{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RFWFVCVXGRYABGTSV7NET3ROQZ","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":"a0326ec4631aa9b760bf1618ecb40406998f024ad23942862d253099734a3f79","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-17T15:17:23Z","title_canon_sha256":"cbb8b9bd88621290992337c6996f38349c9ca87cff1dd0e75b4e7bf33de2760c"},"schema_version":"1.0","source":{"id":"2305.10282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10282","created_at":"2026-07-05T06:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10282v1","created_at":"2026-07-05T06:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10282","created_at":"2026-07-05T06:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"RFWFVCVXGRYA","created_at":"2026-07-05T06:11:12Z"},{"alias_kind":"pith_short_16","alias_value":"RFWFVCVXGRYABGTS","created_at":"2026-07-05T06:11:12Z"},{"alias_kind":"pith_short_8","alias_value":"RFWFVCVX","created_at":"2026-07-05T06:11:12Z"}],"graph_snapshots":[{"event_id":"sha256:89eeef01465aeecc28287b4456a8f9c923eb334bcd86e34a9b63645ad6e94f6e","target":"graph","created_at":"2026-07-05T06:11:12Z","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/2305.10282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes access to both an offline dataset and online interactions with the unknown environment. A central question boils down to how to efficiently utilize online data collection to strengthen and complement the offline dataset and enable effective policy fine-tuning. Leveraging recent advances in reward-agnostic exploration and model-based offline RL, we design a three-stage hybrid RL algorithm that beats the best of both worlds -- pure offline RL and pure online RL -- in terms of sample complexities. The prop","authors_text":"Gen Li, Jason D. Lee, Wenhao Zhan, Yuejie Chi, Yuxin Chen","cross_cats":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-17T15:17:23Z","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10282","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":"sha256:7441b8e8a23faddaffebe5983a37950f015fd820e6570c5b6325a9d3b96dab14","target":"record","created_at":"2026-07-05T06:11:12Z","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":"a0326ec4631aa9b760bf1618ecb40406998f024ad23942862d253099734a3f79","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-17T15:17:23Z","title_canon_sha256":"cbb8b9bd88621290992337c6996f38349c9ca87cff1dd0e75b4e7bf33de2760c"},"schema_version":"1.0","source":{"id":"2305.10282","kind":"arxiv","version":1}},"canonical_sha256":"896c5a8ab73470009a72afda49ee2e864912a0e9dae4eea49b13b0f036770156","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"896c5a8ab73470009a72afda49ee2e864912a0e9dae4eea49b13b0f036770156","first_computed_at":"2026-07-05T06:11:12.099049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:12.099049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"avBi84H6x2PmIDmuX0nnW/MBym2pMuyfNo6uvTu/W+EwYz3kqlp7YCJSdk9tEOYcQlOt0TP6TGv0tj8ztajEDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:12.099447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7441b8e8a23faddaffebe5983a37950f015fd820e6570c5b6325a9d3b96dab14","sha256:89eeef01465aeecc28287b4456a8f9c923eb334bcd86e34a9b63645ad6e94f6e"],"state_sha256":"4c39d99f24ba1079d9213c4f9df9a465007f800d198dd8e72c36f7389c6a5b23"}