arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.06227cs.LGcs.MAstat.ML
收藏

教以学:具有内在状态的智能体的顺序教学

Teaching to Learn: Sequential Teaching of Agents with Inner States

University of Manchester(曼彻斯特大学)

Mustafa Mert Celikok, Pierre-Alexandre Murena, Samuel Kaski

摘要:

在顺序机器教学中,教师的目标是为顺序学习者提供最佳的输入序列,以引导他们走向最佳模型。在本文中,我们扩展这种设置从当前的静态一个数据集分析的学习者改变他们的学习算法或潜在的状态,以提高学习过程中,并推广到新的数据集。我们引入了一个多智能体的制定,学习者的内部状态可能会改变与教学互动,影响学习成绩在未来的任务。为了教这样的学习者,我们提出了一个最优控制的方法,考虑到教学后的学习者的未来表现。这为具有内部状态的学习者建模和元学习算法的机器教学提供了工具。此外,我们区分了操作教学,这可以通过有效地隐藏数据,也用于灌输,从更一般的教育,旨在帮助学习者成为更好的泛化和学习新的数据集在没有老师。

英文摘要:

In sequential machine teaching, a teacher's objective is to provide the optimal sequence of inputs to sequential learners in order to guide them towards the best model. In this paper we extend this setting from current static one-data-set analyses to learners which change their learning algorithm or latent state to improve during learning, and to generalize to new datasets. We introduce a multi-agent formulation in which learners' inner state may change with the teaching interaction, which affects the learning performance in future tasks. In order to teach such learners, we propose an optimal control approach that takes the future performance of the learner after teaching into account. This provides tools for modelling learners having inner states, and machine teaching of meta-learning algorithms. Furthermore, we distinguish manipulative teaching, which can be done by effectively hiding data and also used for indoctrination, from more general education which aims to help the learner become better at generalization and learning in new datasets in the absence of a teacher.

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。

↑