FedMC: Federated Reinforcement Learning on the Edge with Meta-Critic Networks.
Derun ZouXusheng LiuLintan SunJian-Hui DuanRuichen LiYeting XuWenzhong LiSanglu LuPublished in: IPCCC (2022)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- actor critic
- reinforcement learning algorithms
- policy gradient
- edge information
- edge detection
- model free
- network analysis
- network structure
- computer networks
- heterogeneous networks
- edge detector
- markov decision processes
- distributed systems
- digital libraries
- social networks
- machine learning
- weighted graph
- transfer learning
- monte carlo
- network design
- supervised learning
- dynamic programming