mlsanityData to 14 Oct 2026

Deep Reinforcement Learning for Inverse Inorganic Materials Design

arXiv 2210.11931 ↗First posted 21 Oct 2022cond-mat.mtrl-sci cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

A major obstacle to the realization of novel inorganic materials with desirable properties is the inability to perform efficient optimization across both materials properties and synthesis of those materials. In this work, we propose a reinforcement learning (RL) approach to inverse inorganic materials design, which can identify promising compounds with specified properties and synthesizability constraints. Our model learns chemical guidelines such as charge and electronegativity neutrality while maintaining chemical diversity and uniqueness. We demonstrate a multi-objective RL approach, which can generate novel compounds with targeted materials properties including formation energy and bulk/shear modulus alongside a lower sintering temperature synthesis objectives. Using this approach, the model can predict promising compounds of interest, while suggesting an optimized chemical design space for inorganic materials discovery.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 27 of its 119 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

27 of 119 references.

References · 27

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2015Continuous control with deep reinforcement learningcited by 3,407
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  6. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  7. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  8. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  9. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  10. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  11. 2017Deep Reinforcement Learning: An Overviewcited by 333
  12. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 267
15 more
  1. 2018Optimization of Molecules via Deep Reinforcement Learningcited by 200
  2. 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
  3. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 157
  4. 2015Inferring Algorithmic Patterns with Stack-Augmented Recurrent Netscited by 76
  5. 2018Molecular generative model based on conditional variational autoencoder for de novo molecular designcited by 73
  6. 2018Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselinescited by 68
  7. 2019Predicting materials properties without crystal structure: Deep representation learning from stoichiometrycited by 62
  8. 2019Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materialscited by 46
  9. 2022Crystal structure prediction with machine learning-based element substitutioncited by 17
  10. 2022Fast Bayesian Optimization of Needle-in-a-Haystack Problems using Zooming Memory-Based Initialization (ZoMBI)cited by 14
  11. 2020Computational discovery of new 2D materials using deep learning generative modelscited by 10
  12. 2020Constrained Model-Free Reinforcement Learning for Process Optimizationcited by 9
  13. 2020CRYSPNet: Crystal Structure Predictions via Neural Networkcited by 7
  14. 2021Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalinationcited by 6
  15. 2016Learning Operations on a Stack with Neural Turing Machinescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 8; 2026: 8.

19 papers.

Sort:

By area:

  1. 2025Artificial Intelligence and Generative Models for Materials Discovery -- A Reviewcited by 8
  2. 2024Cross-Modal Learning for Chemistry Property Prediction: Large Language Models Meet Graph Machine Learningcited by 4
  3. 2025Generative Models for Crystalline Materialscited by 4
  4. 2026Towards Agentic Intelligence for Materials Sciencecited by 3
  5. 2023VAE for Modified 1-Hot Generative Materials Modeling, A Step Towards Inverse Material Designcited by 2
  6. 2025DiffSyn: A Generative Diffusion Approach to Materials Synthesis Planningcited by 2
  7. 2026MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Sciencecited by 1
  8. 2024Adaptable Method for Crystal Design across Diverse Constraints and Objectives with Pretrained Property Predictorscited by 0
  9. 2025MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structurescited by 0
  10. 2025AIMatDesign: Knowledge-Augmented Reinforcement Learning for Inverse Materials Design under Data Scarcitycited by 0
  11. 2025Unified machine-learning framework for property prediction and time-evolution simulation of strained alloy microstructurecited by 0
  12. 2025Extended Factorization Machine Annealing for Rapid Discovery of Transparent Conducting Materialscited by 0
7 more
  1. 2025Philosophy-informed Machine Learningcited by 0
  2. 2026Neural surrogates for crystal growth dynamics with variable supersaturation: explicit vs. implicit conditioningcited by 0
  3. 2026A Padding Method for Enhanced Encoding of Inorganic Structures with Varying Chemical Compositionscited by 0
  4. 2026Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Designcited by 0
  5. 2026Let CSP Be Your ANCHOR: Adaptive Crystal Search over Frozen Structure Priorscited by 0
  6. 2026Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure Predictioncited by 0
  7. 2026Reinforcement Learning on the Discrete Composition Channel of a Crystal Generator: Validated Gains and Reward Hackingcited by 0