Our goal is for robots to learn conceptual systems su cient for natural language and planning. The learning should be autonomous, without supervision. The rst steps in building a ...
Recent research in machine learning has focused on supervised induction for simple classi cation and reinforcement learning for simple reactive behaviors. In the process, the eld ...
In this paper we address the problem of how decision-theoretic policies can be repaired. This work is motivated by observations made in robotic soccer where decisiontheoretic polic...
Christoph Mies, Alexander Ferrein, Gerhard Lakemey...
This contribution presents a knowledge-based model of the agents’ mutual awareness (social knowledge) and justifies its role in various classes of applications of the concept of...
In this paper, we discuss another approach based on mimicry for interactive comedy, a relatively new genre in interactive drama. An interactive comedy system is proposed in which ...