{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JVKQ2IWNALCEG4VWS5SZEIHMQC","short_pith_number":"pith:JVKQ2IWN","schema_version":"1.0","canonical_sha256":"4d550d22cd02c44372b697659220ec8086a7895e26574dd034f37a016eba4881","source":{"kind":"arxiv","id":"2201.10070","version":1},"attestation_state":"computed","paper":{"title":"MOORe: Model-based Offline-to-Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Wang, Chao Wang, Chongjie Zhang, Yihuan Mao","submitted_at":"2022-01-25T03:14:57Z","abstract_excerpt":"With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online. A smooth transfer of the policy matters in safe real-world deployment. Besides, fast adaptation of the policy plays a vital role in practical online performance improvement. To tackle these challenges, we propose a simple yet efficient algorithm, Model-based Offline-to-Online Reinforcement learning (MOORe), which employs a prioritized sampling scheme that can dynamically adjust the offline and online data for smooth and efficient online adaptation"},"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":"2201.10070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T03:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"8978310f64c8fae98db85671e2c0ac4de94326f20858dd72ce186875079149b6","abstract_canon_sha256":"58d47f677e44842c61c9778683b263e578c58325127922efb840a3b76e682233"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:15.180099Z","signature_b64":"pUrWIGqF7kFFaNOvxzx4EVnNzXYp+zXgCfvh92E73HEmfgzIkIGBN0bhP9tXoiVTJAgC1Wl35gjerocRVJdtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d550d22cd02c44372b697659220ec8086a7895e26574dd034f37a016eba4881","last_reissued_at":"2026-07-05T03:51:15.179684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:15.179684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOORe: Model-based Offline-to-Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Wang, Chao Wang, Chongjie Zhang, Yihuan Mao","submitted_at":"2022-01-25T03:14:57Z","abstract_excerpt":"With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online. A smooth transfer of the policy matters in safe real-world deployment. Besides, fast adaptation of the policy plays a vital role in practical online performance improvement. To tackle these challenges, we propose a simple yet efficient algorithm, Model-based Offline-to-Online Reinforcement learning (MOORe), which employs a prioritized sampling scheme that can dynamically adjust the offline and online data for smooth and efficient online adaptation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10070","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/2201.10070/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":"2201.10070","created_at":"2026-07-05T03:51:15.179738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10070v1","created_at":"2026-07-05T03:51:15.179738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10070","created_at":"2026-07-05T03:51:15.179738+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVKQ2IWNALCE","created_at":"2026-07-05T03:51:15.179738+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVKQ2IWNALCEG4VW","created_at":"2026-07-05T03:51:15.179738+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVKQ2IWN","created_at":"2026-07-05T03:51:15.179738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18855","citing_title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC","json":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC.json","graph_json":"https://pith.science/api/pith-number/JVKQ2IWNALCEG4VWS5SZEIHMQC/graph.json","events_json":"https://pith.science/api/pith-number/JVKQ2IWNALCEG4VWS5SZEIHMQC/events.json","paper":"https://pith.science/paper/JVKQ2IWN"},"agent_actions":{"view_html":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC","download_json":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC.json","view_paper":"https://pith.science/paper/JVKQ2IWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10070&json=true","fetch_graph":"https://pith.science/api/pith-number/JVKQ2IWNALCEG4VWS5SZEIHMQC/graph.json","fetch_events":"https://pith.science/api/pith-number/JVKQ2IWNALCEG4VWS5SZEIHMQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/action/storage_attestation","attest_author":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/action/author_attestation","sign_citation":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/action/citation_signature","submit_replication":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/action/replication_record"}},"created_at":"2026-07-05T03:51:15.179738+00:00","updated_at":"2026-07-05T03:51:15.179738+00:00"}