Table of Contents

Introduction[-]Decision-Theoretic Planning for Teams of Agents[-]Optimal Value Functions for Dec-POMDPs[-]Approximate Value Functions & Heuristic Policy Search[-]Factored Dec-POMDPs: Exploiting Locality of Interaction[-]Lossless Clustering of Histories[-]Conclusions and Discussion[-]Summary[-]Samenvatting[-]Problem Specifications[-]Immediate Reward Value Function Formulations[-]Formalization of Regression to Factored Q-Value Functions[-]Proofs[-]Bibliography[-]Acknowledgments - 222

About the Author

Frans Oliehoek (1981) studied Computer Science at the University of Amsterdam. In 2005 he obtained his M.Sc. in Artificial Intelligence and started his Ph.D. within the Intelligent Autonomous Systems group. This thesis brings together a selection of his research.

Reviews

Frans Oliehoek (1981) studeerde Informatica aan de Universiteit van Amsterdam. In 2005 behaalde hij zijn M.Sc. in de Kunstmatige Intelligentie en begon zijn Ph.D. binnen de Intelligente Autonome Systemen groep. Dit proefschrift bundelt een selectie van zijn onderzoek.