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 2007.15890cs.LGcs.ROstat.ML
收藏

面向深度机器人学习的非平稳优化算法

Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems

Nara Institute of Science and Technology(奈良先端科学技术大学院大学)

Taisuke Kobayashi

摘要:

本文提出了一种新的深度学习优化器,名为d-AmsGrad。在真实世界的数据中,噪声和离群值不能从用于学习机器人技能的数据集中排除。对于那些通过实时的收集数据来学习的机器人来说,这个问题尤其突出,而这些数据是无法手动分类的。因此,已经开发了几种噪声鲁棒优化器来解决这个问题,其中一种名为AmsGrad的优化器是Adam优化器的变体,它证明了它的收敛性。然而,在实践中,它并没有提高机器人场景中的学习性能。这个原因被假设为大多数机器人学习问题是非平稳的,但是AmsGrad假设学习期间的最大二阶动量是平稳给定的。为了适应非定常问题,提出了一种使最大二阶动量缓慢衰减的改进方案。所提出的优化器具有相同的能力,达到全局最优的基线,其性能优于基线的机器人问题。

英文摘要:

This paper proposes a new optimizer for deep learning, named d-AmsGrad. In the real-world data, noise and outliers cannot be excluded from dataset to be used for learning robot skills. This problem is especially striking for robots that learn by collecting data in real time, which cannot be sorted manually. Several noise-robust optimizers have therefore been developed to resolve this problem, and one of them, named AmsGrad, which is a variant of Adam optimizer, has a proof of its convergence. However, in practice, it does not improve learning performance in robotics scenarios. This reason is hypothesized that most of robot learning problems are non-stationary, but AmsGrad assumes the maximum second momentum during learning to be stationarily given. In order to adapt to the non-stationary problems, an improved version, which slowly decays the maximum second momentum, is proposed. The proposed optimizer has the same capability of reaching the global optimum as baselines, and its performance outperformed that of the baselines in robotics problems.

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。

↑