Systems that had to work outside the lab.
Reinforcement learning, explainable AI, robot control. Twelve years, most of it on systems that were measured against people who were already good at the task.
I also advise investors and engineering teams. What that involves.
1,900+ citations, most since 2021
70+ peer-reviewed publications
NeurIPS · ICML · JAIR recent venues
Nature 2022 · Gran Turismo Sophy
Selected work
- arXiv 2026 first author, team lead
- Nature 2022 co-author
- NeurIPS 2023 senior author
Towards a Fuller Understanding of Neurons with Clustered Compositional Explanations
- ICML 2026 senior author
This State Looks Like That: Self-Interpretable Reinforcement Learning Agents using Prototype Soft Actor-Critic
- ICML 2026 co-author
Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
Now
- 2025—
- Team Lead, Project Lead and Staff Research Scientist, Sony AI — Game AI
- 2024—
- High-Qualification Expert Professor, Sapienza University of Rome — Faculty of Information Engineering, Informatics and Statistics
Education
- 2022
- Executive M.B.A., Quantic School of Business and Technology
- 2017
- Ph.D. in Engineering in Computer Science, Sapienza University of Rome
- 2013
- M.Sc. in Artificial Intelligence and Robotics, Sapienza University of Rome
- 2011
- B.Sc. in Computer Engineering, University of Pisa
Advisory
Two engagements, both priced in public: technical due diligence for investors and corporate development, and a fractional research lead retainer for teams building reinforcement learning, agentic, or optimisation systems.
