{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "sutton-dyna-integrated-architecture-1990",
    "title": "Sutton: Dyna integrated learning, planning and reacting",
    "summary": "Presented Dyna architectures that interleave trial-and-error learning, learning a world model, and planning with simulated experience, including Dyna-PI and Dyna-Q demonstrations.",
    "boundary": "The record is Sutton's sole-author ICML 1990 paper. It does not absorb the 1991 SIGART article, Sutton's earlier temporal-difference result, Watkins's Q-learning, later prioritized sweeping or all model-based reinforcement learning.",
    "area": "Reinforcement learning",
    "topic": "Artificial intelligence",
    "year": 1990,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "sutton-dyna-integrated-architecture-1990",
    "target": {
      "record_id": "urn:uuid:d1a7223c-1d5d-4c0d-a03c-656e879979a6",
      "version": 1,
      "content_hash": "sha256:4176b1177eddcd2f1d2b36203cfd46626326b143e058ffe4d0909a2cc45dfd54"
    },
    "humans": [
      "Richard S. Sutton"
    ],
    "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": "elsevier-sutton-dyna-1990",
        "title": "Elsevier DOI for Sutton ICML Dyna paper",
        "url": "https://doi.org/10.1016/B978-1-55860-141-3.50030-4"
      },
      {
        "id": "mlanthology-sutton-dyna-1990",
        "title": "ML Anthology record and abstract for Sutton Dyna",
        "url": "https://mlanthology.org/icml/1990/sutton1990icml-integrated/"
      }
    ],
    "geography": {
      "country_codes": [
        "US"
      ],
      "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://www.derongliu.org/adp/adp-cdrom/refs/sutton19900216.pdf",
      "target": {
        "record_id": "urn:uuid:d1a7223c-1d5d-4c0d-a03c-656e879979a6",
        "version": 1,
        "content_hash": "sha256:4176b1177eddcd2f1d2b36203cfd46626326b143e058ffe4d0909a2cc45dfd54"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-09-26",
      "nationality_inferred": false,
      "sources": [
        {
          "title": "Attribution source",
          "url": "https://www.derongliu.org/adp/adp-cdrom/refs/sutton19900216.pdf"
        }
      ],
      "coverage_status": "COMPLETE",
      "country_labels": {
        "US": "United States"
      }
    },
    "points": "145000",
    "published_grade": {
      "id": "sutton-dyna-integrated-architecture-1990",
      "entry_id": "sutton-dyna-integrated-architecture-1990",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:d1a7223c-1d5d-4c0d-a03c-656e879979a6",
        "version": 1,
        "content_hash": "sha256:4176b1177eddcd2f1d2b36203cfd46626326b143e058ffe4d0909a2cc45dfd54"
      },
      "what_changed": "Interleaved real experience, model learning and simulated planning in Dyna-PI and Dyna-Q demonstrations.",
      "scope": "The record is Sutton's sole-author ICML 1990 paper. It does not absorb the 1991 SIGART article, Sutton's earlier temporal-difference result, Watkins's Q-learning, later prioritized sweeping or all model-based reinforcement learning.",
      "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:d1a7223c-1d5d-4c0d-a03c-656e879979a6",
        "version": 1,
        "content_hash": "sha256:4176b1177eddcd2f1d2b36203cfd46626326b143e058ffe4d0909a2cc45dfd54"
      },
      "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": "Richard S. Sutton",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Elsevier DOI for Sutton ICML Dyna paper",
            "url": "https://doi.org/10.1016/B978-1-55860-141-3.50030-4"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Elsevier DOI for Sutton ICML Dyna paper",
            "url": "https://doi.org/10.1016/B978-1-55860-141-3.50030-4"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "ML Anthology record and abstract for Sutton Dyna",
            "url": "https://mlanthology.org/icml/1990/sutton1990icml-integrated/"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "The record is Sutton's sole-author ICML 1990 paper. It does not absorb the 1991 SIGART article, Sutton's earlier temporal-difference result, Watkins's Q-learning, later prioritized sweeping or all model-based reinforcement learning.",
