Online Control with Adversarial Disturbances

Abstract

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that has full knowledge of the disturbances in hindsight. Our main result is an efficient algorithm that provides nearly tight regret bounds for this problem. From a technical standpoint, this work generalizes upon previous work in two main aspects: our model allows for adversarial noise in the dynamics, and allows for general convex costs.

Cited by in corpus (38)

• Improper Learning for Non-Stochastic Control
• Logarithmic Regret for Adversarial Online Control
• Naive Exploration is Optimal for Online LQR
• Online Optimization with Memory and Competitive Control
• Online Gradient Descent for Linear Dynamical Systems
• Black-Box Control for Linear Dynamical Systems
• An online convex optimization algorithm for controlling linear systems with state and input constraints
• Adaptive Regret for Control of Time-Varying Dynamics
• Non-stationary Online Learning with Memory and Non-stochastic Control
• Improved Analysis for Dynamic Regret of Strongly Convex and Smooth Functions
• Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees
• Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
• Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems
• The Power of Predictions in Online Control
• Making Non-Stochastic Control (Almost) as Easy as Stochastic
• Regret-optimal measurement-feedback control
• Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking
• Robust Regret Optimal Control
• Online Agnostic Boosting via Regret Minimization
• Online Optimal Control with Affine Constraints
• An Iterative Riccati Algorithm for Online Linear Quadratic Control
• Distributed Online Linear Quadratic Control for Linear Time-invariant Systems
• A Regret Minimization Approach to Iterative Learning Control
• Regret Analysis of Distributed Online LQR Control for Unknown LTI Systems
• Online Robust Control of Nonlinear Systems with Large Uncertainty
• Modes of Homogeneous Gradient Flows
• Towards a Dimension-Free Understanding of Adaptive Linear Control
• On the Regret Analysis of Online LQR Control with Predictions
• Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games
• Provable Regret Bounds for Deep Online Learning and Control
• When is Particle Filtering Efficient for Planning in Partially Observed Linear Dynamical Systems?
• Online Learning Robust Control of Nonlinear Dynamical Systems
• Lazy OCO: Online Convex Optimization on a Switching Budget
• Learning-to-learn non-convex piecewise-Lipschitz functions
• A Meta-Learning Control Algorithm with Provable Finite-Time Guarantees
• Regret Bounds for Adaptive Nonlinear Control
• Meta-Learning Guarantees for Online Receding Horizon Learning Control
• Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory