{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QXKTLSM6CFSG3OTGPGXUZSWZUY","short_pith_number":"pith:QXKTLSM6","schema_version":"1.0","canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","source":{"kind":"arxiv","id":"2209.10579","version":2},"attestation_state":"computed","paper":{"title":"First-order Policy Optimization for Robust Markov Decision Process","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Guanghui Lan, Tuo Zhao, Yan Li","submitted_at":"2022-09-21T18:10:28Z","abstract_excerpt":"We consider the problem of solving robust Markov decision process (MDP), which involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. The goal of planning is to find a robust policy that optimizes the worst-case values against the transition uncertainties, and thus encompasses the standard MDP planning as a special case. For $(\\mathbf{s},\\mathbf{a})$-rectangular uncertainty sets, we establish several structural observations on the robust objective, which facilitates the development of a policy-based first-order method, namely the robust policy m"},"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":"2209.10579","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"3427e28384ce67f481b2315922dbafff2e4aae9cef56353ee02c151033bb55f4","abstract_canon_sha256":"ddd4c5bd5a6e03ecb13030c2eaaaa3db68fa5cb6ab39e90b0228b5463c1a1fce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:16.437244Z","signature_b64":"B/eBrt0HAIzdXIpRjynBkYH5BCNYUwWe7syO6Dou1/c6vOTofIPYnpM9uIf4EaxFifYLIqvqyeHzufZBzVtuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","last_reissued_at":"2026-07-05T06:19:16.436765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:16.436765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First-order Policy Optimization for Robust Markov Decision Process","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Guanghui Lan, Tuo Zhao, Yan Li","submitted_at":"2022-09-21T18:10:28Z","abstract_excerpt":"We consider the problem of solving robust Markov decision process (MDP), which involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. The goal of planning is to find a robust policy that optimizes the worst-case values against the transition uncertainties, and thus encompasses the standard MDP planning as a special case. For $(\\mathbf{s},\\mathbf{a})$-rectangular uncertainty sets, we establish several structural observations on the robust objective, which facilitates the development of a policy-based first-order method, namely the robust policy m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10579","kind":"arxiv","version":2},"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/2209.10579/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":"2209.10579","created_at":"2026-07-05T06:19:16.436822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10579v2","created_at":"2026-07-05T06:19:16.436822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10579","created_at":"2026-07-05T06:19:16.436822+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXKTLSM6CFSG","created_at":"2026-07-05T06:19:16.436822+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXKTLSM6CFSG3OTG","created_at":"2026-07-05T06:19:16.436822+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXKTLSM6","created_at":"2026-07-05T06:19:16.436822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28706","citing_title":"Robust Markov Decision Processes on Continuous State Spaces","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31309","citing_title":"Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov Framework","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2408.16286","citing_title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10671","citing_title":"Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21177","citing_title":"Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06039","citing_title":"Value Mirror Descent for Reinforcement Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04795","citing_title":"Sample Complexity for Markov Decision Processes and Stochastic Optimal Control with Static Risk Measures","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY","json":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY.json","graph_json":"https://pith.science/api/pith-number/QXKTLSM6CFSG3OTGPGXUZSWZUY/graph.json","events_json":"https://pith.science/api/pith-number/QXKTLSM6CFSG3OTGPGXUZSWZUY/events.json","paper":"https://pith.science/paper/QXKTLSM6"},"agent_actions":{"view_html":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY","download_json":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY.json","view_paper":"https://pith.science/paper/QXKTLSM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10579&json=true","fetch_graph":"https://pith.science/api/pith-number/QXKTLSM6CFSG3OTGPGXUZSWZUY/graph.json","fetch_events":"https://pith.science/api/pith-number/QXKTLSM6CFSG3OTGPGXUZSWZUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/action/storage_attestation","attest_author":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/action/author_attestation","sign_citation":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/action/citation_signature","submit_replication":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/action/replication_record"}},"created_at":"2026-07-05T06:19:16.436822+00:00","updated_at":"2026-07-05T06:19:16.436822+00:00"}