{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GZQZ7V7IMZO4QAVKPVEYBWEU3S","short_pith_number":"pith:GZQZ7V7I","schema_version":"1.0","canonical_sha256":"36619fd7e8665dc802aa7d4980d894dc848569613f094951d39f643d48bc4223","source":{"kind":"arxiv","id":"2005.00527","version":2},"attestation_state":"computed","paper":{"title":"Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Ruosong Wang, Sham M. Kakade, Simon S. Du","submitted_at":"2020-05-01T17:56:38Z","abstract_excerpt":"Learning to plan for long horizons is a central challenge in episodic reinforcement learning problems. A fundamental question is to understand how the difficulty of the problem scales as the horizon increases. Here the natural measure of sample complexity is a normalized one: we are interested in the number of episodes it takes to provably discover a policy whose value is $\\varepsilon$ near to that of the optimal value, where the value is measured by the normalized cumulative reward in each episode. In a COLT 2018 open problem, Jiang and Agarwal conjectured that, for tabular, episodic reinforc"},"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":"2005.00527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T17:56:38Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"bb6a98d94bcbd4833f55867cfc41561a8733a8700a5611c94d8d9f6c8fceb213","abstract_canon_sha256":"8200d39a7db99849a4207754361e48b30a69abebe755cc2ba6acf7a99d38fc94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:27.603973Z","signature_b64":"2gFt6CjUHHFyEbPxFXWD65edFkkjFL3ZJt9P3WASHKyeS7FTBOXgboc533GblfClqS4kOAumnpvyWjWBLyxqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36619fd7e8665dc802aa7d4980d894dc848569613f094951d39f643d48bc4223","last_reissued_at":"2026-07-05T01:17:27.603425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:27.603425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Ruosong Wang, Sham M. Kakade, Simon S. Du","submitted_at":"2020-05-01T17:56:38Z","abstract_excerpt":"Learning to plan for long horizons is a central challenge in episodic reinforcement learning problems. A fundamental question is to understand how the difficulty of the problem scales as the horizon increases. Here the natural measure of sample complexity is a normalized one: we are interested in the number of episodes it takes to provably discover a policy whose value is $\\varepsilon$ near to that of the optimal value, where the value is measured by the normalized cumulative reward in each episode. In a COLT 2018 open problem, Jiang and Agarwal conjectured that, for tabular, episodic reinforc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00527","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/2005.00527/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":"2005.00527","created_at":"2026-07-05T01:17:27.603490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00527v2","created_at":"2026-07-05T01:17:27.603490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00527","created_at":"2026-07-05T01:17:27.603490+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZQZ7V7IMZO4","created_at":"2026-07-05T01:17:27.603490+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZQZ7V7IMZO4QAVK","created_at":"2026-07-05T01:17:27.603490+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZQZ7V7I","created_at":"2026-07-05T01:17:27.603490+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/GZQZ7V7IMZO4QAVKPVEYBWEU3S","json":"https://pith.science/pith/GZQZ7V7IMZO4QAVKPVEYBWEU3S.json","graph_json":"https://pith.science/api/pith-number/GZQZ7V7IMZO4QAVKPVEYBWEU3S/graph.json","events_json":"https://pith.science/api/pith-number/GZQZ7V7IMZO4QAVKPVEYBWEU3S/events.json","paper":"https://pith.science/paper/GZQZ7V7I"},"agent_actions":{"view_html":"https://pith.science/pith/GZQZ7V7IMZO4QAVKPVEYBWEU3S","download_json":"https://pith.science/pith/GZQZ7V7IMZO4QAVKPVEYBWEU3S.json","view_paper":"https://pith.science/paper/GZQZ7V7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00527&json=true","fetch_graph":"https://pith.science/api/pith-number/GZQZ7V7IMZO4QAVKPVEYBWEU3S/graph.json","fetch_events":"https://pith.science/api/pith-number/GZQZ7V7IMZO4QAVKPVEYBWEU3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZQZ7V7IMZO4QAVKPVEYBWEU3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZQZ7V7IMZO4QAVKPVEYBWEU3S/action/storage_attestation","attest_author":"https://pith.science/pith/GZQZ7V7IMZO4QAVKPVEYBWEU3S/action/author_attestation","sign_citation":"https://pith.science/pith/GZQZ7V7IMZO4QAVKPVEYBWEU3S/action/citation_signature","submit_replication":"https://pith.science/pith/GZQZ7V7IMZO4QAVKPVEYBWEU3S/action/replication_record"}},"created_at":"2026-07-05T01:17:27.603490+00:00","updated_at":"2026-07-05T01:17:27.603490+00:00"}