{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BCP7KPKSNWZCFHU7MV5NNDUUTE","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":"4952b1c75d08546b26f56747692d564b8ea46471624df424c95a048c4ba51def","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-05-27T10:01:52Z","title_canon_sha256":"fa86aa8aede4d054686838e5703b06a1ee6f6577f0cfc70db781758934939730"},"schema_version":"1.0","source":{"id":"2405.17017","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17017","created_at":"2026-07-05T08:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17017v3","created_at":"2026-07-05T08:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17017","created_at":"2026-07-05T08:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"BCP7KPKSNWZC","created_at":"2026-07-05T08:27:08Z"},{"alias_kind":"pith_short_16","alias_value":"BCP7KPKSNWZCFHU7","created_at":"2026-07-05T08:27:08Z"},{"alias_kind":"pith_short_8","alias_value":"BCP7KPKS","created_at":"2026-07-05T08:27:08Z"}],"graph_snapshots":[{"event_id":"sha256:cc84bdc5cfddc7ee7c17f8319a17af4a76587a285e8a3f9d24d6b86889844551","target":"graph","created_at":"2026-07-05T08:27:08Z","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/2405.17017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrea Angiuli, Jean-Pierre Fouque, Mathieu Lauri\\`ere, Mengrui Zhang","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-05-27T10:01:52Z","title":"Analysis of Multiscale Reinforcement Q-Learning Algorithms for Mean Field Control Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17017","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":"sha256:1f3b8cda657aa6500a3300aaf5b0fd0a3c1786bfe9a113652273c852f44fb43e","target":"record","created_at":"2026-07-05T08:27:08Z","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":"4952b1c75d08546b26f56747692d564b8ea46471624df424c95a048c4ba51def","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-05-27T10:01:52Z","title_canon_sha256":"fa86aa8aede4d054686838e5703b06a1ee6f6577f0cfc70db781758934939730"},"schema_version":"1.0","source":{"id":"2405.17017","kind":"arxiv","version":3}},"canonical_sha256":"089ff53d526db2229e9f657ad68e9499307954b613e485f81a369655a2c7faba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"089ff53d526db2229e9f657ad68e9499307954b613e485f81a369655a2c7faba","first_computed_at":"2026-07-05T08:27:08.714813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:08.714813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0F4DvTTmbklkhNe5nBHk3SEqhr3uXmlTL0lm/lx3DhsNTU/mFjKfKs70uGxhLkg4GL6Qw8jOsfNwtouS6/iLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:08.715229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17017","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f3b8cda657aa6500a3300aaf5b0fd0a3c1786bfe9a113652273c852f44fb43e","sha256:cc84bdc5cfddc7ee7c17f8319a17af4a76587a285e8a3f9d24d6b86889844551"],"state_sha256":"0fb6ce3ec3830e84342b615332a9e272a511c73bb30ee1de94c6a60bbf30c3f4"}