{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KRX7FTBPXCNNIW7UI4ND4TWV33","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":"8395c210f0f6b7dab2b60a795cd89e6ef4bd69f5ed0a0bc107ea6463e2c73930","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T14:16:34Z","title_canon_sha256":"cd17bfcc7146baf462f8e72e0ca00c02a2b6a0cdd8c7562b84b4b066bd82b769"},"schema_version":"1.0","source":{"id":"2410.17898","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17898","created_at":"2026-07-05T09:24:46Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17898v1","created_at":"2026-07-05T09:24:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17898","created_at":"2026-07-05T09:24:46Z"},{"alias_kind":"pith_short_12","alias_value":"KRX7FTBPXCNN","created_at":"2026-07-05T09:24:46Z"},{"alias_kind":"pith_short_16","alias_value":"KRX7FTBPXCNNIW7U","created_at":"2026-07-05T09:24:46Z"},{"alias_kind":"pith_short_8","alias_value":"KRX7FTBP","created_at":"2026-07-05T09:24:46Z"}],"graph_snapshots":[{"event_id":"sha256:e084501c0adb3bfdc512186a273681b540de2c6f1282194c28c1412279307061","target":"graph","created_at":"2026-07-05T09:24:46Z","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/2410.17898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms for mean-field games offer a scalable framework for optimizing policies in large populations of interacting agents. Existing methods often depend on online interactions or access to system dynamics, limiting their practicality in real-world scenarios where such interactions are infeasible or difficult to model. In this paper, we present Offline Munchausen Mirror Descent (Off-MMD), a novel mean-field RL algorithm that approximates equilibrium policies in mean-field games using purely offline data. By leveraging iterative mirror descent and importance sampling t","authors_text":"Axel Brunnbauer, Julian Lemmel, Radu Grosu, Sophie Neubauer, Zahra Babaiee","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T14:16:34Z","title":"Scalable Offline Reinforcement Learning for Mean Field Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17898","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":"sha256:67567fed889aabc7978ba9908122986f5d07b7eb9c537a9d44bbbb8ba7accf43","target":"record","created_at":"2026-07-05T09:24:46Z","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":"8395c210f0f6b7dab2b60a795cd89e6ef4bd69f5ed0a0bc107ea6463e2c73930","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T14:16:34Z","title_canon_sha256":"cd17bfcc7146baf462f8e72e0ca00c02a2b6a0cdd8c7562b84b4b066bd82b769"},"schema_version":"1.0","source":{"id":"2410.17898","kind":"arxiv","version":1}},"canonical_sha256":"546ff2cc2fb89ad45bf4471a3e4ed5dec23f866965b96ecbf28a0ea2768c0507","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"546ff2cc2fb89ad45bf4471a3e4ed5dec23f866965b96ecbf28a0ea2768c0507","first_computed_at":"2026-07-05T09:24:46.490495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:46.490495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qIKcRUwcg/kAujFWb0dnbqqEqGapWDlxQY7TUFyKv5NqEv1WO+/3i++znZlzKxlrtT9dXg+XXylgOrBPtSu9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:46.490940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17898","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67567fed889aabc7978ba9908122986f5d07b7eb9c537a9d44bbbb8ba7accf43","sha256:e084501c0adb3bfdc512186a273681b540de2c6f1282194c28c1412279307061"],"state_sha256":"397df236c64c20a2c4a25f9bac6e696e7597eb164e0edaa66275f1c3988df73f"}