Metraipolis › archive › dc_bbebb8d018de

Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry — arXiv:2609.26068

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26068
License (as archived): CC0-1.0
Archived: 2026-10-08T15:08:46.548Z
SHA-256 of the archived text: b4bfac0bfe197f88c1c14dcd506a4c2199db3424ced6a85a8c203167c82b0bc2
Stable URL of this page: https://metraipolis.com/documento/dc_bbebb8d018de

How to cite

Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry — arXiv:2609.26068 — arXiv (en), https://arxiv.org/abs/2609.26068 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bbebb8d018de (Metraipolis archive dc_bbebb8d018de, sha256 b4bfac0bfe197f88c1c14dcd506a4c2199db3424ced6a85a8c203167c82b0bc2)

BibTeX

@misc{dcbbebb8d018de,
  title = {Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry — arXiv:2609.26068},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26068},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bbebb8d018de; sha256 b4bfac0bfe197f88c1c14dcd506a4c2199db3424ced6a85a8c203167c82b0bc2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26068. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning-based control is increasingly central to automating network operations. A learned policy, however, must satisfy cross-layer constraints on interference, power-rate coupling, flow conservation, service chains, capacity, latency, and reliability. Existing methods typically account for only a subset of this geometry and only indirectly, e.g., through reward penalties, Lagrange multipliers, or post-hoc repairs. This paper proposes \emph{Network Feasibility Geometry Reinforcement Learning} (NFG-RL), which models coupled constraints via transport theory and the residual inclusion $\bphi_{\mathfrak{N}}(x,a)\in\cK_{\mathfrak{N}}$, defining the executed policy as the pushforward of a proto-policy through a feasibility-transport map. NFG-RL compiles heterogeneous constraints into typed residual blocks and transports proto-actions through a differentiable variational operator, letting active constraints shape execution, exploration, and actor gradients. Our analysis shows that exact transport yields almost-sure feasible execution, while active constraints contract exploration onto the feasible tangent space. It further establishes a nonnegative first-order gain from critic-tilted transport over plain projection and recovers backpressure scheduling as the gradient of a lifted drift residual. In two public-trace-conditioned wireless-edge surrogate environments, NFG-RL improves feasible utility by \textbf{37.5--41.5\%} over the strongest non-NFG method in each environment, reduces raw-action violation by \textbf{48.5--60.8\%}, and lowers P99 delay by \textbf{57.0--75.5\%}, outperforming a range of optimization and learning baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Networking and Internet Architecture (cs.NI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.26068 — 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 2026-10-08T14:37:29.558Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).