Decentralized Deep Reinforcement Learning for Delay-Power Tradeoff in Vehicular Communications.
Xianfu ChenCelimuge WuHonggang ZhangYan ZhangMehdi BennisHeli VuojalaPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- multi agent
- power consumption
- communication systems
- function approximation
- optimal control
- markov decision processes
- state space
- machine learning
- peer to peer
- trade off
- distributed systems
- communication channels
- optimal policy
- communication networks
- cooperative
- neural network
- power dissipation
- decentralized control
- learning process
- computational complexity
- social networks
- model free
- heterogeneous networks
- deep learning
- wireless link