{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TCA272DRWXHQBXUB5FI7JOGO3N","short_pith_number":"pith:TCA272DR","schema_version":"1.0","canonical_sha256":"9881afe871b5cf00de81e951f4b8cedb529af468e09a9d174fcd9e51e4c47f69","source":{"kind":"arxiv","id":"2607.01525","version":1},"attestation_state":"computed","paper":{"title":"Mean Field Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA","math.PR"],"primary_cat":"math.OC","authors_text":"Mathieu Lauri\\`ere, Ren\\'e Carmona","submitted_at":"2026-07-01T22:44:24Z","abstract_excerpt":"This monograph provides an introduction to mean field reinforcement learning through the lens of Markov decision processes arising from large-population stochastic control with mean field interactions and common noise. Starting from the connection between multi-agent reinforcement learning and mean field control, it develops the probabilistic, mathematical, and control-theoretic framework needed to formulate representative-agent learning problems, analyze their relationship with finite-population systems, and study both general and linear-quadratic models. The presentation includes dynamic pro"},"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":"2607.01525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-07-01T22:44:24Z","cross_cats_sorted":["cs.LG","cs.MA","math.PR"],"title_canon_sha256":"6e3e58b5ea174a16db2162997c5291f3f819effdcf20b39363baf70651472ef2","abstract_canon_sha256":"b60c021a617a8c1af76d44842b85130e0bde433adad8c4947fb3ce446a22dce7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:17:03.134618Z","signature_b64":"2/pMN0Uk1LIJgJSJJRYj8Z9h6bdwyLPypXapLMsDgxMTAC33fpo7qDSexJALXTdoiRhMDVfJHe+JIv2DFWjzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9881afe871b5cf00de81e951f4b8cedb529af468e09a9d174fcd9e51e4c47f69","last_reissued_at":"2026-07-03T00:17:03.134209Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:17:03.134209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean Field Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA","math.PR"],"primary_cat":"math.OC","authors_text":"Mathieu Lauri\\`ere, Ren\\'e Carmona","submitted_at":"2026-07-01T22:44:24Z","abstract_excerpt":"This monograph provides an introduction to mean field reinforcement learning through the lens of Markov decision processes arising from large-population stochastic control with mean field interactions and common noise. Starting from the connection between multi-agent reinforcement learning and mean field control, it develops the probabilistic, mathematical, and control-theoretic framework needed to formulate representative-agent learning problems, analyze their relationship with finite-population systems, and study both general and linear-quadratic models. The presentation includes dynamic pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01525","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/2607.01525/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":"2607.01525","created_at":"2026-07-03T00:17:03.134268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01525v1","created_at":"2026-07-03T00:17:03.134268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01525","created_at":"2026-07-03T00:17:03.134268+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCA272DRWXHQ","created_at":"2026-07-03T00:17:03.134268+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCA272DRWXHQBXUB","created_at":"2026-07-03T00:17:03.134268+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCA272DR","created_at":"2026-07-03T00:17:03.134268+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/TCA272DRWXHQBXUB5FI7JOGO3N","json":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N.json","graph_json":"https://pith.science/api/pith-number/TCA272DRWXHQBXUB5FI7JOGO3N/graph.json","events_json":"https://pith.science/api/pith-number/TCA272DRWXHQBXUB5FI7JOGO3N/events.json","paper":"https://pith.science/paper/TCA272DR"},"agent_actions":{"view_html":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N","download_json":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N.json","view_paper":"https://pith.science/paper/TCA272DR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01525&json=true","fetch_graph":"https://pith.science/api/pith-number/TCA272DRWXHQBXUB5FI7JOGO3N/graph.json","fetch_events":"https://pith.science/api/pith-number/TCA272DRWXHQBXUB5FI7JOGO3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/action/storage_attestation","attest_author":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/action/author_attestation","sign_citation":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/action/citation_signature","submit_replication":"https://pith.science/pith/TCA272DRWXHQBXUB5FI7JOGO3N/action/replication_record"}},"created_at":"2026-07-03T00:17:03.134268+00:00","updated_at":"2026-07-03T00:17:03.134268+00:00"}