{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TJZ574ADCLSEJUWIRRPXRMR66X","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":"96549c1b33a5126227115bdcd5d7268c3a39d15518ef063fba64a9464a5a1601","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T01:44:12Z","title_canon_sha256":"243ac5fb2cf8b2e9a667a1d58342a33de3ba81c2a5a8d260e299cf20539b7f2f"},"schema_version":"1.0","source":{"id":"2206.00177","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00177","created_at":"2026-07-05T04:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00177v2","created_at":"2026-07-05T04:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00177","created_at":"2026-07-05T04:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"TJZ574ADCLSE","created_at":"2026-07-05T04:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"TJZ574ADCLSEJUWI","created_at":"2026-07-05T04:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"TJZ574AD","created_at":"2026-07-05T04:46:00Z"}],"graph_snapshots":[{"event_id":"sha256:18ae76df67bc2657fab2fb1a2fd2cd0cef26df8f003b60bf159fa881511e2419","target":"graph","created_at":"2026-07-05T04:46:00Z","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/2206.00177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a systematic study on gap-dependent sample complexity in offline reinforcement learning. Prior work showed when the density ratio between an optimal policy and the behavior policy is upper bounded (the optimal policy coverage assumption), then the agent can achieve an $O\\left(\\frac{1}{\\epsilon^2}\\right)$ rate, which is also minimax optimal. We show under the optimal policy coverage assumption, the rate can be improved to $O\\left(\\frac{1}{\\epsilon}\\right)$ when there is a positive sub-optimality gap in the optimal $Q$-function. Furthermore, we show when the visitation probab","authors_text":"Qiwen Cui, Simon S. Du, Xinqi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T01:44:12Z","title":"On Gap-dependent Bounds for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00177","kind":"arxiv","version":2},"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":"sha256:9c8a4cff681c72ab039eff0053441719db6f4bcf43d19ea502c1e47cb2b1e6e5","target":"record","created_at":"2026-07-05T04:46:00Z","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":"96549c1b33a5126227115bdcd5d7268c3a39d15518ef063fba64a9464a5a1601","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T01:44:12Z","title_canon_sha256":"243ac5fb2cf8b2e9a667a1d58342a33de3ba81c2a5a8d260e299cf20539b7f2f"},"schema_version":"1.0","source":{"id":"2206.00177","kind":"arxiv","version":2}},"canonical_sha256":"9a73dff00312e444d2c88c5f78b23ef5d4ef6e319efe10a87bf5cc7ac1ce2a46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a73dff00312e444d2c88c5f78b23ef5d4ef6e319efe10a87bf5cc7ac1ce2a46","first_computed_at":"2026-07-05T04:46:00.021722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:00.021722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"adbQVLSgjodI5pQcw84VCmpIDSi9C0Ue15ffywGQxmDKO39cGOcPpIkUA4tnhXuunKeKiW7gJ1KhKfibr0iBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:00.022283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00177","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c8a4cff681c72ab039eff0053441719db6f4bcf43d19ea502c1e47cb2b1e6e5","sha256:18ae76df67bc2657fab2fb1a2fd2cd0cef26df8f003b60bf159fa881511e2419"],"state_sha256":"af7ed2c43190bcb6a7fb2dba5548024f502458a799cf2bae3aca5cfbc935b6da"}