{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BWORDNSR7J6BLUWWFNPHHMNBCG","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":"6488c110b78e5c17e433bd36bb5c4d23d20311da66423470ce38b7086bbb6e61","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-14T13:17:59Z","title_canon_sha256":"fa6a7ada271cc2edc4f7d645a250c2473f0e90597698b7cd21630d8b97b0d813"},"schema_version":"1.0","source":{"id":"2209.06620","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06620","created_at":"2026-07-05T05:36:18Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06620v3","created_at":"2026-07-05T05:36:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06620","created_at":"2026-07-05T05:36:18Z"},{"alias_kind":"pith_short_12","alias_value":"BWORDNSR7J6B","created_at":"2026-07-05T05:36:18Z"},{"alias_kind":"pith_short_16","alias_value":"BWORDNSR7J6BLUWW","created_at":"2026-07-05T05:36:18Z"},{"alias_kind":"pith_short_8","alias_value":"BWORDNSR","created_at":"2026-07-05T05:36:18Z"}],"graph_snapshots":[{"event_id":"sha256:20a63e423e40564e4092fad220544b85ba767f2c731cffb4f553f61e9300e044","target":"graph","created_at":"2026-07-05T05:36:18Z","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/2209.06620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the training environment (e.g., a simulator). This paper attempts to address these issues simultaneously with distributionally robust offline RL, where we learn a distributionally robust policy using historical data obtained from the source environment by optimizing against a worst-case perturbation thereof. In particular, we move beyond tabular settings and con","authors_text":"Jiheng Zhang, Jose Blanchet, Li Xia, Mingwen Liu, Qianchuan Zhao, Xiaoteng Ma, Zhengyuan Zhou, Zhipeng Liang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-14T13:17:59Z","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06620","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":"sha256:3d06df5c8f60d73687c448707d728bcfb5d3ab1df1904bcbae020b8e9ed32a20","target":"record","created_at":"2026-07-05T05:36:18Z","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":"6488c110b78e5c17e433bd36bb5c4d23d20311da66423470ce38b7086bbb6e61","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-14T13:17:59Z","title_canon_sha256":"fa6a7ada271cc2edc4f7d645a250c2473f0e90597698b7cd21630d8b97b0d813"},"schema_version":"1.0","source":{"id":"2209.06620","kind":"arxiv","version":3}},"canonical_sha256":"0d9d11b651fa7c15d2d62b5e73b1a11192e448d43e053e2a629169ac2400c4bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d9d11b651fa7c15d2d62b5e73b1a11192e448d43e053e2a629169ac2400c4bf","first_computed_at":"2026-07-05T05:36:18.713189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:18.713189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gZIonu+ZjyTdjMv+97+r+NYDiw9WCM2jRIfGwmSZcGOX7DcR6Z8PO2Fgsex2yT44rOeI7LyO3VqLkTTmxC5LCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:18.713850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.06620","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d06df5c8f60d73687c448707d728bcfb5d3ab1df1904bcbae020b8e9ed32a20","sha256:20a63e423e40564e4092fad220544b85ba767f2c731cffb4f553f61e9300e044"],"state_sha256":"8bfb8ad9b145720e204fef9bac7173d1b12a3f256f710e6340f37d194004ca08"}