{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:63REFNXYLAPRAKNG66BCQMPRTI","short_pith_number":"pith:63REFNXY","schema_version":"1.0","canonical_sha256":"f6e242b6f8581f1029a6f7822831f19a376716b4b9d5d3b34791334c21d744a4","source":{"kind":"arxiv","id":"2309.16819","version":1},"attestation_state":"computed","paper":{"title":"Multi-Bellman operator for convergence of $Q$-learning with linear function approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Diogo S. Carvalho, Francisco S. Melo, Pedro A. Santos","submitted_at":"2023-09-28T19:56:31Z","abstract_excerpt":"We study the convergence of $Q$-learning with linear function approximation. Our key contribution is the introduction of a novel multi-Bellman operator that extends the traditional Bellman operator. By exploring the properties of this operator, we identify conditions under which the projected multi-Bellman operator becomes contractive, providing improved fixed-point guarantees compared to the Bellman operator. To leverage these insights, we propose the multi $Q$-learning algorithm with linear function approximation. We demonstrate that this algorithm converges to the fixed-point of the project"},"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":"2309.16819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T19:56:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f6d72aa457bfc2ba46de3da0c64cf9cf673eae333af56c8fd91fb5335eee806","abstract_canon_sha256":"6829c7552bb66de10fc7560591741a95266260547a6fd0af462a5b58fd451a3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:27.677194Z","signature_b64":"hJUdUP7JqI1VqsBNotr4t2L1Fr0vk7v3/ZEjLoSX8Jt/vFMQnZ9qOlyakcvFCqCdrtB1b4vWj6InBpDgXxPjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6e242b6f8581f1029a6f7822831f19a376716b4b9d5d3b34791334c21d744a4","last_reissued_at":"2026-07-05T06:55:27.676764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:27.676764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Bellman operator for convergence of $Q$-learning with linear function approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Diogo S. Carvalho, Francisco S. Melo, Pedro A. Santos","submitted_at":"2023-09-28T19:56:31Z","abstract_excerpt":"We study the convergence of $Q$-learning with linear function approximation. Our key contribution is the introduction of a novel multi-Bellman operator that extends the traditional Bellman operator. By exploring the properties of this operator, we identify conditions under which the projected multi-Bellman operator becomes contractive, providing improved fixed-point guarantees compared to the Bellman operator. To leverage these insights, we propose the multi $Q$-learning algorithm with linear function approximation. We demonstrate that this algorithm converges to the fixed-point of the project"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16819","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/2309.16819/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":"2309.16819","created_at":"2026-07-05T06:55:27.676831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16819v1","created_at":"2026-07-05T06:55:27.676831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16819","created_at":"2026-07-05T06:55:27.676831+00:00"},{"alias_kind":"pith_short_12","alias_value":"63REFNXYLAPR","created_at":"2026-07-05T06:55:27.676831+00:00"},{"alias_kind":"pith_short_16","alias_value":"63REFNXYLAPRAKNG","created_at":"2026-07-05T06:55:27.676831+00:00"},{"alias_kind":"pith_short_8","alias_value":"63REFNXY","created_at":"2026-07-05T06:55:27.676831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21443","citing_title":"Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI","json":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI.json","graph_json":"https://pith.science/api/pith-number/63REFNXYLAPRAKNG66BCQMPRTI/graph.json","events_json":"https://pith.science/api/pith-number/63REFNXYLAPRAKNG66BCQMPRTI/events.json","paper":"https://pith.science/paper/63REFNXY"},"agent_actions":{"view_html":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI","download_json":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI.json","view_paper":"https://pith.science/paper/63REFNXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16819&json=true","fetch_graph":"https://pith.science/api/pith-number/63REFNXYLAPRAKNG66BCQMPRTI/graph.json","fetch_events":"https://pith.science/api/pith-number/63REFNXYLAPRAKNG66BCQMPRTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI/action/storage_attestation","attest_author":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI/action/author_attestation","sign_citation":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI/action/citation_signature","submit_replication":"https://pith.science/pith/63REFNXYLAPRAKNG66BCQMPRTI/action/replication_record"}},"created_at":"2026-07-05T06:55:27.676831+00:00","updated_at":"2026-07-05T06:55:27.676831+00:00"}