{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "schrittwieser-et-al-muzero-2020",
    "title": "Schrittwieser and colleagues: MuZero planning with a learned model",
    "summary": "Combined tree search with a learned latent model that predicts reward, policy and value quantities, reporting performance across Atari and board games without being supplied their transition rules.",
    "boundary": "The record is the exact twelve-author Nature paper. Claims remain confined to the reported games, training budgets and evaluation protocol; it does not establish general real-world planning, safety or domain-independent intelligence.",
    "area": "Reinforcement learning",
    "year": 2020,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "schrittwieser-et-al-muzero-2020",
    "target": {
      "record_id": "urn:uuid:2bd865d7-db56-4162-a003-7beab2f539c5",
      "version": 1,
      "content_hash": "sha256:96092eeb77c698f89055451cd8a3e1d6b06b3ae2eaff3fb29b120f71ab6bc616"
    },
    "humans": [
      "Julian Schrittwieser",
      "Ioannis Antonoglou",
      "Thomas Hubert",
      "Karen Simonyan",
      "Laurent Sifre",
      "Simon Schmitt",
      "Arthur Guez",
      "Edward Lockhart",
      "Demis Hassabis",
      "Thore Graepel",
      "Timothy Lillicrap",
      "David Silver"
    ],
    "authors_complete": true,
    "human_role_note": "The named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "arxiv-muzero-2019",
        "title": "arXiv record and full text for MuZero",
        "url": "https://arxiv.org/abs/1911.08265"
      },
      {
        "id": "doi-muzero-nature-2020",
        "title": "Nature DOI for MuZero",
        "url": "https://doi.org/10.1038/s41586-020-03051-4"
      }
    ],
    "geography": {
      "country_codes": [
        "GB"
      ],
      "location_basis": "Documented research locations or paper affiliations for this contribution. Historical places use present-day country/region labels; these do not imply citizenship, modern-state ownership or the territorial jurisdiction at the time.",
      "source_url": "https://arxiv.org/pdf/1911.08265",
      "target": {
        "record_id": "urn:uuid:2bd865d7-db56-4162-a003-7beab2f539c5",
        "version": 1,
        "content_hash": "sha256:96092eeb77c698f89055451cd8a3e1d6b06b3ae2eaff3fb29b120f71ab6bc616"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-09-26",
      "nationality_inferred": false,
      "sources": [
        {
          "title": "Attribution source",
          "url": "https://arxiv.org/pdf/1911.08265"
        }
      ],
      "coverage_status": "COMPLETE",
      "country_labels": {
        "GB": "United Kingdom"
      }
    },
    "points": "85000",
    "published_grade": {
      "id": "schrittwieser-et-al-muzero-2020",
      "entry_id": "schrittwieser-et-al-muzero-2020",
      "band": "A",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:2bd865d7-db56-4162-a003-7beab2f539c5",
        "version": 1,
        "content_hash": "sha256:96092eeb77c698f89055451cd8a3e1d6b06b3ae2eaff3fb29b120f71ab6bc616"
      },
      "what_changed": "Planned with a learned reward/policy/value model and reported strong Atari and board-game results.",
      "scope": "The record is the exact twelve-author Nature paper. Claims remain confined to the reported games, training budgets and evaluation protocol; it does not establish general real-world planning, safety or domain-independent intelligence.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:2bd865d7-db56-4162-a003-7beab2f539c5",
        "version": 1,
        "content_hash": "sha256:96092eeb77c698f89055451cd8a3e1d6b06b3ae2eaff3fb29b120f71ab6bc616"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-09-25T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Julian Schrittwieser",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ioannis Antonoglou",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Thomas Hubert",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Karen Simonyan",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Laurent Sifre",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Simon Schmitt",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Arthur Guez",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Edward Lockhart",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Demis Hassabis",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Thore Graepel",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Timothy Lillicrap",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "David Silver",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "arXiv record and full text for MuZero",
            "url": "https://arxiv.org/abs/1911.08265"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Nature DOI for MuZero",
