Over-the-air Federated Policy Gradient.
Huiwen YangLingying HuangSubhrakanti DeyLing ShiPublished in: CoRR (2023)
Keyphrases
- policy gradient
- actor critic
- parametric optimization
- reinforcement learning
- optimal control
- gradient method
- function approximation
- reinforcement learning algorithms
- approximation methods
- model free reinforcement learning
- partially observable markov decision processes
- state action
- reinforcement learning methods
- average reward
- variance reduction
- cost function
- support vector
- machine learning
- neural network