{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "mnih-et-al-a3c-asynchronous-actor-learners-2016",
    "title": "A3C and asynchronous neural actor-learners",
    "summary": "Ran parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer.",
    "boundary": "The method builds on actor-critic learning, temporal-difference updates and distributed computation. Reported CPU-training, game and control gains apply to the tested configurations; they are not a global convergence guarantee for arbitrary nonlinear policies.",
    "area": "Deep reinforcement-learning training",
    "topic": "Artificial intelligence",
    "year": 2016,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "mnih-et-al-a3c-asynchronous-actor-learners-2016",
    "target": {
      "record_id": "urn:uuid:c6e53dec-39ce-418e-ace1-ada63144a727",
      "version": 1,
      "content_hash": "sha256:387cf81fe52216e26d06551eea6d5ea04a3c269cf6bc8980eaa3337877277463"
    },
    "humans": [
      "Volodymyr Mnih",
      "Adrià Puigdomènech Badia",
      "Mehdi Mirza",
      "Alex Graves",
      "Tim Harley",
      "Timothy P. Lillicrap",
      "David Silver",
      "Koray Kavukcuoglu"
    ],
    "authors_complete": true,
    "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "cur20261015-arxiv-1602-01783v1",
        "title": "Asynchronous Methods for Deep Reinforcement Learning",
        "url": "https://arxiv.org/abs/1602.01783v1"
      }
    ],
    "points": "170000",
    "published_grade": {
      "id": "mnih-et-al-a3c-asynchronous-actor-learners-2016",
      "entry_id": "mnih-et-al-a3c-asynchronous-actor-learners-2016",
      "band": "A",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:c6e53dec-39ce-418e-ace1-ada63144a727",
        "version": 1,
        "content_hash": "sha256:387cf81fe52216e26d06551eea6d5ea04a3c269cf6bc8980eaa3337877277463"
      },
      "what_changed": "Ran parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer.",
      "scope": "Ran parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer. The method builds on actor-critic learning, temporal-difference updates and distributed computation. Reported CPU-training, game and control gains apply to the tested configurations; they are not a global convergence guarantee for arbitrary nonlinear policies.",
      "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:c6e53dec-39ce-418e-ace1-ada63144a727",
        "version": 1,
        "content_hash": "sha256:387cf81fe52216e26d06551eea6d5ea04a3c269cf6bc8980eaa3337877277463"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-10-16T00:00:00Z",
    "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": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Adrià Puigdomènech Badia",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Mehdi Mirza",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        },
        {
          "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": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Tim Harley",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Timothy P. Lillicrap",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        },
        {
          "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": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        },
        {
          "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": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Asynchronous Methods for Deep Reinforcement Learning",
            "url": "https://arxiv.org/abs/1602.01783v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "The method builds on actor-critic learning, temporal-difference updates and distributed computation. Reported CPU-training, game and control gains apply to the tested configurations; they are not a global convergence guarantee for arbitrary nonlinear policies.",
        "domain": "Deep reinforcement-learning training"
      },
      "sources": [
        {
          "citation": "Asynchronous Methods for Deep Reinforcement Learning",
          "url": "https://arxiv.org/abs/1602.01783v1"
        }
      ],
      "statement": "# A3C and asynchronous neural actor-learners\n\nRan parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer.\n\n## Scientific scope\n\nThe method builds on actor-critic learning, temporal-difference updates and distributed computation. Reported CPU-training, game and control gains apply to the tested configurations; they are not a global convergence guarantee for arbitrary nonlinear policies.\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; Adrià Puigdomènech Badia; Mehdi Mirza; Alex Graves; Tim Harley; Timothy P. Lillicrap; David Silver; Koray Kavukcuoglu\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [Asynchronous Methods for Deep Reinforcement Learning](https://arxiv.org/abs/1602.01783v1)\n",
      "summary": "Ran parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer.",
      "title": "A3C and asynchronous neural actor-learners"
    },
    "record_id": "urn:uuid:c6e53dec-39ce-418e-ace1-ada63144a727",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:c6e53dec-39ce-418e-ace1-ada63144a727",
      "version": 1,
      "content_hash": "sha256:387cf81fe52216e26d06551eea6d5ea04a3c269cf6bc8980eaa3337877277463"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:58b5c9029f046fe5eda9be19acdca6ba50c7365022efdd43d1cd92e746550b35"
  },
  "target": {
    "record_id": "urn:uuid:c6e53dec-39ce-418e-ace1-ada63144a727",
    "version": 1,
    "content_hash": "sha256:387cf81fe52216e26d06551eea6d5ea04a3c269cf6bc8980eaa3337877277463"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "mnih-et-al-a3c-asynchronous-actor-learners-2016",
    "entry_id": "mnih-et-al-a3c-asynchronous-actor-learners-2016",
    "revision": 1,
    "title": "A3C and asynchronous neural actor-learners",
    "context": "Deep reinforcement-learning training",
    "track": "Human-designed research method or resource",
    "band": "A",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Ran parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer.",
    "scope": "Ran parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer. The method builds on actor-critic learning, temporal-difference updates and distributed computation. Reported CPU-training, game and control gains apply to the tested configurations; they are not a global convergence guarantee for arbitrary nonlinear policies.",
    "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The method builds on actor-critic learning, temporal-difference updates and distributed computation. Reported CPU-training, game and control gains apply to the tested configurations; they are not a global convergence guarantee for arbitrary nonlinear policies.",
    "references": [
      {
        "title": "Asynchronous Methods for Deep Reinforcement Learning",
        "url": "https://arxiv.org/abs/1602.01783v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      }
    ],
    "roles": [
      {
        "who": "Source-listed authors and technical contributors",
        "credit": "SCIENCE",
        "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities."
      }
    ],
    "target": {
      "record_id": "urn:uuid:c6e53dec-39ce-418e-ace1-ada63144a727",
      "version": 1,
      "content_hash": "sha256:387cf81fe52216e26d06551eea6d5ea04a3c269cf6bc8980eaa3337877277463"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "170000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}