Real-Time Micro-Fulfillment Orchestration in Omnichannel Retail Using Multi-Agent Reinforcement Learning Framework

Author(s)	Mr. Sri Harsha Konda
Country	United States
Abstract	Micro-fulfillment centers (MFCs) have emerged as a response to growing e-commerce demands, yet their integration into omnichannel retail networks creates order routing challenges that traditional optimization struggles to solve efficiently. This paper introduces a multi-agent reinforcement learning (MARL) framework designed for adaptive order allocation across heterogeneous fulfillment nodes: MFCs, dark stores, and conventional distribution centers. Built on a Centralized Training with Decentralized Execution (CTDE) architecture, the framework allows individual agents to make rapid local decisions while preserving coordination at the network level. Computational experiments indicate a 23% reduction in fulfillment time, 18% lower per-order costs, and SLA compliance reaching 94.2% versus 91.2% for the strongest baseline. Performance remains stable across different network sizes and under varying demand conditions. These results suggest that decentralized AI approaches can effectively handle the dynamic nature of modern retail fulfillment.
Keywords	Multi-Agent Reinforcement Learning, Micro-Fulfillment, Order Routing, Omnichannel Retail, Decentralized Optimization
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-13
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.63373

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research