arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2402.02792math.OC
收藏

微分博弈的表示结果与误差估计及其在神经网络中的应用

Representation results and error estimates for differential games with applications using neural networks

Olivier Bokanowski, Xavier Warin

AI总结:

本文研究有限时域微分博弈的确定性最优控制问题,提出反馈策略的神经网络近似方法并给出误差估计与弱收敛结果,同时改进连续与半离散值函数的收敛阶,并通过数值实验验证了方法有效性。

摘要:

我们研究有限时域微分博弈的确定性最优控制问题。我们提出了反馈形式策略的新近似方法,并针对其中一种公式化形式给出了误差估计以及值函数在某种弱意义下的收敛结果。该结果特别适用于神经网络近似。本工作沿用了Bokanowski、Prost和Warin(PDEA, 2023)在确定性最优控制问题中引入的一些思想,但对误差估计采用了简化方法,从而可以考虑全局优化方案而非时间推进方案。我们还在博弈设定下给出了连续最优控制值与半离散最优控制值之间的新近似结果,在动力系统的某些假设下改进了经典收敛阶。数值实验在涉及后向可达性的基础学术问题上进行,并给出了精确解析解,同时还处理了一个存在状态约束的两人博弈问题。我们使用随机梯度类算法来处理极小极大问题。

英文摘要:

We study deterministic optimal control problems for differential games with finite horizon. We propose new approximations of the strategies in feedback form, and show error estimates and a convergence result of the value in some weak sense for one of the formulations. This result applies in particular to neural networks approximations. This work follows some ideas introduced in Bokanowski, Prost and Warin (PDEA, 2023) for deterministic optimal control problems, yet with a simplified approach for the error estimates, which allows to consider a global optimization scheme instead of a time-marching scheme. We also give a new approximation result between the continuous and the semi-discrete optimal control value in the game setting, improving the classical convergence order under some assumptions on the dynamical system. Numerical examples are performed on elementary academic problems related to backward reachability, with exact analytic solutions given, as well as a two-player game in presence of state constraints. We use stochastic gradient type algorithms in order to deal with the min-max problem.

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。

↑