            "url": "https://doi.org/10.1038/s41586-020-03051-4"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "The record is the exact twelve-author Nature paper. Claims remain confined to the reported games, training budgets and evaluation protocol; it does not establish general real-world planning, safety or domain-independent intelligence.",
        "domain": "Reinforcement learning"
      },
      "sources": [
        {
          "citation": "arXiv record and full text for MuZero",
          "url": "https://arxiv.org/abs/1911.08265"
        },
        {
          "citation": "Nature DOI for MuZero",
          "url": "https://doi.org/10.1038/s41586-020-03051-4"
        }
      ],
      "statement": "# Schrittwieser and colleagues: MuZero planning with a learned model\n\nCombined tree search with a learned latent model that predicts reward, policy and value quantities, reporting performance across Atari and board games without being supplied their transition rules.\n\n## Scientific scope\n\nThe record is the exact twelve-author Nature paper. Claims remain confined to the reported games, training budgets and evaluation protocol; it does not establish general real-world planning, safety or domain-independent intelligence.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nJulian Schrittwieser; Ioannis Antonoglou; Thomas Hubert; Karen Simonyan; Laurent Sifre; Simon Schmitt; Arthur Guez; Edward Lockhart; Demis Hassabis; Thore Graepel; Timothy Lillicrap; David Silver\n\nThe named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.\n\n\n\n## Original sources\n\n- [arXiv record and full text for MuZero](https://arxiv.org/abs/1911.08265)\n- [Nature DOI for MuZero](https://doi.org/10.1038/s41586-020-03051-4)\n",
      "summary": "Combined tree search with a learned latent model that predicts reward, policy and value quantities, reporting performance across Atari and board games without being supplied their transition rules.",
      "title": "Schrittwieser and colleagues: MuZero planning with a learned model"
    },
    "record_id": "urn:uuid:2bd865d7-db56-4162-a003-7beab2f539c5",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:2bd865d7-db56-4162-a003-7beab2f539c5",
      "version": 1,
      "content_hash": "sha256:96092eeb77c698f89055451cd8a3e1d6b06b3ae2eaff3fb29b120f71ab6bc616"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:73c8a87c26465550bc53ca225ba0e2550a4f0f8aa5d1d8c4d520897fe88989e2"
  },
  "target": {
    "record_id": "urn:uuid:2bd865d7-db56-4162-a003-7beab2f539c5",
    "version": 1,
    "content_hash": "sha256:96092eeb77c698f89055451cd8a3e1d6b06b3ae2eaff3fb29b120f71ab6bc616"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "schrittwieser-et-al-muzero-2020",
    "entry_id": "schrittwieser-et-al-muzero-2020",
    "revision": 1,
    "title": "Schrittwieser and colleagues: MuZero planning with a learned model",
    "context": "Reinforcement learning",
    "track": "METHOD",
    "band": "A",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-25",
    "evidence_cutoff": "2026-09-25",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Planned with a learned reward/policy/value model and reported strong Atari and board-game results.",
    "scope": "The record is the exact twelve-author Nature paper. Claims remain confined to the reported games, training budgets and evaluation protocol; it does not establish general real-world planning, safety or domain-independent intelligence.",
    "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact twelve-author Nature paper. Claims remain confined to the reported games, training budgets and evaluation protocol; it does not establish general real-world planning, safety or domain-independent intelligence.",
    "references": [
      {
        "title": "arXiv record and full text for MuZero",
        "url": "https://arxiv.org/abs/1911.08265",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      },
      {
        "title": "Nature DOI for MuZero",
        "url": "https://doi.org/10.1038/s41586-020-03051-4",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      }
    ],
    "roles": [
      {
        "who": "The named authors listed in the linked research record",
        "credit": "SCIENCE",
        "did": "Complete source byline retained in the research record; this collective display does not merge person identities or measure labor shares."
      }
    ],
    "target": {
      "record_id": "urn:uuid:2bd865d7-db56-4162-a003-7beab2f539c5",
      "version": 1,
      "content_hash": "sha256:96092eeb77c698f89055451cd8a3e1d6b06b3ae2eaff3fb29b120f71ab6bc616"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "85000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}