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

This paper proposes Meta-SAGE, a novel approach for improving the scalabilityof deep reinforcement learning models for combinatorial optimization (CO)tasks. Our method adapts pre-trained models to larger-scale problems in testtime by suggesting two components: a scale meta-learner (SML) and scheduledadaptation with guided exploration (SAGE). First, SML transforms the contextembedding for subsequent adaptation of SAGE based on scale information. Then,SAGE adjusts the model parameters dedicated to the context embedding for aspecific instance. SAGE introduces locality bias, which encourages selectingnearby locations to determine the next location. The locality bias graduallydecays as the model is adapted to the target instance. Results show thatMeta-SAGE outperforms previous adaptation methods and significantly improvesscalability in representative CO tasks. Our source code is available athttps://github.com/kaist-silab/meta-sage

Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization