Mohamad H. Danesh

I am Mohamad H. Danesh, currently pursuing a PhD at McGill University in the Centre for Intelligent Machines lab. My PhD research centers on the development of safe learning agents, reflecting my commitment to advancing the field’s understanding and application of ethical and risk-aware AI. Prior to embarking on my doctoral journey, I completed my MSc at Oregon State University under the supervision of Prof. Alan Fern. It was during my master’s program that I developed a keen interest in RL, a field that has since become my primary focus. As an upcoming Summer 2024 CHAI intern, I am eager to collaborate with Khanh Nguyen on investigating the dynamics of control allocation among agents, particularly in the context of yielding and requesting control.