Skip to content

A CSMA protocol based on deep reinforcement learning

Notifications You must be signed in to change notification settings

YidingYu/CS-DLMA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 

Repository files navigation

A short introduction to CS-DLMA

CS-DLMA is a carrier sense multiple access (CSMA) protocol for heterogeneous wirless networking. The underpinning technique of CS-DLMA is deep Q-network (DQN). However, conventional DQN algorithms cannot fit in with the specicial issues in CSMA protocols design. We put forth a new DQN algorithm to address these issuses.

How to use the codes

There are three main files in each folder, simulating the interactions of CS-DLMA node with other nodes.

  • run_DQN.py is the main framework, and you can run this file to start the simulation.
  • environment.py simulates the interaction between the CS-DLMA node and the WiFi node. It is similar as OpenAI gym environment.
  • DQN_brain.py builds the CS-DLMA node/agent. The new DQN algorithm is here.

About

A CSMA protocol based on deep reinforcement learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages