Andrea Baisero

I am a PhD student at the Lab for Learning and Planning in Robotics (LLPR) at Northeastern University, where I work on model-free partially observable reinforcement learning.

My research focuses on control problems that require long term information-gathering and memorization strategies, on learning useful representations of history, and on exploiting privileged training information to improve execution performance while retaining theoretical correctness and/or optimal convergence guarantees. Other interests include probability theory, Bayesian statistics and inference, causality, information theory, and game theory.