Federated Reinforcement Learning
@article{Zhuo2019FederatedRL, title={Federated Reinforcement Learning}, author={Hankui Zhuo and Wenfeng Feng and Q. Xu and Qiang Yang and Yufeng Lin}, journal={ArXiv}, year={2019}, volume={abs/1901.08277} }
In reinforcement learning, building policies of high-quality is challenging when the feature space of states is small and the training data is limited. Directly transferring data or knowledge from an agent to another agent will not work due to the privacy requirement of data and models. In this paper, we propose a novel reinforcement learning approach to considering the privacy requirement and building Q-network for each agent with the help of other agents, namely federated reinforcement… CONTINUE READING
Figures, Tables, and Topics from this paper
21 Citations
Federated Reinforcement Distillation with Proxy Experience Memory
- Computer Science, Mathematics
- ArXiv
- 2019
- 5
- PDF
Federated Reinforcement Learning for Fast Personalization
- Computer Science
- 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)
- 2019
- 8
Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits
- Computer Science
- ArXiv
- 2020
- PDF
Federated Reinforcement Learning for Training Control Policies on Multiple IoT Devices
- Computer Science, Medicine
- Sensors
- 2020
- 3
- PDF
Federated Reinforcement Learning for Controlling Multiple Rotary Inverted Pendulums in Edge Computing Environments
- Computer Science
- 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)
- 2020
- 1
Federated Reinforcement Learning for Automatic Control in SDN-based IoT Environments
- 2020 International Conference on Information and Communication Technology Convergence (ICTC)
- 2020
Performance Analysis and Optimization in Privacy-Preserving Federated Learning
- Computer Science
- ArXiv
- 2020
- 4
- PDF
Federated Multi-Agent Actor-Critic Learning for Age Sensitive Mobile Edge Computing
- Computer Science
- ArXiv
- 2020
- PDF
References
SHOWING 1-10 OF 18 REFERENCES
Transfer Learning for Reinforcement Learning Domains: A Survey
- Computer Science
- J. Mach. Learn. Res.
- 2009
- 1,194
- PDF
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
- Computer Science, Mathematics
- ICML
- 2018
- 257
- PDF
Federated Learning: Strategies for Improving Communication Efficiency
- Computer Science
- ArXiv
- 2016
- 1,026
- PDF
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
- Computer Science
- ICML
- 2017
- 196
- PDF
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
- Computer Science, Mathematics
- NIPS
- 2017
- 897
- PDF
Multiagent cooperation and competition with deep reinforcement learning
- Computer Science, Biology
- PloS one
- 2017
- 290
- PDF
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
- Computer Science, Mathematics
- ICML
- 2018
- 60
- PDF
Communication-Efficient Learning of Deep Networks from Decentralized Data
- Computer Science
- AISTATS
- 2017
- 1,648
- Highly Influential
- PDF