Ciao! My name is Pierluca D’Oro. I am a PhD student at MILA, supervised by Pierre-Luc Bacon and Marc G. Bellemare.
My research area is reinforcement learning. I am particularly interested in studying how an agent can intimately exploit knowledge about its own learning process, and in the interaction between RL algorithms and neural networks training.
I did my MSc at Politecnico di Milano, working on model-based reinforcement learning under the supervision of Prof. Marcello Restelli. Previously, I worked on generative models with Prof. Concetto Spampinato at the University of Catania, in my hometown in Sicily. I have also spent some time as an intern at NNAISENSE in Lugano, mainly working with Wojciech Jaśkowski on model-based reinforcement learning.
To get in touch, write me an email at the following address. 