English

Reinforcement Learning Approach to Estimation in Linear Systems

Systems and Control 2022-05-10 v1 Systems and Control

Abstract

This paper addresses two important estimation problems for linear systems, namely system identification and model-free state estimation. Our focus is on ARMAX models with unknown parameters. We first provide a reinforcement learning algorithm for system identification with guaranteed consistency. This algorithm is then used to provide a novel solution to model-free state estimation. These results are then applied to solving the model-free LQG control problem in the reinforcement learning setting.

Keywords

Cite

@article{arxiv.2205.03504,
  title  = {Reinforcement Learning Approach to Estimation in Linear Systems},
  author = {Minyue Fu},
  journal= {arXiv preprint arXiv:2205.03504},
  year   = {2022}
}
R2 v1 2026-06-24T11:09:55.339Z