{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "deep-q-network", "title": "Deep Q-networks for learning control from pixels", "summary": "A deep reinforcement-learning system learned action values from visual observations and rewards across a range of Atari games.", "boundary": "This entry credits the human development of a learning method. Performance varies by game; a game benchmark is not evidence of general scientific competence.", "area": "Reinforcement learning", "topic": "Computing & AI", "year": 2015, "lane": "HUMAN", "result": "ALGORITHM", "package_id": "deep-q-network", "target": { "record_id": "urn:uuid:fc3611d5-c9c7-4051-a005-599dde10647e", "version": 1, "content_hash": "sha256:944ce04e6155ead7850ef5be232630cfea8e210701ff7f9088d2b9b5ee804fc0" }, "humans": [ "Volodymyr Mnih", "Koray Kavukcuoglu", "David Silver", "Andrei A. Rusu", "Joel Veness", "Marc G. Bellemare", "Alex Graves", "Martin Riedmiller", "Andreas K. Fidjeland", "Georg Ostrovski", "Stig Petersen", "Charles Beattie", "Amir Sadik", "Ioannis Antonoglou", "Helen King", "Dharshan Kumaran", "Daan Wierstra", "Shane Legg", "Demis Hassabis" ], "authors_complete": true, "human_role_note": "Source paper byline retained, including repeated label positions. Names are not verified unique identities or measurements of individual effort.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "cov13-paper-deep-q-network", "title": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" }, { "id": "cov13-metadata-deep-q-network", "title": "Human-level control through deep reinforcement learning — deposited bibliography", "url": "https://api.crossref.org/works/10.1038%2Fnature14236" }, { "id": "cov13-reading-deep-q-network-0", "title": "DQN original paper and abstract", "url": "https://www.nature.com/articles/nature14236" } ], "geography": { "country_codes": [ "GB" ], "location_basis": "All nineteen authors share the paper affiliation at Google DeepMind, London, UK.", "source_url": "https://deepmind-media.storage.googleapis.com/dqn/DQNNaturePaper.pdf", "target": { "record_id": "urn:uuid:fc3611d5-c9c7-4051-a005-599dde10647e", "version": 1, "content_hash": "sha256:944ce04e6155ead7850ef5be232630cfea8e210701ff7f9088d2b9b5ee804fc0" }, "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION", "reviewed_on": "2026-09-27", "nationality_inferred": false, "sources": [ { "title": "Original paper: author affiliations", "url": "https://deepmind-media.storage.googleapis.com/dqn/DQNNaturePaper.pdf" } ], "coverage_status": "COMPLETE", "country_labels": { "GB": "United Kingdom" } }, "points": "40000", "published_grade": { "id": "deep-q-network", "entry_id": "deep-q-network", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:fc3611d5-c9c7-4051-a005-599dde10647e", "version": 1, "content_hash": "sha256:944ce04e6155ead7850ef5be232630cfea8e210701ff7f9088d2b9b5ee804fc0" }, "what_changed": "A deep reinforcement-learning system learned action values from visual observations and rewards across a range of Atari games.", "scope": "A deep reinforcement-learning system learned action values from visual observations and rewards across a range of Atari games. Scope limitation: This entry credits the human development of a learning method. Performance varies by game; a game benchmark is not evidence of general scientific competence.", "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:fc3611d5-c9c7-4051-a005-599dde10647e", "version": 1, "content_hash": "sha256:944ce04e6155ead7850ef5be232630cfea8e210701ff7f9088d2b9b5ee804fc0" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-09-13T00:00:00Z", "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": "Volodymyr Mnih", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Koray Kavukcuoglu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "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": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Andrei A. Rusu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Joel Veness", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Marc G. Bellemare", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Alex Graves", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Martin Riedmiller", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Andreas K. Fidjeland", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Georg Ostrovski", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Stig Petersen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Charles Beattie", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Amir Sadik", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "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": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Helen King", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "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": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Daan Wierstra", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Shane Legg", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "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": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "Human-level control through deep reinforcement learning — deposited bibliography", "url": "https://api.crossref.org/works/10.1038%2Fnature14236" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-2", "kind": "source_reference", "source": { "citation": "DQN