I am a Student Researcher at Google DeepMind in Zurich, working on reinforcement learning for LLM post-training. I am also a final-year Ph.D. candidate at Politecnico di Milano, advised by Prof. Nicola Gatti.
Previously, I was a Visiting Ph.D. Researcher at the Machine Intelligence through Decision-making and Interaction (MIDI) Lab at The University of Texas at Austin, advised by Prof. Amy Zhang.
My research focuses on generalization in reinforcement learning, particularly unsupervised RL and continual RL, and extending these foundational principles to LLM post-training.
news
| Aug 2026 | Joined Google DeepMind (Zurich) as a Student Researcher working on RL for LLM post-training. |
|---|---|
| Jul 2026 | Paper accepted at ICML 2026 (Laplacian Representations in RL) and workshop paper at RLC 2026 (Continual RL via Behavioral Foundation Models). |
| Jan 2026 | Our paper "Do it for HER" was accepted at AAAI 2026 for an Oral Presentation! |
| Jul 2025 | Paper on precision UAV formation control accepted at CDC 2025. |
| Apr 2025 | Started visiting research appointment at UT Austin (MIDI Lab) with Prof. Amy Zhang. |
selected publications
conference proceedings
-
ICML 2026Impact of Connectivity on Laplacian Representations in Reinforcement Learning
-
AAAI 2026 OralDo it for HER: First-order Logic Reward Specification in Reinforcement Learning
-
CDC 2025Precision UAV Formation Control via PGPE-enhanced NMPC
-
AAAI 2024Online Markov Decision Processes Configuration with Continuous Decision Space
-
NeurIPS 2022Subgame Solving in Adversarial Team Games
workshop papers
-
RLC 2026Continual Reinforcement Learning via Behavioral Foundation ModelsContinual Reinforcement Learning Workshop
-
ICML 2024Delayed Adversarial Attacks on Stochastic Multi-Armed BanditsWorkshop on Aligning RL Experimentalists and Theorists (ARLET)