{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BCP7KPKSNWZCFHU7MV5NNDUUTE","short_pith_number":"pith:BCP7KPKS","schema_version":"1.0","canonical_sha256":"089ff53d526db2229e9f657ad68e9499307954b613e485f81a369655a2c7faba","source":{"kind":"arxiv","id":"2405.17017","version":3},"attestation_state":"computed","paper":{"title":"Analysis of Multiscale Reinforcement Q-Learning Algorithms for Mean Field Control Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"math.OC","authors_text":"Andrea Angiuli, Jean-Pierre Fouque, Mathieu Lauri\\`ere, Mengrui Zhang","submitted_at":"2024-05-27T10:01:52Z","abstract_excerpt":"Mean Field Control Games (MFCG), introduced in [Angiuli et al., 2022a], represent competitive games between a large number of large collaborative groups of agents in the infinite limit of number and size of groups. In this paper, we prove the convergence of a three-timescale Reinforcement Q-Learning (RL) algorithm to solve MFCG in a model-free approach from the point of view of representative agents. Our analysis uses a Q-table for finite state and action spaces updated at each discrete time-step over an infinite horizon. In [Angiuli et al., 2023], we proved convergence of two-timescale algori"},"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":"2405.17017","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-05-27T10:01:52Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"fa86aa8aede4d054686838e5703b06a1ee6f6577f0cfc70db781758934939730","abstract_canon_sha256":"4952b1c75d08546b26f56747692d564b8ea46471624df424c95a048c4ba51def"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:08.715229Z","signature_b64":"0F4DvTTmbklkhNe5nBHk3SEqhr3uXmlTL0lm/lx3DhsNTU/mFjKfKs70uGxhLkg4GL6Qw8jOsfNwtouS6/iLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"089ff53d526db2229e9f657ad68e9499307954b613e485f81a369655a2c7faba","last_reissued_at":"2026-07-05T08:27:08.714813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:08.714813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of Multiscale Reinforcement Q-Learning Algorithms for Mean Field Control Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"math.OC","authors_text":"Andrea Angiuli, Jean-Pierre Fouque, Mathieu Lauri\\`ere, Mengrui Zhang","submitted_at":"2024-05-27T10:01:52Z","abstract_excerpt":"Mean Field Control Games (MFCG), introduced in [Angiuli et al., 2022a], represent competitive games between a large number of large collaborative groups of agents in the infinite limit of number and size of groups. In this paper, we prove the convergence of a three-timescale Reinforcement Q-Learning (RL) algorithm to solve MFCG in a model-free approach from the point of view of representative agents. Our analysis uses a Q-table for finite state and action spaces updated at each discrete time-step over an infinite horizon. In [Angiuli et al., 2023], we proved convergence of two-timescale algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17017","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/2405.17017/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":"2405.17017","created_at":"2026-07-05T08:27:08.714870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17017v3","created_at":"2026-07-05T08:27:08.714870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17017","created_at":"2026-07-05T08:27:08.714870+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCP7KPKSNWZC","created_at":"2026-07-05T08:27:08.714870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCP7KPKSNWZCFHU7","created_at":"2026-07-05T08:27:08.714870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCP7KPKS","created_at":"2026-07-05T08:27:08.714870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE","json":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE.json","graph_json":"https://pith.science/api/pith-number/BCP7KPKSNWZCFHU7MV5NNDUUTE/graph.json","events_json":"https://pith.science/api/pith-number/BCP7KPKSNWZCFHU7MV5NNDUUTE/events.json","paper":"https://pith.science/paper/BCP7KPKS"},"agent_actions":{"view_html":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE","download_json":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE.json","view_paper":"https://pith.science/paper/BCP7KPKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17017&json=true","fetch_graph":"https://pith.science/api/pith-number/BCP7KPKSNWZCFHU7MV5NNDUUTE/graph.json","fetch_events":"https://pith.science/api/pith-number/BCP7KPKSNWZCFHU7MV5NNDUUTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE/action/storage_attestation","attest_author":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE/action/author_attestation","sign_citation":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE/action/citation_signature","submit_replication":"https://pith.science/pith/BCP7KPKSNWZCFHU7MV5NNDUUTE/action/replication_record"}},"created_at":"2026-07-05T08:27:08.714870+00:00","updated_at":"2026-07-05T08:27:08.714870+00:00"}