Metraipolis › archive › dc_fe660e1fe7a9

Differentiable Agent-Based Modeling for Multi-Echelon Supply Chains: Gradient-Based Optimization of Heterogeneous Policies at Scale — arXiv:2611.10999

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10999
License (as archived)
CC0-1.0
Archived
2026-11-10T18:43:00.074Z
SHA-256 of the archived text
f94ea55a8baf485ba5416175ea1c36d042b3aecc4dc0026d5982ffe2cd09ec76
Stable URL of this page
https://metraipolis.com/documento/dc_fe660e1fe7a9

How to cite

Differentiable Agent-Based Modeling for Multi-Echelon Supply Chains: Gradient-Based Optimization of Heterogeneous Policies at Scale — arXiv:2611.10999 — arXiv (en), https://arxiv.org/abs/2611.10999 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe660e1fe7a9 (Metraipolis archive dc_fe660e1fe7a9, sha256 f94ea55a8baf485ba5416175ea1c36d042b3aecc4dc0026d5982ffe2cd09ec76)
BibTeX
@misc{dcfe660e1fe7a9,
  title = {Differentiable Agent-Based Modeling for Multi-Echelon Supply Chains: Gradient-Based Optimization of Heterogeneous Policies at Scale — arXiv:2611.10999},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10999},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe660e1fe7a9; sha256 f94ea55a8baf485ba5416175ea1c36d042b3aecc4dc0026d5982ffe2cd09ec76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10999. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Global supply chains rely on the interactions of thousands of heterogeneous agents, posing significant challenges for optimization. While traditional optimization often assumes homogeneity to ensure tractability, Reinforcement Learning struggles with sample inefficiency when scaling to high-dimensional state spaces. We propose a Differentiable Agent-Based Model for multi-echelon inventory management. By implementing stochastic dynamics via differentiable tensor operations, we enable direct gradient propagation through the simulation. We validate the framework by recovering theoretical Newsvendor optima without supervision. Crucially, we demonstrate ``Mass Personalization'' by optimizing 10,000 distinct agent policies simultaneously in seconds, achieving a 53% cost reduction compared to scalar baselines. Furthermore, we utilize gradient sensitivity analysis to generate causal heatmaps, accurately recovering inherent lead-time delays from the computation graph. This approach bridges the gap between simulation and optimization, enabling the efficient training of self-correcting Digital Twins.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.10999 — 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 2026-11-10T18:37:37.619Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).