2017 IEEE Wireless Communications and Networking Conference (WCNC) 2017
DOI: 10.1109/wcnc.2017.7925694
|View full text |Cite
|
Sign up to set email alerts
|

Multi-Agent Reinforcement Learning Based Cognitive Anti-Jamming

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
66
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 101 publications
(72 citation statements)
references
References 13 publications
0
66
0
Order By: Relevance
“…Then, user n broadcasts its channel. • Independent Q-earning [14]: Each user adopts a standard Q-learning method. The coordination among users is not considered, and other users are treated as part of its environment.…”
Section: Numerical Results and Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…Then, user n broadcasts its channel. • Independent Q-earning [14]: Each user adopts a standard Q-learning method. The coordination among users is not considered, and other users are treated as part of its environment.…”
Section: Numerical Results and Discussionmentioning
confidence: 99%
“…Based on the Q-learning method, the anti-jamming decisionmaking problem in single-user scenarios were investigated in [11]- [13]. Then, the authors in [14]- [16] extended it to the multi-user scenarios, and they resorted to the Markov game framework [17], which is the extension of the Markov decision process and can characterize the relationship among multiple users. Moreover, the corresponding multi-user reinforcement learning anti-jamming algorithm was designed.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…One of the first wireless security issues that apply reinforcement learning techniques is anti-jamming communications [8], [10]- [14], showing that a transmitter can use RL algorithms such as Q-learning to optimize its transmit power and channel selection in some simplified communication scenarios, such as very few number of feasible actions and possible states, without being aware of the network model and the jamming model. As summarized in Table I, the RL techniques have also been used in spoofing detection [6], [13], smart attacks [13] and malware detection [9].…”
Section: Rl-based Mec Security Solutionsmentioning
confidence: 99%
“…Fortunately, many approaches have also been proposed to learn how to act in an unknown communication environment. The classical theory of reinforcement learning (RL), in which an agent learns and adapts its strategy by using the feedback of its actions that have been used in the past, has received much attention. Specifically, this theory learns an optimal strategy by repeatedly interacting with the environment.…”
Section: Introductionmentioning
confidence: 99%