论文标题
使用适用于非平稳问题的优化器进行深入的机器人学习
Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems
论文作者
论文摘要
本文提出了一种用于深度学习的新优化器，名为D-Amsgrad。在实际数据中，不能将噪声和离群值从数据集中排除，以用于学习机器人技能。对于通过实时收集数据来学习的机器人来说，这个问题尤其引人注目，这无法手动分类。因此，已经开发了几种噪声优化器来解决此问题，其中一个名为Amsgrad（Amsgrad），它是Adam Optimizer的一种变体，具有其收敛性。但是，在实践中，它并不能提高机器人方案中的学习绩效。假设这个原因是大多数机器人学习问题都是非平稳的，但是Amsgrad假定学习过程中的最大动量。为了适应非平稳问题，提出了改进的版本，该版本慢慢衰减了第二动量。所提出的优化器具有与基准相同的能力达到全局最佳的功能，并且其性能优于机器人问题中的基准的功能。
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.
