{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6QYLJ7IUQ4KMGUDF5SVJSTJAEO","short_pith_number":"pith:6QYLJ7IU","schema_version":"1.0","canonical_sha256":"f430b4fd148714c35065ecaa994d2023a25dd0130fa7f955198fc0dbeace3a56","source":{"kind":"arxiv","id":"2408.14785","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junsu Kim, Seohong Park, Sergey Levine","submitted_at":"2024-08-27T05:23:45Z","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-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.14785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T05:23:45Z","cross_cats_sorted":[],"title_canon_sha256":"1bd37defdf64e72541c6fb02bbdfec63d2ce277f949ba5f6a8e57ca0a97bacdf","abstract_canon_sha256":"1b21266697d5f7a34dea37cafbf1ec5fac1346c26efc8918336deb04eab13a38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:38.942358Z","signature_b64":"YwBvjIhHz08TUgTjJt7uSTZ2cxTHUCcgqgfbeijWnKiEr+7JJeFjbx3AuTgCbyvY7iRo8vcIDvE0gT53QojWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f430b4fd148714c35065ecaa994d2023a25dd0130fa7f955198fc0dbeace3a56","last_reissued_at":"2026-07-05T08:59:38.941780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:38.941780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junsu Kim, Seohong Park, Sergey Levine","submitted_at":"2024-08-27T05:23:45Z","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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14785","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.14785/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.14785","created_at":"2026-07-05T08:59:38.941843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14785v1","created_at":"2026-07-05T08:59:38.941843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14785","created_at":"2026-07-05T08:59:38.941843+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QYLJ7IUQ4KM","created_at":"2026-07-05T08:59:38.941843+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QYLJ7IUQ4KMGUDF","created_at":"2026-07-05T08:59:38.941843+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QYLJ7IU","created_at":"2026-07-05T08:59:38.941843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.08902","citing_title":"Intention-Conditioned Flow Occupancy Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07637","citing_title":"Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07637","citing_title":"Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO","json":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO.json","graph_json":"https://pith.science/api/pith-number/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/graph.json","events_json":"https://pith.science/api/pith-number/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/events.json","paper":"https://pith.science/paper/6QYLJ7IU"},"agent_actions":{"view_html":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO","download_json":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO.json","view_paper":"https://pith.science/paper/6QYLJ7IU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14785&json=true","fetch_graph":"https://pith.science/api/pith-number/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/graph.json","fetch_events":"https://pith.science/api/pith-number/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/action/storage_attestation","attest_author":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/action/author_attestation","sign_citation":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/action/citation_signature","submit_replication":"https://pith.science/pith/6QYLJ7IUQ4KMGUDF5SVJSTJAEO/action/replication_record"}},"created_at":"2026-07-05T08:59:38.941843+00:00","updated_at":"2026-07-05T08:59:38.941843+00:00"}