Rate Maximization with Reinforcement Learning for Time-Varying Energy Harvesting Broadcast Channels.
Heasung KimWonjae ShinHeecheol YangNayoung LeeJungwoo LeePublished in: GLOBECOM (2019)
Keyphrases
- reinforcement learning
- state space
- energy saving
- function approximation
- reinforcement learning algorithms
- markov decision processes
- energy consumption
- energy minimization
- multi agent
- multi channel
- learning process
- mimo systems
- temporal difference
- energy efficient
- model free
- low energy
- data broadcasting
- minimum energy
- machine learning
- energy efficiency
- learning algorithm
- power consumption
- data dissemination
- optimal policy
- wireless sensor networks
- bit errors
- objective function
- energy dissipation