Federated Reinforcement Learning

By Hankui Zhuo, Wenfeng Feng, Qian Xu, Qiang Yang, Yufeng Lin. 2019

84 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xiang Li
2. Azzam Mourad
3. Na Li
4. Wenhao Yang
5. Sawsan AbdulRahman
6. Dusist Niyato
7. Steven H. Low
8. Zhihua Zhang

Citations in the corpus

• Communication Efficient Decentralized Training with Multiple Local Updates (2019, background): “Federated Learning (FL), which has a central parameter server, enables massive edge computing devices to jointly learn a centralized model while keeping all local data localized [13, 34, 26, 12, 18, 30, 57].”
• On the Convergence of FedAvg on Non-IID Data (2019, background): “As a special case of distributed machine learning approaches, Federated Learning (FL) enables end devices to collaboratively learn a shared model while keeping all the training data on device [9, 24, 16, 8, 21, 42].”
• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2019, background): “Adjusting FL to train separate and different kinds of models still remains as a challenge [242], [243].”
• Federated Hierarchical Hybrid Networks for Clickbait Detection (2019, background): “Zhuo et al. propose federated reinforcement learning, which considers the privacy requirement and builds Q-network for each agent with the help of other agents (Zhuo et al., 2019).”
• Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges (2021, background): “…DRL, multi-agent RL, and robust RL mentioned above, a wide range of branches in the RL field, such as transfer RL [99], meta RL [197], federated RL [198], inverse RL [37], integral RL [13], Bayesian RL [199], hierarchical RL [200], interpretable RL [201], etc., can improve the learning efficiency…”
• FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction (2022, background): “Federated learning (FL) is an emerging distributed machine learning paradigm that leverages decentralized data from multiple clients to jointly train a shared global model under the coordination of a central server, without sharing the individuals’ raw data [4, 8, 19, 20, 31].”
• A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond (2021, methodology): “[76] proposed an FL method based on reinforce-”
• Federated Learning for Healthcare Informatics (2019, background): “ormulate a trainingaccelerationproblemunderbothcommunicationandlearningresource budget. Reinforcement learning and round robin learning are widely used to managethecommunicationandcomputationresources[4,94,101,38]. FederatedLearningforHealthcareInformatics 9 2.2.4Peer-to-PeerLearning In federated le”