{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q72GTGCFF35CGAFWVZ7MAVTLVT","short_pith_number":"pith:Q72GTGCF","schema_version":"1.0","canonical_sha256":"87f46998452efa2300b6ae7ec0566bacfd7a80daaf92f86abce24cc12db7b621","source":{"kind":"arxiv","id":"2102.10362","version":3},"attestation_state":"computed","paper":{"title":"Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nelson Vadori, Sumitra Ganesh, Thomas Spooner","submitted_at":"2021-02-20T14:51:12Z","abstract_excerpt":"Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales quadratically. In this paper, we address this problem through a factor baseline which exploits independence structure encoded in a novel action-target influence network. Factored policy gradients (FPGs), which follow, provide a common framework for analysing key state-of-the-art algorithms, are shown to generalise traditional policy gradients, and yield a princip"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.10362","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T14:51:12Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"fba46a29f71819cecfd49b64504a68a64ee12091bcb03372b1cfadd458994e59","abstract_canon_sha256":"8fd4f9152d05d73adfeb8c53b7940afd6c6ae2844f12e8b1373fe7ff8a87878c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:05.703588Z","signature_b64":"t3M1/OKboK76YG9jYX1Lyst/B/aUCGyWRYChX72pI7qDUbsq+vkw9rt1RJZe3D7Ct4WOIjTfknbx1UPQkxucDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87f46998452efa2300b6ae7ec0566bacfd7a80daaf92f86abce24cc12db7b621","last_reissued_at":"2026-07-05T03:34:05.703076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:05.703076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nelson Vadori, Sumitra Ganesh, Thomas Spooner","submitted_at":"2021-02-20T14:51:12Z","abstract_excerpt":"Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales quadratically. In this paper, we address this problem through a factor baseline which exploits independence structure encoded in a novel action-target influence network. Factored policy gradients (FPGs), which follow, provide a common framework for analysing key state-of-the-art algorithms, are shown to generalise traditional policy gradients, and yield a princip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10362","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.10362/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.10362","created_at":"2026-07-05T03:34:05.703140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10362v3","created_at":"2026-07-05T03:34:05.703140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10362","created_at":"2026-07-05T03:34:05.703140+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q72GTGCFF35C","created_at":"2026-07-05T03:34:05.703140+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q72GTGCFF35CGAFW","created_at":"2026-07-05T03:34:05.703140+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q72GTGCF","created_at":"2026-07-05T03:34:05.703140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT","json":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT.json","graph_json":"https://pith.science/api/pith-number/Q72GTGCFF35CGAFWVZ7MAVTLVT/graph.json","events_json":"https://pith.science/api/pith-number/Q72GTGCFF35CGAFWVZ7MAVTLVT/events.json","paper":"https://pith.science/paper/Q72GTGCF"},"agent_actions":{"view_html":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT","download_json":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT.json","view_paper":"https://pith.science/paper/Q72GTGCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10362&json=true","fetch_graph":"https://pith.science/api/pith-number/Q72GTGCFF35CGAFWVZ7MAVTLVT/graph.json","fetch_events":"https://pith.science/api/pith-number/Q72GTGCFF35CGAFWVZ7MAVTLVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT/action/storage_attestation","attest_author":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT/action/author_attestation","sign_citation":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT/action/citation_signature","submit_replication":"https://pith.science/pith/Q72GTGCFF35CGAFWVZ7MAVTLVT/action/replication_record"}},"created_at":"2026-07-05T03:34:05.703140+00:00","updated_at":"2026-07-05T03:34:05.703140+00:00"}