Michael Schreibauer
Papers
1
Total Citations
8
H-Index
1
About
Michael Schreibauer is a leading researcher at the intersection of reinforcement learning (RL) and robotics, with a focus on developing algorithms that enable autonomous systems to learn complex behaviors directly from interaction with the real world. His most influential work, "Least-squares policy iteration algorithms for robotics: Online, continuous, and automatic," has garnered 8 citations and addresses a critical bottleneck in robot learning: the need for algorithms that can operate online, in continuous state and action spaces, and with minimal human intervention. Schreibauer’s major contribution lies in advancing least-squares policy iteration methods, making them practical for real-time robot control—a feat that bridges theoretical RL with physical hardware constraints. His work is particularly notable for tackling the challenges of sample efficiency and stability in continuous domains, paving the way for robots that can adapt autonomously to dynamic environments. By focusing on automatic feature selection and online learning, Schreibauer has helped move RL from simulation-based successes to tangible robotic applications, earning recognition among peers for his rigorous, application-driven approach. His research continues to inspire new generations of roboticists seeking to deploy intelligent, learning-enabled machines in the wild.
Research Focus
Key Achievements
Top Papers
- 1