{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LCFFQAKSRL4XI7YDLP72D2NZ7D","short_pith_number":"pith:LCFFQAKS","schema_version":"1.0","canonical_sha256":"588a5801528af9747f035bffa1e9b9f8c06eb06e4e6bc12b764ccf6c057250a2","source":{"kind":"arxiv","id":"2407.04521","version":2},"attestation_state":"computed","paper":{"title":"Unified continuous-time q-learning for mean-field game and mean-field control problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.CP"],"primary_cat":"math.OC","authors_text":"Fengyi Yuan, Xiang Yu, Xiaoli Wei","submitted_at":"2024-07-05T14:06:59Z","abstract_excerpt":"This paper studies the continuous-time q-learning in mean-field jump-diffusion models when the population distribution is not directly observable. We propose the integrated q-function in decoupled form (decoupled Iq-function) from the representative agent's perspective and establish its martingale characterization, which provides a unified policy evaluation rule for both mean-field game (MFG) and mean-field control (MFC) problems. Moreover, we consider the learning procedure where the representative agent updates the population distribution based on his own state values. Depending on the task "},"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":"2407.04521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-07-05T14:06:59Z","cross_cats_sorted":["cs.LG","q-fin.CP"],"title_canon_sha256":"1799f05ad60916078d6b384c2ffb58d7ce7a751179f3b1953d3d15fc99ab4f7b","abstract_canon_sha256":"59f6dd108cb657a3ef0e0da7f76a2e9944a660af49045866232f9675246032d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:26.226262Z","signature_b64":"IThJfYtjEFOHKq2SH1QujP2re87nAWOlZQW1AakCL+xcpxcZ/my8k25/rdvgPSeSij1JvDXp6bT/q4ScLpWbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"588a5801528af9747f035bffa1e9b9f8c06eb06e4e6bc12b764ccf6c057250a2","last_reissued_at":"2026-07-05T10:36:26.225774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:26.225774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified continuous-time q-learning for mean-field game and mean-field control problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-fin.CP"],"primary_cat":"math.OC","authors_text":"Fengyi Yuan, Xiang Yu, Xiaoli Wei","submitted_at":"2024-07-05T14:06:59Z","abstract_excerpt":"This paper studies the continuous-time q-learning in mean-field jump-diffusion models when the population distribution is not directly observable. We propose the integrated q-function in decoupled form (decoupled Iq-function) from the representative agent's perspective and establish its martingale characterization, which provides a unified policy evaluation rule for both mean-field game (MFG) and mean-field control (MFC) problems. Moreover, we consider the learning procedure where the representative agent updates the population distribution based on his own state values. Depending on the task "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04521","kind":"arxiv","version":2},"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/2407.04521/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":"2407.04521","created_at":"2026-07-05T10:36:26.225831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04521v2","created_at":"2026-07-05T10:36:26.225831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04521","created_at":"2026-07-05T10:36:26.225831+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCFFQAKSRL4X","created_at":"2026-07-05T10:36:26.225831+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCFFQAKSRL4XI7YD","created_at":"2026-07-05T10:36:26.225831+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCFFQAKS","created_at":"2026-07-05T10:36:26.225831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.20356","citing_title":"Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise","ref_index":88,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20718","citing_title":"Policy Gradient for Continuous-Time Mean-Field Control","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27378","citing_title":"Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27372","citing_title":"Continuous-time q-learning for mean-field control with common noise, part-I: Theoretical foundations","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D","json":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D.json","graph_json":"https://pith.science/api/pith-number/LCFFQAKSRL4XI7YDLP72D2NZ7D/graph.json","events_json":"https://pith.science/api/pith-number/LCFFQAKSRL4XI7YDLP72D2NZ7D/events.json","paper":"https://pith.science/paper/LCFFQAKS"},"agent_actions":{"view_html":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D","download_json":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D.json","view_paper":"https://pith.science/paper/LCFFQAKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04521&json=true","fetch_graph":"https://pith.science/api/pith-number/LCFFQAKSRL4XI7YDLP72D2NZ7D/graph.json","fetch_events":"https://pith.science/api/pith-number/LCFFQAKSRL4XI7YDLP72D2NZ7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D/action/storage_attestation","attest_author":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D/action/author_attestation","sign_citation":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D/action/citation_signature","submit_replication":"https://pith.science/pith/LCFFQAKSRL4XI7YDLP72D2NZ7D/action/replication_record"}},"created_at":"2026-07-05T10:36:26.225831+00:00","updated_at":"2026-07-05T10:36:26.225831+00:00"}