mlsanityData to 14 Oct 2026

Deep reinforcement learning for process design: Review and perspective

arXiv 2308.07822 ↗First posted 15 Aug 2023cs.LG cs.SY eess.SYcited by 10

Not on the map. Why?

Abstract (arXiv)

The transformation towards renewable energy and feedstock supply in the chemical industry requires new conceptual process design approaches. Recently, breakthroughs in artificial intelligence offer opportunities to accelerate this transition. Specifically, deep reinforcement learning, a subclass of machine learning, has shown the potential to solve complex decision-making problems and aid sustainable process design. We survey state-of-the-art research in reinforcement learning for process design through three major elements: (i) information representation, (ii) agent architecture, and (iii) environment and reward. Moreover, we discuss perspectives on underlying challenges and promising future works to unfold the full potential of reinforcement learning for process design in chemical engineering.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 16 of its 66 references that are in the map. First posted on arXiv 15 Aug 2023.

Builds on

16 of 66 references.

References · 16

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  3. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 267
  4. 2017Bridging the Gap Between Value and Policy Based Reinforcement Learningcited by 182
  5. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 179
  6. 2018Molecular Hypergraph Grammar with its Application to Molecular Optimizationcited by 56
  7. 2021Molecular Contrastive Learning with Chemical Element Knowledge Graphcited by 50
  8. 2022Toward automatic generation of control structures for process flow diagrams with large language modelscited by 12
  9. 2021Automated Synthesis of Steady-State Continuous Processes using Reinforcement Learningcited by 10
  10. 2022SFILES 2.0: An extended text-based flowsheet representationcited by 10
  11. 2022Learning from flowsheets: A generative transformer model for autocompletion of flowsheetscited by 10
  12. 2020Deep Reinforcement Learning for Process Synthesiscited by 6
4 more
  1. 2021Integrating process design and control using reinforcement learningcited by 6
  2. 2023Transfer learning for process design with reinforcement learningcited by 4
  3. 2022Synthesis of separation processes with reinforcement learningcited by 2
  4. 2022Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 3.

10 papers.

  1. 2024Generative AI and Process Systems Engineering: The Next Frontiercited by 9
  2. 2025Multi-agent systems for chemical engineering: A review and perspectivecited by 9
  3. 2024Graph-to-SFILES: Control structure prediction from process topologies using generative artificial intelligencecited by 5
  4. 2025Learning to control inexact Benders decomposition via reinforcement learningcited by 5
  5. 2025Molecular Machine Learning in Chemical Process Designcited by 5
  6. 2025Federated Learning from Molecules to Processes: A Perspectivecited by 3
  7. 2026Context is all you need: Towards autonomous model-based process design using agentic AI in flowsheet simulationscited by 2
  8. 2025Artificial Liver Classifier: A New Alternative to Conventional Machine Learning Modelscited by 0
  9. 2026Enhanced Reinforcement Learning-based Process Synthesis via Quantum Computingcited by 0
  10. 2026Augmenting PID Control with Deep Reinforcement Learning: A Hybrid Approach to the Industrial Benchmarkcited by 0