Research on Deployment of Communication Node Vehicles Based on Deep Reinforcement Learning.
Ruopeng YangXiaofei ZouZongzhe NieChangsheng YinPublished in: CCIS (2018)
Keyphrases
- reinforcement learning
- message transmission
- communication systems
- real time
- learning algorithm
- graph structure
- function approximation
- directed graph
- multi agent
- markov decision processes
- temporal difference
- state space
- model free
- optimal path
- communication overhead
- moving vehicles
- network nodes
- communication networks
- communication cost
- xml documents
- travel time
- road traffic