{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LCKAUDW4D74A7SIBNP7TR7CNTE","short_pith_number":"pith:LCKAUDW4","schema_version":"1.0","canonical_sha256":"58940a0edc1ff80fc9016bff38fc4d990aa2da5830ef0e5c0ed5dea31bcab25c","source":{"kind":"arxiv","id":"2404.10745","version":2},"attestation_state":"computed","paper":{"title":"Achieving Constant Regret in Linear Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiafan He, Quanquan Gu, Weitong Zhang, Zhiyuan Fan","submitted_at":"2024-04-16T17:23:19Z","abstract_excerpt":"We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high probability. We introduce an algorithm, Cert-LSVI-UCB, for misspecified linear Markov decision processes (MDPs) where both the transition kernel and the reward function can be approximated by some linear function up to misspecification level $\\zeta$. At the core of Cert-LSVI-UCB is an innovative \\method, which facilitates a fine-grained concentration analysis for multi-phase value-targeted regression, enabling us to esta"},"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":"2404.10745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T17:23:19Z","cross_cats_sorted":[],"title_canon_sha256":"54ccb752d527953d8532c1c5d95c7bf832d5589bbcfa038ee4df7ca3af974869","abstract_canon_sha256":"ee2d36dd7485c6c19c1cd0df2c44ae97355ee2c2ef81dcb12355aafdb4774573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:13.145443Z","signature_b64":"4JYfJo+ojQVS75BsdDJjkrEu8bhM38vPBo/dMkqU3qqNrKz94mRdmCQLPwworhF7zHCZEqWs+A9WELKesrzQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58940a0edc1ff80fc9016bff38fc4d990aa2da5830ef0e5c0ed5dea31bcab25c","last_reissued_at":"2026-07-05T09:48:13.145043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:13.145043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving Constant Regret in Linear Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiafan He, Quanquan Gu, Weitong Zhang, Zhiyuan Fan","submitted_at":"2024-04-16T17:23:19Z","abstract_excerpt":"We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high probability. We introduce an algorithm, Cert-LSVI-UCB, for misspecified linear Markov decision processes (MDPs) where both the transition kernel and the reward function can be approximated by some linear function up to misspecification level $\\zeta$. At the core of Cert-LSVI-UCB is an innovative \\method, which facilitates a fine-grained concentration analysis for multi-phase value-targeted regression, enabling us to esta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10745","kind":"arxiv","version":2},"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/2404.10745/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":"2404.10745","created_at":"2026-07-05T09:48:13.145091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10745v2","created_at":"2026-07-05T09:48:13.145091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10745","created_at":"2026-07-05T09:48:13.145091+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCKAUDW4D74A","created_at":"2026-07-05T09:48:13.145091+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCKAUDW4D74A7SIB","created_at":"2026-07-05T09:48:13.145091+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCKAUDW4","created_at":"2026-07-05T09:48:13.145091+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/LCKAUDW4D74A7SIBNP7TR7CNTE","json":"https://pith.science/pith/LCKAUDW4D74A7SIBNP7TR7CNTE.json","graph_json":"https://pith.science/api/pith-number/LCKAUDW4D74A7SIBNP7TR7CNTE/graph.json","events_json":"https://pith.science/api/pith-number/LCKAUDW4D74A7SIBNP7TR7CNTE/events.json","paper":"https://pith.science/paper/LCKAUDW4"},"agent_actions":{"view_html":"https://pith.science/pith/LCKAUDW4D74A7SIBNP7TR7CNTE","download_json":"https://pith.science/pith/LCKAUDW4D74A7SIBNP7TR7CNTE.json","view_paper":"https://pith.science/paper/LCKAUDW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10745&json=true","fetch_graph":"https://pith.science/api/pith-number/LCKAUDW4D74A7SIBNP7TR7CNTE/graph.json","fetch_events":"https://pith.science/api/pith-number/LCKAUDW4D74A7SIBNP7TR7CNTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCKAUDW4D74A7SIBNP7TR7CNTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCKAUDW4D74A7SIBNP7TR7CNTE/action/storage_attestation","attest_author":"https://pith.science/pith/LCKAUDW4D74A7SIBNP7TR7CNTE/action/author_attestation","sign_citation":"https://pith.science/pith/LCKAUDW4D74A7SIBNP7TR7CNTE/action/citation_signature","submit_replication":"https://pith.science/pith/LCKAUDW4D74A7SIBNP7TR7CNTE/action/replication_record"}},"created_at":"2026-07-05T09:48:13.145091+00:00","updated_at":"2026-07-05T09:48:13.145091+00:00"}