{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XSARQZM34HXDLRAHFUU4YEG6E3","short_pith_number":"pith:XSARQZM3","schema_version":"1.0","canonical_sha256":"bc8118659be1ee35c4072d29cc10de26e4ac0d7827b84a8857efef908004d851","source":{"kind":"arxiv","id":"2504.21326","version":1},"attestation_state":"computed","paper":{"title":"Q-function Decomposition with Intervention Semantics with Factored Action Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Debarun Bhattacharjya, Elliot Nelson, Junkyu Lee, Miao Liu, Songtao Lu, Tian Gao","submitted_at":"2025-04-30T05:26:51Z","abstract_excerpt":"Many practical reinforcement learning environments have a discrete factored action space that induces a large combinatorial set of actions, thereby posing significant challenges. Existing approaches leverage the regular structure of the action space and resort to a linear decomposition of Q-functions, which avoids enumerating all combinations of factored actions. In this paper, we consider Q-functions defined over a lower dimensional projected subspace of the original action space, and study the condition for the unbiasedness of decomposed Q-functions using causal effect estimation from the no"},"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":"2504.21326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T05:26:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c70854c3d0e1c3ea19e6fc5b0d14b10e83f1759dc8ba15b6ab0a2a4ae2bdc11c","abstract_canon_sha256":"5e912adec6eaaf92d16fb2bc22f5b9a8507b445cff5d54eae0a0a4d1b2babb45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:22.258339Z","signature_b64":"a/kE+S4ZnW+i2BbiHEZSbC5mHRji+IUpVIEDxqUSaX9G/2q8hS7tPmMhxQF5FktHk8uVNu/4zdx7bzYoa7C5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc8118659be1ee35c4072d29cc10de26e4ac0d7827b84a8857efef908004d851","last_reissued_at":"2026-07-05T10:56:22.257800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:22.257800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-function Decomposition with Intervention Semantics with Factored Action Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Debarun Bhattacharjya, Elliot Nelson, Junkyu Lee, Miao Liu, Songtao Lu, Tian Gao","submitted_at":"2025-04-30T05:26:51Z","abstract_excerpt":"Many practical reinforcement learning environments have a discrete factored action space that induces a large combinatorial set of actions, thereby posing significant challenges. Existing approaches leverage the regular structure of the action space and resort to a linear decomposition of Q-functions, which avoids enumerating all combinations of factored actions. In this paper, we consider Q-functions defined over a lower dimensional projected subspace of the original action space, and study the condition for the unbiasedness of decomposed Q-functions using causal effect estimation from the no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21326","kind":"arxiv","version":1},"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/2504.21326/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":"2504.21326","created_at":"2026-07-05T10:56:22.257856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21326v1","created_at":"2026-07-05T10:56:22.257856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21326","created_at":"2026-07-05T10:56:22.257856+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSARQZM34HXD","created_at":"2026-07-05T10:56:22.257856+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSARQZM34HXDLRAH","created_at":"2026-07-05T10:56:22.257856+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSARQZM3","created_at":"2026-07-05T10:56:22.257856+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/XSARQZM34HXDLRAHFUU4YEG6E3","json":"https://pith.science/pith/XSARQZM34HXDLRAHFUU4YEG6E3.json","graph_json":"https://pith.science/api/pith-number/XSARQZM34HXDLRAHFUU4YEG6E3/graph.json","events_json":"https://pith.science/api/pith-number/XSARQZM34HXDLRAHFUU4YEG6E3/events.json","paper":"https://pith.science/paper/XSARQZM3"},"agent_actions":{"view_html":"https://pith.science/pith/XSARQZM34HXDLRAHFUU4YEG6E3","download_json":"https://pith.science/pith/XSARQZM34HXDLRAHFUU4YEG6E3.json","view_paper":"https://pith.science/paper/XSARQZM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21326&json=true","fetch_graph":"https://pith.science/api/pith-number/XSARQZM34HXDLRAHFUU4YEG6E3/graph.json","fetch_events":"https://pith.science/api/pith-number/XSARQZM34HXDLRAHFUU4YEG6E3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSARQZM34HXDLRAHFUU4YEG6E3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSARQZM34HXDLRAHFUU4YEG6E3/action/storage_attestation","attest_author":"https://pith.science/pith/XSARQZM34HXDLRAHFUU4YEG6E3/action/author_attestation","sign_citation":"https://pith.science/pith/XSARQZM34HXDLRAHFUU4YEG6E3/action/citation_signature","submit_replication":"https://pith.science/pith/XSARQZM34HXDLRAHFUU4YEG6E3/action/replication_record"}},"created_at":"2026-07-05T10:56:22.257856+00:00","updated_at":"2026-07-05T10:56:22.257856+00:00"}