Multi-Agent Reinforcement Learning-Based Computation Offloading for Unmanned Aerial Vehicle Post-Disaster Rescue
Lixing Wang, Huirong Jiao · 2024
Read Multi-Agent Reinforcement Learning-Based Computation Offloading for Unmanned Aerial Vehicle Post-Disaster Rescue by Lixing Wang, Huirong Jiao (2024) 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-11679107.txt.
Description
Lixing Wang and Huirong Jiao present a 2024 study on drones sharing computing work after disasters. Rescue drones see and sense a lot but carry small batteries and weak processors. They must offload heavy tasks to edge servers, and several drones must coordinate who sends what.
Their algorithm teaches a team of drone agents to cooperate, guided by a shared critic network. Experience is sorted into good and bad buffers, so agents learn from successes and failures separately, cutting wasted effort. Simulations tuned the key settings first. Against two rival methods, the new algorithm achieved the lowest total system cost, with better stability and scaling as the fleet grows. The authors aim it at real rescue deployments.
Catalog record
| CREATOR | Lixing Wang, Huirong Jiao |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |