Mouhssine Rifaki

Research

I use RL to train embodied agents by improving their adaptive perception and foveation through robotics. Currently, my ideas include developing adaptive sensors that can dynamically switch modalities based upon prediction errors and control systems that can take input from these dynamic sensors. The unifying theme here is that perception, decision making and physical action need to be designed together. I am also interested in deep learning theory, and I write notes on it from time to time.