Get Started
Home
Topics
Search
Library
Research questionHow can joint replenishment be coordinated in real time across many heterogeneous items?Joint ordering couples thousands of item decisions through demand uncertainty, lead times, and shared costs. Optimization can become slow at scale, while learning systems must assign credit across a high-dimensional action space.
AI
Business
Machine Learning
Reinforcement Learning
Technology
Latest papersRecent research connected to this question, newest first.OR-Transformer: Scaling Real-Time Decision-Making to 1,000 ItemsThe source develops a deep reinforcement-learning policy with permutation-equivariant item representations and differentiable inventory-dynamics training for this replenishment setting. Evidence compares learning policies with rolling-horizon mixed-integer optimization on the reported item scales and demand conditions; it does not establish broader supply-chain planning performance.research paper · Sep 4, 2026
Related questions
How can LLMs adapt coupled retail supply-chain pipelines when changing requirements have multiple routes with different downstream effects?How can multimodal agents collaborate asynchronously under time pressure with split information and imperfect communication?How can return narratives guide inspection depth and recovery allocation under uncertain asset condition and limited labor?How can long-horizon LLM agents learn when to group actions without overcommitting?