After completion of the course,
- The student understands and is able to apply multi-agent systems including agent architectures, interaction, intelligence, negotiation, and communication.
- The student is able to analyze a real-world case and apply multi-agent concepts to capture this in a Multi-Agent model.
- The student understands seminal and novel scientific studies in the multi-agent domain.
- The student will be able to analyze opportunities and barriers to implementing multi-agent techniques in practice and evaluate the effectiveness of alternative approaches.
- The student will gain experience in creating multi-agent systems by conducting research by choosing an appropriate research question, agent design methodology, and implementation platform.
- The student will be able to design and implement a basic multi-agent system and learn how to report and reflect on multi-agent systems. Working in a small group, the student will produce and present a report on the project in English.
|
|
|
Multi-agent systems offer a powerful way to design and implement systems that can be applied to complex real-world problems in which no central authority is prevalent. In many real-life cases, actors have the autonomy to make decisions, have emergent behavior, respond to changes in the environment and learn over time. Think of citizen mobility in smart cities, flows of goods in global supply chains, migration of workers across regions, consumption of electricity in smart grids, et cetera. Also recent challenges such as the C19 pandemic and response of people to various policies have been studied with multi-agent systems. The multi-agent paradigm offers a set of concepts to model and build systems that can be used to research and facilitate multi-actor and decentral systems. Elements of Artificial Intelligence are also applied in multi-agent systems to implement adaptive behavior of individual agents.
|
|