{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PEVUTGEGMV43GJE54LQP7UACTP","short_pith_number":"pith:PEVUTGEG","schema_version":"1.0","canonical_sha256":"792b4998866579b3249de2e0ffd0029bf6a537cbe966c1ee9431c6bebbbbc48c","source":{"kind":"arxiv","id":"2310.17966","version":2},"attestation_state":"computed","paper":{"title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gao Huang, Hao Chen, Jiawei Gao, Liwei Wu, Matthieu Gaetan Lin, Ning Jia, Qisen Yang, Shenzhi Wang, Shiji Song","submitted_at":"2023-10-27T08:30:54Z","abstract_excerpt":"Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-training on a pre-collected dataset with fine-tuning in an online environment. However, the incorporation of online fine-tuning can intensify the well-known distributional shift problem. Existing solutions tackle this problem by imposing a policy constraint on the policy improvement objective in both offline and online learning. They typically advocate a single balance between policy improvement and constraints across diverse data collections. This one-size-fits-all manner may not optimally leverage each col"},"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":"2310.17966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T08:30:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbe7796ee71b37596a2fd901bf59d1161ba34237afbb78838d8c1819fcdb40ec","abstract_canon_sha256":"91a43e08628c8ca07e11632c925b677d859caec886621abeae3258dfd904c992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:37.957226Z","signature_b64":"TAzIuyGwPYb+dTPX8PIyg0hSfF3fEgXKCSgiUg6QnVNP6Hlb7//zEo4j2L2qaZtmKPLXAY6t45Mb6oHc/TUZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"792b4998866579b3249de2e0ffd0029bf6a537cbe966c1ee9431c6bebbbbc48c","last_reissued_at":"2026-07-05T07:06:37.956633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:37.956633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gao Huang, Hao Chen, Jiawei Gao, Liwei Wu, Matthieu Gaetan Lin, Ning Jia, Qisen Yang, Shenzhi Wang, Shiji Song","submitted_at":"2023-10-27T08:30:54Z","abstract_excerpt":"Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-training on a pre-collected dataset with fine-tuning in an online environment. However, the incorporation of online fine-tuning can intensify the well-known distributional shift problem. Existing solutions tackle this problem by imposing a policy constraint on the policy improvement objective in both offline and online learning. They typically advocate a single balance between policy improvement and constraints across diverse data collections. This one-size-fits-all manner may not optimally leverage each col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17966","kind":"arxiv","version":2},"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/2310.17966/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":"2310.17966","created_at":"2026-07-05T07:06:37.956695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17966v2","created_at":"2026-07-05T07:06:37.956695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17966","created_at":"2026-07-05T07:06:37.956695+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEVUTGEGMV43","created_at":"2026-07-05T07:06:37.956695+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEVUTGEGMV43GJE5","created_at":"2026-07-05T07:06:37.956695+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEVUTGEG","created_at":"2026-07-05T07:06:37.956695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP","json":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP.json","graph_json":"https://pith.science/api/pith-number/PEVUTGEGMV43GJE54LQP7UACTP/graph.json","events_json":"https://pith.science/api/pith-number/PEVUTGEGMV43GJE54LQP7UACTP/events.json","paper":"https://pith.science/paper/PEVUTGEG"},"agent_actions":{"view_html":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP","download_json":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP.json","view_paper":"https://pith.science/paper/PEVUTGEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17966&json=true","fetch_graph":"https://pith.science/api/pith-number/PEVUTGEGMV43GJE54LQP7UACTP/graph.json","fetch_events":"https://pith.science/api/pith-number/PEVUTGEGMV43GJE54LQP7UACTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/action/storage_attestation","attest_author":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/action/author_attestation","sign_citation":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/action/citation_signature","submit_replication":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/action/replication_record"}},"created_at":"2026-07-05T07:06:37.956695+00:00","updated_at":"2026-07-05T07:06:37.956695+00:00"}