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

arXiv: https://arxiv.org/abs/2403.20109 · HTML: https://mlsanity.com/paper/2403.20109/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 17 of its 55 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 17 of 17)

- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Count-Based Exploration with Neural Density Models](https://mlsanity.com/paper/1703.01310/) (2017)
- [Deep Reinforcement Learning for De-Novo Drug Design](https://mlsanity.com/paper/1711.10907/) (2017)
- [Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models](https://mlsanity.com/paper/1507.00814/) (2015)
- [Multi-Objective De Novo Drug Design with Conditional Graph Generative Model](https://mlsanity.com/paper/1801.07299/) (2018)
- [SELFIES and the future of molecular string representations](https://mlsanity.com/paper/2204.00056/) (2022)
- [Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation](https://mlsanity.com/paper/2110.01219/) (2021)
- [Group SELFIES: A Robust Fragment-Based Molecular String Representation](https://mlsanity.com/paper/2211.13322/) (2022)
- [Computer-Aided Multi-Objective Optimization in Small Molecule Discovery](https://mlsanity.com/paper/2210.07209/) (2022)
- [Artificial Intelligence in Drug Discovery: Applications and Techniques](https://mlsanity.com/paper/2106.05386/) (2021)
- [Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning](https://mlsanity.com/paper/2012.11293/) (2020)
- [LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward](https://mlsanity.com/paper/2210.05409/) (2022)
- [Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug Design](https://mlsanity.com/paper/2401.06771/) (2023)

## Built on by (most cited first, 7 of 7)

- [A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization](https://mlsanity.com/paper/2505.16094/) (2025)
- [Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling](https://mlsanity.com/paper/2601.21669/) (2026)
- [Diversity-Aware Reinforcement Learning for de novo Drug Design](https://mlsanity.com/paper/2410.10431/) (2024)
- [Diverse Mini-Batch Selection in Reinforcement Learning for Efficient Chemical Exploration in de novo Drug Design](https://mlsanity.com/paper/2506.21158/) (2025)
- [Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generation](https://mlsanity.com/paper/2601.08963/) (2026)
- [C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs](https://mlsanity.com/paper/2604.23061/) (2026)
- [Fairness Definitions and Metrics in Deep Reinforcement Learning for Drug Discovery in Healthcare: A Rapid Evidence Review](https://mlsanity.com/paper/2606.02902/) (2026)

## 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.