Statistical learning theory for control: A finite-sample perspective
Learning algorithms have become an integral component to modern engineering solutions.
Examples range from self-driving cars and recommender systems to finance and even …
Examples range from self-driving cars and recommender systems to finance and even …
Neural operators for bypassing gain and control computations in pde backstepping
We introduce a framework for eliminating the computation of controller gain functions in PDE
control. We learn the nonlinear operator from the plant parameters to the control gains with a …
control. We learn the nonlinear operator from the plant parameters to the control gains with a …
Maximum diffusion reinforcement learning
Robots and animals both experience the world through their bodies and senses. Their
embodiment constrains their experiences, ensuring that they unfold continuously in space …
embodiment constrains their experiences, ensuring that they unfold continuously in space …
The power of learned locally linear models for nonlinear policy optimization
D Pfrommer, M Simchowitz… - International …, 2023 - proceedings.mlr.press
A common pipeline in learning-based control is to iteratively estimate a model of system
dynamics, and apply a trajectory optimization algorithm-eg $\mathtt {iLQR} $-on the learned …
dynamics, and apply a trajectory optimization algorithm-eg $\mathtt {iLQR} $-on the learned …
Meta-learning operators to optimality from multi-task non-iid data
A powerful concept behind much of the recent progress in machine learning is the extraction
of common features across data from heterogeneous sources or tasks. Intuitively, using all of …
of common features across data from heterogeneous sources or tasks. Intuitively, using all of …
Regret lower bounds for learning linear quadratic gaussian systems
I Ziemann, H Sandberg - IEEE Transactions on Automatic …, 2024 - ieeexplore.ieee.org
In this article, we establish regret lower bounds for adaptively controlling an unknown linear
Gaussian system with quadratic costs. We combine ideas from experiment design …
Gaussian system with quadratic costs. We combine ideas from experiment design …
How are policy gradient methods affected by the limits of control?
We study stochastic policy gradient methods from the perspective of control-theoretic
limitations. Our main result is that ill-conditioned linear systems in the sense of Doyle …
limitations. Our main result is that ill-conditioned linear systems in the sense of Doyle …
Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
A powerful concept behind much of the recent progress in machine learning is the extraction
of common features across data from heterogeneous sources or tasks. Intuitively, using all of …
of common features across data from heterogeneous sources or tasks. Intuitively, using all of …
End-to-end guarantees for indirect data-driven control of bilinear systems with finite stochastic data
In this paper we propose an end-to-end algorithm for indirect data-driven control for bilinear
systems with stability guarantees. We consider the case where the collected iid data is …
systems with stability guarantees. We consider the case where the collected iid data is …
The fundamental limitations of learning linear-quadratic regulators
We present a local minimax lower bound on the excess cost of designing a linear-quadratic
controller from offline data. The bound is valid for any offline exploration policy that consists …
controller from offline data. The bound is valid for any offline exploration policy that consists …