I am a first-year Computer Science PhD student at Brown University, advised by George Konidaris in the Intelligent Robot Lab (IRL).

Previously, I was an MSc (Thesis) student in Computing Science at the University of Alberta, advised by Martha White in the RLAI Lab. I earned my bachelor’s degree in my home country, Armenia, in National Polytechnic University of Armenia.

During my master’s, I focused on developing online reinforcement learning agents that dynamically tune hyperparameters during allocated agent-environment interactions. I have also contributed to designing environments that are partially observable, never-ending, and continually changing, to evaluate the agent’s adaptability.

I am interested in developing agents that operate in a partially observable setting in an online manner. In my opinion, one way to achieve this is by quantifying the amount of information an agent needs for efficient decision-making, as the agent relies on its experience in such environments. This interest also leads me to explore capacity-constrained agents—those with limits on the information they can obtain about the world they inhabit—which I believe is a key ingredient in achieving natural intelligence.

Contact: ahakhver [at] brown [dot] edu