Anti-Jamming Communication Using Imitation Learning
Zhanyang Zhou, Yingtao Niu, Boyu Wan, Wenhao Zhou, Shu-Chuan Chu, Erdem Koyuncu · 2023
Read Anti-Jamming Communication Using Imitation Learning by Zhanyang Zhou, Yingtao Niu, Boyu Wan, Wenhao Zhou, Shu-Chuan Chu, Erdem Koyuncu (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10670521.txt.
Description
Wireless links can be blocked on purpose by hostile jammers, and Zhanyang Zhou and co-authors set out in 2023 to keep such links working. Their paper deals with how a radio should pick its next move when an attacker keeps changing the blocked channels. Older fixed plans and two common learning methods make poor use of past data, the authors note.
The team first builds an expert plan from past samples, then trains a neural network to copy that plan. The trained network then makes fast choices in order during real use. In tests, the method beat both older learning methods, handled wide state spaces well, and held up better when the channel faded.
Catalog record
| CREATOR | Zhanyang Zhou, Yingtao Niu, Boyu Wan, Wenhao Zhou, Shu-Chuan Chu, Erdem Koyuncu |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |