Michael P. Deisenroth

Papers

Total Citations

H-Index

About

Michael P. Deisenroth is a leading figure in machine learning and robotics, with a primary focus on probabilistic approaches to decision-making and control. His major contributions lie in developing data-efficient methods for robot learning, particularly through Gaussian processes and Bayesian optimization, enabling robots to learn complex tasks with minimal interaction. His work on PILCO (Probabilistic Inference for Learning Control) revolutionized model-based reinforcement learning by providing a principled framework for handling uncertainty, leading to robust policy learning. Deisenroth’s research has garnered significant impact, with his most cited works accumulating thousands of citations, reflecting their influence on both theoretical foundations and practical applications in autonomous systems. Notably, his co-authored textbook, "Mathematics for Machine Learning," has become a standard reference for students and practitioners worldwide, demystifying the mathematical underpinnings of the field. Through his contributions, Deisenroth has shaped how machines learn from data and interact with the physical world, bridging the gap between probabilistic modeling and real-world robotics.