We study the problem of control policy design for decentralized state-feedback linear quadratic control with a partially nested information structure . We propose a model-based learningsolution, which consists of two steps . We show that thesuboptimality gap between our control policy and the optimal decentralizedcontrol policy scaleslinearly with the estimation error of the system model . Using this result, weprovide an end-to-end sample complexity result for learning decentralizedcontrollers for a linear quad ratic control problem with a . partially nestedinformation structure, we provide an end to the . end to end complexity result .

Author(s) : Lintao Ye, Hao Zhu, Vijay Gupta

Links : PDF - Abstract

Code :

Keywords : control - partially - complexity - policy - structure -

Leave a Reply

Your email address will not be published. Required fields are marked *