Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient.
Yufei WangTianwei NiPublished in: CoRR (2020)
Keyphrases
- actor critic
- reinforcement learning
- approximate dynamic programming
- policy gradient
- optimal control
- temporal difference
- neuro fuzzy
- gradient method
- global optimization
- policy iteration
- reinforcement learning algorithms
- function approximation
- average reward
- markov decision processes
- dynamic programming
- multi agent systems
- model free
- dynamical systems
- learning algorithm
- machine learning
- control strategy
- optimal solution