activity
20172023
most citedGlobal Convergence of Policy Gradient for Sequential Zero-Sum Linear Quadratic Dynamic Games

26 citations · 61 across the 18 of their papers we have counts for

collaborators
Showing math.OCShow all

25 papers · 1 filter

math.OC20226 cited

Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies

Bin Hu, Kaiqing Zhang, Na Li +3

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical…

math.OC2021

Discrete-Time Linear-Quadratic Regulation via Optimal Transport

Mathias Hudoba de Badyn, Erik Miehling, Dylan Janak +5

In this paper, we consider a discrete-time stochastic control problem with uncertain initial and target states. We first discuss the connection between optimal transport and stocha…

math.OC2020

Graph-theoretic optimization for edge consensus

Mathias Hudoba de Badyn, Dillon R. Foight, Daniel Calderone +2

We consider network structures that optimize the norm of weighted, time scaled consensus networks, under a minimal representation of such consensus networks describ…

math.OC20203 cited

A Note on Nesterov's Accelerated Method in Nonconvex Optimization: a Weak Estimate Sequence Approach

Jingjing Bu, Mehran Mesbahi

We present a variant of accelerated gradient descent algorithms, adapted from Nesterov's optimal first-order methods, for weakly-quasi-convex and weakly-quasi-strongly-convex funct…

math.OC2020

Performance and design of consensus on matrix-weighted and time scaled graphs

Dillon R. Foight, Mathias Hudoba de Badyn, Mehran Mesbahi

In this paper, we consider the -norm of networked systems with multi-time scale consensus dynamics and vector-valued agent states. This allows us to explore how meas…

math.OC2020

From noisy data to feedback controllers: non-conservative design via a matrix S-lemma

Henk J. van Waarde, M. Kanat Camlibel, Mehran Mesbahi

We propose a new method to obtain feedback controllers of an unknown dynamical system directly from noisy input/state data. The key ingredient of our design is a new matrix S-lemma…