6 papers
Monotone Neural Policy Iteration for High-Dimensional First-Order Hamilton--Jacobi--Bellman Equations
Minseok Kim, Yeongjong Kim, Namkyeong Cho +1
We analyze a neural semi-discrete method for high-dimensional first-order Hamilton-Jacobi-Bellman (HJB) equations with known or learned dynamics. Centered differences and an artifi…
Policy Iteration for Stationary Discounted Hamilton--Jacobi--Bellman Equations: A Viscosity Approach
Namkyeong Cho, Yeoneung Kim
We study policy iteration (PI) for deterministic infinite-horizon discounted control problems characterized by stationary Hamilton--Jacobi--Bellman equations. For general viscosity…
Physics-informed approach for exploratory Hamilton--Jacobi--Bellman equations via policy iterations
Yeongjong Kim, Namkyeong Cho, Minseok Kim +1
We propose a mesh-free policy iteration framework based on physics-informed neural networks (PINNs) for solving entropy-regularized stochastic control problems. The method iterativ…
Physics-Informed Policy Iteration for High-Dimensional Hamilton--Jacobi--Bellman Equations: Interior Error Bounds without Boundary Data
Yeongjong Kim, Minseok Kim, Yeoneung Kim +1
We develop a physics-informed policy-iteration method for stationary second-order Hamilton--Jacobi--Bellman equations arising in continuous-time stochastic control. Each policy-eva…
On the stability of Lipschitz continuous control problems and its application to reinforcement learning
Namkyeong Cho, Yeoneung Kim
We address the crucial yet underexplored stability properties of the Hamilton--Jacobi--Bellman (HJB) equation in model-free reinforcement learning contexts, specifically for Lipsch…
Sobolev Training for Operator Learning
Namkyeong Cho, Junseung Ryu, Hyung Ju Hwang
This study investigates the impact of Sobolev Training on operator learning frameworks for improving model performance. Our research reveals that integrating derivative information…