I'm Luca 🇮🇹, currently PhD Student at Politecnico di Milano (expected graduation Jan 2025).

Some info:

• 🔭 I’m currently working on solving decision problems at scale. In particular:
  • 🛩️ Deep Reinforcement Learning for Multi-UAV Control
  • 🃏 solving big imperfect information games, with a team twist!
• 🌱 Currently learning JAX and the novel FLAX.nnx and playing with Llama 3
• 📕 Probably reading some Sci-fi book (suggesting Ubik by P.K.Dick 🎆)
• 📫 How to reach me: write an email at <myname> dot carminati at hotmail dot it... ask me about anything 🤗

• 🎓 Writing my PhD Thesis
• 🧪 Extending the Team Games frameworks to automatically reorder games if computationally advantageous
• 📖 Curating the submission of journal papers on Monte-Carlo sampling and my whole PhD's Team game lore
• 🛩️ Preparing a journal submission on effective techniques for Mission Planning with RL for Multi-UAVs
• 👨🏻‍💻 My own RL library, focused on seamlessly dealing with multimodal inputs and hybrid action spaces

Here you can have my CV if interested: AcademicCV - Luca Carminati.pdf

PS: My profile picture is a realistic portrait of me debugging, which I am probably doing right now. Original here