FedHQL: Federated Heterogeneous Q-Learning.
Flint Xiaofeng FanYining MaZhongxiang DaiCheston TanBryan Kian Hsiang LowRoger WattenhoferPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- cooperative
- distributed information systems
- function approximation
- multi agent
- learning algorithm
- state space
- digital libraries
- learning rate
- multi agent reinforcement learning
- stochastic approximation
- heterogeneous networks
- distributed data
- model free
- path planning
- action selection
- database
- artificial neural networks
- support vector
- real world