{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7BQDFQL3RDEIYYA4TB7MC2LDCX","short_pith_number":"pith:7BQDFQL3","schema_version":"1.0","canonical_sha256":"f86032c17b88c88c601c987ec1696315fadc272da3538882d958f50031698770","source":{"kind":"arxiv","id":"2410.18626","version":2},"attestation_state":"computed","paper":{"title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haochi Wu, Liyu Zhang, Mingyang Sun, Quan Kong, Ruilong Deng, Xu Wan","submitted_at":"2024-10-24T10:35:02Z","abstract_excerpt":"Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \\Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action s"},"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":"2410.18626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T10:35:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e561d890ab78cd77649d3304008130846d941159febd3be452a2cecfdff6584f","abstract_canon_sha256":"45751c041e106f7ea030b57fc8218ffa59f9995396fd99ed6b46ee5998627329"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:51.074916Z","signature_b64":"0Gw4R9zTQZ9NYbPIQSyxRa3ERsDqtI1LRgyoCbmgL8HPURcFZSsYiGn8grpZ3biL15eJ39h/GXrpMUBuXqtpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f86032c17b88c88c601c987ec1696315fadc272da3538882d958f50031698770","last_reissued_at":"2026-07-05T10:17:51.074389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:51.074389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haochi Wu, Liyu Zhang, Mingyang Sun, Quan Kong, Ruilong Deng, Xu Wan","submitted_at":"2024-10-24T10:35:02Z","abstract_excerpt":"Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \\Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18626","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/2410.18626/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":"2410.18626","created_at":"2026-07-05T10:17:51.074463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18626v2","created_at":"2026-07-05T10:17:51.074463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18626","created_at":"2026-07-05T10:17:51.074463+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BQDFQL3RDEI","created_at":"2026-07-05T10:17:51.074463+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BQDFQL3RDEIYYA4","created_at":"2026-07-05T10:17:51.074463+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BQDFQL3","created_at":"2026-07-05T10:17:51.074463+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/7BQDFQL3RDEIYYA4TB7MC2LDCX","json":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX.json","graph_json":"https://pith.science/api/pith-number/7BQDFQL3RDEIYYA4TB7MC2LDCX/graph.json","events_json":"https://pith.science/api/pith-number/7BQDFQL3RDEIYYA4TB7MC2LDCX/events.json","paper":"https://pith.science/paper/7BQDFQL3"},"agent_actions":{"view_html":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX","download_json":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX.json","view_paper":"https://pith.science/paper/7BQDFQL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18626&json=true","fetch_graph":"https://pith.science/api/pith-number/7BQDFQL3RDEIYYA4TB7MC2LDCX/graph.json","fetch_events":"https://pith.science/api/pith-number/7BQDFQL3RDEIYYA4TB7MC2LDCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/action/storage_attestation","attest_author":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/action/author_attestation","sign_citation":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/action/citation_signature","submit_replication":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/action/replication_record"}},"created_at":"2026-07-05T10:17:51.074463+00:00","updated_at":"2026-07-05T10:17:51.074463+00:00"}