We describe a generalized Q-learning type algorithm for reinforcement learning in competitive multi-agent games. We make the observation that in a competitive setting with adaptive...
Pieter Jan't Hoen, Sander M. Bohte, Han La Poutr&e...
Neither `design' nor `evolutionary' approaches to building behavior-based robots feature a role for development in the genesis of behavioral organization. However, the n...
The Procedural Reasoning System (PRS) is the best established agent architecture currently available. It has been deployed in many major industrial applications, ranging from fault...
Mark d'Inverno, Michael Luck, Michael P. Georgeff,...
Integrity constraints are valuable tools for enforcing consistency of data in a database. Global integrity constraints ensure integrity and consistency of data spanning multiple d...
Behaviors in soccer-agent domains can involve individual plays, several players involved in tactical plays or the whole team trying to follow strategies supported by specific form...