arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.09324cs.LGcs.AIstat.ML
收藏

Q-学习中强化教学的样本复杂度

The Sample Complexity of Teaching-by-Reinforcement on Q-Learning

UW Madison(威斯康星大学麦迪逊分校);MPI-SWS(马克斯·普朗克软件系统研究所)

Xuezhou Zhang, Shubham Kumar Bharti, Yuzhe Ma, Adish Singla, Xiaojin Zhu

摘要:

我们研究了教学的样本复杂性,在文献中被称为“教学维度”(TDim),为教学的强化范式,教师通过奖励指导学生。这与机器人应用所激发的演示教学范式不同,在这种范式中,教师通过提供状态/动作轨迹的演示来教学。强化教学范式适用于更广泛的现实世界的设置,演示是不方便的,但还没有被系统地研究。在本文中,我们专注于一个特定的家庭的强化学习算法,Q-学习,并在不同的教师与不同的控制权的环境下的TDim的特点,并提出匹配的最佳教学算法。我们的TDim结果提供了强化学习所需的最小样本数量,我们讨论了它们与标准PAC风格RL样本复杂性和演示教学样本复杂性结果的联系。我们的教学算法有可能加快RL代理学习的应用程序中,有一个有用的老师。

英文摘要:

We study the sample complexity of teaching, termed as "teaching dimension" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the student through rewards. This is distinct from the teaching-by-demonstration paradigm motivated by robotics applications, where the teacher teaches by providing demonstrations of state/action trajectories. The teaching-by-reinforcement paradigm applies to a wider range of real-world settings where a demonstration is inconvenient, but has not been studied systematically. In this paper, we focus on a specific family of reinforcement learning algorithms, Q-learning, and characterize the TDim under different teachers with varying control power over the environment, and present matching optimal teaching algorithms. Our TDim results provide the minimum number of samples needed for reinforcement learning, and we discuss their connections to standard PAC-style RL sample complexity and teaching-by-demonstration sample complexity results. Our teaching algorithms have the potential to speed up RL agent learning in applications where a helpful teacher is available.

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。

↑