Power Allocation in HetNets with Hybrid Energy Supply Using Actor-Critic Reinforcement Learning.
Yifei WeiZhiqiang ZhangF. Richard YuZhu HanPublished in: GLOBECOM (2017)
Keyphrases
- actor critic
- reinforcement learning
- power allocation
- temporal difference
- approximate dynamic programming
- policy gradient
- optimal control
- reinforcement learning algorithms
- neuro fuzzy
- gradient method
- resource allocation
- function approximation
- policy iteration
- average reward
- learning algorithm
- rl algorithms
- optimal policy
- markov decision processes
- state space
- multi agent
- convergence rate
- reinforcement learning methods
- evolutionary algorithm