Metraipolis › archive › dc_a4e749393129

Fast-Convergent Meta-RL via Gradient-Clustered BS Sampling for Edge Caching — arXiv:2609.16370

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.16370
License (as archived): CC0-1.0
Archived: 2026-10-15T22:39:27.184Z
SHA-256 of the archived text: c257ae32e3886e6ab24a0c71ab5580e96c975072e75796ceee537a21d7f882eb
Stable URL of this page: https://metraipolis.com/documento/dc_a4e749393129

How to cite

Fast-Convergent Meta-RL via Gradient-Clustered BS Sampling for Edge Caching — arXiv:2609.16370 — arXiv (en), https://arxiv.org/abs/2609.16370 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4e749393129 (Metraipolis archive dc_a4e749393129, sha256 c257ae32e3886e6ab24a0c71ab5580e96c975072e75796ceee537a21d7f882eb)

BibTeX

@misc{dca4e749393129,
  title = {Fast-Convergent Meta-RL via Gradient-Clustered BS Sampling for Edge Caching — arXiv:2609.16370},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16370},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4e749393129; sha256 c257ae32e3886e6ab24a0c71ab5580e96c975072e75796ceee537a21d7f882eb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16370. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Wireless edge caching networks typically consist of many independent Base Stations (BSs), each facing its own request rate and content popularity profile. Training a Reinforcement Learning (RL) caching agent from scratch at every BS forces each agent to relearn, through slow trial and error, a decision problem that is structurally identical across the network. Meta-reinforcement learning removes this redundancy by learning a shared initialization that adapts to any BS in a few local updates; however, meta-training itself becomes the bottleneck at scale: the meta-gradient must be estimated from a small subset of BSs at each meta-iteration, and sampling this subset uniformly at random yields a high-variance estimate, an issue existing meta-RL caching frameworks leave unaddressed. This paper proposes a meta-reinforcement learning framework for caching across independent, non-overlapping BSs that directly targets this bottleneck. Each BS runs a local Proximal Policy Optimization (PPO) agent, formulated as a Semi-Markov Decision Process (SMDP) over content popularity, size, lifetime, and importance, while a shared meta-policy is learned via a Model-Agnostic Meta-Learning (MAML)-style loop. To scale meta-training and accelerate convergence, we introduce gradient-based clustering, which groups BSs by local gradient similarity and draws from every cluster, in proportion to its size, at each meta-iteration. We prove, via an Analysis of Variance (ANOVA)-style decomposition of gradient variance, that this strategy yields a strictly lower-variance meta-gradient estimator than uniform random sampling under BS heterogeneity.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-16 in eess.SY).
Categorie arXiv: Networking and Internet Architecture (cs.NI) ; Machine Learning (cs.LG); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.16370 — 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 2026-10-15T22:15:42.183Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).