{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6EKVWULUOC6VBCV75MCVZ4H5K2","short_pith_number":"pith:6EKVWULU","schema_version":"1.0","canonical_sha256":"f1155b517470bd508abfeb055cf0fd568bc5cb30fe70c21d8cd23af2712b6d91","source":{"kind":"arxiv","id":"2003.12151","version":3},"attestation_state":"computed","paper":{"title":"Q-Learning in Regularized Mean-field Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi","submitted_at":"2020-03-24T12:50:48Z","abstract_excerpt":"In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algo"},"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":"2003.12151","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-24T12:50:48Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"e78aae9206280f4b006176e6b3e1a2b8fe94850b1b3f65ba77a959d57687bd2b","abstract_canon_sha256":"c5f54dc989fd9df5b2efe329fb08b2618f89a9af77973787b2625894e332370f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:54.366625Z","signature_b64":"icwSQMNeBG+GZz8IeOBK+Dnf1j1LBaOm/EJMrkwiEm+cezAUUas1ke4/7dzR2TC7Dm3udiBGtY3iUnGBqU0qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1155b517470bd508abfeb055cf0fd568bc5cb30fe70c21d8cd23af2712b6d91","last_reissued_at":"2026-07-05T05:14:54.366087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:54.366087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Learning in Regularized Mean-field Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi","submitted_at":"2020-03-24T12:50:48Z","abstract_excerpt":"In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12151","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/2003.12151/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":"2003.12151","created_at":"2026-07-05T05:14:54.366140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.12151v3","created_at":"2026-07-05T05:14:54.366140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12151","created_at":"2026-07-05T05:14:54.366140+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EKVWULUOC6V","created_at":"2026-07-05T05:14:54.366140+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EKVWULUOC6VBCV7","created_at":"2026-07-05T05:14:54.366140+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EKVWULU","created_at":"2026-07-05T05:14:54.366140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27378","citing_title":"Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2","json":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2.json","graph_json":"https://pith.science/api/pith-number/6EKVWULUOC6VBCV75MCVZ4H5K2/graph.json","events_json":"https://pith.science/api/pith-number/6EKVWULUOC6VBCV75MCVZ4H5K2/events.json","paper":"https://pith.science/paper/6EKVWULU"},"agent_actions":{"view_html":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2","download_json":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2.json","view_paper":"https://pith.science/paper/6EKVWULU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.12151&json=true","fetch_graph":"https://pith.science/api/pith-number/6EKVWULUOC6VBCV75MCVZ4H5K2/graph.json","fetch_events":"https://pith.science/api/pith-number/6EKVWULUOC6VBCV75MCVZ4H5K2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/action/storage_attestation","attest_author":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/action/author_attestation","sign_citation":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/action/citation_signature","submit_replication":"https://pith.science/pith/6EKVWULUOC6VBCV75MCVZ4H5K2/action/replication_record"}},"created_at":"2026-07-05T05:14:54.366140+00:00","updated_at":"2026-07-05T05:14:54.366140+00:00"}