{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MHIFF3OIHPRJU7T7QPBYQZRNYN","short_pith_number":"pith:MHIFF3OI","schema_version":"1.0","canonical_sha256":"61d052edc83be29a7e7f83c388662dc37289a1fd3e4327e6e88ff496ac20f9e8","source":{"kind":"arxiv","id":"2307.15890","version":1},"attestation_state":"computed","paper":{"title":"First-order Policy Optimization for Robust Policy Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Guanghui Lan, Yan Li","submitted_at":"2023-07-29T05:22:43Z","abstract_excerpt":"We adopt a policy optimization viewpoint towards policy evaluation for robust Markov decision process with $\\mathrm{s}$-rectangular ambiguity sets. The developed method, named first-order policy evaluation (FRPE), provides the first unified framework for robust policy evaluation in both deterministic (offline) and stochastic (online) settings, with either tabular representation or generic function approximation. In particular, we establish linear convergence in the deterministic setting, and $\\tilde{\\mathcal{O}}(1/\\epsilon^2)$ sample complexity in the stochastic setting. FRPE also extends natu"},"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":"2307.15890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-29T05:22:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c33ccc8c6dae384347f3070a9997e6a81048a10ac41f079bb5566e91502c0c59","abstract_canon_sha256":"0e7bb9cd8d745861e7e1cc6aa464b9e5865ea00d3121b89adf366b75a4e58c48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:55.820338Z","signature_b64":"dFz+WTRakYjUQVfn2oAb90Xmes1F89SA4JzbVo8G3W739RXCFQ3BIxAPsa43fWYekeplv6QpJoiGUqVIibowDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d052edc83be29a7e7f83c388662dc37289a1fd3e4327e6e88ff496ac20f9e8","last_reissued_at":"2026-07-05T06:35:55.819847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:55.819847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First-order Policy Optimization for Robust Policy Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Guanghui Lan, Yan Li","submitted_at":"2023-07-29T05:22:43Z","abstract_excerpt":"We adopt a policy optimization viewpoint towards policy evaluation for robust Markov decision process with $\\mathrm{s}$-rectangular ambiguity sets. The developed method, named first-order policy evaluation (FRPE), provides the first unified framework for robust policy evaluation in both deterministic (offline) and stochastic (online) settings, with either tabular representation or generic function approximation. In particular, we establish linear convergence in the deterministic setting, and $\\tilde{\\mathcal{O}}(1/\\epsilon^2)$ sample complexity in the stochastic setting. FRPE also extends natu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15890","kind":"arxiv","version":1},"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/2307.15890/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":"2307.15890","created_at":"2026-07-05T06:35:55.819911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15890v1","created_at":"2026-07-05T06:35:55.819911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15890","created_at":"2026-07-05T06:35:55.819911+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHIFF3OIHPRJ","created_at":"2026-07-05T06:35:55.819911+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHIFF3OIHPRJU7T7","created_at":"2026-07-05T06:35:55.819911+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHIFF3OI","created_at":"2026-07-05T06:35:55.819911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28706","citing_title":"Robust Markov Decision Processes on Continuous State Spaces","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN","json":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN.json","graph_json":"https://pith.science/api/pith-number/MHIFF3OIHPRJU7T7QPBYQZRNYN/graph.json","events_json":"https://pith.science/api/pith-number/MHIFF3OIHPRJU7T7QPBYQZRNYN/events.json","paper":"https://pith.science/paper/MHIFF3OI"},"agent_actions":{"view_html":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN","download_json":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN.json","view_paper":"https://pith.science/paper/MHIFF3OI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15890&json=true","fetch_graph":"https://pith.science/api/pith-number/MHIFF3OIHPRJU7T7QPBYQZRNYN/graph.json","fetch_events":"https://pith.science/api/pith-number/MHIFF3OIHPRJU7T7QPBYQZRNYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN/action/storage_attestation","attest_author":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN/action/author_attestation","sign_citation":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN/action/citation_signature","submit_replication":"https://pith.science/pith/MHIFF3OIHPRJU7T7QPBYQZRNYN/action/replication_record"}},"created_at":"2026-07-05T06:35:55.819911+00:00","updated_at":"2026-07-05T06:35:55.819911+00:00"}