Decentralized Deep Reinforcement Learning for Delay-Power Tradeoff in Vehicular Communications.
Xianfu ChenCelimuge WuHonggang ZhangYan ZhangMehdi BennisHeli VuojalaPublished in: ICC (2019)
Keyphrases
- reinforcement learning
- power consumption
- cooperative
- multi agent
- communication systems
- function approximation
- reinforcement learning algorithms
- distributed systems
- communication networks
- peer to peer
- temporal difference
- state space
- trade off
- continuous state
- model free
- machine learning
- deep learning
- decentralized control
- optimal control
- markov decision processes
- computational complexity
- learning algorithm