mlsanityData to 7 Oct 2026

Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

arXiv 2002.07717 ↗First posted 18 Feb 2020stat.ML cs.LGcited by 51

Not on the map. Why?

Abstract (arXiv)

Automating molecular design using deep reinforcement learning (RL) holds the promise of accelerating the discovery of new chemical compounds. Existing approaches work with molecular graphs and thus ignore the location of atoms in space, which restricts them to 1) generating single organic molecules and 2) heuristic reward functions. To address this, we present a novel RL formulation for molecular design in Cartesian coordinates, thereby extending the class of molecules that can be built. Our reward function is directly based on fundamental physical properties such as the energy, which we approximate via fast quantum-chemical methods. To enable progress towards de-novo molecular design, we introduce MolGym, an RL environment comprising several challenging molecular design tasks along with baselines. In our experiments, we show that our agent can efficiently learn to solve these tasks from scratch by working in a translation and rotation invariant state-action space.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 13; 2023: 13; 2024: 3; 2025: 8; 2026: 3.

51 papers.

Sort:

By area:

  1. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  2. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  3. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
  4. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  5. 2021Inverse design of 3d molecular structures with conditional generative neural networkscited by 93
  6. 2022ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphscited by 69
  7. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  8. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  9. 2021Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spacescited by 45
  10. 20223DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Designcited by 33
  11. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  12. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generationcited by 27
38 more
  1. 2022Graph Neural Networks for Moleculescited by 21
  2. 2021Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learningcited by 19
  3. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  4. 2023De novo Drug Design using Reinforcement Learning with Multiple GPT Agentscited by 19
  5. 2023Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generationcited by 17
  6. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generationcited by 17
  7. 2023MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modelingcited by 14
  8. 2025Equivariant Neural Diffusion for Molecule Generationcited by 13
  9. 2023Reinforcement Learning for Generative AI: A Surveycited by 11
  10. 2023DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraintscited by 10
  11. 2023An Equivariant Generative Framework for Molecular Graph-Structure Co-Designcited by 10
  12. 2021Generating stable molecules using imitation and reinforcement learningcited by 9
  13. 2024Molecular relaxation by reverse diffusion with time step predictioncited by 9
  14. 2023ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generationcited by 8
  15. 2021Structure-aware generation of drug-like moleculescited by 7
  16. 2022Near-optimal Policy Identification in Active Reinforcement Learningcited by 7
  17. 2023PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embeddingcited by 7
  18. 2021Augmenting Molecular Deep Generative Models with Topological Data Analysis Representationscited by 6
  19. 2025BARNN: A Bayesian Autoregressive and Recurrent Neural Networkcited by 5
  20. 2023StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapescited by 4
  21. 2023Automated patent extraction powers generative modeling in focused chemical spacescited by 4
  22. 20253DMolFormer: A Dual-channel Framework for Structure-based Drug Discoverycited by 4
  23. 2025De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learningcited by 4
  24. 20233D Molecular Generation via Virtual Dynamicscited by 3
  25. 2024Overcoming Order in Autoregressive Graph Generationcited by 3
  26. 2021Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspectivecited by 2
  27. 2025NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generationcited by 2
  28. 2021An In-depth Summary of Recent Artificial Intelligence Applications in Drug Designcited by 1
  29. 2022Reinforcement Learning for Personalized Drug Discovery and Design for Complex Diseases: A Systems Pharmacology Perspectivecited by 1
  30. 2022Automating Rigid Origami Designcited by 1
  31. 2024Tokenizing 3D Molecule Structure with Quantized Spherical Coordinatescited by 1
  32. 2025Atomic Proximal Policy Optimization for Electric Robo-Taxi Dispatch and Charger Allocationcited by 1
  33. 2025Reinforcement Learning for Chemical Ordering in Alloy Nanoparticlescited by 1
  34. 2022Bayesian Sequential Stacking Algorithm for Concurrently Designing Molecules and Synthetic Reaction Networkscited by 0
  35. 2022Processing Network Controls via Deep Reinforcement Learningcited by 0
  36. 2022Cluster Generation via Deep Energy-Based Modelcited by 0
  37. 2026AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learningcited by 0
  38. 2026PGFS++: Molecular Property Improvement under Synthesis and Diversity Constraintscited by 0

50 most cited of 51 All 51 (JSON)