Enrico Marchesini’s research focuses on safe and trustworthy deep reinforcement learning, with applications to multi-agent systems, robotics, and autonomous decision-making. His work bridges control theory and artificial intelligence to develop algorithms that ensure robust, verifiable behavior in complex environments.

He has authored papers in leading venues such as AAAI, ICRA, AAMAS, and ICLR, and collaborates on interdisciplinary projects integrating trust and human-robot interaction. Before joining IE University, he was involved in research funded by the U.S. National Science Foundation and contributed to the formal verification of AI systems for safety-critical tasks.