{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:N3CZULAX7N7N43GA3BWR4MWZON","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e9566cc8f457f14f5232469dbce576c45551857712ac7d9da3da07857d50ca18","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-09-08T13:29:57Z","title_canon_sha256":"8579a426fcc8b88f7e9081a5db5436675c8aecdb3b1882c32217ce3237ab7243"},"schema_version":"1.0","source":{"id":"2309.04317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04317","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04317v1","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04317","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"N3CZULAX7N7N","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"pith_short_16","alias_value":"N3CZULAX7N7N43GA","created_at":"2026-07-05T06:48:58Z"},{"alias_kind":"pith_short_8","alias_value":"N3CZULAX","created_at":"2026-07-05T06:48:58Z"}],"graph_snapshots":[{"event_id":"sha256:ccda43d60e1d292e15444917134067b96ca8dbe01b26bebcfcde0df4a3ae32a5","target":"graph","created_at":"2026-07-05T06:48:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.04317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huy\\^en Pham, Xavier Warin","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-09-08T13:29:57Z","title":"Actor critic learning algorithms for mean-field control with moment neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04317","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b567b66a583b2fb3233a95fcc3fb43afd8f818fd4c488c91de3f2ae9003c4b96","target":"record","created_at":"2026-07-05T06:48:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e9566cc8f457f14f5232469dbce576c45551857712ac7d9da3da07857d50ca18","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-09-08T13:29:57Z","title_canon_sha256":"8579a426fcc8b88f7e9081a5db5436675c8aecdb3b1882c32217ce3237ab7243"},"schema_version":"1.0","source":{"id":"2309.04317","kind":"arxiv","version":1}},"canonical_sha256":"6ec59a2c17fb7ede6cc0d86d1e32d97350d949e7453b68d326e6cc4854429126","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ec59a2c17fb7ede6cc0d86d1e32d97350d949e7453b68d326e6cc4854429126","first_computed_at":"2026-07-05T06:48:58.149720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:58.149720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EBxft8At5MOmhZZdS7ZCz5Hp6QXZv0fBdHYwwrxiDIlVO0zY3ZPLFd7Thmi2edUEbfoBKmdR2NJ6B/DZaTL0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:58.150285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b567b66a583b2fb3233a95fcc3fb43afd8f818fd4c488c91de3f2ae9003c4b96","sha256:ccda43d60e1d292e15444917134067b96ca8dbe01b26bebcfcde0df4a3ae32a5"],"state_sha256":"86d9f2f1e7f7379c7bc4506c1379a8c04a426f70fefc7fb742338e8864b94522"}