{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZTM4EVFXJFNXNNDOF2SUEJB54F","short_pith_number":"pith:ZTM4EVFX","schema_version":"1.0","canonical_sha256":"ccd9c254b7495b76b46e2ea542243de1538af45d6000cfddc3d6bcc8447574ed","source":{"kind":"arxiv","id":"2408.02489","version":1},"attestation_state":"computed","paper":{"title":"Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Huy\\^en Pham (LPSM (UMR\\_8001)), Noufel Frikha (CES), Xuanye Song (LPSM (UMR\\_8001))","submitted_at":"2024-08-05T14:11:51Z","abstract_excerpt":"We consider reinforcement learning (RL) methods for finding optimal policies in linear quadratic (LQ) mean field control (MFC) problems over an infinite horizon in continuous time, with common noise and entropy regularization. We study policy gradient (PG) learning and first demonstrate convergence in a model-based setting by establishing a suitable gradient domination condition.Next, our main contribution is a comprehensive error analysis, where we prove the global linear convergence and sample complexity of the PG algorithm with two-point gradient estimates in a model-free setting with unkno"},"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":"2408.02489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-08-05T14:11:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5f2932043f022097b624e7c3c90b14cb92e99b361fd86b110eeea2056190e213","abstract_canon_sha256":"8130c6f912264bc134db1555c3e5906c2d46f22ae2506d6a53975ac9e7bc81ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:13.478614Z","signature_b64":"5R4XrnLMk1ipmjYwSpS/wV/K6K555L3Yo6JkhkU5v5XlTSbMlx+aogOPc5yhhw14dlMpkfbEWNqTdSiH/8a4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccd9c254b7495b76b46e2ea542243de1538af45d6000cfddc3d6bcc8447574ed","last_reissued_at":"2026-07-05T08:52:13.478079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:13.478079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Huy\\^en Pham (LPSM (UMR\\_8001)), Noufel Frikha (CES), Xuanye Song (LPSM (UMR\\_8001))","submitted_at":"2024-08-05T14:11:51Z","abstract_excerpt":"We consider reinforcement learning (RL) methods for finding optimal policies in linear quadratic (LQ) mean field control (MFC) problems over an infinite horizon in continuous time, with common noise and entropy regularization. We study policy gradient (PG) learning and first demonstrate convergence in a model-based setting by establishing a suitable gradient domination condition.Next, our main contribution is a comprehensive error analysis, where we prove the global linear convergence and sample complexity of the PG algorithm with two-point gradient estimates in a model-free setting with unkno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02489","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/2408.02489/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":"2408.02489","created_at":"2026-07-05T08:52:13.478137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02489v1","created_at":"2026-07-05T08:52:13.478137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02489","created_at":"2026-07-05T08:52:13.478137+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTM4EVFXJFNX","created_at":"2026-07-05T08:52:13.478137+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTM4EVFXJFNXNNDO","created_at":"2026-07-05T08:52:13.478137+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTM4EVFX","created_at":"2026-07-05T08:52:13.478137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26498","citing_title":"Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01525","citing_title":"Mean Field Reinforcement Learning","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20718","citing_title":"Policy Gradient for Continuous-Time Mean-Field Control","ref_index":38,"is_internal_anchor":false},{"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":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F","json":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F.json","graph_json":"https://pith.science/api/pith-number/ZTM4EVFXJFNXNNDOF2SUEJB54F/graph.json","events_json":"https://pith.science/api/pith-number/ZTM4EVFXJFNXNNDOF2SUEJB54F/events.json","paper":"https://pith.science/paper/ZTM4EVFX"},"agent_actions":{"view_html":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F","download_json":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F.json","view_paper":"https://pith.science/paper/ZTM4EVFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02489&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTM4EVFXJFNXNNDOF2SUEJB54F/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTM4EVFXJFNXNNDOF2SUEJB54F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F/action/storage_attestation","attest_author":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F/action/author_attestation","sign_citation":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F/action/citation_signature","submit_replication":"https://pith.science/pith/ZTM4EVFXJFNXNNDOF2SUEJB54F/action/replication_record"}},"created_at":"2026-07-05T08:52:13.478137+00:00","updated_at":"2026-07-05T08:52:13.478137+00:00"}