mlsanityData to 7 Oct 2026

Symmetry-Aware Actor-Critic for 3D Molecular Design

arXiv 2011.12747 ↗First posted 25 Nov 2020stat.ML cs.LG physics.chem-phcited by 55

Not on the map. Why?

Abstract (arXiv)

Automating molecular design using deep reinforcement learning (RL) has the potential to greatly accelerate the search for novel materials. Despite recent progress on leveraging graph representations to design molecules, such methods are fundamentally limited by the lack of three-dimensional (3D) information. In light of this, we propose a novel actor-critic architecture for 3D molecular design that can generate molecular structures unattainable with previous approaches. This is achieved by exploiting the symmetries of the design process through a rotationally covariant state-action representation based on a spherical harmonics series expansion. We demonstrate the benefits of our approach on several 3D molecular design tasks, where we find that building in such symmetries significantly improves generalization and the quality of generated molecules.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 18; 2023: 10; 2024: 5; 2025: 8; 2026: 2.

55 papers.

Sort:

By area:

  1. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  2. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  3. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  4. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 182
  5. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  6. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  7. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
  8. 2021Inverse design of 3d molecular structures with conditional generative neural networkscited by 93
  9. 2022ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphscited by 69
  10. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  11. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  12. 2021Particle Cloud Generation with Message Passing Generative Adversarial Networkscited by 45
38 more
  1. 2021Physics-Guided Deep Learning for Dynamical Systems: A Surveycited by 43
  2. 2023Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Spacecited by 40
  3. 20233D molecule generation by denoising voxel gridscited by 38
  4. 2021Learning to design drug-like molecules in three-dimensional space using deep generative modelscited by 37
  5. 20223DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Designcited by 33
  6. 2022SchNetPack 2.0: A neural network toolbox for atomistic machine learningcited by 29
  7. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generationcited by 27
  8. 2021Multi-Agent MDP Homomorphic Networkscited by 24
  9. 2022Maximum Class Separation as Inductive Bias in One Matrixcited by 21
  10. 2024Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structurescited by 20
  11. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  12. 2023De novo Drug Design using Reinforcement Learning with Multiple GPT Agentscited by 19
  13. 2023Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generationcited by 17
  14. 2022Equivariant Networks for Zero-Shot Coordinationcited by 16
  15. 2023Generation of 3D Molecules in Pockets via Language Modelcited by 13
  16. 2022Scalable Fragment-Based 3D Molecular Design with Reinforcement Learningcited by 11
  17. 2023Deep Learning Methods for Small Molecule Drug Discovery: A Surveycited by 10
  18. 2025Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objectscited by 10
  19. 2021Generating stable molecules using imitation and reinforcement learningcited by 9
  20. 2024Molecular relaxation by reverse diffusion with time step predictioncited by 9
  21. 2022Near-optimal Policy Identification in Active Reinforcement Learningcited by 7
  22. 2021Augmenting Molecular Deep Generative Models with Topological Data Analysis Representationscited by 6
  23. 2021Surrogate- and invariance-boosted contrastive learning for data-scarce applications in sciencecited by 6
  24. 2024Overcoming Order in Autoregressive Graph Generationcited by 3
  25. 2024Rectified Flow For Structure Based Drug Designcited by 3
  26. 2025Clifford Group Equivariant Diffusion Models for 3D Molecular Generationcited by 3
  27. 2022Atomistic structure search using local surrogate modecited by 2
  28. 2023Molecular Conformation Generation via Shifting Scorescited by 2
  29. 2025NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generationcited by 2
  30. 2021An In-depth Summary of Recent Artificial Intelligence Applications in Drug Designcited by 1
  31. 2022Reinforcement Learning for Personalized Drug Discovery and Design for Complex Diseases: A Systems Pharmacology Perspectivecited by 1
  32. 20223D pride without 2D prejudice: Bias-controlled multi-level generative models for structure-based ligand designcited by 1
  33. 2022Automating Rigid Origami Designcited by 1
  34. 2024FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproductioncited by 1
  35. 2025Symmetries-enhanced Multi-Agent Reinforcement Learningcited by 1
  36. 2025Learning Abstract World Models with a Group-Structured Latent Spacecited by 1
  37. 2025Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existencecited by 1
  38. 2022Cluster Generation via Deep Energy-Based Modelcited by 0

50 most cited of 55 All 55 (JSON)