arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2007.00425cs.LGstat.ML
收藏

交互限制的逆强化学习

Interaction-limited Inverse Reinforcement Learning

Idiap Research Institute(伊迪亚普研究所);EPFL(洛桑联邦理工学院)

Martin Troussard, Emmanuel Pignat, Parameswaran Kamalaruban, Sylvain Calinon, Volkan Cevher

摘要:

本文提出了一种逆强化学习(IRL)框架,当学习者-教师\textit{interaction}在训练过程中是\textit{limited}时,该框架可以加速学习。我们的设置是由现实的情况下,一个有用的老师是不可用的,或者当老师无法访问学生的学习动态的动机。我们提出了两种不同的培训策略:课程逆强化学习(CIRL)涵盖教师的角度,和自定进度逆强化学习(SPIRL)侧重于学习者的角度。使用模拟实验和实验与一个真正的机器人学习的任务,从一个人的演示,我们表明,我们的训练策略可以允许更快的训练比随机教师CIRL比一批学习者SPIRL。

英文摘要:

This paper proposes an inverse reinforcement learning (IRL) framework to accelerate learning when the learner-teacher \textit{interaction} is \textit{limited} during training. Our setting is motivated by the realistic scenarios where a helpful teacher is not available or when the teacher cannot access the learning dynamics of the student. We present two different training strategies: Curriculum Inverse Reinforcement Learning (CIRL) covering the teacher's perspective, and Self-Paced Inverse Reinforcement Learning (SPIRL) focusing on the learner's perspective. Using experiments in simulations and experiments with a real robot learning a task from a human demonstrator, we show that our training strategies can allow a faster training than a random teacher for CIRL and than a batch learner for SPIRL.

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。

↑