Alkis Gotovos

Papers

Total Citations

296

H-Index

About

Alkis Gotovos is a researcher at the forefront of sequential decision-making under uncertainty, with a focus on safe optimization and autonomous robotic exploration. His most influential work, "Safe Exploration for Optimization with Gaussian Processes" (2015, 197 citations), addresses the critical challenge of balancing exploration and exploitation in unknown environments while ensuring safety constraints are respected—a problem central to applications like robotics and autonomous systems. This work has become a cornerstone in the field of Bayesian optimization and safe learning. Gotovos also made significant contributions to environmental monitoring with his research on "Fully autonomous focused exploration for robotic environmental monitoring" (2014, 99 combined citations), where he developed algorithms that enable robots to autonomously identify critical spatial phenomena, such as pollution hotspots or hazardous events, rather than simply minimizing prediction error everywhere. His work bridges theoretical rigor and practical deployment, offering tools for robots to operate efficiently and safely in real-world settings. With a citation count exceeding 300, Gotovos’s research continues to inspire advances in safe reinforcement learning and autonomous sensing, making him a key figure in the intersection of machine learning and robotics.