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 language | English |
---|---|
Pages (from-to) | 51-63 |
Number of pages | 13 |
Journal | Proceedings of Machine Learning Research |
Volume | 211 |
State | Published - 2023 |
Externally published | Yes |
Event | 5th Annual Conference on Learning for Dynamics and Control, L4DC 2023 - Philadelphia, United States Duration: 15 Jun 2023 → 16 Jun 2023 |
Keywords
- Latent model learning
- linear quadratic Gaussian (LQG)
- state representation learning for control