SyncAI.news, a Varaisys broadcasting
Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry
ZZ

Zuyuan Zhang, Zeyu Fang, Mahdi Imani, Nathaniel D. Bastian, Tian Lan

· 1 min read

ResearcharXiv cs.LG

Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry

arXiv:2609.26068v1 Announce Type: cross Abstract: 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.

Original source

This story was published by arXiv cs.LG and written by Zuyuan Zhang, Zeyu Fang, Mahdi Imani, Nathaniel D. Bastian, Tian Lan. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News