        "domain": "Reinforcement learning"
      },
      "sources": [
        {
          "citation": "Elsevier DOI for Sutton ICML Dyna paper",
          "url": "https://doi.org/10.1016/B978-1-55860-141-3.50030-4"
        },
        {
          "citation": "ML Anthology record and abstract for Sutton Dyna",
          "url": "https://mlanthology.org/icml/1990/sutton1990icml-integrated/"
        }
      ],
      "statement": "# Sutton: Dyna integrated learning, planning and reacting\n\nPresented Dyna architectures that interleave trial-and-error learning, learning a world model, and planning with simulated experience, including Dyna-PI and Dyna-Q demonstrations.\n\n## Scientific scope\n\nThe record is Sutton's sole-author ICML 1990 paper. It does not absorb the 1991 SIGART article, Sutton's earlier temporal-difference result, Watkins's Q-learning, later prioritized sweeping or all model-based reinforcement learning.\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\nRichard S. Sutton\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- [Elsevier DOI for Sutton ICML Dyna paper](https://doi.org/10.1016/B978-1-55860-141-3.50030-4)\n- [ML Anthology record and abstract for Sutton Dyna](https://mlanthology.org/icml/1990/sutton1990icml-integrated/)\n",
      "summary": "Presented Dyna architectures that interleave trial-and-error learning, learning a world model, and planning with simulated experience, including Dyna-PI and Dyna-Q demonstrations.",
      "title": "Sutton: Dyna integrated learning, planning and reacting"
    },
    "record_id": "urn:uuid:d1a7223c-1d5d-4c0d-a03c-656e879979a6",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:d1a7223c-1d5d-4c0d-a03c-656e879979a6",
      "version": 1,
      "content_hash": "sha256:4176b1177eddcd2f1d2b36203cfd46626326b143e058ffe4d0909a2cc45dfd54"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:2174bf4a353f7c4a7cc6bc8b583dd96c5ef179417d95ad6ecd31b32f68c4522e"
  },
  "target": {
    "record_id": "urn:uuid:d1a7223c-1d5d-4c0d-a03c-656e879979a6",
    "version": 1,
    "content_hash": "sha256:4176b1177eddcd2f1d2b36203cfd46626326b143e058ffe4d0909a2cc45dfd54"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "sutton-dyna-integrated-architecture-1990",
    "entry_id": "sutton-dyna-integrated-architecture-1990",
    "revision": 1,
    "title": "Sutton: Dyna integrated learning, planning and reacting",
    "context": "Reinforcement learning",
    "track": "ALGORITHM",
    "band": "A",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-25",
    "evidence_cutoff": "2026-09-25",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Interleaved real experience, model learning and simulated planning in Dyna-PI and Dyna-Q demonstrations.",
    "scope": "The record is Sutton's sole-author ICML 1990 paper. It does not absorb the 1991 SIGART article, Sutton's earlier temporal-difference result, Watkins's Q-learning, later prioritized sweeping or all model-based reinforcement learning.",
    "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is Sutton's sole-author ICML 1990 paper. It does not absorb the 1991 SIGART article, Sutton's earlier temporal-difference result, Watkins's Q-learning, later prioritized sweeping or all model-based reinforcement learning.",
    "references": [
      {
        "title": "ML Anthology record and abstract for Sutton Dyna",
        "url": "https://mlanthology.org/icml/1990/sutton1990icml-integrated/",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      }
    ],
    "roles": [
      {
        "who": "Richard S. Sutton",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:d1a7223c-1d5d-4c0d-a03c-656e879979a6",
      "version": 1,
      "content_hash": "sha256:4176b1177eddcd2f1d2b36203cfd46626326b143e058ffe4d0909a2cc45dfd54"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "145000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}