基于掌握率的课程学习
Mastering Rate based Curriculum Learning
摘要：
最近的自动课程学习算法，特别是教师-学生算法，依赖于学习进度的概念，假设好的下一个任务是学习者进展最快或偏离的任务。在这项工作中，我们首先提出了一个更简单和改进的版本，这些算法。然后，我们认为，学习进展的概念本身有几个缺点，导致低样本效率的学习者。最后，我们提出了一个新的算法，掌握率的概念的基础上，显着优于学习进度为基础的算法。
英文摘要：
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.
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。
