Metraipolis › archive › dc_d2afe7f8dba9
SLA-Aware Task Offloading in the IoT Edge-Cloud Continuum: Class-Weighted Deep Reinforcement Learning Against an Exact Optimum — arXiv:2611.10638
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10638
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:07.004Z
- SHA-256 of the archived text
e1bd62aa6d89b84924ae518b4bd0b25b098f65e6e89d55bc7a4f061bbf1c6dba- Stable URL of this page
https://metraipolis.com/documento/dc_d2afe7f8dba9
How to cite
SLA-Aware Task Offloading in the IoT Edge-Cloud Continuum: Class-Weighted Deep Reinforcement Learning Against an Exact Optimum — arXiv:2611.10638 — arXiv (en), https://arxiv.org/abs/2611.10638 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2afe7f8dba9 (Metraipolis archive dc_d2afe7f8dba9, sha256 e1bd62aa6d89b84924ae518b4bd0b25b098f65e6e89d55bc7a4f061bbf1c6dba)
BibTeX
@misc{dcd2afe7f8dba9,
title = {SLA-Aware Task Offloading in the IoT Edge-Cloud Continuum: Class-Weighted Deep Reinforcement Learning Against an Exact Optimum — arXiv:2611.10638},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10638},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2afe7f8dba9; sha256 e1bd62aa6d89b84924ae518b4bd0b25b098f65e6e89d55bc7a4f061bbf1c6dba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10638. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep reinforcement learning (RL) is often used to decide where Internet of Things (IoT) tasks with different latency limits run in the edge-cloud continuum, yet some methods give every missed task the same penalty and few compare their agents with an optimal policy. This benchmark study builds four offloading systems small enough to solve exactly by dynamic programming and measures reward and learner against the optimum. A bonus for a met limit makes each miss cost its penalty plus the bonus, which shifts the class weights of published per-class rewards. A class-blind penalty stays 65% to 118% above the optimal cost even with a perfect learner, while a corrected per-class penalty comes within 0.13% of the optimum. With a per-class reward, tuned proximal policy optimization (PPO) agents come within 9% to 11% of the optimum in the smallest system, and the corrected one beats a tuned reservation rule in 9 of 10 seeds. In larger systems the agents stay 41% to 76% above the optimum, and a tuned rule beats their mean. Training ten times longer does not close this gap, and a PPO-Lagrangian agent with reachable targets does no better than the per-class reward. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI). Pagina del lavoro: https://arxiv.org/abs/2611.10638 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.497Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).