Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?

arXiv:2212.14511v2 Announce Type: replace
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 …

abstract arxiv control cs.lg cs.sy dynamic eess.sy linear math.oc observable solve space state stat.ml study type