We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
Abstract. We present The Cruncher, a simple representation framework and algorithm based on minimum description length for automatically forming an ontology of concepts from attrib...
We show that reputation is a basic ingredient in the Virtual Organisation (VO) formation process. Agents can use their experiences gained in direct past interactions to model other...
Personalized rendering of web pages gives the users greater control to view only what they prefer. The goal of this work is to provide a tool that will let users customize the con...
Solving in an efficient manner many different optimal control tasks within the same underlying environment requires decomposing the environment into its computationally elemental ...