{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HALL3ALP6PKHLZTOOIYPSKJ724","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":"4b9f37958bfd579ee28ceb5604fd42e8a5d05fdc529a1dbc3ac8e9e5520fca11","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-28T00:38:54Z","title_canon_sha256":"66b057fc7eb8e5ba69f4cf54757ccfe68c5661d0e54b8a3d51682dcb278699da"},"schema_version":"1.0","source":{"id":"2106.14352","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14352","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14352v1","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14352","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"HALL3ALP6PKH","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"HALL3ALP6PKHLZTO","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"HALL3ALP","created_at":"2026-07-05T02:52:49Z"}],"graph_snapshots":[{"event_id":"sha256:f5163749d0c6ae58b67a638dcf8e0de5b24938e9e0ed299030cb549cffb4b07e","target":"graph","created_at":"2026-07-05T02:52:49Z","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/2106.14352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Eric Xia, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-28T00:38:54Z","title":"Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14352","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:afbc47dbecd7dfab1aa3675ee98a12f78a2bf3e2aa2104687f5d68874f796cb6","target":"record","created_at":"2026-07-05T02:52:49Z","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":"4b9f37958bfd579ee28ceb5604fd42e8a5d05fdc529a1dbc3ac8e9e5520fca11","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-28T00:38:54Z","title_canon_sha256":"66b057fc7eb8e5ba69f4cf54757ccfe68c5661d0e54b8a3d51682dcb278699da"},"schema_version":"1.0","source":{"id":"2106.14352","kind":"arxiv","version":1}},"canonical_sha256":"3816bd816ff3d475e66e7230f9293fd7237709f962a4b4cf1c88658eb2985ea4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3816bd816ff3d475e66e7230f9293fd7237709f962a4b4cf1c88658eb2985ea4","first_computed_at":"2026-07-05T02:52:49.698431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:49.698431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+8YYeM2kkHONpT5zQoEHmXzh0EVoa7aHXUs2mP2ePIt7R6BMhAV2IrnsLieMAIH9qZvkGCd48CQcoz1I72+fBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:49.698933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.14352","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afbc47dbecd7dfab1aa3675ee98a12f78a2bf3e2aa2104687f5d68874f796cb6","sha256:f5163749d0c6ae58b67a638dcf8e0de5b24938e9e0ed299030cb549cffb4b07e"],"state_sha256":"3683b44619267b58c58903eb6e5a482daa96a6059ed521961d1338c664b23af3"}