Learning-based Control of Unknown Linear Systems with Thompson Sampling
Provides a theoretical regret bound for Thompson sampling in LQ control, addressing a key open problem for control theorists and reinforcement learning researchers.
The paper proposes a Thompson sampling-based algorithm for unknown linear quadratic control, achieving the first O(√T) expected Bayesian regret bound. Numerical simulations demonstrate its performance.
We propose a Thompson sampling-based learning algorithm for the Linear Quadratic (LQ) control problem with unknown system parameters. The algorithm is called Thompson sampling with dynamic episodes (TSDE) where two stopping criteria determine the lengths of the dynamic episodes in Thompson sampling. The first stopping criterion controls the growth rate of episode length. The second stopping criterion is triggered when the determinant of the sample covariance matrix is less than half of the previous value. We show under some conditions on the prior distribution that the expected (Bayesian) regret of TSDE accumulated up to time T is bounded by O(\sqrt{T}). Here O(.) hides constants and logarithmic factors. This is the first O(\sqrt{T} ) bound on expected regret of learning in LQ control. By introducing a reinitialization schedule, we also show that the algorithm is robust to time-varying drift in model parameters. Numerical simulations are provided to illustrate the performance of TSDE.