MacGAN: A Moment-Actor-Critic Reinforcement Learning-Based Generative Adversarial Network for Molecular Generation.
Huidong TangChen LiShuai JiangHuachong YuSayaka KameiYoshihiro YamanishiYasuhiko MorimotoPublished in: APWeb-WAIM (1) (2023)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- function approximation
- optimal control
- reinforcement learning algorithms
- approximate dynamic programming
- policy gradient
- neuro fuzzy
- policy iteration
- gradient method
- natural actor critic
- model free
- markov decision processes
- neural network
- reinforcement learning methods
- supervised learning
- state space
- learning algorithm
- wavelet neural network
- optimal policy
- rl algorithms
- linear programming