{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HFQM5I4MP2ZHNNOB7PULJ5M3MS","short_pith_number":"pith:HFQM5I4M","schema_version":"1.0","canonical_sha256":"3960cea38c7eb276b5c1fbe8b4f59b64bd382bfb8748db4e9b83d11a15433ddb","source":{"kind":"arxiv","id":"2505.22781","version":1},"attestation_state":"computed","paper":{"title":"Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Antonio Ocello, Daniil Tiapkin, Eric Moulines, Lorenzo Mancini, Mathieu Lauri\\`ere","submitted_at":"2025-05-28T18:50:25Z","abstract_excerpt":"We introduce Mean-Field Trust Region Policy Optimization (MF-TRPO), a novel algorithm designed to compute approximate Nash equilibria for ergodic Mean-Field Games (MFG) in finite state-action spaces. Building on the well-established performance of TRPO in the reinforcement learning (RL) setting, we extend its methodology to the MFG framework, leveraging its stability and robustness in policy optimization. Under standard assumptions in the MFG literature, we provide a rigorous analysis of MF-TRPO, establishing theoretical guarantees on its convergence. Our results cover both the exact formulati"},"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":"2505.22781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-28T18:50:25Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"4db9fd7e2f164d7147b73b85966c37049952ff6dfac6a36fcd36e3c51926b374","abstract_canon_sha256":"831f665f66aaf99ff86568ea1e6a1b98aa61a3fc99dfde5af7021a7ae14efd28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:49.892701Z","signature_b64":"dRVWO6847p1d2PhvF3+7QooXYJLUch1oU1e7YPS00FrmKGyieDMrwSnXhmNTPgwBf+I0aXaY/YoicmMwT+ibCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3960cea38c7eb276b5c1fbe8b4f59b64bd382bfb8748db4e9b83d11a15433ddb","last_reissued_at":"2026-07-05T11:11:49.892235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:49.892235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Antonio Ocello, Daniil Tiapkin, Eric Moulines, Lorenzo Mancini, Mathieu Lauri\\`ere","submitted_at":"2025-05-28T18:50:25Z","abstract_excerpt":"We introduce Mean-Field Trust Region Policy Optimization (MF-TRPO), a novel algorithm designed to compute approximate Nash equilibria for ergodic Mean-Field Games (MFG) in finite state-action spaces. Building on the well-established performance of TRPO in the reinforcement learning (RL) setting, we extend its methodology to the MFG framework, leveraging its stability and robustness in policy optimization. Under standard assumptions in the MFG literature, we provide a rigorous analysis of MF-TRPO, establishing theoretical guarantees on its convergence. Our results cover both the exact formulati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22781","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/2505.22781/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":"2505.22781","created_at":"2026-07-05T11:11:49.892294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22781v1","created_at":"2026-07-05T11:11:49.892294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22781","created_at":"2026-07-05T11:11:49.892294+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFQM5I4MP2ZH","created_at":"2026-07-05T11:11:49.892294+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFQM5I4MP2ZHNNOB","created_at":"2026-07-05T11:11:49.892294+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFQM5I4M","created_at":"2026-07-05T11:11:49.892294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11042","citing_title":"Towards Model-Free Learning in Dynamic Population Games: An Application to Karma Economies","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS","json":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS.json","graph_json":"https://pith.science/api/pith-number/HFQM5I4MP2ZHNNOB7PULJ5M3MS/graph.json","events_json":"https://pith.science/api/pith-number/HFQM5I4MP2ZHNNOB7PULJ5M3MS/events.json","paper":"https://pith.science/paper/HFQM5I4M"},"agent_actions":{"view_html":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS","download_json":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS.json","view_paper":"https://pith.science/paper/HFQM5I4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22781&json=true","fetch_graph":"https://pith.science/api/pith-number/HFQM5I4MP2ZHNNOB7PULJ5M3MS/graph.json","fetch_events":"https://pith.science/api/pith-number/HFQM5I4MP2ZHNNOB7PULJ5M3MS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS/action/storage_attestation","attest_author":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS/action/author_attestation","sign_citation":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS/action/citation_signature","submit_replication":"https://pith.science/pith/HFQM5I4MP2ZHNNOB7PULJ5M3MS/action/replication_record"}},"created_at":"2026-07-05T11:11:49.892294+00:00","updated_at":"2026-07-05T11:11:49.892294+00:00"}