EasyDeepLearn

LQG — Linear Quadratic Gaussian control.

hard

Answer

  • Extension of LQR to noisy partial observations.
  • Optimal controller = Kalman filter (state estimation) + LQR (control).
  • Certainty equivalence: LQ control on filtered state estimate is optimal.
  • Bridge between control theory + POMDP-RL.
  • Modern: neural networks approximate both filter + controller.
  • Foundation of classical control theory taught in every EE / ME curriculum.
Check yourself — multiple choice
  • Same as LQR
  • LQR + Kalman filter for noisy partial obs; certainty equivalence: LQ control on filtered estimate is optimal; classical control foundation extended to POMDP-RL
  • Random
  • Not real

LQG: Kalman filter + LQR; certainty equivalence; classical control bridge.

#planning#theory

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions