Dynamic Bandwidth Allocation Scheme for Wireless Networks with Energy Harvesting Using Actor-Critic Deep Reinforcement Learning.
Quang Vinh DoInsoo KooPublished in: ICAIIC (2019)
Keyphrases
- wireless networks
- allocation scheme
- actor critic
- reinforcement learning
- bandwidth allocation
- low bandwidth
- function approximation
- temporal difference
- wireless communication
- policy gradient
- optimal control
- reinforcement learning algorithms
- cellular networks
- approximate dynamic programming
- policy iteration
- ad hoc networks
- neuro fuzzy
- call admission control
- evaluation method
- video delivery
- markov decision processes
- packet scheduling
- gradient method
- energy consumption
- state space
- machine learning
- learning algorithm
- multimedia services
- network coding
- average reward
- optimal policy
- policy gradient methods
- temporal difference learning
- model free
- control strategy
- quality of service
- dynamic environments
- supervised learning