{
  "abstract": "The embodiment of the present discloses a method for training a policy model based on reinforcement learning and apparatus, and an electronic device. The method includes: determining an observation data sequence generated by an agent during a time period of executing a target task, a preset time window, and an expert data sequence corresponding to the target task; determining a cost matrix and a transport matrix based on the preset time window, the observation data sequence, and the expert data sequence; determining a reward value for each observation data in the observation data sequence based on the cost matrix and the transport matrix; and training the policy model based on the observation data and the reward value of the observation data.",
  "assignees": [
    "HORIZON ROBOTICS INC"
  ],
  "authors": [
    "FU YUWEI",
    "XU WEI",
    "ZHANG HAICHAO"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000001947",
  "categories": [
    "robotics-automation/robot-architectures"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 121
  },
  "figures": [],
  "files": [
    {
      "bytes": 9948,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "7c8cf2686cc00082f2546784cfca965f77a1de749727b349938c0ff8436d877f"
    },
    {
      "bytes": 1267,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "7e9325bfa783edcfcce96cae9e8f04aef8b1b9df1637e41ef8cd78b8e4c3569a"
    },
    {
      "bytes": 1330,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "9fa7f122b3da144e06310a59d693541ceef7aba48de689b19d716cb33298cbb5"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000001947/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b25j9/163",
    "b25j9/163",
    "b25j9/163",
    "b25j9/16",
    "b25j9/161",
    "b25j9/161"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000001947",
  "published_at": "2026-09-15T19:09:41.592638Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-03-12",
  "source_id": "US-2026070214-A1",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US2026070214A1",
  "supersedes": null,
  "title": "Method and electronic device for training policy model based on reinforcement learning",
  "uuid": "01a0a679-9758-76cf-86ce-4c0367634e9c"
}