{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TCKMWPLUKNFNEEUPMGBZXODNMW","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":"13592c2b168c7c7c847fc2279ec5e2488754edfff5af8fdc3c1bc68525e48522","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-08T15:26:18Z","title_canon_sha256":"eb51a47f1760b448f898294f3b6c646a617bcbd1d9c90feb4cfdd28bb3e75112"},"schema_version":"1.0","source":{"id":"2408.04526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04526","created_at":"2026-07-05T08:53:34Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04526v1","created_at":"2026-07-05T08:53:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04526","created_at":"2026-07-05T08:53:34Z"},{"alias_kind":"pith_short_12","alias_value":"TCKMWPLUKNFN","created_at":"2026-07-05T08:53:34Z"},{"alias_kind":"pith_short_16","alias_value":"TCKMWPLUKNFNEEUP","created_at":"2026-07-05T08:53:34Z"},{"alias_kind":"pith_short_8","alias_value":"TCKMWPLU","created_at":"2026-07-05T08:53:34Z"}],"graph_snapshots":[{"event_id":"sha256:d1f3695f31b0b3acacbf3aa754331b398abe2250917eed8eeaa21f972d57dd24","target":"graph","created_at":"2026-07-05T08:53:34Z","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/2408.04526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether hybrid RL can improve upon the existing lower bounds established in purely offline and purely online RL without relying on the single-policy concentrability assumption. While Li et al. (2023) provided an affirmative answer to this question in the tabular PAC RL case, the question remains unsettled for both the regret-minimizing RL case and the non-tabular case.","authors_text":"Kevin Tan, Wei Fan, Yuting Wei","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-08T15:26:18Z","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04526","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:d6f91489424e16a7183632a11e6fbd44129c4fc7d995ae69cb4053dd6b43c112","target":"record","created_at":"2026-07-05T08:53:34Z","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":"13592c2b168c7c7c847fc2279ec5e2488754edfff5af8fdc3c1bc68525e48522","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-08T15:26:18Z","title_canon_sha256":"eb51a47f1760b448f898294f3b6c646a617bcbd1d9c90feb4cfdd28bb3e75112"},"schema_version":"1.0","source":{"id":"2408.04526","kind":"arxiv","version":1}},"canonical_sha256":"9894cb3d74534ad2128f61839bb86d65bf3688d99013a4612206c08db6549ac4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9894cb3d74534ad2128f61839bb86d65bf3688d99013a4612206c08db6549ac4","first_computed_at":"2026-07-05T08:53:34.573040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:34.573040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"57FK13IFIw+CNYdSPEOgbHSilrjulhJPKxrq/KSYUPPiDLZSMUMy/3tgFHioM+AuTOc+1S8ljxxYcmDy5W9pAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:34.573394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6f91489424e16a7183632a11e6fbd44129c4fc7d995ae69cb4053dd6b43c112","sha256:d1f3695f31b0b3acacbf3aa754331b398abe2250917eed8eeaa21f972d57dd24"],"state_sha256":"b627e3db12bfcfda036ef1e212e312c14d44189173710946d20ac8f97f116c08"}