{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZEQTYTHTPDOBNI63XMAVKMJYZZ","short_pith_number":"pith:ZEQTYTHT","schema_version":"1.0","canonical_sha256":"c9213c4cf378dc16a3dbbb01553138ce626e7b8f98c9142f6b92f1afd5e84f1a","source":{"kind":"arxiv","id":"2309.01448","version":1},"attestation_state":"computed","paper":{"title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gao Huang, Qihang Zhang, Qisen Yang, Shenzhi Wang, Shiji Song","submitted_at":"2023-09-04T08:59:04Z","abstract_excerpt":"Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution is to impose a policy constraint on a policy improvement objective. However, existing methods generally adopt a ``one-size-fits-all'' practice, i.e., keeping only a single improvement-constraint balance for all the samples in a mini-batch or even the entire offline dataset. In this work, we argue that different samples should be treated with different policy"},"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":"2309.01448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T08:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"7c61c8c420fc9cacd863954c0c05cf1818ebbc84c124d047050ef044c7bf14d8","abstract_canon_sha256":"6430f85ccb161543b69f907f2a38e46ed22de9e82b9b2e4a3788cc643c188382"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:37.999013Z","signature_b64":"98tDzRkqNH8gv1o/ZQA5ZYVSDidSC9kxdmqKOdIjdMC6lG5SDyCFCJM5hTlE6DCUvB0RkpLDLhOUrTP3o4S9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9213c4cf378dc16a3dbbb01553138ce626e7b8f98c9142f6b92f1afd5e84f1a","last_reissued_at":"2026-07-05T06:47:37.998555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:37.998555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gao Huang, Qihang Zhang, Qisen Yang, Shenzhi Wang, Shiji Song","submitted_at":"2023-09-04T08:59:04Z","abstract_excerpt":"Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution is to impose a policy constraint on a policy improvement objective. However, existing methods generally adopt a ``one-size-fits-all'' practice, i.e., keeping only a single improvement-constraint balance for all the samples in a mini-batch or even the entire offline dataset. In this work, we argue that different samples should be treated with different policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01448","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/2309.01448/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":"2309.01448","created_at":"2026-07-05T06:47:37.998604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01448v1","created_at":"2026-07-05T06:47:37.998604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01448","created_at":"2026-07-05T06:47:37.998604+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEQTYTHTPDOB","created_at":"2026-07-05T06:47:37.998604+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEQTYTHTPDOBNI63","created_at":"2026-07-05T06:47:37.998604+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEQTYTHT","created_at":"2026-07-05T06:47:37.998604+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/ZEQTYTHTPDOBNI63XMAVKMJYZZ","json":"https://pith.science/pith/ZEQTYTHTPDOBNI63XMAVKMJYZZ.json","graph_json":"https://pith.science/api/pith-number/ZEQTYTHTPDOBNI63XMAVKMJYZZ/graph.json","events_json":"https://pith.science/api/pith-number/ZEQTYTHTPDOBNI63XMAVKMJYZZ/events.json","paper":"https://pith.science/paper/ZEQTYTHT"},"agent_actions":{"view_html":"https://pith.science/pith/ZEQTYTHTPDOBNI63XMAVKMJYZZ","download_json":"https://pith.science/pith/ZEQTYTHTPDOBNI63XMAVKMJYZZ.json","view_paper":"https://pith.science/paper/ZEQTYTHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01448&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEQTYTHTPDOBNI63XMAVKMJYZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEQTYTHTPDOBNI63XMAVKMJYZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEQTYTHTPDOBNI63XMAVKMJYZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEQTYTHTPDOBNI63XMAVKMJYZZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZEQTYTHTPDOBNI63XMAVKMJYZZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZEQTYTHTPDOBNI63XMAVKMJYZZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZEQTYTHTPDOBNI63XMAVKMJYZZ/action/replication_record"}},"created_at":"2026-07-05T06:47:37.998604+00:00","updated_at":"2026-07-05T06:47:37.998604+00:00"}