Federated Deep Reinforcement Learning for Internet of Things With Decentralized Cooperative Edge Caching.
Xiaofei WangChenyang WangXiuhua LiVictor C. M. LeungTarik TalebPublished in: IEEE Internet Things J. (2020)
Keyphrases
- cooperative
- reinforcement learning
- multi agent
- multiagent reinforcement learning
- proxy cache
- multi agent reinforcement learning
- edge information
- function approximation
- edge detection
- key technologies
- mobile devices
- data access
- temporal difference
- edge map
- weighted graph
- game theory
- markov decision processes
- distributed systems
- learning algorithm
- stochastic games
- reinforcement learning algorithms
- fully distributed
- digital libraries
- optimal control
- optimal policy
- state space
- query processing
- ubiquitous computing
- edge detector
- evolutionary learning
- peer to peer