Normative reasoning with an adaptive self-interested agent model based on Markov decision processes

Authors:
Moser Silva Fagundes;Holger Billhardt;Sascha Ossowski
Affiliations:
Centre for Intelligent Information Technologies, University Rey Juan Carlos, Madrid, Spain;Centre for Intelligent Information Technologies, University Rey Juan Carlos, Madrid, Spain;Centre for Intelligent Information Technologies, University Rey Juan Carlos, Madrid, Spain
Venue:
IBERAMIA'10 Proceedings of the 12th Ibero-American conference on Advances in artificial intelligence
Year:
2010

Citing 10
Cited 0

An Architecture for Normative Reactive Agents

Proceedings of the 5th Pacific Rim International Workshop on Multi Agents: Intelligent Agents and Multi-Agent Systems
Deliberative Normative Agents: Principles and Architecture

ATAL '99 6th International Workshop on Intelligent Agents VI, Agent Theories, Architectures, and Languages (ATAL),
Towards Socially Sophisticated BDI Agents

ICMAS '00 Proceedings of the Fourth International Conference on MultiAgent Systems (ICMAS-2000)
Normative system games

Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Ubi Lex, Ibi Poena: Designing Norm Enforcement in E-Institutions

Coordination, Organizations, Institutions, and Norms in Agent Systems II
Organising MAS: a formal model based on organisational mechanisms

Proceedings of the 2009 ACM symposium on Applied Computing
Efficient solution algorithms for factored MDPs

Journal of Artificial Intelligence Research
Hybrid BDI-POMDP framework for multiagent teaming

Journal of Artificial Intelligence Research
Adaptive Deterrence Sanctions in a Normative Framework

WI-IAT '09 Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology - Volume 02
A BDI architecture for normative decision making

Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Rational self-interested agents, which act so as to achieve the best expected outcome, should violate the norms if the expected rewards obtained with the defections from the norms surpass the expected rewards obtained by being norm-compliant. It means they should estimate the earnings brought about by the violations and the losses caused by their respective reactions. In this paper, we present a rational self-interested agent model that takes into account the possibility of breaking norms. To develop such model, we employ Markov Decision Processes (MDPs). Our approach consists of representing the reactions for norm violations within the MDPs in such a way that the agent is able to reason about how those violations affect her expected utilities and future options. Finally, we perform an experiment in order to establish comparisons between the model presented in this work and its norm-compliant version.