Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES.
Esben Jannik BjerrumChristian MargreitterThomas BlaschkeRaquel Lopez-Rios de CastroPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimization problems
- model free
- optimization process
- global optimization
- function approximation
- optimization algorithm
- robotic control
- human genome
- optimization method
- supervised learning
- least squares
- state space
- constrained optimization
- three dimensional
- reinforcement learning algorithms
- multiobjective optimization
- drug discovery
- learning algorithm
- faster convergence
- machine learning