{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OHQ6D2GRDHVDI7A3HTOCKQH6N7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7b5ce9bef229c9466529a7e0106ea7dadc9e4af91026ed7e71b4a85e06bd1e18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T02:29:40Z","title_canon_sha256":"bdf3e940afe15824feeaf56c31f2522630ee25379e3608c5559b98dcfe3fb0bd"},"schema_version":"1.0","source":{"id":"2306.03362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03362","created_at":"2026-07-05T06:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03362v1","created_at":"2026-07-05T06:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03362","created_at":"2026-07-05T06:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"OHQ6D2GRDHVD","created_at":"2026-07-05T06:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"OHQ6D2GRDHVDI7A3","created_at":"2026-07-05T06:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"OHQ6D2GR","created_at":"2026-07-05T06:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:e35ff8e7e79831210849595c908238467522ac5442dca3a1dc96c4a7ba30078d","target":"graph","created_at":"2026-07-05T06:17:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.03362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gao Huang, Matthieu Gaetan Lin, Qisen Yang, Shenzhi Wang, Shiji Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T02:29:40Z","title":"Boosting Offline Reinforcement Learning with Action Preference Query"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03362","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fd28342a8484c38f303c2f2a0aacf4832a8354a8ba7bb3d8d16ea489f18733fc","target":"record","created_at":"2026-07-05T06:17:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7b5ce9bef229c9466529a7e0106ea7dadc9e4af91026ed7e71b4a85e06bd1e18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T02:29:40Z","title_canon_sha256":"bdf3e940afe15824feeaf56c31f2522630ee25379e3608c5559b98dcfe3fb0bd"},"schema_version":"1.0","source":{"id":"2306.03362","kind":"arxiv","version":1}},"canonical_sha256":"71e1e1e8d119ea347c1b3cdc2540fe6fcfd3f88e66cfdfdba61ee0570eb7357e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71e1e1e8d119ea347c1b3cdc2540fe6fcfd3f88e66cfdfdba61ee0570eb7357e","first_computed_at":"2026-07-05T06:17:57.289106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:57.289106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LqTbKzmBDi/zCvce3IHAGgSS9WOqO9/XubzSK/+rUCyOA8s0ovl2S3zRUyq3OLFkRhlQFW9SpOVnThLdBD46Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:57.289504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd28342a8484c38f303c2f2a0aacf4832a8354a8ba7bb3d8d16ea489f18733fc","sha256:e35ff8e7e79831210849595c908238467522ac5442dca3a1dc96c4a7ba30078d"],"state_sha256":"7729a658429bb2f68a2235f9f9ad2a2f59fa0805d358f471433609435747412f"}