Department of Mathematics

We introduce a continuous policy-value iteration algorithm where the approximations of the value function of a stochastic control problem and the optimal control are simultaneously updated through Lan... More

Consider a stochastic differential game with N players in a linear-quadratic framework with ergodic cost, where d-dimensional diffusion processes govern the state dynamics with an unknown common drift... More

We will discuss some answers to this question that combine ideas from high dimensional geometry and quadratic optimization with linear constraints, and highlight some open questions.

Abstract : We study stochastic control with partial and decentralized information and discuss optimality, approximations, and learning theoretic results, in both discrete-time and continuous-time.
... More