Abstract. A reinforcement architecture is introduced that consists of three complementary learning systems with different generalization abilities. The ACTOR learns state-action as...
In this paper we argue that RoboCup is a useful tool for the teaching of AI in undergraduate education. We provide case studies, from two Swedish universities, of how RoboCup based...
When using communication in multi-robot systems it's often not desirable to choose an form of communication that separates the messages from the physical environment in which...
We apply evolutionary algorithm (EA) to the design of controller for adaptive robots. EAs can be successful for more complicated tasks, where traditional engineering methods strugg...
In this paper the problems of organization and representation of concept knowledge are addressed from an autonomous agent perspective. The first part of the paper discusses the qu...