{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:63REFNXYLAPRAKNG66BCQMPRTI","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":"6829c7552bb66de10fc7560591741a95266260547a6fd0af462a5b58fd451a3e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T19:56:31Z","title_canon_sha256":"2f6d72aa457bfc2ba46de3da0c64cf9cf673eae333af56c8fd91fb5335eee806"},"schema_version":"1.0","source":{"id":"2309.16819","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16819","created_at":"2026-07-05T06:55:27Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16819v1","created_at":"2026-07-05T06:55:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16819","created_at":"2026-07-05T06:55:27Z"},{"alias_kind":"pith_short_12","alias_value":"63REFNXYLAPR","created_at":"2026-07-05T06:55:27Z"},{"alias_kind":"pith_short_16","alias_value":"63REFNXYLAPRAKNG","created_at":"2026-07-05T06:55:27Z"},{"alias_kind":"pith_short_8","alias_value":"63REFNXY","created_at":"2026-07-05T06:55:27Z"}],"graph_snapshots":[{"event_id":"sha256:06b0b28caa51c89d166535ca05ff7db3add051fadbb42a4db31056b7aeae4a6e","target":"graph","created_at":"2026-07-05T06:55:27Z","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/2309.16819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Diogo S. Carvalho, Francisco S. Melo, Pedro A. Santos","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T19:56:31Z","title":"Multi-Bellman operator for convergence of $Q$-learning with linear function approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16819","kind":"arxiv","version":1},"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:e6174348f85e380a8bf52f8a13c76f386510342917d67116b247cce2a5e84a4c","target":"record","created_at":"2026-07-05T06:55:27Z","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":"6829c7552bb66de10fc7560591741a95266260547a6fd0af462a5b58fd451a3e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T19:56:31Z","title_canon_sha256":"2f6d72aa457bfc2ba46de3da0c64cf9cf673eae333af56c8fd91fb5335eee806"},"schema_version":"1.0","source":{"id":"2309.16819","kind":"arxiv","version":1}},"canonical_sha256":"f6e242b6f8581f1029a6f7822831f19a376716b4b9d5d3b34791334c21d744a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6e242b6f8581f1029a6f7822831f19a376716b4b9d5d3b34791334c21d744a4","first_computed_at":"2026-07-05T06:55:27.676764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:27.676764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hJUdUP7JqI1VqsBNotr4t2L1Fr0vk7v3/ZEjLoSX8Jt/vFMQnZ9qOlyakcvFCqCdrtB1b4vWj6InBpDgXxPjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:27.677194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16819","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6174348f85e380a8bf52f8a13c76f386510342917d67116b247cce2a5e84a4c","sha256:06b0b28caa51c89d166535ca05ff7db3add051fadbb42a4db31056b7aeae4a6e"],"state_sha256":"94154f919a97b22994a9fb1bcd5f304e667b6cd2e0d31d9fb621d8da0fbf8436"}