论文标题
在线控制中预测的力量
The Power of Predictions in Online Control
论文作者
论文摘要
我们研究了在线线性二次调节器控制中预测的影响，并在动力学中都具有随机和对抗性干扰。在这两种情况下，我们都表征了最佳策略，并以最低成本和动态遗憾得出紧密的界限。也许令人惊讶的是，我们的分析表明，常规的贪婪MPC方法在随机和对抗性环境中都是近乎最佳的政策。具体来说，对于长度-$ t $问题，MPC仅需要$ o（\ log t）$预测才能达到$ o（1）$ dynamic遗憾，这与我们在所需的预测范围内的下限匹配（最高较低阶段），以保持持续的遗憾。
We study the impact of predictions in online Linear Quadratic Regulator control with both stochastic and adversarial disturbances in the dynamics. In both settings, we characterize the optimal policy and derive tight bounds on the minimum cost and dynamic regret. Perhaps surprisingly, our analysis shows that the conventional greedy MPC approach is a near-optimal policy in both stochastic and adversarial settings. Specifically, for length-$T$ problems, MPC requires only $O(\log T)$ predictions to reach $O(1)$ dynamic regret, which matches (up to lower-order terms) our lower bound on the required prediction horizon for constant regret.
