DSAC-T: Distributional Soft Actor-Critic with Three Refinements.
Jingliang DuanWenxuan WangLiming XiaoJiaxin GaoShengbo Eben LiPublished in: CoRR (2023)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- approximate dynamic programming
- optimal control
- policy gradient
- neuro fuzzy
- gradient method
- reinforcement learning algorithms
- function approximation
- policy iteration
- dynamic programming
- learning algorithm
- average reward
- model free
- step size
- evaluation function
- markov decision processes
- temporal difference learning
- dynamical systems
- state space
- optimal solution