在本文中，我们介绍了一种方法来适应时间差（TD）学习的步长。TD方法的性能往往取决于选择良好的步长，但很少有算法已经开发出自动设置TD学习的步长。当前方法的一个重要限制是它们适应由学习系统的所有权重共享的单步的。矢量步长通过在每个特征的基础上指定参数来实现更大的优化。此外，以不同速率调整参数具有作为表示学习的简单形式的附加益处。我们将增量Delta Bar Delta（IDBD）--一种用于监督学习的矢量化自适应步长方法--推广到TD学习，我们将其命名为TIDBD。我们证明了TIDBD能够在平稳和非平稳预测任务中找到合适的步长，优于普通TD方法和具有标量步长自适应的TD方法;我们证明了它可以区分与给定任务相关和不相关的特征，执行表示学习;我们在一个真实世界的机器人预测任务上表明，TIDBD能够优于普通的TD方法和用AlphaBound和RMSprop增强的TD方法。
英文摘要：
In this paper, we introduce a method for adapting the step-sizes of temporal difference (TD) learning. The performance of TD methods often depends on well chosen step-sizes, yet few algorithms have been developed for setting the step-size automatically for TD learning. An important limitation of current methods is that they adapt a single step-size shared by all the weights of the learning system. A vector step-size enables greater optimization by specifying parameters on a per-feature basis. Furthermore, adapting parameters at different rates has the added benefit of being a simple form of representation learning. We generalize Incremental Delta Bar Delta (IDBD)---a vectorized adaptive step-size method for supervised learning---to TD learning, which we name TIDBD. We demonstrate that TIDBD is able to find appropriate step-sizes in both stationary and non-stationary prediction tasks, outperforming ordinary TD methods and TD methods with scalar step-size adaptation; we demonstrate that it can differentiate between features which are relevant and irrelevant for a given task, performing representation learning; and we show on a real-world robot prediction task that TIDBD is able to outperform ordinary TD methods and TD methods augmented with AlphaBound and RMSprop.
Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations
Tsinghua University（清华大学）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；KIRC, Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能研究院知识图谱与推理中心（KIRC））；Beijing National Research Center for Information Science and Technology（北京国家信息科学与技术研究中心）
Adapting to Dynamic LEO-B5G Systems: Meta-Critic Learning Based Efficient Resource Scheduling
Interdisciplinary Centre for Security, Reliability and Trust, Luxembourg University（卢森堡大学安全、可靠性与跨学科信任中心）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Faculty of Information Technology, University of Jyväskylä（于韦斯屈莱大学信息技术学院）；Institute for Infocomm Research, Agency for Science, Technology, and Research, Singapore（新加坡科技研究局信息通信研究院）
