%ATian, Yi%AZhang, Kaiqing%ATedrake, Russ%ASra, Suvrit%D2023%I
%K
%MOSTI ID: 10430535
%PMedium: X
%TCan Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?
%XWe study the task of learning state representations from potentially high-dimensional observations,
with the goal of controlling an unknown partially observable system. We pursue a direct latent
model learning approach, where a dynamic model in some latent state space is learned by predicting
quantities directly related to planning (e.g., costs) without reconstructing the observations.
In particular, we focus on an intuitive cost-driven state representation learning method for solving
Linear Quadratic Gaussian (LQG) control, one of the most fundamental partially observable control
problems. As our main results, we establish finite-sample guarantees of finding a near-optimal
state representation function and a near-optimal controller using the directly learned latent model.
To the best of our knowledge, despite various empirical successes, prior to this work it was unclear
if such a cost-driven latent model learner enjoys finite-sample guarantees. Our work underscores
the value of predicting multi-step costs, an idea that is key to our theory, and notably also an idea
that is known to be empirically valuable for learning state representations.
Country unknown/Code not availableOSTI-MSA