{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HALL3ALP6PKHLZTOOIYPSKJ724","short_pith_number":"pith:HALL3ALP","schema_version":"1.0","canonical_sha256":"3816bd816ff3d475e66e7230f9293fd7237709f962a4b4cf1c88658eb2985ea4","source":{"kind":"arxiv","id":"2106.14352","version":1},"attestation_state":"computed","paper":{"title":"Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Xia, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan","submitted_at":"2021-06-28T00:38:54Z","abstract_excerpt":"Various algorithms in reinforcement learning exhibit dramatic variability in their convergence rates and ultimate accuracy as a function of the problem structure. Such instance-specific behavior is not captured by existing global minimax bounds, which are worst-case in nature. We analyze the problem of estimating optimal $Q$-value functions for a discounted Markov decision process with discrete states and actions and identify an instance-dependent functional that controls the difficulty of estimation in the $\\ell_\\infty$-norm. Using a local minimax framework, we show that this functional arise"},"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":"2106.14352","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-28T00:38:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66b057fc7eb8e5ba69f4cf54757ccfe68c5661d0e54b8a3d51682dcb278699da","abstract_canon_sha256":"4b9f37958bfd579ee28ceb5604fd42e8a5d05fdc529a1dbc3ac8e9e5520fca11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:49.698933Z","signature_b64":"+8YYeM2kkHONpT5zQoEHmXzh0EVoa7aHXUs2mP2ePIt7R6BMhAV2IrnsLieMAIH9qZvkGCd48CQcoz1I72+fBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3816bd816ff3d475e66e7230f9293fd7237709f962a4b4cf1c88658eb2985ea4","last_reissued_at":"2026-07-05T02:52:49.698431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:49.698431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Xia, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan","submitted_at":"2021-06-28T00:38:54Z","abstract_excerpt":"Various algorithms in reinforcement learning exhibit dramatic variability in their convergence rates and ultimate accuracy as a function of the problem structure. Such instance-specific behavior is not captured by existing global minimax bounds, which are worst-case in nature. We analyze the problem of estimating optimal $Q$-value functions for a discounted Markov decision process with discrete states and actions and identify an instance-dependent functional that controls the difficulty of estimation in the $\\ell_\\infty$-norm. Using a local minimax framework, we show that this functional arise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14352","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/2106.14352/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":"2106.14352","created_at":"2026-07-05T02:52:49.698488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14352v1","created_at":"2026-07-05T02:52:49.698488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14352","created_at":"2026-07-05T02:52:49.698488+00:00"},{"alias_kind":"pith_short_12","alias_value":"HALL3ALP6PKH","created_at":"2026-07-05T02:52:49.698488+00:00"},{"alias_kind":"pith_short_16","alias_value":"HALL3ALP6PKHLZTO","created_at":"2026-07-05T02:52:49.698488+00:00"},{"alias_kind":"pith_short_8","alias_value":"HALL3ALP","created_at":"2026-07-05T02:52:49.698488+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/HALL3ALP6PKHLZTOOIYPSKJ724","json":"https://pith.science/pith/HALL3ALP6PKHLZTOOIYPSKJ724.json","graph_json":"https://pith.science/api/pith-number/HALL3ALP6PKHLZTOOIYPSKJ724/graph.json","events_json":"https://pith.science/api/pith-number/HALL3ALP6PKHLZTOOIYPSKJ724/events.json","paper":"https://pith.science/paper/HALL3ALP"},"agent_actions":{"view_html":"https://pith.science/pith/HALL3ALP6PKHLZTOOIYPSKJ724","download_json":"https://pith.science/pith/HALL3ALP6PKHLZTOOIYPSKJ724.json","view_paper":"https://pith.science/paper/HALL3ALP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14352&json=true","fetch_graph":"https://pith.science/api/pith-number/HALL3ALP6PKHLZTOOIYPSKJ724/graph.json","fetch_events":"https://pith.science/api/pith-number/HALL3ALP6PKHLZTOOIYPSKJ724/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HALL3ALP6PKHLZTOOIYPSKJ724/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HALL3ALP6PKHLZTOOIYPSKJ724/action/storage_attestation","attest_author":"https://pith.science/pith/HALL3ALP6PKHLZTOOIYPSKJ724/action/author_attestation","sign_citation":"https://pith.science/pith/HALL3ALP6PKHLZTOOIYPSKJ724/action/citation_signature","submit_replication":"https://pith.science/pith/HALL3ALP6PKHLZTOOIYPSKJ724/action/replication_record"}},"created_at":"2026-07-05T02:52:49.698488+00:00","updated_at":"2026-07-05T02:52:49.698488+00:00"}