no code implementations • 8 Dec 2021 • Ben Hambly, Renyuan Xu, Huining Yang
In contrast to classical stochastic control theory and other analytical approaches for solving financial decision-making problems that heavily reply on model assumptions, new developments from reinforcement learning (RL) are able to make full use of the large amount of financial data with fewer model assumptions and to improve decisions in complex financial environments.
no code implementations • 27 Jul 2021 • Ben Hambly, Renyuan Xu, Huining Yang
We consider a general-sum N-player linear-quadratic game with stochastic dynamics over a finite horizon and prove the global convergence of the natural policy gradient method to the Nash equilibrium.
no code implementations • 20 Nov 2020 • Ben Hambly, Renyuan Xu, Huining Yang
In particular, we consider the convergence of policy gradient methods in the setting of known and unknown parameters.