arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.03772cs.LGcs.AIcs.ROstat.ML
收藏

通过在真实世界机器人上评估深度强化学习算法的再现性调查

A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots

Danish Technological Institute (DTI)(丹麦技术研究所(DTI));University of Southern Denmark (SDU)(南丹麦大学(SDU))

Nicolai A. Lynnerup, Laura Nolling, Rasmus Hasle, John Hallam

摘要:

随着强化学习(RL)在解决复杂任务方面取得更大成功,需要更加小心,以确保RL研究是可重复的,并且本文中的算法可以以最小的偏差轻松公平地进行比较。然而,由于算法的内在方差、环境的随机性和许多(可能未报告的)超参数,RL结果非常难以重现。在这项工作中,我们调查的许多问题,导致不可复制的研究,以及如何管理这些。我们进一步展示了如何利用严格和标准化的评估方法来简化不同算法的文档,评估和公平比较过程,其中我们强调了选择正确的测量指标和对结果进行适当统计的重要性,以便公正地报告结果。

英文摘要:

As reinforcement learning (RL) achieves more success in solving complex tasks, more care is needed to ensure that RL research is reproducible and that algorithms herein can be compared easily and fairly with minimal bias. RL results are, however, notoriously hard to reproduce due to the algorithms' intrinsic variance, the environments' stochasticity, and numerous (potentially unreported) hyper-parameters. In this work we investigate the many issues leading to irreproducible research and how to manage those. We further show how to utilise a rigorous and standardised evaluation approach for easing the process of documentation, evaluation and fair comparison of different algorithms, where we emphasise the importance of choosing the right measurement metrics and conducting proper statistics on the results, for unbiased reporting of the results.

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。

↑