Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II
Abstract
We study the problem of state representation learning for control from partial and potentially high-dimensional observations. We approach this problem via cost-driven state representation learning, in which we learn a dynamical model in a latent state space by predicting cumulative costs. In particular, we establish finite-sample guarantees on finding a near-optimal representation function and a near-optimal controller using the learned latent model for infinite-horizon time-invariant Linear Quadratic Gaussian (LQG) control. We study two approaches to cost-driven representation learning, which differ in whether the transition function of the latent state is learned explicitly or implicitly. The first approach has also been investigated in Part I of this work, for finite-horizon time-varying LQG control. The second approach closely resembles MuZero, a recent breakthrough in empirical reinforcement learning, in that it learns latent dynamics implicitly by predicting cumulative costs. A key technical contribution of this Part II is to prove persistency of excitation for a new stochastic process that arises from the analysis of quadratic regression in our approach, and may be of independent interest.
Keywords
Cite
@article{arxiv.2603.07437,
title = {Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II},
author = {Yi Tian and Kaiqing Zhang and Russ Tedrake and Suvrit Sra},
journal= {arXiv preprint arXiv:2603.07437},
year = {2026}
}
Comments
38 pages; preliminary version appeared in IEEE CDC 2023; this is the extended journal version, with an end-to-end guarantee added