Scholarlink

This paper presents a novel Reinforcement Learning framework for facility layout planning. The framework leverages reinforcement learning to create and improve layout configurations through an intuitive setup process. The proposed methodology includes a graphical user interface application that allows practitioners to easily configure their problem setting for facility layout optimization tasks. A proof of concept demonstrates the effectiveness of the framework, showcasing the successful optimization of an exemplary layout configuration. The framework bridges the gap between advanced machine learning techniques and practical application in layout planning. We demonstrate that the framework presented is able to train RL-agents, which achieve close to optimal solutions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Reinforcement Learning Based Framework to the Facility Layout Problem

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Lukas Rissmann,
  • Sebastian Meissner

摘要

This paper presents a novel Reinforcement Learning framework for facility layout planning. The framework leverages reinforcement learning to create and improve layout configurations through an intuitive setup process. The proposed methodology includes a graphical user interface application that allows practitioners to easily configure their problem setting for facility layout optimization tasks. A proof of concept demonstrates the effectiveness of the framework, showcasing the successful optimization of an exemplary layout configuration. The framework bridges the gap between advanced machine learning techniques and practical application in layout planning. We demonstrate that the framework presented is able to train RL-agents, which achieve close to optimal solutions.