SkillAgentSearch skills...

B2DQN

Code for my publication: Efficient Exploration through Bootstrapped and Bayesian Deep Q-Networks for Joint Power Control and Beamforming in mmWave Networks. Paper accepted for publication to IEEE Communications Letters.

Install / Use

/learn @bszeng/B2DQN
About this skill

Quality Score

0/100

Supported Platforms

Universal

README

Bootstrapped and Bayesian Deep Q-Networks

How to use

  • Set the number of antennas in the base station. In environment.py change the line self.M_ULA to the values of your choice. The code expects M = 4, 8, 16, 32, and 64.
  • Run DQN variants algorithms. Run the scripts DQN, BoDQN, BaDQN, and B2DQN.py in folder Codes. The result is the same as that in folder Results.
  • Show the results. Run the script Results_plot.ipynb in folder Results to show Figure 3, Figure 4, and Table IV in the paper.
View on GitHub
GitHub Stars7
CategoryDevelopment
Updated1mo ago
Forks1

Languages

Jupyter Notebook

Security Score

70/100

Audited on Mar 5, 2026

No findings