English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Optimization problems over dynamic networks have been extensively studied andwidely used in the past decades to formulate numerous real-world problems.However, (1) traditional optimization-based approaches do not scale to largenetworks, and (2) the design of good heuristics or approximation algorithmsoften requires significant manual trial-and-error. In this work, we argue thatdata-driven strategies can automate this process and learn efficient algorithmswithout compromising optimality. To do so, we present network control problemsthrough the lens of reinforcement learning and propose a graph network-basedframework to handle a broad class of problems. Instead of naively computingactions over high-dimensional graph elements, e.g., edges, we propose abi-level formulation where we (1) specify a desired next state via RL, and (2)solve a convex program to best achieve it, leading to drastically improvedscalability and performance. We further highlight a collection of desirablefeatures to system designers, investigate design decisions, and presentexperiments on real-world control problems showing the utility, scalability,and flexibility of our framework.

Graph Reinforcement Learning for Network Control via Bi-Level Optimization