Citing 5
Cited 2

Evolving Beharioral Strategies in Predators and Prey

IJCAI '95 Proceedings of the Workshop on Adaption and Learning in Multi-Agent Systems
Tropos: An Agent-Oriented Software Development Methodology

Autonomous Agents and Multi-Agent Systems
The dMARS Architecture: A Specification of the Distributed Multi-Agent Reasoning System

Autonomous Agents and Multi-Agent Systems
Emotion based adaptive reasoning for resource bounded agents

Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
Toward a motivated BDI agent using attributes embedded in mental states

CAEPIA'05 Proceedings of the 11th Spanish association conference on Current Topics in Artificial Intelligence

Tuning agents' behaviours using embedded attributes

AIAP'07 Proceedings of the 25th conference on Proceedings of the 25th IASTED International Multi-Conference: artificial intelligence and applications
Abstract mental descriptions for agent design

Intelligent Decision Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

The growth in the demand of autonomous agent systems which take decisions on behalf of other agents or human users, increases the necessity to study systems which use affective elements to manage their resources and to take decisions in order to become more efficient and to facilitate human-machine interaction. In this paper we present an architecture that allows an agent to select a sequence of actions based on a previously predefined planning structure, by using a tree of goals and a set of informational beliefs. The affective elements which we call attributes, such as urgency, insistence and intensity, have the capacity to alter the agents' behaviours, modifying their priorities with regard to resource consumption, the implicit costs of action execution and even their capabilities to execute an action. In a preliminary experiment made in a multi-agent system environment, a modified predator-prey workbench, we show how the attributes linked to these beliefs change the agents' behaviour and improve their global performance.