What is it about?
Models network users' repeated interactions from a game-theoretic perspective, and incorporates reinforcement learning to allow users to play against other users with known and unknown strategies.
Featured Image
Why is it important?
In ad hoc wireless networks, users may communicate with other users by direct transmission or by cooperative relaying for each other, without requiring centralized control or fixed network infrastructure. Moreover, network users do not necessarily belong to a single authority and thus may have different goals and tasks. Additionally, network users could have a non-stationary behavior that includes cooperation and/or defection. In such scenarios, assuming fully cooperative behaviors is unwarranted.
Perspectives
To the best of the author’s knowledge, no prior work has employed the repeated prisoner’s dilemma model along with reinforcement learning to allow network nodes to act rationally and achieve their maximum expected return values.
Prof. Mohammed W Baidas
Kuwait University
Read the Original
This page is a summary of: Cooperation in wireless networks: a game-theoretic framework with reinforcement learning, IET Communications, March 2014, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-com.2013.0817.
You can read the full text:
Contributors
The following have contributed to this page
