About me
I am Lead Research Scientist in Motion Planning and Prediction Applied Research team at FiveAI where I am tackling a variety of research and engineering challenges, such as robustifying planners, multi-agent interactions, integrating prediction into planning, etc. I am exploring hybrid combinations of machine learning (deep learning, reinforcement learning with classical approaches such as Monte Carlo methods, Bayesian inference and Game Theory algorithms. The safety critical nature of the application means that any solutions need to handle a large degree of uncertainty, generalise to novel situations and constrain the amount of risk when interacting with other human traffic participants. Previously, I completed a PhD within the ILCC institute of the School of Informatics at the University of Edinburgh under the supervision of Alex Lascarides and Subramanian Ramamoorthy.
Research interests
- Machine Learning: (Multi-agent) Reinforcement Learning, Imitation Learning, Deep Learning, Bayesian Methods, Planning and Decision Making
- Multi-agent Systems and Game Theory
- Quantifying and handling Uncertainty/Risk in Planning/Reinforcement Learning
Education
- PhD Informatics. Low-resource learning in complex games, School of Informatics, University of Edinburgh, 2018
- BSc (Hons) Robotics with Artificial Intelligence, University of Bradford, 2013 (1st class);
Awards
- Received Best student Overall Performance Award, University of Bradford, 2013
- Received Best Student Paper Award for “Exploiting action categories in learning complex games”, 2017