Main Page | See live article | Alphabetical index

Distributed Artificial Intelligence

Distributed Artificial Intelligence

Distributed Artificial Intelligence (DAI) is a subfield of AI research dedicated to the development of solutions for complex problems, that are not easily solveable with classic algorithmical programs.

There are three main streams in DAI research

The key concept used in DPS and MABS is the abstraction called agent. An agent is a virtual (or physical) autonomous entity that has an understanding of its environment an acts upon it. An agent is usually able to communicate with other agents in the same system to achieve a common goal, that one agent alone could not achieve.

A first classification that is useful is to divide agents into:

Well recognied agent architectures that describe how an agent is internally structured are: Another important thing about agents is the ability to communicate. Important Agent Communication Languages a(ACL) are FIPA ACL (Foundation for Intelligent Physical Agents, a standardization consortium) and KQML (Knowledge Query and Manipulation Language), that both rely on speech act theory developed by Searle 1960 and enhanced by Winograd and Flores in the 70s. Both languages are very similar and describe a set of performatives and their meaning (e.g. ask-one). the content of the performative is not standardized, but varies from system to system. To make agents understand each other they have to not only speak the same language, but also have a common ontology. An ontology describes what kind of things an agent can deal with and how they are related to each other. It's part of the agents knowledge base.

Important researchers in the area of agents are:

Many papers about agents and MAS can be found at CiteSeer ( )

See also Collective intelligence