Fair Resource Reusing for D2D Communication Based on Reinforcement Learning.
Fang-Chang KuoHwang-Cheng WangJia-Hao XuChih-Cheng TsengPublished in: SGIoT (2020)
Keyphrases
- reinforcement learning
- resource allocation
- function approximation
- communication systems
- communication overhead
- image registration
- state space
- communication channels
- reinforcement learning algorithms
- optimal policy
- communication cost
- neural network
- temporal difference learning
- resource sharing
- communication networks
- dynamic programming
- learning algorithm
- real time
- resource management
- data acquisition
- information exchange
- transfer learning
- temporal difference
- digital libraries
- communication patterns
- distributed control
- multi agent reinforcement learning