Marco Wiering
Papers
7
Total Citations
825
H-Index
5
About
Marco Wiering is a leading researcher in artificial intelligence and robotics, whose work has profoundly shaped reinforcement learning and autonomous navigation. His seminal contributions are anchored by his highly cited work on "Reinforcement Learning" (2012), which has garnered over 675 citations and serves as a foundational resource for students and researchers in the field. Wiering has pioneered methods that integrate deep neural networks with reinforcement learning, notably in "Two-stage visual navigation by deep neural networks and multi-goal reinforcement learning," advancing how robots plan and execute complex tasks. He has also made significant strides in indoor localization, using denoising autoencoders and semi-supervised learning to enable robust 3D mapping without expensive hardware. Beyond these technical achievements, Wiering has been a driving force in collaborative robotics, co-founding the Dutch RoboSoccer Team "Clockwork Orange" and the Dutch AIBO Team, which united top Dutch universities to compete internationally. His work on model-based POMDPs and region-enhanced neural Q-learning has further addressed the challenge of decision-making under uncertainty, solidifying his reputation as a versatile innovator who bridges theory and real-world robotic applications.
Research Focus
Key Achievements
Top Papers
- 1Reinforcement Learning675 citations · 2012
- 2International Conference on Control, Automation, Robotics and Vision76 citations · 2010
- 3
- 4
- 5Clockwork Orange: The Dutch RoboSoccer Team5 citations · 2002
- 6The Dutch AIBO Team 20044 citations · 2004
- 7Region enhanced neural Q-learning for solving model-based POMDPs3 citations · 2010