Proximal Deterministic Policy Gradient.
Marco MaggipintoGian Antonio SustoPratik ChaudhariPublished in: IROS (2020)
Keyphrases
- policy gradient
- reinforcement learning
- function approximation
- parametric optimization
- actor critic
- model free reinforcement learning
- gradient method
- optimal control
- approximation methods
- variance reduction
- single agent
- reinforcement learning methods
- multi agent
- sample size
- reinforcement learning algorithms
- average reward