{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:K74ISTEGZ2GM6YZFS5MPG22QJT","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":"294738af4fd2f23801ed7b41343f5ab881833dff6d5dbebe90f5c8ded80b3b9e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T04:01:11Z","title_canon_sha256":"324c00503e3fe2f6c4312e213e77b6ae66b54f569b654d2f69a0e60ae1e1a092"},"schema_version":"1.0","source":{"id":"2205.11027","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11027","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11027v3","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11027","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"K74ISTEGZ2GM","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_16","alias_value":"K74ISTEGZ2GM6YZF","created_at":"2026-07-05T05:46:51Z"},{"alias_kind":"pith_short_8","alias_value":"K74ISTEG","created_at":"2026-07-05T05:46:51Z"}],"graph_snapshots":[{"event_id":"sha256:01f0ec561ba980bd00902c170315de7be200bd109c78d375d795552e93d56233","target":"graph","created_at":"2026-07-05T05:46:51Z","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/2205.11027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas. Unfortunately, existing offline RL methods are often over-conservative, inevitably hurting generalization performance outside data distribution. In our study, one interesting observation is that deep Q functions approximate well inside the convex hull of training data. Inspired by this, we propose a new method, DOGE (Distance-sensitive Offline RL with better GEneralization). DOGE marries dataset geometry with deep function approximato","authors_text":"Haoran Xu, Jianxiong Li, Jingjing Liu, Xiangyu Zhu, Xianyuan Zhan, Ya-Qin Zhang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T04:01:11Z","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11027","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":"sha256:20151c13afa5310cf28d5d0ebb884a8e80b220ed1c92c33e7842440e4eba0f2a","target":"record","created_at":"2026-07-05T05:46:51Z","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":"294738af4fd2f23801ed7b41343f5ab881833dff6d5dbebe90f5c8ded80b3b9e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T04:01:11Z","title_canon_sha256":"324c00503e3fe2f6c4312e213e77b6ae66b54f569b654d2f69a0e60ae1e1a092"},"schema_version":"1.0","source":{"id":"2205.11027","kind":"arxiv","version":3}},"canonical_sha256":"57f8894c86ce8ccf63259758f36b504cd44cd9d15110163a133a18f2135cc1c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57f8894c86ce8ccf63259758f36b504cd44cd9d15110163a133a18f2135cc1c2","first_computed_at":"2026-07-05T05:46:51.521348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:51.521348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LYpveNaGz/cA0zUNgFGHPBQnvg3mjocvSmz5FbymlQ6iZvon+af+hu1XwO1cqOztavzmm9HGCzfm43TXxNwmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:51.521769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11027","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20151c13afa5310cf28d5d0ebb884a8e80b220ed1c92c33e7842440e4eba0f2a","sha256:01f0ec561ba980bd00902c170315de7be200bd109c78d375d795552e93d56233"],"state_sha256":"240e64f876b6e3479a2d6d1902de4689c87cd1a169525aaa344af2a0a4a19530"}