{
  "abstract": "Training and/or utilizing a hierarchical reinforcement learning (HRL) model for robotic control. The HRL model can include at least a higher-level policy model and a lower-level policy model. Some implementations relate to technique(s) that enable more efficient off-policy training to be utilized in training of the higher-level policy model and/or the lower-level policy model. Some of those implementations utilize off-policy correction, which re-labels higher-level actions of experience data, generated in the past utilizing a previously trained version of the HRL model, with modified higher-level actions. The modified higher-level actions are then utilized to off-policy train the higher-level policy model. This can enable effective off-policy training despite the lower-level policy model being a different version at training time (relative to the version when the experience data was collected).",
  "assignees": [
    "GOOGLE LLC"
  ],
  "authors": [
    "GU SHIXIANG",
    "LEE HONGLAK",
    "Levine Sergey"
  ],
  "canonical_url": "https://opentechnical.org/p/OT-2026-000001734",
  "categories": [
    "robotics-automation/robot-architectures"
  ],
  "extent": {
    "figures": 0,
    "paragraphs": 0,
    "words": 127
  },
  "figures": [],
  "files": [
    {
      "bytes": 9957,
      "media_type": "text/html; charset=utf-8",
      "name": "index.html",
      "sha256": "f717e87fb6aa02c1b72a95ec899469c26e2444930441cbffbb47ded20aede31a"
    },
    {
      "bytes": 1350,
      "media_type": "text/markdown; charset=utf-8",
      "name": "publication.md",
      "sha256": "779c84086d685e0e3e33b3ddceab2a196cc8c503f726399bb71543e6ea535145"
    },
    {
      "bytes": 1449,
      "media_type": "text/plain; charset=utf-8",
      "name": "publication.txt",
      "sha256": "d191671eb88560edc732bd27955db926018627e76f80e5539490948705fea197"
    }
  ],
  "integrity": {
    "hash_algorithm": "sha256",
    "keys_url": "https://opentechnical.org/integrity/keys",
    "record_url": "https://opentechnical.org/p/OT-2026-000001734/integrity",
    "signature_algorithm": "Ed25519",
    "signature_file": "manifest.sig",
    "verify_url": "https://opentechnical.org/integrity/verify"
  },
  "keywords": [
    "b25j9/1602",
    "b25j9/163",
    "b25j9/163",
    "g06n3/092",
    "b25j9/16",
    "b25j9/16"
  ],
  "language": "en",
  "license": {
    "name": "Creative Commons Attribution 4.0 International",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "publication_id": "OT-2026-000001734",
  "published_at": "2026-09-15T19:08:03.434986Z",
  "publisher": "Nebula Innovations Limited",
  "record_type": "record",
  "schema": "opentechnical-publication-manifest/1.0",
  "source_date": "2026-03-19",
  "source_id": "US-2026077490-A1",
  "source_name": "the United States Patent and Trademark Office",
  "source_url": "https://patents.google.com/patent/US2026077490A1",
  "supersedes": null,
  "title": "Data-efficient hierarchical reinforcement learning",
  "uuid": "01a0a678-17e9-7d4b-ba7a-0e532551b2b2"
}