Towards a Dimension-Free Understanding of Adaptive Linear Control
arXiv:2103.10620
Abstract
We study the problem of adaptive control of the linear quadratic regulator for systems in very high, or even infinite dimension. We demonstrate that while sublinear regret requires finite dimensional inputs, the ambient state dimension of the system need not be bounded in order to perform online control. We provide the first regret bounds for LQR which hold for infinite dimensional systems, replacing dependence on ambient dimension with more natural notions of problem complexity. Our guarantees arise from a novel perturbation bound for certainty equivalence which scales with the prediction error in estimating the system parameters, without requiring consistent parameter recovery in more stringent measures like the operator norm. When specialized to finite dimensional settings, our bounds recover near optimal dimension and time horizon dependence.
arXiv commentpresented at COLT 2021
References in corpus (17)
- Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
- Provably Efficient Reinforcement Learning with Linear Function Approximation
- Contextual Decision Processes with Low Bellman Rank are PAC-Learnable
- Gradient Descent Learns Linear Dynamical Systems
- Near optimal finite time identification of arbitrary linear dynamical systems
- Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches
- Improper Learning for Non-Stochastic Control
- Non-Asymptotic Analysis of Robust Control from Coarse-Grained Identification
- Online Control with Adversarial Disturbances
- Model-Free Linear Quadratic Control via Reduction to Expert Prediction
- Thompson Sampling for Linear-Quadratic Control Problems
- Active Learning for Nonlinear System Identification with Guarantees
- PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
- Information Theoretic Regret Bounds for Online Nonlinear Control
- Online Nonparametric Regression
- Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation
- Some Trace Inequalities for Operators in Hilbert Spaces