Title: Multi-Agent Reinforcement Learning: An Overview (PART 2)
Abstract: Multi-agent systems are receiving increasing attention by the research community. Their inherent complexity makes it hard if not impossible to control such systems by design, which explains a keen interest of the community in adaptive multi-agent systems, i.e., multi-agent learning. Reinforcement learning is one of the most popular approaches to single-agent learning, because it is explicitly agent-centric, it is founded in psychological models, and it provides convergence guarantees under the proper assumptions. Reinforcement learning has been applied to multi-agent settings with promising results. However, the theoretical convergence guarantees based on classical proofs are lost since common assumptions, such as a Markovian environment, are violated. In the talk, an overview of the state of the art in this field will be presented.
Sala Seminari, DEIB
November 26 2014, 12:00 - 13:00