Deep Reinforcement Learning Optimal Transmission Policy for Communication Systems With Energy Harvesting and Adaptive MQAM.
Mingyu LiXiaohui ZhaoHui LiangFengye HuPublished in: IEEE Trans. Veh. Technol. (2019)
Keyphrases
- communication systems
- reinforcement learning
- optimal policy
- control policy
- information processing systems
- computer systems
- dynamic programming
- control policies
- policy search
- average reward
- multiple access
- blind equalization
- underwater acoustic
- power allocation
- energy consumption
- action selection
- optimal control
- function approximation
- multiple input multiple output
- state space
- actor critic
- channel estimation
- data transmission
- model free
- physical layer
- ultra wideband
- reinforcement learning algorithms
- policy gradient
- markov decision problems
- wireless channels
- average cost
- database
- communication technologies
- human computer interaction
- information systems
- learning algorithm
- machine learning