The Power of Predictions in Online Control
The Power of Predictions in Online Control
复制标题
DOI：
--
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Chenkai Yu;Guanya Shi;Soon-Jo Chung;Yisong Yue;A. Wierman
中科院分区：
文献类型：
--
作者：
Chenkai Yu;Guanya Shi;Soon-Jo Chung;Yisong Yue;A. Wierman
我们研究的影响，预测在线线性二次型调节器控制与随机和对抗性干扰的动态。在这两种情况下，我们的最优策略的特点，并得出严格的界限上的最小成本和动态遗憾。也许令人惊讶的是，我们的分析表明，传统的贪婪MPC方法在随机和对抗环境中都是接近最优的政策。具体来说，对于长度为$T$的问题，MPC只需要$O（\log T）$的预测就可以达到$O（1）$的动态后悔，这与我们在恒定后悔所需的预测范围上的下限相匹配（直到低阶项）。
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.