arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.03807cs.LGcs.AIstat.ML
收藏

一种实用的强化学习干扰度量方法

Towards a practical measure of interference for reinforcement learning

University of Alberta(阿尔伯塔大学);DeepMind;Huawei Technologies(华为技术有限公司)

Vincent Liu, Adam White, Hengshuai Yao, Martha White

摘要:

灾难性干扰在许多基于网络的学习系统中是常见的,并且存在许多减轻它的建议。但是,在我们克服干扰之前,我们必须更好地理解它。在这项工作中,我们提供了一个定义的干扰控制强化学习。我们系统地评估我们的新措施,通过评估与学习性能的几个措施,包括稳定性,样本效率,在线和离线控制性能在各种学习架构的相关性。我们的新干扰度量允许我们对常用的深度学习架构提出新的科学问题。特别是,我们表明,目标网络频率是干扰的主要因素,最后一层的更新导致显着更高的干扰比更新内部的网络。这种新的措施可能是昂贵的计算,我们得出结论,一个有效的代理措施的动机和经验证明,它与我们的干扰定义。

英文摘要:

Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. But, before we overcome interference we must understand it better. In this work, we provide a definition of interference for control in reinforcement learning. We systematically evaluate our new measures, by assessing correlation with several measures of learning performance, including stability, sample efficiency, and online and offline control performance across a variety of learning architectures. Our new interference measure allows us to ask novel scientific questions about commonly used deep learning architectures. In particular we show that target network frequency is a dominating factor for interference, and that updates on the last layer result in significantly higher interference than updates internal to the network. This new measure can be expensive to compute; we conclude with motivation for an efficient proxy measure and empirically demonstrate it is correlated with our definition of interference.

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。

↑