Status:
Personal website:
+44 1865 615351
Research groups:
Address
University of Oxford
Andrew Wiles Building
Radcliffe Observatory Quarter
Woodstock Road
Oxford
OX2 6GG
Research interests:
Reinforcement Learning
Stochastic Control and Game Theory
Mathematical Finance
Further details:
I am a DPhil student at the EPSRC CDT in Industrially Focused Mathematical Modelling (InFoMM), supervised by Prof. Ben Hambly. My research focuses on decision-making under uncertainty in bargaining, in collaboration with BP.
Teaching:
MT19: TA for B8.1 Probability, Measure and Martingales
HT20: TA for B8.3 Mathematical Models of Financial Derivatives
Prizes, awards, and scholarships:
EPSRC InFoMM CDT Studentship, University of Oxford, 2018-2022
International Excellence Awards, University of Manchester, 2016-2017
Major / recent publications:
Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games
Hambly, B; Xu, R; Yang, H. Submitted, 2021.
Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
Hambly, B; Xu, R; Yang, H. SIAM Journal on Control and Optimization, 59 (5), pp. 3359-3391, 2021.