arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.09480cs.AIcs.LGcs.SYeess.SY
收藏

由工业控制问题启发的基准环境

A Benchmark Environment Motivated by Industrial Control Problems

Siemens AG, Corporate Technology(西门子股份公司企业技术部)

Daniel Hein, Stefan Depeweg, Michel Tokic, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing

AI总结:

本文提出一个结合工业控制问题的基准环境,旨在解决真实工业环境与现有人工基准之间缺乏联系的问题,通过详细描述基准动态并识别典型实验设置来促进强化学习方法的改进。

摘要:

在强化学习(RL)研究领域,频繁出现新的有前景的方法被开发并引入RL社区。然而,尽管许多研究人员渴望将他们的方法应用于现实世界的问题,但在真实工业环境中实施这些方法往往是一个令人沮丧和繁琐的过程。通常,学术研究小组只能有限地访问真实工业数据和应用。因此,新方法通常通过使用人工软件基准来开发、评估和比较。一方面,这些基准旨在提供可解释的RL训练场景和对所用方法学习过程的深入见解。另一方面,它们通常与现实工业应用缺乏相似性。为此,我们利用行业经验设计了一个基准,以弥合自由可用、文档齐全且有动机的人工基准与真实工业问题属性之间的差距。所得到的工业基准(IB)已通过在GitHub上发布其Java和Python代码,包括一个OpenAI Gym包装器,向RL社区公开。在本文中,我们详细阐述了IB的动力学,并识别了能够捕捉现实世界工业控制问题中常见情况的典型实验设置。

英文摘要:

In the research area of reinforcement learning (RL), frequently novel and promising methods are developed and introduced to the RL community. However, although many researchers are keen to apply their methods on real-world problems, implementing such methods in real industry environments often is a frustrating and tedious process. Generally, academic research groups have only limited access to real industrial data and applications. For this reason, new methods are usually developed, evaluated and compared by using artificial software benchmarks. On one hand, these benchmarks are designed to provide interpretable RL training scenarios and detailed insight into the learning process of the method on hand. On the other hand, they usually do not share much similarity with industrial real-world applications. For this reason we used our industry experience to design a benchmark which bridges the gap between freely available, documented, and motivated artificial benchmarks and properties of real industrial problems. The resulting industrial benchmark (IB) has been made publicly available to the RL community by publishing its Java and Python code, including an OpenAI Gym wrapper, on Github. In this paper we motivate and describe in detail the IB's dynamics and identify prototypic experimental settings that capture common situations in real-world industry control 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。

↑