An online learning algorithm to play discounted repeated games in wireless networks. (January 2022)
- Record Type:
- Journal Article
- Title:
- An online learning algorithm to play discounted repeated games in wireless networks. (January 2022)
- Main Title:
- An online learning algorithm to play discounted repeated games in wireless networks
- Authors:
- Parras, Juan
Apellániz, Patricia A.
Zazo, Santiago - Abstract:
- Abstract: Discounted repeated games are currently being used to model the conflicts that arise between the nodes in a wireless network, such as distributed resource allocation, interference management or defending the network against attacks. In current literature, it is frequent that authors devise a specific strategy that performs well only for their concrete problem, thus, it would be desirable to have a generic algorithm that allows learning strategies for such games. However, current learning algorithms focus on average payoff repeated games, and we show analytically that there are important differences that prevent us from using such algorithms for discounted repeated games. In this work, we aim to fill this gap and we propose LEWIS, a lightweight, online learning algorithm specifically designed for these games, that deals with imperfect and incomplete information and is able to return a good payoff. We test LEWIS on two settings based on current literature problems to show that it has a good performance, hence, being a promising method to learn how to play a discounted repeated game in wireless networks. Highlights: Discounted repeated games are widely used in wireless networks. Most works propose specific learning methods for such games. We propose a generic online learning algorithm valid for low capabilities devices. We test our method using two problems from current literature.
- Is Part Of:
- Engineering applications of artificial intelligence. Volume 107(2022)
- Journal:
- Engineering applications of artificial intelligence
- Issue:
- Volume 107(2022)
- Issue Display:
- Volume 107, Issue 2022 (2022)
- Year:
- 2022
- Volume:
- 107
- Issue:
- 2022
- Issue Sort Value:
- 2022-0107-2022-0000
- Page Start:
- Page End:
- Publication Date:
- 2022-01
- Subjects:
- Repeated games -- Online learning -- Wireless networks -- Folk theorem
Engineering -- Data processing -- Periodicals
Artificial intelligence -- Periodicals
Expert systems (Computer science) -- Periodicals
Ingénierie -- Informatique -- Périodiques
Intelligence artificielle -- Périodiques
Systèmes experts (Informatique) -- Périodiques
Artificial intelligence
Engineering -- Data processing
Expert systems (Computer science)
Periodicals
620.00285 - Journal URLs:
- http://www.sciencedirect.com/science/journal/09521976 ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.engappai.2021.104520 ↗
- Languages:
- English
- ISSNs:
- 0952-1976
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3755.704500
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 20585.xml