{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BX2MMW7HNHXNSAURKSJ2EOAW2B","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":"6a4947a8bbdf84d981b7682d02c58785a14f4a45d6a61ae9ef6c12081a99a38c","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-16T17:15:28Z","title_canon_sha256":"d0c5834d0e7924f612f72757d087e354767cc2c4c505b315ab984870d82ca83a"},"schema_version":"1.0","source":{"id":"2003.07337","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.07337","created_at":"2026-07-05T00:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"2003.07337v1","created_at":"2026-07-05T00:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.07337","created_at":"2026-07-05T00:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"BX2MMW7HNHXN","created_at":"2026-07-05T00:48:11Z"},{"alias_kind":"pith_short_16","alias_value":"BX2MMW7HNHXNSAUR","created_at":"2026-07-05T00:48:11Z"},{"alias_kind":"pith_short_8","alias_value":"BX2MMW7H","created_at":"2026-07-05T00:48:11Z"}],"graph_snapshots":[{"event_id":"sha256:041513d2e7693fa35959a2c1c21deb7c4469c77ff0b0e10abbfaa4d3a924c187","target":"graph","created_at":"2026-07-05T00:48:11Z","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/2003.07337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\\ell_\\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of local minimax lower bounds for policy evaluation, thereby providing an instance-dependent baseline by which to compare algorithms. Theory-inspired simulations show that the widely-used temporal difference (TD) algorithm is strictly suboptimal when evaluated in a non-asymptotic setting, even when combined with Polyak-Ruppert iterate averaging. We remedy this ","authors_text":"Ashwin Pananjady, Feng Ruan, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-16T17:15:28Z","title":"Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.07337","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":"sha256:37bdac3793ded8bf4ea13a632af44d36ba66fe259534bf103e7a6df8a9d25803","target":"record","created_at":"2026-07-05T00:48:11Z","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":"6a4947a8bbdf84d981b7682d02c58785a14f4a45d6a61ae9ef6c12081a99a38c","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-16T17:15:28Z","title_canon_sha256":"d0c5834d0e7924f612f72757d087e354767cc2c4c505b315ab984870d82ca83a"},"schema_version":"1.0","source":{"id":"2003.07337","kind":"arxiv","version":1}},"canonical_sha256":"0df4c65be769eed902915493a23816d0785afe950ddebd3336b2780dc9843a70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0df4c65be769eed902915493a23816d0785afe950ddebd3336b2780dc9843a70","first_computed_at":"2026-07-05T00:48:11.648699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:48:11.648699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oj8z/7M7e0k6DxHcKw0YHsIUY+HULXLu8SvlMY/jdl+BsTszdK3eUOjN9hEsAxuhWMJ6opWBlK1koH28Zh17Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:48:11.649256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.07337","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37bdac3793ded8bf4ea13a632af44d36ba66fe259534bf103e7a6df8a9d25803","sha256:041513d2e7693fa35959a2c1c21deb7c4469c77ff0b0e10abbfaa4d3a924c187"],"state_sha256":"ff010ce0c4301d574bb4606fcb8ec508f00b2c969e762791095f8604d7a3d320"}