Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy.
Yunhao TangMingzhang YinMingyuan ZhouPublished in: CoRR (2019)
Keyphrases
- policy gradient
- model free reinforcement learning
- reinforcement learning
- actor critic
- function approximation
- policy search
- gradient method
- optimal control
- policy gradient methods
- reinforcement learning algorithms
- approximation methods
- single agent
- variance reduction
- state space
- state action
- multi agent systems
- learning automata
- model free
- dynamic programming
- machine learning