Action-factorized Rainbow deep Q-network with token Transformer for computation offloading in edge computing-enabled Internet of Ships

Shengtian Zhang, Haolin Yang, Hyeonseok Kim, Incheol Shin, Robert M X Wu · 2026

Read Action-factorized Rainbow deep Q-network with token Transformer for computation offloading in edge computing-enabled Internet of Ships by Shengtian Zhang, Haolin Yang, Hyeonseok Kim, Incheol Shin, Robert M X Wu (2026) 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/plos-pone-0348376.txt.

Description

Shengtian Zhang and co-workers design a learning algorithm that decides where ships should run their computing tasks. Connected ships can send work to nearby edge servers instead of far-off clouds, saving time and power. Their 2026 study tackles the hard mix of choices involved, which shifts as sea channels change minute by minute.

The method splits big decisions into smaller factors and reads the situation through a transformer-style encoder. In tests it beat rival approaches on a combined score of delay and energy. It also never produced an invalid choice, so every plan it made could actually run. Smarter offloading could help fleets digitize without draining batteries or clogging links.

Catalog record

CREATORShengtian Zhang, Haolin Yang, Hyeonseok Kim, Incheol Shin, Robert M X Wu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE74733
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0348376

Browse the full library · About the Tower of Babel