Game AI Researcher - Game Developer - Teaching Assistant
I am a PhD student under the Microsoft Scholarship programme in the Intelligent Games and Game Intelligence training centre, and a part of Game AI research group at Queen Mary University of London.
My research is based on the intersection of Reinforcement Learning, Statistical Forward Planning and World Models. Train vs test time compute has been a major area of research in the LLM community - with major improvements showcased by the "thinking mode" available to all newer LLM models. My research is looking into using a similar approach, combining RL with World Models to develop controllable and efficient agents inside of the simulated environments.