{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J74XVZNW7KVSYIMWWA7E5Q6K6V","short_pith_number":"pith:J74XVZNW","canonical_record":{"source":{"id":"1910.04295","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-09T23:19:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c95cb9f59160080d3d8c033af9badddc67b0b785390c6b410da9b6d6fc5a4046","abstract_canon_sha256":"526f5b138a1cc37eaa7fdefefd2558880b27a03029b106a33879922913619e40"},"schema_version":"1.0"},"canonical_sha256":"4ff97ae5b6faab2c2196b03e4ec3caf55554e91a0951ecb17dc5628e065b2b5d","source":{"kind":"arxiv","id":"1910.04295","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04295","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04295v2","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04295","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"pith_short_12","alias_value":"J74XVZNW7KVS","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"pith_short_16","alias_value":"J74XVZNW7KVSYIMW","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"pith_short_8","alias_value":"J74XVZNW","created_at":"2026-07-05T10:55:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J74XVZNW7KVSYIMWWA7E5Q6K6V","target":"record","payload":{"canonical_record":{"source":{"id":"1910.04295","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-09T23:19:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c95cb9f59160080d3d8c033af9badddc67b0b785390c6b410da9b6d6fc5a4046","abstract_canon_sha256":"526f5b138a1cc37eaa7fdefefd2558880b27a03029b106a33879922913619e40"},"schema_version":"1.0"},"canonical_sha256":"4ff97ae5b6faab2c2196b03e4ec3caf55554e91a0951ecb17dc5628e065b2b5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:14.350241Z","signature_b64":"C2P9ZxX0ffoc3pOOfVIRkxUkOw2Q8cjcm4COGMHbB+LX8cHdiM4UW2IXCleVfQJiqm0WXtywq2uVOzXQIeFjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ff97ae5b6faab2c2196b03e4ec3caf55554e91a0951ecb17dc5628e065b2b5d","last_reissued_at":"2026-07-05T10:55:14.349691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:14.349691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.04295","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:55:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZOCgpD5p/YZNgvH/7zwv4Ac5NZifv4NRsFk6K3dRPAuJLUv11asjdR9eV1RkfoDNEBR7WSApnoP9+hhRnv/NBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:56:14.081841Z"},"content_sha256":"9da9916978cc350a45c099b7a874c3a51ae1adea17d1cc67c5d79fd22164d2a6","schema_version":"1.0","event_id":"sha256:9da9916978cc350a45c099b7a874c3a51ae1adea17d1cc67c5d79fd22164d2a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J74XVZNW7KVSYIMWWA7E5Q6K6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Mathieu Lauri\\`ere, Ren\\'e Carmona, Zongjun Tan","submitted_at":"2019-10-09T23:19:39Z","abstract_excerpt":"We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots communicating through a central unit dispatching the optimal policy computed by maximizing an aggregate reward. An approximate solution is obtained by learning the optimal policy of a generic agent interacting with the statistical distribution of the states and actions of the other agents. We first provide a full analysis this discrete-time mean field control pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04295","kind":"arxiv","version":2},"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/1910.04295/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":"2026-07-05T10:55:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ZQY3upB4mD8OdUZs+iJ69MrxbBiCaS2I1x/jTGQzCZD5Ymi3zAKFwQYktkDUXcRDQdSd9vQzLKCjhC38OU8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:56:14.082369Z"},"content_sha256":"dc231a9837e46ec3c3c8baa53232df1c013ae391127b660a8d5c4f0ca14a41c2","schema_version":"1.0","event_id":"sha256:dc231a9837e46ec3c3c8baa53232df1c013ae391127b660a8d5c4f0ca14a41c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J74XVZNW7KVSYIMWWA7E5Q6K6V/bundle.json","state_url":"https://pith.science/pith/J74XVZNW7KVSYIMWWA7E5Q6K6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J74XVZNW7KVSYIMWWA7E5Q6K6V/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":"2026-08-19T04:56:14Z","links":{"resolver":"https://pith.science/pith/J74XVZNW7KVSYIMWWA7E5Q6K6V","bundle":"https://pith.science/pith/J74XVZNW7KVSYIMWWA7E5Q6K6V/bundle.json","state":"https://pith.science/pith/J74XVZNW7KVSYIMWWA7E5Q6K6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J74XVZNW7KVSYIMWWA7E5Q6K6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J74XVZNW7KVSYIMWWA7E5Q6K6V","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":"526f5b138a1cc37eaa7fdefefd2558880b27a03029b106a33879922913619e40","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-09T23:19:39Z","title_canon_sha256":"c95cb9f59160080d3d8c033af9badddc67b0b785390c6b410da9b6d6fc5a4046"},"schema_version":"1.0","source":{"id":"1910.04295","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04295","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04295v2","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04295","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"pith_short_12","alias_value":"J74XVZNW7KVS","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"pith_short_16","alias_value":"J74XVZNW7KVSYIMW","created_at":"2026-07-05T10:55:14Z"},{"alias_kind":"pith_short_8","alias_value":"J74XVZNW","created_at":"2026-07-05T10:55:14Z"}],"graph_snapshots":[{"event_id":"sha256:dc231a9837e46ec3c3c8baa53232df1c013ae391127b660a8d5c4f0ca14a41c2","target":"graph","created_at":"2026-07-05T10:55:14Z","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/1910.04295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots communicating through a central unit dispatching the optimal policy computed by maximizing an aggregate reward. An approximate solution is obtained by learning the optimal policy of a generic agent interacting with the statistical distribution of the states and actions of the other agents. We first provide a full analysis this discrete-time mean field control pro","authors_text":"Mathieu Lauri\\`ere, Ren\\'e Carmona, Zongjun Tan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-09T23:19:39Z","title":"Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04295","kind":"arxiv","version":2},"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":"sha256:9da9916978cc350a45c099b7a874c3a51ae1adea17d1cc67c5d79fd22164d2a6","target":"record","created_at":"2026-07-05T10:55:14Z","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":"526f5b138a1cc37eaa7fdefefd2558880b27a03029b106a33879922913619e40","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-09T23:19:39Z","title_canon_sha256":"c95cb9f59160080d3d8c033af9badddc67b0b785390c6b410da9b6d6fc5a4046"},"schema_version":"1.0","source":{"id":"1910.04295","kind":"arxiv","version":2}},"canonical_sha256":"4ff97ae5b6faab2c2196b03e4ec3caf55554e91a0951ecb17dc5628e065b2b5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ff97ae5b6faab2c2196b03e4ec3caf55554e91a0951ecb17dc5628e065b2b5d","first_computed_at":"2026-07-05T10:55:14.349691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:14.349691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C2P9ZxX0ffoc3pOOfVIRkxUkOw2Q8cjcm4COGMHbB+LX8cHdiM4UW2IXCleVfQJiqm0WXtywq2uVOzXQIeFjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:14.350241Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.04295","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9da9916978cc350a45c099b7a874c3a51ae1adea17d1cc67c5d79fd22164d2a6","sha256:dc231a9837e46ec3c3c8baa53232df1c013ae391127b660a8d5c4f0ca14a41c2"],"state_sha256":"4a3164e542f937dffa3332f440a5b229a147e3caf8714c8bb8c4f8679844a2d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/91BAdj7wDPqJZBcTs8SjTONRGbrazvH3rzysGljpe2C6LaT1h0bjN/oFLycRtvyRQ10p8E7ln7EsBI5zjx/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:56:14.088034Z","bundle_sha256":"294216c289a6e7d6c1cf98b14c406d3b61cc610cdfbc7ef89e172fa86f32f2da"}}