Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES.
Esben Jannik BjerrumChristian MargreitterThomas BlaschkeSimona KolarovaRaquel Lopez-Rios de CastroPublished in: J. Comput. Aided Mol. Des. (2023)
Keyphrases
- reinforcement learning
- global optimization
- three dimensional
- optimization problems
- wide variety
- machine learning
- supervised learning
- optimization methods
- function approximation
- optimization process
- faster convergence
- mass spectrometry
- multi agent systems
- learning process
- least squares
- multi agent
- markov decision processes
- model free
- robotic control