If multiple cleaning robots are used to cooperatively clean a larger room, e.g. an airport, the room must be partitioned among the robots. This paper describes a dynamic and decen...
This paper presents a novel method for on-line coordination in multiagent reinforcement learning systems. In this method a reinforcement-learning agent learns to select its action ...
Abstract. We present a method to test a group of agents for (unwanted) emergent behavior by using techniques from learning of cooperative behavior. The general idea is to mimick us...
By using other agents' experiences and knowledge, a learning agent may learn faster, make fewer mistakes, and create some rules for unseen situations. These benefits would be ...
This keynote paper argues for an increased understanding of the various roles involved in the development work to be able to achieve the goal of developing increased usability. Hum...