摘要
由Robotics&Machine Learning Daily News的新闻记者兼工作人员新闻编辑-根据NewsRx记者在华盛顿特区的新闻报道原创G，由Inve Ntors Heesche,Kai(Munchen,DE);Hein,Daniel(Munchen,DE);Schoner,Holger(M Unchen,DE);2024年5月16日在线提供。本专利申请没有受让人。记者从发明人提供的背景信息中获得了以下引述：“机器学习方法正越来越多地用于复杂技术系统的控制，例如燃气轮机，风力涡轮机，内燃机，机器人，制造装置或电网。使用这种学习方法，控制装置的机器学习模型可以被建立，根据培训数据，从技术系统当前运行标志ALS出发，为了确定用于控制技术系统的那些控制动作，这些控制动作具体地导致技术系统的期望或优化行为，并因此优化其性能。这种用于控制技术系统的机械学习模型通常也被称为策略或控制模型。可以培训这样的政策。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – According to news reporting originatin g from Washington, D.C., by NewsRx journalists, a patent application by the inve ntors Heesche, Kai (Munchen, DE); Hein, Daniel (Munchen, DE); Schoner, Holger (M unchen, DE); Sterzing, Volkmar (Neubiberg, DE); Udluft, Steffen (Eichenau, DE); Weber, Marc Christian (Munchen, DE), filed on December 28, 2021, was made availa ble online on May 16, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “Machine learning methods are increasingly being used in the c ontrol of complex technical systems, such as for example gas turbines, wind turb ines, combustion engines, robots, manufacturing installations or power grids. Us ing such learning methods, a machine learning model of a control device may be t rained, on the basis of training data and proceeding from current operating sign als of a technical system, to determine those control actions for controlling th e technical system that specifically bring about a desired or optimized behavior of the technical system and thus optimize the performance thereof. Such a machi ne learning model for controlling a technical system is often also referred to a s a policy or control model. A large number of known training methods, such as f or example reinforcement learning methods, are available to train such a policy.
NETL
NSTL