论文标题
具有有限样本保证的参数化不确定动态环境的在线学习
Online Learning of Parameterized Uncertain Dynamical Environments with Finite-sample Guarantees
论文作者
论文摘要
我们为一类完全可观察到的一类未知和不确定的动态环境提供了一种新颖的在线学习算法。首先，我们获得了一种新型的概率表征，该系统的平均行为是已知的，但会受到添加剂，未知的次高斯干扰。这种特征依赖于最近的度量结果集中度，并且是根据歧义集进行的。其次，我们将结果扩展到其平均行为也未知但通过参数化的平均行为类别描述的环境。我们的算法通过在线学习参数依赖性，并保留相似的概率保证，从而对添加剂，未知的干扰保留相似的概率保证，从而使歧义性适应歧义。我们说明了受环境不确定性的差异驱动机器人的结果。
We present a novel online learning algorithm for a class of unknown and uncertain dynamical environments that are fully observable. First, we obtain a novel probabilistic characterization of systems whose mean behavior is known but which are subject to additive, unknown subGaussian disturbances. This characterization relies on recent concentration of measure results and is given in terms of ambiguity sets. Second, we extend the results to environments whose mean behavior is also unknown but described by a parameterized class of possible mean behaviors. Our algorithm adapts the ambiguity set dynamically by learning the parametric dependence online, and retaining similar probabilistic guarantees with respect to the additive, unknown disturbance. We illustrate the results on a differential-drive robot subject to environmental uncertainty.
