{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "alphazero-general-self-play-2018", "title": "Silver and colleagues: AlphaZero across chess, shogi and Go", "summary": "Generalized self-play reinforcement learning and tree search into one algorithm evaluated across chess, shogi and Go, starting from random play with only the game rules supplied.", "boundary": "The record is the exact 2018 Science paper and its three-game evaluations. AlphaGo, AlphaGo Zero, later MuZero systems, domain-independent intelligence claims and performance outside the reported game settings remain separate.", "area": "Reinforcement learning", "year": 2018, "lane": "HUMAN", "result": "ALGORITHM", "package_id": "alphazero-general-self-play-2018", "target": { "record_id": "urn:uuid:7ef427da-098f-4393-ac44-3da8589323f6", "version": 1, "content_hash": "sha256:352eeee897407dc7ba33ab86d89400def14fb57f8005fcddc63718cb52478678" }, "humans": [ "David Silver", "Thomas Hubert", "Julian Schrittwieser", "Ioannis Antonoglou", "Matthew Lai", "Arthur Guez", "Marc Lanctot", "Laurent Sifre", "Dharshan Kumaran", "Thore Graepel", "Timothy Lillicrap", "Karen Simonyan", "Demis Hassabis" ], "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": "ucl-alphazero-preprint-2018", "title": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" }, { "id": "pubmed-alphazero-2018", "title": "PubMed record for AlphaZero Science paper", "url": "https://pubmed.ncbi.nlm.nih.gov/30523106/" } ], "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://www.davidsilver.uk/wp-content/uploads/2020/03/alphazero-science_compressed.pdf", "target": { "record_id": "urn:uuid:7ef427da-098f-4393-ac44-3da8589323f6", "version": 1, "content_hash": "sha256:352eeee897407dc7ba33ab86d89400def14fb57f8005fcddc63718cb52478678" }, "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION", "reviewed_on": "2026-09-26", "nationality_inferred": false, "sources": [ { "title": "Attribution source", "url": "https://www.davidsilver.uk/wp-content/uploads/2020/03/alphazero-science_compressed.pdf" } ], "coverage_status": "COMPLETE", "country_labels": { "GB": "United Kingdom" } }, "points": "230000", "published_grade": { "id": "alphazero-general-self-play-2018", "entry_id": "alphazero-general-self-play-2018", "band": "A", "modifier": "+", "target": { "record_id": "urn:uuid:7ef427da-098f-4393-ac44-3da8589323f6", "version": 1, "content_hash": "sha256:352eeee897407dc7ba33ab86d89400def14fb57f8005fcddc63718cb52478678" }, "what_changed": "A shared learning-and-search recipe was demonstrated across three distinct board games.", "scope": "Exact 13-author 2018 Science paper and chess, shogi, Go evaluations; no domain-independent intelligence claim.", "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:7ef427da-098f-4393-ac44-3da8589323f6", "version": 1, "content_hash": "sha256:352eeee897407dc7ba33ab86d89400def14fb57f8005fcddc63718cb52478678" }, "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": "David Silver", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Matthew Lai", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Marc Lanctot", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dharshan Kumaran", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "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": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "PubMed record for AlphaZero Science paper", "url": "https://pubmed.ncbi.nlm.nih.gov/30523106/" } } ], "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 2018 Science paper and its three-game evaluations. AlphaGo, AlphaGo Zero, later MuZero systems, domain-independent intelligence claims and performance outside the reported game settings remain separate.", "domain": "Reinforcement learning" }, "sources": [ { "citation": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf" }, { "citation": "PubMed record for AlphaZero Science paper", "url": "https://pubmed.ncbi.nlm.nih.gov/30523106/" } ], "statement": "# Silver and colleagues: AlphaZero across chess, shogi and Go\n\nGeneralized self-play reinforcement learning and tree search into one algorithm evaluated across chess, shogi and Go, starting from random play with only the game rules supplied.\n\n## Scientific scope\n\nThe record is the exact 2018 Science paper and its three-game evaluations. AlphaGo, AlphaGo Zero, later MuZero systems, domain-independent intelligence claims and performance outside the reported game settings remain separate.\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\nDavid Silver; Thomas Hubert; Julian Schrittwieser; Ioannis Antonoglou; Matthew Lai; Arthur Guez; Marc Lanctot; Laurent Sifre; Dharshan Kumaran; Thore Graepel; Timothy Lillicrap; Karen Simonyan; Demis Hassabis\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- [Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play](https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf)\n- [PubMed record for AlphaZero Science paper](https://pubmed.ncbi.nlm.nih.gov/30523106/)\n", "summary": "Generalized self-play reinforcement learning and tree search into one algorithm evaluated across chess, shogi and Go, starting from random play with only the game rules supplied.", "title": "Silver and colleagues: AlphaZero across chess, shogi and Go" }, "record_id": "urn:uuid:7ef427da-098f-4393-ac44-3da8589323f6", "version": 1, "source_ref": { "record_id": "urn:uuid:7ef427da-098f-4393-ac44-3da8589323f6", "version": 1, "content_hash": "sha256:352eeee897407dc7ba33ab86d89400def14fb57f8005fcddc63718cb52478678" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:b2dda74485a6e2025db79aa141e25d562a9e521df7fc5be83b2cb6a631691032" }, "target": { "record_id": "urn:uuid:7ef427da-098f-4393-ac44-3da8589323f6", "version": 1, "content_hash": "sha256:352eeee897407dc7ba33ab86d89400def14fb57f8005fcddc63718cb52478678" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "alphazero-general-self-play-2018", "entry_id": "alphazero-general-self-play-2018", "revision": 1, "title": "Silver and colleagues: AlphaZero across chess, shogi and Go", "context": "Artificial intelligence", "track": "Reinforcement-learning algorithm", "band": "A", "modifier": "+", "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-09-25", "evidence_cutoff": "2026-09-25", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "A shared learning-and-search recipe was demonstrated across three distinct board games.", "scope": "Exact 13-author 2018 Science paper and chess, shogi, Go evaluations; no domain-independent intelligence claim.", "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact 2018 Science paper and its three-game evaluations. AlphaGo, AlphaGo Zero, later MuZero systems, domain-independent intelligence claims and performance outside the reported game settings remain separate.", "references": [ { "title": "Silver et al., A general reinforcement learning algorithm that masters chess, shogi and Go through self-play", "url": "https://discovery.ucl.ac.uk/10069050/1/alphazero_preprint.pdf", "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work." }, { "title": "PubMed record for AlphaZero Science paper", "url": "https://pubmed.ncbi.nlm.nih.gov/30523106/", "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:7ef427da-098f-4393-ac44-3da8589323f6", "version": 1, "content_hash": "sha256:352eeee897407dc7ba33ab86d89400def14fb57f8005fcddc63718cb52478678" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "230000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }