Regret Analysis of Policy Optimization over Submanifolds for Linearly Constrained Online LQG

arXiv:2403.08553v1 Announce Type: cross
Abstract: Recent advancement in online optimization and control has provided novel tools to study online linear quadratic regulator (LQR) problems, where cost matrices are varying adversarially over time. However, the controller parameterization of existing works may not satisfy practical conditions like sparsity due to physical connections. In this work, we study online linear quadratic Gaussian problems with a given linear constraint imposed on the controller. Inspired by the recent work of [1] which proposed, for a …

abstract advancement analysis arxiv control cost cs.lg cs.sy eess.sy however linear math.oc novel optimization policy practical regulator sparsity study tools type