Federico Sandrelli

Papers

Total Citations

H-Index

About

Federico Sandrelli is a rising researcher in the field of reinforcement learning, with a particular focus on risk-aware decision-making and policy optimization. His work bridges the gap between theoretical safety guarantees and practical algorithm design, addressing the critical challenge of deploying autonomous systems in high-stakes environments. Sandrelli’s most-cited paper, "Risk-averse policy optimization via risk-neutral policy optimization" (2022, 9 citations), introduces a novel framework that transforms risk-averse objectives into standard risk-neutral optimization problems, enabling the use of efficient, well-established algorithms without sacrificing safety. This contribution offers a computationally tractable approach to managing tail risks, making it highly relevant for applications in robotics, finance, and autonomous driving. By simplifying the integration of risk constraints, Sandrelli’s work has the potential to accelerate the adoption of reinforcement learning in real-world scenarios where reliability is paramount. His research continues to explore the intersection of optimization theory and practical deployment, positioning him as a promising voice in the next generation of safe AI systems.