arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2506.04497math.OC
收藏

最大化预测在控制中的价值:仅有准确性是不够的

Maximizing the Value of Predictions in Control: Accuracy Is Not Enough

Yiheng Lin, Christopher Yeh, Zaiwei Chen, Adam Wierman

AI总结:

本文研究在线最优控制中随机预测的价值,提出预测能力概念并给出LQR闭式解及一般情形下界,证明弱依赖预测也能显著提升控制性能。

摘要:

我们研究具有随机扰动的在线最优控制中随机预测的价值。先前的工作基于预测误差提供性能保证,但忽略了预测与扰动之间的随机依赖性。我们引入一个通用框架来建模它们的联合分布,并将“预测能力”定义为与忽略预测相比,最优使用预测所带来的控制成本改进。在时变线性二次调节器(LQR)设置中,我们推导出预测能力的闭式表达式,并讨论其与预测准确性的不匹配以及与在线策略优化的联系。为了扩展到LQR之外,我们研究一般动态和成本。我们在两个充分条件下建立了预测能力的下界,这些条件推广了LQR设置的性质,刻画了纳入随机预测的根本收益。我们将该下界应用于非二次成本,并表明即使是弱依赖的预测也能带来显著的性能提升。

英文摘要:

We study the value of stochastic predictions in online optimal control with random disturbances. Prior work provides performance guarantees based on prediction error but ignores the stochastic dependence between predictions and disturbances. We introduce a general framework modeling their joint distribution and define "prediction power" as the control cost improvement from the optimal use of predictions compared to ignoring the predictions. In the time-varying Linear Quadratic Regulator (LQR) setting, we derive a closed-form expression for prediction power and discuss its mismatch with prediction accuracy and connection with online policy optimization. To extend beyond LQR, we study general dynamics and costs. We establish a lower bound of prediction power under two sufficient conditions that generalize the properties of the LQR setting, characterizing the fundamental benefit of incorporating stochastic predictions. We apply this lower bound to non-quadratic costs and show that even weakly dependent predictions yield significant performance gains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