{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CG7ZBZFIOMYSTAXX5ZFKNMY3KX","short_pith_number":"pith:CG7ZBZFI","schema_version":"1.0","canonical_sha256":"11bf90e4a873312982f7ee4aa6b31b55cd7a4e8cc92cbfc5c625b86b41d07e29","source":{"kind":"arxiv","id":"2603.09344","version":3},"attestation_state":"computed","paper":{"title":"Robust Regularized Policy Iteration under Transition Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Dongxu Zhang, Hongqiang Lin, Pengfei Wang, Qixian Huang, Weihao Tang, Yiding Sun, Zhenghui Fu","submitted_at":"2026-03-10T08:18:27Z","abstract_excerpt":"Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs where value estimates and learned dynamics are unreliable. To address policy-induced extrapolation and transition uncertainty in a unified framework, we formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set and optimizing the policy against the worst-case dynamics. We propose Robu"},"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":"2603.09344","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-10T08:18:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8b833861e770c85688edeb56612806732967813773fd077622bc60e719fa574f","abstract_canon_sha256":"11bc489f9d539d3a895ed745d66e08c70c540469e289fbede25f11b2d8210fcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:21.878934Z","signature_b64":"n9lAlwa9W2u4w1TUu6TocJhHIPVIV350f4zftbZMDAH8n8BT7CKl1vF4vrp5MLSacMSbutHexpRXPuFuQNEPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11bf90e4a873312982f7ee4aa6b31b55cd7a4e8cc92cbfc5c625b86b41d07e29","last_reissued_at":"2026-06-19T16:11:21.878541Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:21.878541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Regularized Policy Iteration under Transition Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Dongxu Zhang, Hongqiang Lin, Pengfei Wang, Qixian Huang, Weihao Tang, Yiding Sun, Zhenghui Fu","submitted_at":"2026-03-10T08:18:27Z","abstract_excerpt":"Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs where value estimates and learned dynamics are unreliable. To address policy-induced extrapolation and transition uncertainty in a unified framework, we formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set and optimizing the policy against the worst-case dynamics. We propose Robu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09344","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/2603.09344/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":"2603.09344","created_at":"2026-06-19T16:11:21.878598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.09344v3","created_at":"2026-06-19T16:11:21.878598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09344","created_at":"2026-06-19T16:11:21.878598+00:00"},{"alias_kind":"pith_short_12","alias_value":"CG7ZBZFIOMYS","created_at":"2026-06-19T16:11:21.878598+00:00"},{"alias_kind":"pith_short_16","alias_value":"CG7ZBZFIOMYSTAXX","created_at":"2026-06-19T16:11:21.878598+00:00"},{"alias_kind":"pith_short_8","alias_value":"CG7ZBZFI","created_at":"2026-06-19T16:11:21.878598+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/CG7ZBZFIOMYSTAXX5ZFKNMY3KX","json":"https://pith.science/pith/CG7ZBZFIOMYSTAXX5ZFKNMY3KX.json","graph_json":"https://pith.science/api/pith-number/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/graph.json","events_json":"https://pith.science/api/pith-number/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/events.json","paper":"https://pith.science/paper/CG7ZBZFI"},"agent_actions":{"view_html":"https://pith.science/pith/CG7ZBZFIOMYSTAXX5ZFKNMY3KX","download_json":"https://pith.science/pith/CG7ZBZFIOMYSTAXX5ZFKNMY3KX.json","view_paper":"https://pith.science/paper/CG7ZBZFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.09344&json=true","fetch_graph":"https://pith.science/api/pith-number/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/graph.json","fetch_events":"https://pith.science/api/pith-number/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/action/storage_attestation","attest_author":"https://pith.science/pith/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/action/author_attestation","sign_citation":"https://pith.science/pith/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/action/citation_signature","submit_replication":"https://pith.science/pith/CG7ZBZFIOMYSTAXX5ZFKNMY3KX/action/replication_record"}},"created_at":"2026-06-19T16:11:21.878598+00:00","updated_at":"2026-06-19T16:11:21.878598+00:00"}