{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7B3VSIKTIQKWKW4S2LO67532VU","short_pith_number":"pith:7B3VSIKT","canonical_record":{"source":{"id":"2309.10953","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-09-19T22:37:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0bc0a00d77ae39466a5888dc62a5c1317be17ad0291bc4ee2efa6598b7ef3c40","abstract_canon_sha256":"2fe237464b06728ee8818be3752cef02cb9a00c4e1fcb97bd4fbf17f3ed94988"},"schema_version":"1.0"},"canonical_sha256":"f8775921534415655b92d2ddeff77aad1e6fd766bb11675001135976cf26b922","source":{"kind":"arxiv","id":"2309.10953","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10953","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10953v3","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10953","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"pith_short_12","alias_value":"7B3VSIKTIQKW","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"pith_short_16","alias_value":"7B3VSIKTIQKWKW4S","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"pith_short_8","alias_value":"7B3VSIKT","created_at":"2026-07-05T10:25:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7B3VSIKTIQKWKW4S2LO67532VU","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10953","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-09-19T22:37:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0bc0a00d77ae39466a5888dc62a5c1317be17ad0291bc4ee2efa6598b7ef3c40","abstract_canon_sha256":"2fe237464b06728ee8818be3752cef02cb9a00c4e1fcb97bd4fbf17f3ed94988"},"schema_version":"1.0"},"canonical_sha256":"f8775921534415655b92d2ddeff77aad1e6fd766bb11675001135976cf26b922","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:03.352621Z","signature_b64":"qc84y/oiUh3V4APa8X2CbvbK3MycC6Z8adfxuNJvXwYeYqlKqgY6UH2mjxBvHWB2UUd8+Yf7Xry3ZLGPdfXrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8775921534415655b92d2ddeff77aad1e6fd766bb11675001135976cf26b922","last_reissued_at":"2026-07-05T10:25:03.352118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:03.352118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10953","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:25:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03uSYl5u8RwQyJpzDTQkEX/omW6dfBaQgV/iT2FjH78ZLeqbk9lAP9TQ6W8GzvSa8wBzof4460WzFLHWumVgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:20:39.667108Z"},"content_sha256":"09eea0ec907499b2ff4c78880f02ed13ebbe679368e708de05737d7afdef249f","schema_version":"1.0","event_id":"sha256:09eea0ec907499b2ff4c78880f02ed13ebbe679368e708de05737d7afdef249f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7B3VSIKTIQKWKW4S2LO67532VU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Alan Raydan, Andrea Angiuli, Jean-Pierre Fouque, Ruimeng Hu","submitted_at":"2023-09-19T22:37:47Z","abstract_excerpt":"We present the development and analysis of a reinforcement learning (RL) algorithm designed to solve continuous-space mean field game (MFG) and mean field control (MFC) problems in a unified manner. The proposed approach pairs the actor-critic (AC) paradigm with a representation of the mean field distribution via a parameterized score function, which can be efficiently updated in an online fashion, and uses Langevin dynamics to obtain samples from the resulting distribution. The AC agent and the score function are updated iteratively to converge, either to the MFG equilibrium or the MFC optimu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10953","kind":"arxiv","version":3},"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/2309.10953/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:25:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ghE/ZYHIl42DSiex8ys+dqS5FijnqlXx+w6OnlkRipRkLClaFXQs+wUKPYzSjMLR2dpr+KI9/3LAh75L76WDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:20:39.667724Z"},"content_sha256":"c26e1238b157eb34e257272abe300d5bda01e6c7fbb6b9a8621ab8a00ea2e0e0","schema_version":"1.0","event_id":"sha256:c26e1238b157eb34e257272abe300d5bda01e6c7fbb6b9a8621ab8a00ea2e0e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7B3VSIKTIQKWKW4S2LO67532VU/bundle.json","state_url":"https://pith.science/pith/7B3VSIKTIQKWKW4S2LO67532VU