{
  "abstract": "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for off-line learning using a reward prediction model. One of the methods includes obtaining robot experience data; training, on a first subset of the robot experience data, a reward prediction model that receives a reward input comprising an input observation and generates as output a reward prediction that is a prediction of a task-specific reward for the particular task that should be assigned to the input observation; processing experiences in the robot experience data using the trained reward prediction model to generate a respective reward prediction for each of the processed experiences; and training a policy neural network on (i) the processed experiences and (ii) the respective reward predictions for the processed experiences.",
  "assignees": [
    "GDM HOLDING LLC"
  ],
  "authors": [
    "Reed Scott Ellison",
    "ZOLNA KONRAD"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000001838",
  "categories": [
    "robotics-automation/robot-architectures"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 125
  },
  "figures": [],
  "files": [
    {
      "bytes": 9949,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "7ccd3d8c6e342a398dbf69b8d912fbf0eb197898550d695f508b95e8625940fe"
    },
    {
      "bytes": 1318,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "6b6ba8da61168a9f9a368af9c4393b3a773d0f41e55cdfea086e5fd0ddb79f2c"
    },
    {
      "bytes": 1400,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "4190c3f7d4315025013ddeb61b06024fee492b5d058a20fa58b7e7a5c3554c13"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000001838/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b25j9/161",
    "b25j9/161",
    "g06n3/006",
    "g06n3/092",
    "b25j9/16",
    "b25j9/163"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000001838",
  "published_at": "2026-09-15T19:08:58.398080Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-03-17",
  "source_id": "US-12576515-B2",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US12576515B2",
  "supersedes": null,
  "title": "Off-line learning for robot control using a reward prediction model",
  "uuid": "01a0a678-ee9d-77c6-9ff5-65d8d2173f86"
}