{
  "abstract": "One embodiment of a method for training a machine learning model to control a robot includes causing a model of the robot to move within a simulation based on one or more outputs of the machine learning model, computing an error within the simulation, computing at least one of a reward or an observation based on the error, and updating one or more parameters of the machine learning model based on the at least one of a reward or an observation.",
  "assignees": [
    "NVIDIA CORP"
  ],
  "authors": [
    "FOX DIETER",
    "NARANG YASHRAJ SHYAM",
    "TANG BINGJIE",
    "TOZETO RAMOS FABIO"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000002833",
  "categories": [
    "robotics-automation/robot-architectures"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 81
  },
  "figures": [],
  "files": [
    {
      "bytes": 9683,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "f4326cd050ca302aef37e6ee9557aa297d594417b5d4b837602f1179c7fd8603"
    },
    {
      "bytes": 972,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "7469748e62d6bd84d6da1da7a4deb77d7d692f21f9ad9d0ca8e1b1838f7c1ca1"
    },
    {
      "bytes": 1029,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "eef161c4f71e381d346e409e855a3c9d454a08ccc8c184569e8b778f8e327f08"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000002833/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b25j9/163",
    "b25j9/163",
    "b25j9/163",
    "b25j9/16",
    "b25j9/1605",
    "b25j9/1605"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000002833",
  "published_at": "2026-09-15T19:15:39.164247Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-02-17",
  "source_id": "US-12552021-B2",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US12552021B2",
  "supersedes": null,
  "title": "Techniques for training and implementing reinforcement learning policies for robot control",
  "uuid": "01a0a67f-0c1b-7bf8-8fae-963898fdd204"
}