Revisiting Discrete Soft Actor-Critic.
Haibin ZhouZichuan LinJunyou LiDeheng YeQiang FuWei YangPublished in: CoRR (2022)
Keyphrases
- actor critic
- reinforcement learning
- lyapunov stability
- policy gradient
- approximate dynamic programming
- gradient method
- optimal control
- neuro fuzzy
- temporal difference
- function approximation
- policy iteration
- markov decision processes
- reinforcement learning algorithms
- variance reduction
- tracking error
- state space
- machine learning