Probabilistic Reasoning in Multiagent Systems: A Graphical Models Approach

Probalistic reasoning with graphical models, also known as Bayesian networks or belief networks, has become an active field of research and practice in artifical intelligence, operations research and statistics in the last two decades. The success of this technique in modeling intelligent decision support systems under the centralized and single-agent paradim has been striking. In this book, the author extends graphical dependence models to the distributed and multi-agent paradigm. He identifies the major technical challenges involved in such an endeavor and presents the results gleaned from a decade's research.

Addresses the challenges of building intelligent agents to cooperate on complex tasks in uncertain environments.

Booknews

Investigating the use of Bayesian networks or belief networks for building intelligent decision support systems, Xiang (computing and information science, U. of Guelph, Canada) extends the application of these graphical dependence models from the centralized and single- agent paradigm to representation formalisms under the distributed and multiagent paradigm. After identifying the technical challenges to such an application, he presents his research on the matter. The foci of the work is the structuring of multiple agents' knowledge as a set of probabilistic graphical models, the compilation of the models into graphical structures for message passing, and the use of message passing to accomplish tasks in model verification and compilation and distributed interference. Annotation c. Book News, Inc., Portland, OR