发表机构
U2IS, ENSTA, Institut Polytechnique de Paris; L2S, Inria, Université Paris-Saclay, CentraleSupelec; Inria, École Normale Supérieure, PSL Research University(巴黎理工学院; 巴黎萨克雷大学; 巴黎文理研究大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
针对环面上仅通过样本访问的控制仿射最优控制问题,提出兼容随机优化的对偶、原始及原始-对偶公式,证明随机一阶方法收敛,并引入可计算性能上界度量,初步验证有效。
AI 中文摘要
我们考虑环面上的控制仿射最优控制问题,其中动力学和代价函数仅通过样本访问。从这类问题的弱形式出发,我们推导出对偶、原始和原始-对偶三种公式,它们与随机优化兼容。我们证明了在一般条件下随机一阶方法收敛到最优值。此外,我们引入了一个可计算的度量,在额外正则性假设下,该度量上界限制了优化过程中产生的次优控制器的性能。初步结果表明,该方法能有效求解一个简单的控制问题。最后,我们讨论了最优占用测度有界性的条件,这是原始和原始-对偶方法的关键假设。
英文摘要
We consider control-affine optimal control problems on the torus, where the dynamics and cost functions are only accessed through samples. Starting from a weak formulation of such problems, we derive a dual, a primal, and a primal-dual formulation, compatible with stochastic optimization. We show convergence of stochastic first-order methods to the optimal value under generic conditions. In addition, we introduce a computable metric that upper-bounds the performance of suboptimal controllers produced during optimization, under additional regularity assumptions. Preliminary results show that the method can efficiently solve a simple control problem. Finally, we discuss conditions for the boundedness of the optimal occupation measure, a key assumption for the primal and primal-dual approaches.