Averaged Soft Actor-Critic for Deep Reinforcement Learning.
Feng DingGuanfeng MaZhikui ChenJing GaoPeng LiPublished in: Complex. (2021)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- reinforcement learning algorithms
- approximate dynamic programming
- policy gradient
- optimal control
- neuro fuzzy
- gradient method
- function approximation
- state space
- policy iteration
- model free
- learning algorithm
- temporal difference learning
- machine learning
- policy gradient methods
- step size
- reward function
- evaluation function
- control problems
- markov decision processes
- average reward
- linear programming
- multi agent
- single agent
- mathematical model
- rl algorithms
- dynamic programming