Papers
4
Total Citations
124
H-Index
3
About
Alonso Marco is a leading researcher at the intersection of robotics, machine learning, and optimal control, with a primary focus on developing data-efficient algorithms for autonomous systems. His most influential contribution is the pioneering work on trading off simulations and physical experiments in reinforcement learning using Bayesian optimization. This highly cited paper (111 citations) addresses a critical bottleneck in robotics: the impractical number of real-world trials required by traditional RL. By intelligently leveraging cheap simulations alongside costly physical experiments, Marco’s framework dramatically accelerates the learning of control policies, making automation more practical. He has also advanced automatic tuning of multivariate PID controllers using model-based policy search, extending frameworks like PILCO to simplify complex industrial control tasks. Earlier in his career, Marco contributed to digital torque/motion control for direct-drive robotic applications and mobile robotics navigation. His research elegantly bridges theoretical optimization with real-world robotic deployment, offering pragmatic solutions that reduce manual tuning and experimental burden—work that is essential for scaling autonomous systems in industry and research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4