original paper and abstract", "url": "https://www.nature.com/articles/nature14236" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "This entry credits the human development of a learning method. Performance varies by game; a game benchmark is not evidence of general scientific competence.", "domain": "Reinforcement learning" }, "sources": [ { "citation": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236" }, { "citation": "Human-level control through deep reinforcement learning — deposited bibliography", "url": "https://api.crossref.org/works/10.1038%2Fnature14236" }, { "citation": "DQN original paper and abstract", "url": "https://www.nature.com/articles/nature14236" } ], "statement": "# Deep Q-networks for learning control from pixels\n\nA deep reinforcement-learning system learned action values from visual observations and rewards across a range of Atari games.\n\n## Scientific scope\n\nThis entry credits the human development of a learning method. Performance varies by game; a game benchmark is not evidence of general scientific competence.\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\nVolodymyr Mnih; Koray Kavukcuoglu; David Silver; Andrei A. Rusu; Joel Veness; Marc G. Bellemare; Alex Graves; Martin Riedmiller; Andreas K. Fidjeland; Georg Ostrovski; Stig Petersen; Charles Beattie; Amir Sadik; Ioannis Antonoglou; Helen King; Dharshan Kumaran; Daan Wierstra; Shane Legg; Demis Hassabis\n\nSource paper byline retained, including repeated label positions. Names are not verified unique identities or measurements of individual effort.\n\n\n\n## Original sources\n\n- [Human-level control through deep reinforcement learning](https://doi.org/10.1038/nature14236)\n- [Human-level control through deep reinforcement learning — deposited bibliography](https://api.crossref.org/works/10.1038%2Fnature14236)\n- [DQN original paper and abstract](https://www.nature.com/articles/nature14236)\n", "summary": "A deep reinforcement-learning system learned action values from visual observations and rewards across a range of Atari games.", "title": "Deep Q-networks for learning control from pixels" }, "record_id": "urn:uuid:fc3611d5-c9c7-4051-a005-599dde10647e", "version": 1, "source_ref": { "record_id": "urn:uuid:fc3611d5-c9c7-4051-a005-599dde10647e", "version": 1, "content_hash": "sha256:944ce04e6155ead7850ef5be232630cfea8e210701ff7f9088d2b9b5ee804fc0" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:e0e290188643978f5a9e6d598a964e24e5d4a563783537aae2e59b1de721534b" }, "target": { "record_id": "urn:uuid:fc3611d5-c9c7-4051-a005-599dde10647e", "version": 1, "content_hash": "sha256:944ce04e6155ead7850ef5be232630cfea8e210701ff7f9088d2b9b5ee804fc0" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "deep-q-network", "entry_id": "deep-q-network", "revision": 1, "title": "Deep Q-networks for learning control from pixels", "context": "Reinforcement learning", "track": "Scoped scientific or research-capability contribution", "band": "A", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-09-14", "evidence_cutoff": "2026-09-14", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "A deep reinforcement-learning system learned action values from visual observations and rewards across a range of Atari games.", "scope": "A deep reinforcement-learning system learned action values from visual observations and rewards across a range of Atari games. Scope limitation: This entry credits the human development of a learning method. Performance varies by game; a game benchmark is not evidence of general scientific competence.", "evidence_summary": "Assessment uses the catalogue-linked source evidence for the stated contribution. This entry credits the human development of a learning method. Performance varies by game; a game benchmark is not evidence of general scientific competence.", "references": [ { "title": "Human-level control through deep reinforcement learning", "url": "https://doi.org/10.1038/nature14236", "locator": "Retained catalogue source evidence; See the linked reading source and editorial batch for the scope reviewed; not a full-paper audit." }, { "title": "Human-level control through deep reinforcement learning — deposited bibliography", "url": "https://api.crossref.org/works/10.1038%2Fnature14236", "locator": "Retained catalogue source evidence; Exact DOI identity, deposited byline and supplied abstract; source bytes retained locally." }, { "title": "DQN original paper and abstract", "url": "https://www.nature.com/articles/nature14236", "locator": "Retained catalogue source evidence; Source support for the stated contribution and boundary. Full-paper review, independent replay and current clinical advice are not claimed." } ], "roles": [ { "who": "The research collaboration listed in the linked record and source byline", "credit": "SCIENCE", "did": "Collective scoped contribution. The complete recorded byline remains in the research record; this label does not collapse people into one individual." } ], "target": { "record_id": "urn:uuid:fc3611d5-c9c7-4051-a005-599dde10647e", "version": 1, "content_hash": "sha256:944ce04e6155ead7850ef5be232630cfea8e210701ff7f9088d2b9b5ee804fc0" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "40000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }