{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:W4GQJHCHFTVZ6Z7GDMH4S5ATJY","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":"5965da1c1751fd47adf750482b87534c8c470996bc017f3f44f42ed008e447a8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T15:54:28Z","title_canon_sha256":"c0f845f46d821f1f7806d13c18da19020db06e8814a717a52e6d79112d99d0d7"},"schema_version":"1.0","source":{"id":"2210.08323","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.08323","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2210.08323v3","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08323","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"W4GQJHCHFTVZ","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"W4GQJHCHFTVZ6Z7G","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"W4GQJHCH","created_at":"2026-07-05T05:58:17Z"}],"graph_snapshots":[{"event_id":"sha256:20ca7b96613587784f5a4f25e474feee98e19ad31f590f134eda6541c0db6253","target":"graph","created_at":"2026-07-05T05:58:17Z","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/2210.08323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haoran Xu, Jianxiong Li, Li Jiang, Xianyuan Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T15:54:28Z","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08323","kind":"arxiv","version":3},"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":"sha256:91423b2a878f176f2286f87fd96c9596f4354d5fbd7c51d48d3222afd3094312","target":"record","created_at":"2026-07-05T05:58:17Z","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":"5965da1c1751fd47adf750482b87534c8c470996bc017f3f44f42ed008e447a8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T15:54:28Z","title_canon_sha256":"c0f845f46d821f1f7806d13c18da19020db06e8814a717a52e6d79112d99d0d7"},"schema_version":"1.0","source":{"id":"2210.08323","kind":"arxiv","version":3}},"canonical_sha256":"b70d049c472ceb9f67e61b0fc974134e1025e388ebd4f21a86537e758af9eae7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b70d049c472ceb9f67e61b0fc974134e1025e388ebd4f21a86537e758af9eae7","first_computed_at":"2026-07-05T05:58:17.573981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:17.573981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ba04Pz3prgvssJpRCeQ6gKUjrZtjmpxln2XtCVmc1CcPAW1Wc8tl1iccFl+8yNWZIpqvn1il4a9u4VogtvZDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:17.574406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.08323","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91423b2a878f176f2286f87fd96c9596f4354d5fbd7c51d48d3222afd3094312","sha256:20ca7b96613587784f5a4f25e474feee98e19ad31f590f134eda6541c0db6253"],"state_sha256":"e995318335bb8df7c3cba4a7085e8530fdf0f147b408cfa6f2e267e73bd2c0c2"}