Distributed Policy Gradient with Heterogeneous Computations for Federated Reinforcement Learning.
Ye ZhuXiaowen GongPublished in: CISS (2023)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- function approximation
- reinforcement learning algorithms
- multi agent
- policy search
- policy gradient methods
- gradient method
- optimal control
- model free reinforcement learning
- state space
- temporal difference
- single agent
- function approximators
- reinforcement learning methods
- markov decision processes
- optimal policy
- approximate dynamic programming
- learning algorithm
- approximation methods
- variance reduction
- neural network
- learning tasks
- state action
- supervised learning
- dynamic programming