8 papers
Finite-Sample Metric Non-Collapse for Geometrically Supervised Latent World Models in Control
Alain Bensoussan, Minh-Nhat Phung, Minh-Binh Tran
We establish a finite-sample learning-to-control theory for geometrically supervised latent models of nonlinear deterministic systems. Geometric supervision is used only during tra…
A Structure-Preserving Neural-Spectral Method for Reconstructing Controls of Wave Equations
Tan-Phuc Nguyen, Minh-Binh Tran, Son Tu
The numerical reconstruction of controls for partial differential equations remains comparatively underdeveloped, despite the extensive analytical literature on controllability. Th…
Computational Control of Nonlinear Partial Differential Equations Using Machine Learning
Maximilian Kurbanov, Minh-Nhat Phung, Minh-Binh Tran
The numerical reconstruction of controls for nonlinear partial differential equations (PDEs) remains a challenging and relatively underdeveloped problem, despite the extensive lite…
Control, Optimal Transport and Neural Differential Equations in Supervised Learning
Minh-Nhat Phung, Minh-Binh Tran
We study the fundamental computational problem of approximating optimal transport (OT) equations using neural differential equations (Neural ODEs). More specifically, we develop a…
Operator Splitting, Policy Iteration, and Machine Learning for Stochastic Optimal Control
Alain Bensoussan, Thien P. B. Nguyen, Minh-Binh Tran +1
We propose a splitting approach to solve the second-order Hamilton--Jacobi equation, reducing it to a heat step and a purely first-order step. The latter is implemented using a gra…
A Relative Ignorability Framework for Decision-Relevant Observability in Control Theory and Reinforcement Learning
MaryLena Bleile, Minh-Nhat Phung, Minh-Binh Tran
Sequential decision-making systems routinely operate with missing or incomplete data. Classical reinforcement learning theory, which is commonly used to solve sequential decision p…