{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N3CZULAX7N7N43GA3BWR4MWZON","short_pith_number":"pith:N3CZULAX","schema_version":"1.0","canonical_sha256":"6ec59a2c17fb7ede6cc0d86d1e32d97350d949e7453b68d326e6cc4854429126","source":{"kind":"arxiv","id":"2309.04317","version":1},"attestation_state":"computed","paper":{"title":"Actor critic learning algorithms for mean-field control with moment neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Huy\\^en Pham, Xavier Warin","submitted_at":"2023-09-08T13:29:57Z","abstract_excerpt":"We develop a new policy gradient and actor-critic algorithm for solving mean-field control problems within a continuous time reinforcement learning setting. Our approach leverages a gradient-based representation of the value function, employing parametrized randomized policies. The learning for both the actor (policy) and critic (value function) is facilitated by a class of moment neural network functions on the Wasserstein space of probability measures, and the key feature is to sample directly trajectories of distributions. A central challenge addressed in this study pertains to the computat"},"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":"2309.04317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-09-08T13:29:57Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"8579a426fcc8b88f7e9081a5db5436675c8aecdb3b1882c32217ce3237ab7243","abstract_canon_sha256":"e9566cc8f457f14f5232469dbce576c45551857712ac7d9da3da07857d50ca18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:58.150285Z","signature_b64":"EBxft8At5MOmhZZdS7ZCz5Hp6QXZv0fBdHYwwrxiDIlVO0zY3ZPLFd7Thmi2edUEbfoBKmdR2NJ6B/DZaTL0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec59a2c17fb7ede6cc0d86d1e32d97350d949e7453b68d326e6cc4854429126","last_reissued_at":"2026-07-05T06:48:58.149720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:58.149720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Actor critic learning algorithms for mean-field control with moment neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Huy\\^en Pham, Xavier Warin","submitted_at":"2023-09-08T13:29:57Z","abstract_excerpt":"We develop a new policy gradient and actor-critic algorithm for solving mean-field control problems within a continuous time reinforcement learning setting. Our approach leverages a gradient-based representation of the value function, employing parametrized randomized policies. The learning for both the actor (policy) and critic (value function) is facilitated by a class of moment neural network functions on the Wasserstein space of probability measures, and the key feature is to sample directly trajectories of distributions. A central challenge addressed in this study pertains to the computat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04317","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/2309.04317/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":"2309.04317","created_at":"2026-07-05T06:48:58.149789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04317v1","created_at":"2026-07-05T06:48:58.149789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04317","created_at":"2026-07-05T06:48:58.149789+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3CZULAX7N7N","created_at":"2026-07-05T06:48:58.149789+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3CZULAX7N7N43GA","created_at":"2026-07-05T06:48:58.149789+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3CZULAX","created_at":"2026-07-05T06:48:58.149789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27181","citing_title":"Numerical Approximation for Path-Dependent McKean-Vlasov Control with Non-Asymptotic Error Estimates","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06675","citing_title":"An Effective Particle Gradient Projection Method for Solving Stochastic and Mean Field Control Problem","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON","json":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON.json","graph_json":"https://pith.science/api/pith-number/N3CZULAX7N7N43GA3BWR4MWZON/graph.json","events_json":"https://pith.science/api/pith-number/N3CZULAX7N7N43GA3BWR4MWZON/events.json","paper":"https://pith.science/paper/N3CZULAX"},"agent_actions":{"view_html":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON","download_json":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON.json","view_paper":"https://pith.science/paper/N3CZULAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04317&json=true","fetch_graph":"https://pith.science/api/pith-number/N3CZULAX7N7N43GA3BWR4MWZON/graph.json","fetch_events":"https://pith.science/api/pith-number/N3CZULAX7N7N43GA3BWR4MWZON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON/action/storage_attestation","attest_author":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON/action/author_attestation","sign_citation":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON/action/citation_signature","submit_replication":"https://pith.science/pith/N3CZULAX7N7N43GA3BWR4MWZON/action/replication_record"}},"created_at":"2026-07-05T06:48:58.149789+00:00","updated_at":"2026-07-05T06:48:58.149789+00:00"}