mlsanityData to 7 Oct 2026

Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular Generation

arXiv 2403.20109 ↗First posted 29 Mar 2024cs.LG cs.AI q-bio.BMcited by 7

Not on the map. Why?

Abstract (arXiv)

Optimizing techniques for discovering molecular structures with desired properties is crucial in artificial intelligence(AI)-based drug discovery. Combining deep generative models with reinforcement learning has emerged as an effective strategy for generating molecules with specific properties. Despite its potential, this approach is ineffective in exploring the vast chemical space and optimizing particular chemical properties. To overcome these limitations, we present Mol-AIR, a reinforcement learning-based framework using adaptive intrinsic rewards for effective goal-directed molecular generation. Mol-AIR leverages the strengths of both history-based and learning-based intrinsic rewards by exploiting random distillation network and counting-based strategies. In benchmark tests, Mol-AIR demonstrates superior performance over existing approaches in generating molecules with desired properties without any prior knowledge, including penalized LogP, QED, and celecoxib similarity. We believe that Mol-AIR represents a significant advancement in drug discovery, offering a more efficient path to discovering novel therapeutics.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 17 of its 55 references that are in the map. First posted on arXiv 29 Mar 2024.

Builds on

17 of 55 references.

References · 17

  1. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  2. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  3. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  4. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  5. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
  6. 2017Count-Based Exploration with Neural Density Modelscited by 255
  7. 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
  8. 2015Incentivizing Exploration In Reinforcement Learning With Deep Predictive Modelscited by 154
  9. 2018Multi-Objective De Novo Drug Design with Conditional Graph Generative Modelcited by 101
  10. 2022SELFIES and the future of molecular string representationscited by 76
  11. 2021Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generationcited by 68
  12. 2022Group SELFIES: A Robust Fragment-Based Molecular String Representationcited by 32
5 more
  1. 2022Computer-Aided Multi-Objective Optimization in Small Molecule Discoverycited by 31
  2. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  3. 2020Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learningcited by 16
  4. 2022LECO: Learnable Episodic Count for Task-Specific Intrinsic Rewardcited by 11
  5. 2023Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug Designcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 4.

7 papers.

  1. 2025A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimizationcited by 12
  2. 2026Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scalingcited by 4
  3. 2024Diversity-Aware Reinforcement Learning for de novo Drug Designcited by 3
  4. 2025Diverse Mini-Batch Selection in Reinforcement Learning for Efficient Chemical Exploration in de novo Drug Designcited by 1
  5. 2026Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generationcited by 0
  6. 2026C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMscited by 0
  7. 2026Fairness Definitions and Metrics in Deep Reinforcement Learning for Drug Discovery in Healthcare: A Rapid Evidence Reviewcited by 0