Multiagent Systems: A Survey from a Machine Learning Perspective Peter Stone Distributed Artificial Intelligence (DAI) has existed as a subfield of AI for more than a decade. But in the past couple of years, a subfield of DAI that focusses on behavior management, as opposed to information management, has emerged. This young subfield is called "Multiagent Systems." This survey of Multiagent Systems will serve as an introduction to the field. A series of increasingly complex general multiagent scenarios will be presented. For each scenario, the issues that arise will be described along with a sampling of the techniques that exist to deal with them. The presented techniques will not be exhaustive, but they will be biased towards RL and other Machine Learning approaches. Additional opportunities for applying ML to Multiagent Systems will be highlighted. In the spirit of RL and friends, it's going to be informal. Come and chat!