Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular Generation.
Jinyeong ParkJaegyoon AhnJonghwan ChoiJibum KimPublished in: CoRR (2024)
Keyphrases
- goal directed
- reinforcement learning
- autonomous learning
- state space
- markov decision processes
- function approximation
- autonomous robots
- dna computing
- molecular structures
- three dimensional
- automated planning
- machine learning
- molecular dynamics
- drug discovery
- model free
- dynamic programming
- learning algorithm
- cell biology
- adaptive control
- learning capabilities
- control policy
- learning process
- multi agent
- neural network