Frans A. Oliehoek

Papers

Total Citations

H-Index

About

Frans A. Oliehoek is a leading researcher in artificial intelligence, specializing in multi-agent systems, reinforcement learning, and decentralized decision-making under uncertainty. His work addresses fundamental challenges in coordinating autonomous agents in complex, real-world environments. Oliehoek is best known for pioneering advances in decentralized partially observable Markov decision processes (Dec-POMDPs), providing both theoretical foundations and scalable algorithms that enable teams of agents to act effectively without central control. His research has had significant practical impact, particularly in robotics and logistics, as demonstrated by his work on decentralized online planning for multi-robot warehouse commissioning—a problem where robots must efficiently gather and deliver items while respecting capacity constraints. This paper, though early in citation count, highlights his focus on moving beyond infeasible centralized approaches to real-world multi-agent coordination. With over 5,000 citations across his career, Oliehoek’s contributions have shaped modern multi-agent reinforcement learning. He is also recognized for his influential book on Dec-POMDPs and his role in advancing AI for autonomous systems, making him a key figure for students and researchers exploring cooperative AI.