10 papers
Structural Averaged Controllability for Linear Ensemble Systems: Multi-input Case
Amirreza Neshaei Moghaddam, Xudong Chen, Bahman Gharesifard
We study structural averaged controllability for multi-input linear ensemble systems. In this problem, one asks whether a sparsity pattern admits a linear ensemble system that is a…
From Schrodinger Bridge to Optimal Transport over Sub-Riemannian Manifolds
Daniel Owusu Adu, Karthik Elamvazhuthi, Bahman Gharesifard
We study the least-energy way to reshape a probability distribution when motion is constrained to a horizontal bundle, that is, optimal transport and distribution steering in sub-R…
Global exponential stabilization of a force- and torque-actuated unicycle by flexible-step MPC
Ala Kolsi, Christian Ebenbauer, Bahman Gharesifard +1
We study the problem of global exponential stabilization of a force- and torque-controlled unicycle model in discrete time. To this end, we extend a recently introduced approach to…
On Reward-Balancing Methods for Reinforcement Learning
Simone Baroncini, Bahman Gharesifard, Giuseppe Notarstefano
This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consis…
Flexible-step MPC for Unknown Linear Time-Invariant Systems
Markus Pietschner, Christian Ebenbauer, Bahman Gharesifard +1
We propose a novel flexible-step model predictive control algorithm for unknown linear time-invariant discrete-time systems. The goal is to asymptotically stabilize the system with…
Sample Complexity of Linear Quadratic Regulator Without Initial Stability
Amirreza Neshaei Moghaddam, Alex Olshevsky, Bahman Gharesifard
Inspired by REINFORCE, we introduce a novel receding-horizon algorithm for the Linear Quadratic Regulator (LQR) problem with unknown dynamics. Unlike prior methods, our algorithm a…
Inferring Global Exponential Stability Properties using Lie-bracket Approximations
Marc Weber, Bahman Gharesifard, Christian Ebenbauer
In the present paper, a novel result for inferring uniform global, not semi-global, exponential stability in the sense of Lyapunov with respect to input-affine systems from global…
Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens
Amirreza Neshaei Moghaddam, Alex Olshevsky, Bahman Gharesifard
We provide the first known algorithm that provably achieves -optimality within function evaluations for the discounted discret…
Flexible-step MPC for Switched Linear Systems with No Quadratic Common Lyapunov Function
Annika Fürnsinn, Christian Ebenbauer, Bahman Gharesifard
In this paper, we develop a systematic method for constructing a generalized discrete-time control Lyapunov function for the flexible-step Model Predictive Control (MPC) scheme, re…
Sparse Linear Ensemble Systems and Structural Averaged Controllability: Single-input Case
Xudong Chen, Bahman Gharesifard
We consider continuum ensembles of linear time-invariant control systems with single inputs. A sparsity pattern is said to be structurally averaged controllability if it admits an…