Using Reinforcement Learning in a Game-like Setup for Automated Process Synthesis without Prior Process Knowledge

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

5 Scopus citations

Abstract

The present work uses reinforcement learning (RL) for automated flowsheet synthesis. The task of synthesizing a flowsheet is reformulated into a two-player game, in which an agent learns by self-play without prior knowledge. The hierarchical RL scheme developed in our previous work (Göttl et al., 2021b) is coupled with an improved training process. The training process is analyzed in detail using the synthesis of ethyl tert-butyl ether (ETBE) as an example. This analysis uncovers how the agent's evolution is driven by the two-player setup.

Original languageEnglish
Title of host publicationComputer Aided Chemical Engineering
PublisherElsevier B.V.
Pages1555-1560
Number of pages6
DOIs
StatePublished - Jan 2022

Publication series

NameComputer Aided Chemical Engineering
Volume49
ISSN (Print)1570-7946

Keywords

  • Artificial Intelligence
  • Automated Process Synthesis
  • Flowsheet Synthesis
  • Machine Learning
  • Reinforcement Learning

Fingerprint

Dive into the research topics of 'Using Reinforcement Learning in a Game-like Setup for Automated Process Synthesis without Prior Process Knowledge'. Together they form a unique fingerprint.

Cite this