4 papers
State-dependent temperature control in Langevin diffusions using numerical exploratory Hamiltonian-Jacobi-Bellman equations
Taorui Wang, Xun Li, Gu Wang +1
Choosing how much noise to add in Langevin dynamics is essential for making these algorithms effective in challenging optimization problems. One promising approach is to determine…
Continuous Policy and Value Iteration for Relaxed Stochastic Control Problems and Its Convergence
Qi Feng, Gu Wang
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…
Ergodic McKean-Vlasov Games: Verification Theorems and Linear-Quadratic Applications
Qingshuo Song, Gu Wang, Zuo Quan Xu +1
This paper investigates two-player ergodic nonzero-sum stochastic differential games with McKean-Vlasov dynamics. We establish a verification theorem connecting solutions of couple…
Exit problem as the generalized solution of Dirichlet problem
Yuecai Han, Qingshuo Song, Gu Wang
This paper investigates sufficient conditions for a Feynman-Kac functional up to an exit time to be the generalized viscosity solution of a Dirichlet problem. The key ingredient is…