Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?

Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

We 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.

Original languageEnglish
Pages (from-to)51-63
Number of pages13
JournalProceedings of Machine Learning Research
Volume211
StatePublished - 2023
Externally publishedYes
Event5th Annual Conference on Learning for Dynamics and Control, L4DC 2023 - Philadelphia, United States
Duration: 15 Jun 202316 Jun 2023

Keywords

  • Latent model learning
  • linear quadratic Gaussian (LQG)
  • state representation learning for control

Fingerprint

Dive into the research topics of 'Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?'. Together they form a unique fingerprint.

Cite this