{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OHQ6D2GRDHVDI7A3HTOCKQH6N7","short_pith_number":"pith:OHQ6D2GR","schema_version":"1.0","canonical_sha256":"71e1e1e8d119ea347c1b3cdc2540fe6fcfd3f88e66cfdfdba61ee0570eb7357e","source":{"kind":"arxiv","id":"2306.03362","version":1},"attestation_state":"computed","paper":{"title":"Boosting Offline Reinforcement Learning with Action Preference Query","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gao Huang, Matthieu Gaetan Lin, Qisen Yang, Shenzhi Wang, Shiji Song","submitted_at":"2023-06-06T02:29:40Z","abstract_excerpt":"Training practical agents usually involve offline and online reinforcement learning (RL) to balance the policy's performance and interaction costs. In particular, online fine-tuning has become a commonly used method to correct the erroneous estimates of out-of-distribution data learned in the offline training phase. However, even limited online interactions can be inaccessible or catastrophic for high-stake scenarios like healthcare and autonomous driving. In this work, we introduce an interaction-free training scheme dubbed Offline-with-Action-Preferences (OAP). The main insight is that, comp"},"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":"2306.03362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T02:29:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdf3e940afe15824feeaf56c31f2522630ee25379e3608c5559b98dcfe3fb0bd","abstract_canon_sha256":"7b5ce9bef229c9466529a7e0106ea7dadc9e4af91026ed7e71b4a85e06bd1e18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:57.289504Z","signature_b64":"LqTbKzmBDi/zCvce3IHAGgSS9WOqO9/XubzSK/+rUCyOA8s0ovl2S3zRUyq3OLFkRhlQFW9SpOVnThLdBD46Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71e1e1e8d119ea347c1b3cdc2540fe6fcfd3f88e66cfdfdba61ee0570eb7357e","last_reissued_at":"2026-07-05T06:17:57.289106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:57.289106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Offline Reinforcement Learning with Action Preference Query","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gao Huang, Matthieu Gaetan Lin, Qisen Yang, Shenzhi Wang, Shiji Song","submitted_at":"2023-06-06T02:29:40Z","abstract_excerpt":"Training practical agents usually involve offline and online reinforcement learning (RL) to balance the policy's performance and interaction costs. In particular, online fine-tuning has become a commonly used method to correct the erroneous estimates of out-of-distribution data learned in the offline training phase. However, even limited online interactions can be inaccessible or catastrophic for high-stake scenarios like healthcare and autonomous driving. In this work, we introduce an interaction-free training scheme dubbed Offline-with-Action-Preferences (OAP). The main insight is that, comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03362","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/2306.03362/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":"2306.03362","created_at":"2026-07-05T06:17:57.289161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03362v1","created_at":"2026-07-05T06:17:57.289161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03362","created_at":"2026-07-05T06:17:57.289161+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHQ6D2GRDHVD","created_at":"2026-07-05T06:17:57.289161+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHQ6D2GRDHVDI7A3","created_at":"2026-07-05T06:17:57.289161+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHQ6D2GR","created_at":"2026-07-05T06:17:57.289161+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/OHQ6D2GRDHVDI7A3HTOCKQH6N7","json":"https://pith.science/pith/OHQ6D2GRDHVDI7A3HTOCKQH6N7.json","graph_json":"https://pith.science/api/pith-number/OHQ6D2GRDHVDI7A3HTOCKQH6N7/graph.json","events_json":"https://pith.science/api/pith-number/OHQ6D2GRDHVDI7A3HTOCKQH6N7/events.json","paper":"https://pith.science/paper/OHQ6D2GR"},"agent_actions":{"view_html":"https://pith.science/pith/OHQ6D2GRDHVDI7A3HTOCKQH6N7","download_json":"https://pith.science/pith/OHQ6D2GRDHVDI7A3HTOCKQH6N7.json","view_paper":"https://pith.science/paper/OHQ6D2GR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03362&json=true","fetch_graph":"https://pith.science/api/pith-number/OHQ6D2GRDHVDI7A3HTOCKQH6N7/graph.json","fetch_events":"https://pith.science/api/pith-number/OHQ6D2GRDHVDI7A3HTOCKQH6N7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHQ6D2GRDHVDI7A3HTOCKQH6N7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHQ6D2GRDHVDI7A3HTOCKQH6N7/action/storage_attestation","attest_author":"https://pith.science/pith/OHQ6D2GRDHVDI7A3HTOCKQH6N7/action/author_attestation","sign_citation":"https://pith.science/pith/OHQ6D2GRDHVDI7A3HTOCKQH6N7/action/citation_signature","submit_replication":"https://pith.science/pith/OHQ6D2GRDHVDI7A3HTOCKQH6N7/action/replication_record"}},"created_at":"2026-07-05T06:17:57.289161+00:00","updated_at":"2026-07-05T06:17:57.289161+00:00"}