{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MHIFF3OIHPRJU7T7QPBYQZRNYN","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":"0e7bb9cd8d745861e7e1cc6aa464b9e5865ea00d3121b89adf366b75a4e58c48","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-29T05:22:43Z","title_canon_sha256":"c33ccc8c6dae384347f3070a9997e6a81048a10ac41f079bb5566e91502c0c59"},"schema_version":"1.0","source":{"id":"2307.15890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15890","created_at":"2026-07-05T06:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15890v1","created_at":"2026-07-05T06:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15890","created_at":"2026-07-05T06:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"MHIFF3OIHPRJ","created_at":"2026-07-05T06:35:55Z"},{"alias_kind":"pith_short_16","alias_value":"MHIFF3OIHPRJU7T7","created_at":"2026-07-05T06:35:55Z"},{"alias_kind":"pith_short_8","alias_value":"MHIFF3OI","created_at":"2026-07-05T06:35:55Z"}],"graph_snapshots":[{"event_id":"sha256:49823825474bd4eda9e8b7789cca4232ac27fe52a63c5843270d4839d8717ffb","target":"graph","created_at":"2026-07-05T06:35:55Z","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/2307.15890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guanghui Lan, Yan Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-29T05:22:43Z","title":"First-order Policy Optimization for Robust Policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15890","kind":"arxiv","version":1},"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":"sha256:17aff7868b358e9be88ad8e2e2138bdd22ad54d882b4f6a8ce9989e50bfd9854","target":"record","created_at":"2026-07-05T06:35:55Z","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":"0e7bb9cd8d745861e7e1cc6aa464b9e5865ea00d3121b89adf366b75a4e58c48","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-29T05:22:43Z","title_canon_sha256":"c33ccc8c6dae384347f3070a9997e6a81048a10ac41f079bb5566e91502c0c59"},"schema_version":"1.0","source":{"id":"2307.15890","kind":"arxiv","version":1}},"canonical_sha256":"61d052edc83be29a7e7f83c388662dc37289a1fd3e4327e6e88ff496ac20f9e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61d052edc83be29a7e7f83c388662dc37289a1fd3e4327e6e88ff496ac20f9e8","first_computed_at":"2026-07-05T06:35:55.819847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:55.819847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dFz+WTRakYjUQVfn2oAb90Xmes1F89SA4JzbVo8G3W739RXCFQ3BIxAPsa43fWYekeplv6QpJoiGUqVIibowDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:55.820338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17aff7868b358e9be88ad8e2e2138bdd22ad54d882b4f6a8ce9989e50bfd9854","sha256:49823825474bd4eda9e8b7789cca4232ac27fe52a63c5843270d4839d8717ffb"],"state_sha256":"abc076ae1c9c46b4405a88e5399eb5dd594e71738ac44981942c03c04be27248"}