Algorithmic and Human Teaching of Sequential Decision Tasks
Algorithmic and Human Teaching of Sequential Decision Tasks
复制标题
顺序决策任务的算法和人类教学
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
M. Lopes
中科院分区：
文献类型：
--
作者：
M. Cakmak;M. Lopes
一个有帮助的老师可以显著提高学习代理的学习率。教学算法已经在算法教学领域得到了正式的研究。这些对老师如何在教授新概念时选择最有信息量的例子提供了重要的见解。然而，到目前为止，该领域只专注于分类任务。本文介绍了一种新的序列决策任务最优教学方法。我们提出了一种算法，可以自动选择最具信息量的演示集，并在几个导航任务中对其进行评估。接下来，我们将探索使用该算法为人类在教授顺序决策任务时如何选择示例生成指令的想法。我们提出了一个用户研究，证明了这些指令的效用。
A helpful teacher can significantly improve the learning rate of a learning agent. Teaching algorithms have been formally studied within the field of Algorithmic Teaching. These give important insights into how a teacher can select the most informative examples while teachinga new concept. However the field has so far focused purely on classification tasks. In this paper we introducea novel method for optimally teaching sequential decision tasks. We present an algorithm that automatically selects the set of most informative demonstrations andevaluate it on several navigation tasks. Next, we explore the idea of using this algorithm to produce instructions for humans on how to choose examples when teaching sequential decision tasks. We present a user study that demonstrates the utility of such instructions.