论文标题
基于掌握率的课程学习
Mastering Rate based Curriculum Learning
论文作者
论文摘要
最近的自动课程学习算法，尤其是教师学生算法，依赖于学习进度的概念，这是一个良好的下一个任务是学习者在学习中取得最快进步或离题的任务。在这项工作中，我们首先提出了这些算法的更简单，改进的版本。然后，我们认为学习进度的概念本身具有几个缺点，从而导致学习者的样本效率较低。我们最终根据掌握率的概念提出了一种新的算法，该算法的表现显着胜过学习基于进度的算法。
Recent automatic curriculum learning algorithms, and in particular Teacher-Student algorithms, rely on the notion of learning progress, making the assumption that the good next tasks are the ones on which the learner is making the fastest progress or digress. In this work, we first propose a simpler and improved version of these algorithms. We then argue that the notion of learning progress itself has several shortcomings that lead to a low sample efficiency for the learner. We finally propose a new algorithm, based on the notion of mastering rate, that significantly outperforms learning progress-based algorithms.
