Reinforcement Learning for Distributed Power Control and Channel Access in Cognitive Wireless Mesh Networks

Xianfu Chen, Zhifeng Zhao, Honggang Zhang

Research output: Chapter in Book/Report/Conference proceedingChapter or book articleScientificpeer-review

2 Citations (Scopus)
Original languageEnglish
Title of host publicationCognitive Communications
Subtitle of host publicationDistributed Artificial Intelligence (DAI), Regulatory Policy and Economics, Implementation
Number of pages31
ISBN (Print)978-1-11995-150-6
Publication statusPublished - 24 Jul 2012
MoE publication typeA3 Part of a book or another research book


  • CogMesh framework, two major technical issues
  • CogMesh, and problem of opportunistic spectrum access
  • CogMesh, self-organized/self-configured network architecture
  • Conjecture-based multi-agent Q-learning algorithm
  • Distributed learning algorithms and dynamic conjectures, OSA in CogMesh
  • E-greedy method, single-/multi-agent learning algorithms for balancing
  • Resource allocation in CogMesh, stochastic learning process
  • RL for distributed power control, in CogMesh
  • Stochastic power allocation, performance balancing competing objectives

Cite this