{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QRDRHTD2TM2EQCDPOHGHHOZZQO","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":"4a5ebd0b0fd302b8e684693813b23f397fabef0bf867401657147815a658be4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T16:31:07Z","title_canon_sha256":"934ba41752d5e643e5c61ee8a4ca663378f88e8797a7da7b2b087708b9d4eaea"},"schema_version":"1.0","source":{"id":"2405.20984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20984","created_at":"2026-07-05T08:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20984v1","created_at":"2026-07-05T08:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20984","created_at":"2026-07-05T08:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"QRDRHTD2TM2E","created_at":"2026-07-05T08:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"QRDRHTD2TM2EQCDP","created_at":"2026-07-05T08:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"QRDRHTD2","created_at":"2026-07-05T08:25:44Z"}],"graph_snapshots":[{"event_id":"sha256:666b3a61542557035fbda004e8b6177cd4d35db067e12baf9c96df49fd093299","target":"graph","created_at":"2026-07-05T08:25:44Z","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/2405.20984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we tackle the fundamental dilemma of offline-to-online fine-tuning: if the agent remains pessimistic, it may fail to learn a better policy, while if it becomes optimistic directly, performance may suffer from a sudden drop. We show that Bayesian design principles are crucial in solving such a dilemma. Instead of adopting optimistic or pessimistic policies, the agen","authors_text":"Changjie Fan, Chengjie Wu, Chongjie Zhang, Hao Hu, Jianing Ye, Qianchuan Zhao, Tangjie Lv, Yiqin Yang, Yujing Hu, Ziqing Mai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T16:31:07Z","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20984","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":"sha256:850d593c17803bfca2914632b4fd0e0d629a6ef9ee0f1c283500a97ddcc3099b","target":"record","created_at":"2026-07-05T08:25:44Z","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":"4a5ebd0b0fd302b8e684693813b23f397fabef0bf867401657147815a658be4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T16:31:07Z","title_canon_sha256":"934ba41752d5e643e5c61ee8a4ca663378f88e8797a7da7b2b087708b9d4eaea"},"schema_version":"1.0","source":{"id":"2405.20984","kind":"arxiv","version":1}},"canonical_sha256":"844713cc7a9b3448086f71cc73bb3983b4536418ee3185d762dccd8a75bcff56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"844713cc7a9b3448086f71cc73bb3983b4536418ee3185d762dccd8a75bcff56","first_computed_at":"2026-07-05T08:25:44.363854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:44.363854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cWoWFuPSgXoDf0cTrxIJpYy9m/4Ta9UfLA282J0owm6qF4CsPFKT5aWtlg84kzqrvhsVSxsfVrQTIYG+YX7LAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:44.364285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:850d593c17803bfca2914632b4fd0e0d629a6ef9ee0f1c283500a97ddcc3099b","sha256:666b3a61542557035fbda004e8b6177cd4d35db067e12baf9c96df49fd093299"],"state_sha256":"49580d33fb4d55fb56f981bbf289c0e42bd5c4a73a02260917fbfa8e0c74fac9"}