UMBC ebiquity
Proceedings of the 18th International Joint Conference on Artificial Intelligence
TAGA: Travel Market Framework in Agentcities (Demonstration)
August 10, 2003
Travel Agent Game in Agentcities (TAGA) is a framework that extends and enhances the Trading Agent Competition (TAC) system to work in Agentcities, an open multiagent systems environment of FIPA-compliant systems. TAGA makes several contributions: auction services are added to enrich the Agentcities environment, the use of the semantic web languages RDF and DAML+OIL improve the interoperability among agents, and the DAML-S ontology is employed to support service registration, discovery, and invocation. The FIPA and Agentcities standards for agent communication, infrastructure and services provide an important foundation in building this distributed and open market framework. TAGA is intended as a platform for research in multi-agent systems, the semantic web, and/or automated trading in dynamic markets, as well as a self-contained application for teaching and experimentation with these technologies. It is running as a continuous open game at http://taga.umbc.edu/, and the source code is available for research and teaching purposes.
InProceedings
Morgan Kaufmann
Downloads: 170 downloads