Wiering

About

Marco Wiering is a leading figure in reinforcement learning and robotics, with a focus on enabling autonomous agents to learn effectively in complex, real-world environments. His key research areas include robot learning, multi-agent systems, and state-space reduction techniques. Wiering’s major contribution lies in developing algorithms that allow robots to learn online despite vast state spaces—a critical challenge in domains like RoboCup. His 2005 paper on the interval estimation algorithm proposes a method to significantly reduce state space by selecting among behaviors, making reinforcement learning feasible during live games. This work, though cited modestly, has influenced practical robot learning. His 1999 study on reinforcement learning soccer teams with incomplete world models further advanced multi-agent coordination under uncertainty. While his citation counts are moderate, Wiering’s impact is notable for bridging theory and application, particularly in competitive robotics. His achievements include pioneering approaches that enable real-time learning in dynamic settings, inspiring subsequent work in autonomous systems and adaptive control.

Research Focus

Key Achievements

Top Papers

1. 1
   On-line robot learning using the interval estimation algorithm

   3 citations · 2005
2. 2
   Reinforcement Learning Soccer Teams with Incomplete World Models Neural Networks for Robot Learning

   2 citations · 1999

Key Collaborators

Contact & Links