{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Q72GTGCFF35CGAFWVZ7MAVTLVT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8fd4f9152d05d73adfeb8c53b7940afd6c6ae2844f12e8b1373fe7ff8a87878c","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T14:51:12Z","title_canon_sha256":"fba46a29f71819cecfd49b64504a68a64ee12091bcb03372b1cfadd458994e59"},"schema_version":"1.0","source":{"id":"2102.10362","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10362","created_at":"2026-07-05T03:34:05Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10362v3","created_at":"2026-07-05T03:34:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10362","created_at":"2026-07-05T03:34:05Z"},{"alias_kind":"pith_short_12","alias_value":"Q72GTGCFF35C","created_at":"2026-07-05T03:34:05Z"},{"alias_kind":"pith_short_16","alias_value":"Q72GTGCFF35CGAFW","created_at":"2026-07-05T03:34:05Z"},{"alias_kind":"pith_short_8","alias_value":"Q72GTGCF","created_at":"2026-07-05T03:34:05Z"}],"graph_snapshots":[{"event_id":"sha256:15f6cbf979c6a9c77bfc39fcb5d3f9cbf344bc9cb8c0c9303ed59a35f8fa04cb","target":"graph","created_at":"2026-07-05T03:34:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.10362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Nelson Vadori, Sumitra Ganesh, Thomas Spooner","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T14:51:12Z","title":"Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10362","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6f93b1cabe7999069a5e41c09a3e0fcd30ce4fa932eaf19e8da49c2bed774add","target":"record","created_at":"2026-07-05T03:34:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8fd4f9152d05d73adfeb8c53b7940afd6c6ae2844f12e8b1373fe7ff8a87878c","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T14:51:12Z","title_canon_sha256":"fba46a29f71819cecfd49b64504a68a64ee12091bcb03372b1cfadd458994e59"},"schema_version":"1.0","source":{"id":"2102.10362","kind":"arxiv","version":3}},"canonical_sha256":"87f46998452efa2300b6ae7ec0566bacfd7a80daaf92f86abce24cc12db7b621","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87f46998452efa2300b6ae7ec0566bacfd7a80daaf92f86abce24cc12db7b621","first_computed_at":"2026-07-05T03:34:05.703076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:34:05.703076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t3M1/OKboK76YG9jYX1Lyst/B/aUCGyWRYChX72pI7qDUbsq+vkw9rt1RJZe3D7Ct4WOIjTfknbx1UPQkxucDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:34:05.703588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10362","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f93b1cabe7999069a5e41c09a3e0fcd30ce4fa932eaf19e8da49c2bed774add","sha256:15f6cbf979c6a9c77bfc39fcb5d3f9cbf344bc9cb8c0c9303ed59a35f8fa04cb"],"state_sha256":"5e5f698d292bdaf79e83f7fe7eba7bc6b0119a2054a9dc3e6aeecf8637acd968"}