{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6QYLJ7IUQ4KMGUDF5SVJSTJAEO","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":"1b21266697d5f7a34dea37cafbf1ec5fac1346c26efc8918336deb04eab13a38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T05:23:45Z","title_canon_sha256":"1bd37defdf64e72541c6fb02bbdfec63d2ce277f949ba5f6a8e57ca0a97bacdf"},"schema_version":"1.0","source":{"id":"2408.14785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14785","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14785v1","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14785","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"6QYLJ7IUQ4KM","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_16","alias_value":"6QYLJ7IUQ4KMGUDF","created_at":"2026-07-05T08:59:38Z"},{"alias_kind":"pith_short_8","alias_value":"6QYLJ7IU","created_at":"2026-07-05T08:59:38Z"}],"graph_snapshots":[{"event_id":"sha256:5b2b5ca1f294750a41165cc8026efbb350ceb02ac20c938a50f569cb261561f7","target":"graph","created_at":"2026-07-05T08:59:38Z","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/2408.14785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline-to-online reinforcement learning (RL), a framework that trains a policy with offline RL and then further fine-tunes it with online RL, has been considered a promising recipe for data-driven decision-making. While sensible, this framework has drawbacks: it requires domain-specific offline RL pre-training for each task, and is often brittle in practice. In this work, we propose unsupervised-to-online RL (U2O RL), which replaces domain-specific supervised offline RL with unsupervised offline RL, as a better alternative to offline-to-online RL. U2O RL not only enables reusing a single pre-","authors_text":"Junsu Kim, Seohong Park, Sergey Levine","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T05:23:45Z","title":"Unsupervised-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14785","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":"sha256:8a8cef240156865c2dd97bf32ffe4d66ce0556af7e4a25e0cc6b45ac3f923037","target":"record","created_at":"2026-07-05T08:59:38Z","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":"1b21266697d5f7a34dea37cafbf1ec5fac1346c26efc8918336deb04eab13a38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T05:23:45Z","title_canon_sha256":"1bd37defdf64e72541c6fb02bbdfec63d2ce277f949ba5f6a8e57ca0a97bacdf"},"schema_version":"1.0","source":{"id":"2408.14785","kind":"arxiv","version":1}},"canonical_sha256":"f430b4fd148714c35065ecaa994d2023a25dd0130fa7f955198fc0dbeace3a56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f430b4fd148714c35065ecaa994d2023a25dd0130fa7f955198fc0dbeace3a56","first_computed_at":"2026-07-05T08:59:38.941780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:38.941780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YwBvjIhHz08TUgTjJt7uSTZ2cxTHUCcgqgfbeijWnKiEr+7JJeFjbx3AuTgCbyvY7iRo8vcIDvE0gT53QojWCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:38.942358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a8cef240156865c2dd97bf32ffe4d66ce0556af7e4a25e0cc6b45ac3f923037","sha256:5b2b5ca1f294750a41165cc8026efbb350ceb02ac20c938a50f569cb261561f7"],"state_sha256":"19073c62254d4869df34d17f1173afd57d095cceb520fd8ed9d36b07d000a2e6"}