{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2WNJ33BKIQHZX4QSZH7LRPK3GX","short_pith_number":"pith:2WNJ33BK","schema_version":"1.0","canonical_sha256":"d59a9dec2a440f9bf212c9feb8bd5b35f3aa8939feb7cb4e083af1d0d04f9709","source":{"kind":"arxiv","id":"2302.02948","version":4},"attestation_state":"computed","paper":{"title":"Efficient Online Reinforcement Learning with Offline Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ilya Kostrikov, Laura Smith, Philip J. Ball, Sergey Levine","submitted_at":"2023-02-06T17:30:22Z","abstract_excerpt":"Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human expert or a sub-optimal exploration policy. Previous methods have relied on extensive modifications and additional complexity to ensure the effective use of this data. Instead, we ask: can we simply apply existing off-policy methods to leverage offline data when learning online? In this work, we demonstrate that the answer is yes; however, a set of minimal but im"},"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":"2302.02948","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T17:30:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be7fa1af956b1e2aa90aea42acf62866861a1d59f34578a1c26fde23c27c8e9a","abstract_canon_sha256":"455565e0e8852fd2770db23f66ab4522c9b4742982c6a38db453d1d22a947783"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:45.472210Z","signature_b64":"oaNi5fsTmIYxY4mWQ0PDQyQ+1K/tpoJWlI4J3czTrQRmFkw7KFj5bE+zWXJrCefH5K+9xzDeyMK5HzOuQLk8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d59a9dec2a440f9bf212c9feb8bd5b35f3aa8939feb7cb4e083af1d0d04f9709","last_reissued_at":"2026-07-05T06:15:45.471723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:45.471723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Online Reinforcement Learning with Offline Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ilya Kostrikov, Laura Smith, Philip J. Ball, Sergey Levine","submitted_at":"2023-02-06T17:30:22Z","abstract_excerpt":"Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human expert or a sub-optimal exploration policy. Previous methods have relied on extensive modifications and additional complexity to ensure the effective use of this data. Instead, we ask: can we simply apply existing off-policy methods to leverage offline data when learning online? In this work, we demonstrate that the answer is yes; however, a set of minimal but im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02948","kind":"arxiv","version":4},"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/2302.02948/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":"2302.02948","created_at":"2026-07-05T06:15:45.471781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02948v4","created_at":"2026-07-05T06:15:45.471781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02948","created_at":"2026-07-05T06:15:45.471781+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WNJ33BKIQHZ","created_at":"2026-07-05T06:15:45.471781+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WNJ33BKIQHZX4QS","created_at":"2026-07-05T06:15:45.471781+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WNJ33BK","created_at":"2026-07-05T06:15:45.471781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24160","citing_title":"An Introduction to Causal Reinforcement Learning","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23640","citing_title":"Learning Process Rewards via Success Visitation Matching for Efficient RL","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13675","citing_title":"Improving Robotic Generalist Policies via Flow Reversal Steering","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02635","citing_title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11151","citing_title":"RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14427","citing_title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2304.10573","citing_title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11151","citing_title":"RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05812","citing_title":"Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05812","citing_title":"Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX","json":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX.json","graph_json":"https://pith.science/api/pith-number/2WNJ33BKIQHZX4QSZH7LRPK3GX/graph.json","events_json":"https://pith.science/api/pith-number/2WNJ33BKIQHZX4QSZH7LRPK3GX/events.json","paper":"https://pith.science/paper/2WNJ33BK"},"agent_actions":{"view_html":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX","download_json":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX.json","view_paper":"https://pith.science/paper/2WNJ33BK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02948&json=true","fetch_graph":"https://pith.science/api/pith-number/2WNJ33BKIQHZX4QSZH7LRPK3GX/graph.json","fetch_events":"https://pith.science/api/pith-number/2WNJ33BKIQHZX4QSZH7LRPK3GX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/action/storage_attestation","attest_author":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/action/author_attestation","sign_citation":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/action/citation_signature","submit_replication":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/action/replication_record"}},"created_at":"2026-07-05T06:15:45.471781+00:00","updated_at":"2026-07-05T06:15:45.471781+00:00"}