Abstract: In this paper, we propose a model-free solution to the linear quadratic regulation (LQR) problem of continuous-time systems based on reinforcement learning using dynamic output feedback. The ...

Abstract: A seminal work of [Ahn-Guha-McGregor, PODS’12] showed that one can compute a cut sparsifier of an unweighted undirected graph by taking a near-linear number of linear measurements on the ...

This repository is an implementation of the paper entitled "On Representing Mixed-Integer Linear Programs by Graph Neural Networks." (ICLR 2023) The paper can be found here. Our codes are modified ...

py-pde is a Python package for solving partial differential equations (PDEs). The package provides classes for grids on which scalar and tensor fields can be defined. The associated differential ...