A close link between education, research and collaboration is the starting point for all our activities. We offer a wide range of attractive professional programs, in medicine, psychology, law and engineering. Our vision is to be a prominent university for a knowledge-driven society.
The real world is distributed. Distributed artificial intelligence is about this spread of knowledge, skills and abilities, across different units and different places. The course introduces Multi-Agent Systems - the main concept and technology for distributed AI. We will discuss how to build systems that can function as part of a Multi-agent System; how to organize different intelligent devices, how to use negotiation or auctions to distribute tasks to autonomous agents and many more topics from Swarm Intelligence to teams of intelligent robots.
Reinforcement learning - (RL) is a method for learning to make an optimal decision through trial and error. The goal of RL is to achieve an optimal policy for each state in a system. The course covers the underlying formalism of RL called Markovska decision-making processes and basic RL algorithms. Examples are dynamic programming. We will show how to model a problem as a Markovska decision-making process and implement basic RL algorithms to solve them. In addition, we will explore different ways to compare and evaluate the performance of learning methods.