Stein Variational Policy Gradient.
Yang LiuPrajit RamachandranQiang LiuJian PengPublished in: CoRR (2017)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- parametric optimization
- function approximation
- optimal control
- image segmentation
- gradient method
- reinforcement learning algorithms
- model free reinforcement learning
- average reward
- approximation methods
- variance reduction
- single agent
- neural network
- partially observable markov decision processes
- state action
- reinforcement learning methods
- control problems
- sufficient conditions
- multi agent