FedDdrl: Federated Double Deep Reinforcement Learning for Heterogeneous IoT with Adaptive Early Client Termination and Local Epoch Adjustment.
Yi Jie WongMau-Luen ThamBan-Hoe KwanYasunori OwadaPublished in: Sensors (2023)
Keyphrases
- reinforcement learning
- management system
- client server
- adaptive control
- data sources
- learning capabilities
- function approximation
- distributed systems
- machine learning
- model free
- big data
- cloud computing
- state space
- distributed data
- mobile devices
- learning algorithm
- heterogeneous data
- heterogeneous networks
- real world