Nowadays, Deep Learning (DL) methods often overcome the limitations of traditional signal processing approaches. Nevertheless, DL methods are barely applied in real-life applications. This is mainly due to limited robustness and distributional shift between training and test data. To this end, recent work has proposed uncertainty mechanisms to increase their reliability. Besides, meta-learning aims at improving the generalization capability of DL models. By taking advantage of that, this paper proposes an uncertainty-based Meta-Reinforcement Learning (Meta-RL) approach with Out-of-Distribution (OOD) detection. The presented method performs a given task in unseen environments and provides information about its complexity. This is done by determining first and second-order statistics on the estimated reward. Using information about its complexity, the proposed algorithm is able to point out when tracking is reliable. To evaluate the proposed method, we benchmark it on a radar-tracking dataset. There, we show that our method outperforms related Meta-RL approaches on unseen tracking scenarios in peak performance by 16% and the baseline by 35% while detecting OOD data with an F1-Score of 72%. This shows that our method is robust to environmental changes and reliably detects OOD scenarios.
翻译:目前,深学习(DL)方法往往克服传统信号处理方法的局限性。然而,DL方法在现实应用中几乎没有应用,这主要是因为培训和测试数据之间的可靠性和分布变化有限。为此,最近的工作提出了提高可靠性的不确定性机制。此外,元学习的目的是提高DL模型的普及能力。利用这一方法,本文件建议采用基于不确定性的Meta-加强学习(Meta-RL)方法,进行分配外检测。提出的方法在无形环境中执行特定任务,并提供有关其复杂性的信息。这主要通过确定关于估计奖励的第一和第二顺序统计来完成。使用有关其复杂性的信息,拟议的算法能够指出追踪的可靠性。为了评价拟议的方法,我们用雷达跟踪数据集来衡量它。我们的方法在以16 %的最高性能和以35 %的基线探测ODD数据时,用F1-Score 72%的可靠情景来检测环境数据。这显示我们的方法是可靠地探测72%的OD。