This paper presents local asymptotic minimax regret lower bounds for adaptive Linear Quadratic Regulators (LQR). We consider affinely parametrized $B$-matrices and known $A$-matrices and aim to understand when logarithmic regret is impossible even in the presence of structural side information. After defining the intrinsic notion of an uninformative optimal policy in terms of a singularity condition for Fisher information we obtain local minimax regret lower bounds for such uninformative instances of LQR by appealing to van Trees' inequality (Bayesian Cram\'er-Rao) and a representation of regret in terms of a quadratic form (Bellman error). It is shown that if the parametrization induces an uninformative optimal policy, logarithmic regret is impossible and the rate is at least order square root in the time horizon. We explicitly characterize the notion of an uninformative optimal policy in terms of the nullspaces of system-theoretic quantities and the particular instance parametrization.
翻译:本文展示了当地适应性线性二次曲线管理器(LQR) 的微缩最小遗憾下限。 我们考虑对准的 $B$- 矩阵和已知的$A$- 矩阵, 目的是了解即使存在结构性侧面信息, 也不可能对准的遗憾。 在从渔业信息的单一性条件的角度界定了非信息性最佳政策的内在概念之后, 我们通过呼吁范树的不平等( Bayesian Cram\'er-Rao) 和以二次形式表示遗憾( Bellman 错误), 获得了本地小型马克斯对此类无信息性LQR (LQR) 的下限的下限。 这表明, 如果对准性政策引出非信息性的最佳政策, 则不可能对准的遗憾, 且利率在时间范围中至少是平方根。 我们明确定义了在系统理论的无效空间和特定实例对称的不明显最佳政策概念。