Certainty Equivalent Control of LQR is Efficient
share
We study the performance of the certainty equivalent controller on the Linear Quadratic Regulator (LQR) with unknown transition dynamics. We show that the sub-optimality gap between the cost incurred by playing the certainty equivalent controller on the true system and the cost incurred by using the optimal LQR controller enjoys a fast statistical rate, scaling as the square of the parameter error. Our result improves upon recent work by Dean et al. (2017), who present an algorithm achieving a sub-optimality gap linear in the parameter error. A key part of our analysis relies on perturbation bounds for discrete Riccati equations. We provide two new perturbation bounds, one that expands on an existing result from Konstantinov et al. (1993), and another based on a new elementary proof strategy. Our results show that certainty equivalent control with ε-greedy exploration achieves Õ(√(T)) regret in the adaptive LQR setting, yielding the first guarantee of a computationally tractable algorithm that achieves nearly optimal regret for adaptive LQR.
READ FULL TEXT