Briefly
I am a PhD Student under the supervision of Prof. Marcello Restelli, at the Department of Electronics, Informatics and Bio-engineering (DEIB) of Politecnico di Milano.
You can find my (mostly) up to date CV here. My Scholar or BlueSky profile might be more up-to-date with my most recent agenda. Also, feel free to drop an email for any inquiries or questions!
My research interest lies in Reinforcement Learning (RL). Generally, I am interested in how to overcome common limitations, such as the need for data abundance (i.e., fast simulation) or centralized training when many agents are involved; these are often rather limiting requirements indeed. More specifically, my current research explores what can be done prior to task specification: what kind of pre-training can enhance decision-making policies to simplify RL. More broadly, my aim is to advance theoretical understanding that can lead to successful application of RL in the real world. This calls for the study of partial observability, multi-agent scenarios, and reinforcement learning with general utilities, among others. I am passionate about applying RL to challenging and real-world tasks, and I am currently collaborating with Siemens AT on applying scalable MARL techniques for Industry 4.0 and Industrial Production Scheduling.
News
- I am presenting our recent work Towards Principled Multi-Agent Task Agnostic Exploration at the UK Multi-Agent Systems Symposium. See you in London!
- Our work on Scalable Multi-Agent Offline Reinforcement Learning and the Role of Information was accepted at RLDM 2025!
- I am visiting Stefano V. Albrecht and David Abel at the Autonomous Agents Research Group in Edinburgh, U.K.
- I am giving a talk to the RL Virtual Reading Group about advancing our understanding of learning purely explorative policies in POMDPs. You can find the recording on You Tube.
- Grateful to be part of the Best Reviewer Award team at ICML2024.
- I am attending the Machine Learning Summer School in Onna, Japan.
- Our paper The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough was accepted at the just born RLC conference!
- Our paper How to explore with belief: state entropy maximization in POMDPs was accepted at ICML 2024.
- I am attending the Reinforcement Learning Summer School in Barcelona, Spain.
- I am taking part to the organization of the 15th European Workshop on Reinforcement Learning in Milan, Italy.
- The first paper of my Ph.D. Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning was accepted at NeurIPs 2023!