Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.07437 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910045164273664 |
|---|---|
| author | Tian, Yi Zhang, Kaiqing Tedrake, Russ Sra, Suvrit |
| author_facet | Tian, Yi Zhang, Kaiqing Tedrake, Russ Sra, Suvrit |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07437 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II Tian, Yi Zhang, Kaiqing Tedrake, Russ Sra, Suvrit Machine Learning Systems and Control Optimization and Control 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. |
| title | Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II |
| topic | Machine Learning Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2603.07437 |