Diogo Carvalho is a Ph.D. student at Instituto Superior Técnico (IST) of the University of Lisbon and the Artificial Intelligence for People and Society Research Group (GAIPS) of INESC-ID. He received the M.Sc. degree in Applied Mathematics and Computation from IST. His research is on reinforcement learning, mostly focused on the theory of Q-learning with function approximation. He is also interested in other reinforcement learning topics such as hierarchies, multiple agents, non-stationarities, and representation learning.

Publications: Google Scholar