67 citations · 190 across the 13 of their papers we have counts for
15 papers
Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control
Daniel Pfrommer, Swati Padmanabhan, Kwangjun Ahn +4
Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables stronger guarantees on the performance of the learned c…
On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control
Daniel Pfrommer, Swati Padmanabhan, Kwangjun Ahn +4
Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables stronger guarantees on the performance of the learned c…
Globally Convergent Policy Search over Dynamic Filters for Output Estimation
Jack Umenberger, Max Simchowitz, Juan C. Perdomo +2
We introduce the first direct policy search algorithm which provably converges to the globally optimal filter for the classical problem of predicting the outputs…
Stabilizing Dynamical Systems via Policy Gradient Methods
Juan C. Perdomo, Jack Umenberger, Max Simchowitz
Stabilizing an unknown control system is one of the most fundamental problems in control systems engineering. In this paper, we provide a simple, model-free algorithm for stabilizi…
Distributed Identification of Contracting and/or Monotone Network Dynamics
Max Revay, Jack Umenberger, Ian R. Manchester
This paper proposes methods for identification of large-scale networked systems with guarantees that the resulting model will be contracting -- a strong form of nonlinear stability…
Shortest Paths in Graphs of Convex Sets
Tobia Marcucci, Jack Umenberger, Pablo A. Parrilo +1
Given a graph, the shortest-path problem requires finding a sequence of edges with minimum cumulative length that connects a source vertex to a target vertex. We consider a variant…
Optimistic robust linear quadratic dual control
Jack Umenberger, Thomas B. Schon
Recent work by Mania et al. has proved that certainty equivalent control achieves nearly optimal regret for linear systems with quadratic costs. However, when parameter uncertainty…
Robust exploration in linear quadratic reinforcement learning
Jack Umenberger, Mina Ferizbegovic, Thomas B. Schön +1
This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex opti…
On the smoothness of nonlinear system identification
Antônio H. Ribeiro, Koen Tiels, Jack Umenberger +2
We shed new light on the \textit{smoothness} of optimization problems arising in prediction error parameter estimation of linear and nonlinear systems. We show that for regions of…
Nonlinear input design as optimal control of a Hamiltonian system
Jack Umenberger, Thomas B. Schön
We propose an input design method for a general class of parametric probabilistic models, including nonlinear dynamical systems with process noise. The goal of the procedure is to…
Inverse Quadratic Optimal Control for Discrete-Time Linear Systems
Han Zhang, Jack Umenberger, Xiaoming Hu
In this paper, we consider the inverse optimal control problem for the discrete-time linear quadratic regulator, over finite-time horizons. Given observations of the optimal trajec…
Learning convex bounds for linear quadratic control policy synthesis
Jack Umenberger, Thomas B. Schön
Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics,…
Specialized Interior Point Algorithm for Stable Nonlinear System Identification
Jack Umenberger, Ian R. Manchester
Estimation of nonlinear dynamic models from data poses many challenges, including model instability and non-convexity of long-term simulation fidelity. Recently Lagrangian relaxati…
Linear System Identification via EM with Latent Disturbances and Lagrangian Relaxation
Jack Umenberger, Johan Wågberg, Ian R. Manchester +1
In the application of the Expectation Maximization algorithm to identification of dynamical systems, internal states are typically chosen as latent variables, for simplicity. In th…
Real-Time Planning with Primitives for Dynamic Walking over Uneven Terrain
Ian R. Manchester, Jack Umenberger
We present an algorithm for receding-horizon motion planning using a finite family of motion primitives for underactuated dynamic walking over uneven terrain. The motion primitives…