EarlGAN: An enhanced actor-critic reinforcement learning agent-driven GAN for de novo drug design.
Huidong TangChen LiShuai JiangHuachong YuSayaka KameiYoshihiro YamanishiYasuhiko MorimotoPublished in: Pattern Recognit. Lett. (2023)
Keyphrases
- learning agent
- reinforcement learning
- drug design
- reinforcement learning algorithms
- temporal difference
- function approximation
- state space
- model free
- learning algorithm
- policy iteration
- drug discovery
- markov decision processes
- stochastic games
- average reward
- machine learning
- learning capabilities
- solving problems
- single agent
- multi agent
- learning process
- learning tasks
- optimal policy
- reward function
- supervised learning
- knowledge base
- sufficient conditions