{
  "abstract": "Systems and methods for implementation of a multi-agent reinforcement learning based decision system for a materials handling system, including initializing a simulation environment comprising decision points for dispatching materials and attributes of the materials handling system, the simulation environment configured to request a decision for materials dispatch at the decision points to the multi-agent reinforcement learning based decision system; initializing the reinforcement learning agents representative of the decision points for the multi-agent reinforcement learning based decision system; initializing domain expert heuristics for the decision points for the multi-agent reinforcement learning based decision system; and iteratively training the reinforcement learning based decision system with the initialized domain expert heuristics on the simulation environment.",
  "assignees": [
    "HITACHI LTD"
  ],
  "authors": [
    "GUPTA CHETAN",
    "KATSUMATA DAISUKE",
    "LEE XIAN YEOW",
    "MATSUI TAKAHARU",
    "WANG HAIYAN"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000001650",
  "categories": [
    "material-handling/conveying-systems"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 112
  },
  "figures": [],
  "files": [
    {
      "bytes": 10128,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "a65c3420affb5e2db0b9bd3176c53239dfbe271012e5cccdbe62c234337908c6"
    },
    {
      "bytes": 1422,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "492ed5097218b7a2157a317e8d802d04eafeed62036cb6799e670ba8460759e4"
    },
    {
      "bytes": 1467,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "d83afc39b9e79997a4bcf895b3be33ddae44865cb153dc3c4bfaab922e5e810b"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000001650/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b65g1/1373",
    "b65g1/1373",
    "g05d1/667",
    "b65g1/137",
    "g05d101/15",
    "g05d105/20"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000001650",
  "published_at": "2026-09-15T19:07:20.411639Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-03-19",
  "source_id": "US-2026077949-A1",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US2026077949A1",
  "supersedes": null,
  "title": "Multi-agent reinforcement learning framework for dynamic dispatching in material handling systems",
  "uuid": "01a0a677-6fdb-768f-b33e-64bfd725c219"
}