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7B3VSIKTIQKWKW4S2LO67532VU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T16:20:39Z","links":{"resolver":"https://pith.science/pith/7B3VSIKTIQKWKW4S2LO67532VU","bundle":"https://pith.science/pith/7B3VSIKTIQKWKW4S2LO67532VU/bundle.json","state":"https://pith.science/pith/7B3VSIKTIQKWKW4S2LO67532VU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7B3VSIKTIQKWKW4S2LO67532VU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7B3VSIKTIQKWKW4S2LO67532VU","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":"2fe237464b06728ee8818be3752cef02cb9a00c4e1fcb97bd4fbf17f3ed94988","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-09-19T22:37:47Z","title_canon_sha256":"0bc0a00d77ae39466a5888dc62a5c1317be17ad0291bc4ee2efa6598b7ef3c40"},"schema_version":"1.0","source":{"id":"2309.10953","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10953","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10953v3","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10953","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"pith_short_12","alias_value":"7B3VSIKTIQKW","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"pith_short_16","alias_value":"7B3VSIKTIQKWKW4S","created_at":"2026-07-05T10:25:03Z"},{"alias_kind":"pith_short_8","alias_value":"7B3VSIKT","created_at":"2026-07-05T10:25:03Z"}],"graph_snapshots":[{"event_id":"sha256:c26e1238b157eb34e257272abe300d5bda01e6c7fbb6b9a8621ab8a00ea2e0e0","target":"graph","created_at":"2026-07-05T10:25:03Z","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/2309.10953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the development and analysis of a reinforcement learning (RL) algorithm designed to solve continuous-space mean field game (MFG) and mean field control (MFC) problems in a unified manner. The proposed approach pairs the actor-critic (AC) paradigm with a representation of the mean field distribution via a parameterized score function, which can be efficiently updated in an online fashion, and uses Langevin dynamics to obtain samples from the resulting distribution. The AC agent and the score function are updated iteratively to converge, either to the MFG equilibrium or the MFC optimu","authors_text":"Alan Raydan, Andrea Angiuli, Jean-Pierre Fouque, Ruimeng Hu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-09-19T22:37:47Z","title":"Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10953","kind":"arxiv","version":3},"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":"sha256:09eea0ec907499b2ff4c78880f02ed13ebbe679368e708de05737d7afdef249f","target":"record","created_at":"2026-07-05T10:25:03Z","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":"2fe237464b06728ee8818be3752cef02cb9a00c4e1fcb97bd4fbf17f3ed94988","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-09-19T22:37:47Z","title_canon_sha256":"0bc0a00d77ae39466a5888dc62a5c1317be17ad0291bc4ee2efa6598b7ef3c40"},"schema_version":"1.0","source":{"id":"2309.10953","kind":"arxiv","version":3}},"canonical_sha256":"f8775921534415655b92d2ddeff77aad1e6fd766bb11675001135976cf26b922","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8775921534415655b92d2ddeff77aad1e6fd766bb11675001135976cf26b922","first_computed_at":"2026-07-05T10:25:03.352118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:03.352118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qc84y/oiUh3V4APa8X2CbvbK3MycC6Z8adfxuNJvXwYeYqlKqgY6UH2mjxBvHWB2UUd8+Yf7Xry3ZLGPdfXrAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:03.352621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10953","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09eea0ec907499b2ff4c78880f02ed13ebbe679368e708de05737d7afdef249f","sha256:c26e1238b157eb34e257272abe300d5bda01e6c7fbb6b9a8621ab8a00ea2e0e0"],"state_sha256":"cdb18ae08af71143a220329f05aa46d18d2b418bbaeee6f43b388beaf27779dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tIjQXano3p/g9KYyFBCI8Yakp3jd11rjRfWTknFO1IeG4NqAljsCv80SKpsgAuTnsilt4X2+T+qZXK9O531MDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:20:39.671868Z","bundle_sha256":"6c9beabd07c29930a5bc558fe073b03c0f6458bb76c2d109ec4cbbb489224042"}}