Deep Reinforcement Learning Based Bandwidth Part Assignment in 5G NR-U.
S. Ram AdityaShyamal DhuaAnimesh KumarVimal Bastin Edwin JosephR. RajavelsamyPublished in: CCNC (2024)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- state space
- multi agent
- computational power
- function approximation
- robotic control
- bandwidth utilization
- storage capacity
- temporal difference
- noise reduction
- markov decision processes
- dynamic programming
- markov decision process
- deep learning
- bandwidth allocation
- optimal policy
- action selection
- hidden markov models
- learning process
- image quality assessment
- learning algorithm
- multi agent reinforcement learning
- policy search
- machine learning
- neural network