{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W4GQJHCHFTVZ6Z7GDMH4S5ATJY","short_pith_number":"pith:W4GQJHCH","schema_version":"1.0","canonical_sha256":"b70d049c472ceb9f67e61b0fc974134e1025e388ebd4f21a86537e758af9eae7","source":{"kind":"arxiv","id":"2210.08323","version":3},"attestation_state":"computed","paper":{"title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoran Xu, Jianxiong Li, Li Jiang, Xianyuan Zhan","submitted_at":"2022-10-15T15:54:28Z","abstract_excerpt":"Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy evaluation. Imitation-based methods avoid off-policy evaluation but are too conservative to surpass the dataset. In this study, we propose an alternative approach, inheriting the training stability of imitation-style methods while still allowing logical out-of-distribution generalization. We decompose the conventional reward-maximizing policy in offline RL into a g"},"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":"2210.08323","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T15:54:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0f845f46d821f1f7806d13c18da19020db06e8814a717a52e6d79112d99d0d7","abstract_canon_sha256":"5965da1c1751fd47adf750482b87534c8c470996bc017f3f44f42ed008e447a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:17.574406Z","signature_b64":"9ba04Pz3prgvssJpRCeQ6gKUjrZtjmpxln2XtCVmc1CcPAW1Wc8tl1iccFl+8yNWZIpqvn1il4a9u4VogtvZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b70d049c472ceb9f67e61b0fc974134e1025e388ebd4f21a86537e758af9eae7","last_reissued_at":"2026-07-05T05:58:17.573981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:17.573981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoran Xu, Jianxiong Li, Li Jiang, Xianyuan Zhan","submitted_at":"2022-10-15T15:54:28Z","abstract_excerpt":"Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy evaluation. Imitation-based methods avoid off-policy evaluation but are too conservative to surpass the dataset. In this study, we propose an alternative approach, inheriting the training stability of imitation-style methods while still allowing logical out-of-distribution generalization. We decompose the conventional reward-maximizing policy in offline RL into a g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08323","kind":"arxiv","version":3},"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/2210.08323/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":"2210.08323","created_at":"2026-07-05T05:58:17.574041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08323v3","created_at":"2026-07-05T05:58:17.574041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08323","created_at":"2026-07-05T05:58:17.574041+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4GQJHCHFTVZ","created_at":"2026-07-05T05:58:17.574041+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4GQJHCHFTVZ6Z7G","created_at":"2026-07-05T05:58:17.574041+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4GQJHCH","created_at":"2026-07-05T05:58:17.574041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22711","citing_title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY","json":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY.json","graph_json":"https://pith.science/api/pith-number/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/graph.json","events_json":"https://pith.science/api/pith-number/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/events.json","paper":"https://pith.science/paper/W4GQJHCH"},"agent_actions":{"view_html":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY","download_json":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY.json","view_paper":"https://pith.science/paper/W4GQJHCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08323&json=true","fetch_graph":"https://pith.science/api/pith-number/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/graph.json","fetch_events":"https://pith.science/api/pith-number/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/action/storage_attestation","attest_author":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/action/author_attestation","sign_citation":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/action/citation_signature","submit_replication":"https://pith.science/pith/W4GQJHCHFTVZ6Z7GDMH4S5ATJY/action/replication_record"}},"created_at":"2026-07-05T05:58:17.574041+00:00","updated_at":"2026-07-05T05:58:17.574041+00:00"}