Berkay Demirel is a research assistant in the Artifical Intelligence and Machine Learning group at Universitat Pompeu Fabra (UPF). Under the supervision of Marti Sanchez-Fibla, he's currently working on understanding the limitations of the state of the art reinforcement learning architectures. He is also working towards finishing his thesis "State-space Decomposition Techniques for Deep Q Networks" for M.Sc. Cognitive Systems & Interactive Media at UPF. Before coming to Barcelona, he completed his bachelor's degree magna cum laude in Psychology with a focus on clinical applications. During his bachelor years, he has studied in various institutions around the globe, including Maltepe University, Sydney University and Wurzburg University.