arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.01788cs.AI
收藏

基于近似影响的抽象的损失界

Loss Bounds for Approximate Influence-Based Abstraction

Delft University of Technology(代尔夫特理工大学)

Elena Congeduti, Alexander Mey, Frans A. Oliehoek

摘要:

序贯决策技术在提高许多现实系统的性能方面有着巨大的潜力,但计算复杂性阻碍了其原则性应用。基于影响的抽象旨在通过对局部子问题以及系统其余部分对它们施加的“影响”进行建模来获得杠杆作用。虽然计算这种影响的精确表示可能是棘手的,但学习近似表示提供了一种有前途的方法来实现可扩展的解决方案。本文从理论的角度研究了这种方法的性能。的主要贡献是推导出的充分条件近似的影响表示,可以保证解决方案的小价值损失。特别是,我们表明,交叉熵训练的神经网络非常适合学习近似的影响表示。此外,我们提供了一个基于样本的制定的界限,这减少了差距的应用。最后,我们的理论见解的驱动下,我们提出了近似误差估计,经验显示,以及相关的价值损失。

英文摘要:

Sequential decision making techniques hold great promise to improve the performance of many real-world systems, but computational complexity hampers their principled application. Influence-based abstraction aims to gain leverage by modeling local subproblems together with the 'influence' that the rest of the system exerts on them. While computing exact representations of such influence might be intractable, learning approximate representations offers a promising approach to enable scalable solutions. This paper investigates the performance of such approaches from a theoretical perspective. The primary contribution is the derivation of sufficient conditions on approximate influence representations that can guarantee solutions with small value loss. In particular we show that neural networks trained with cross entropy are well suited to learn approximate influence representations. Moreover, we provide a sample based formulation of the bounds, which reduces the gap to applications. Finally, driven by our theoretical insights, we propose approximation error estimators, which empirically reveal to correlate well with the value loss.

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。

↑