{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QXKTLSM6CFSG3OTGPGXUZSWZUY","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":"ddd4c5bd5a6e03ecb13030c2eaaaa3db68fa5cb6ab39e90b0228b5463c1a1fce","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","title_canon_sha256":"3427e28384ce67f481b2315922dbafff2e4aae9cef56353ee02c151033bb55f4"},"schema_version":"1.0","source":{"id":"2209.10579","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10579","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10579v2","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10579","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"QXKTLSM6CFSG","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"QXKTLSM6CFSG3OTG","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"QXKTLSM6","created_at":"2026-07-05T06:19:16Z"}],"graph_snapshots":[{"event_id":"sha256:f49286143a4f8c6152ec608bcaafe0541fe3c894e011294088165e9bc90f391f","target":"graph","created_at":"2026-07-05T06:19:16Z","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/2209.10579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guanghui Lan, Tuo Zhao, Yan Li","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","title":"First-order Policy Optimization for Robust Markov Decision Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10579","kind":"arxiv","version":2},"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":"sha256:96ee7031b8adc4801a15709f0457188591a26b401f1b5b73fe342998ec2ac6d5","target":"record","created_at":"2026-07-05T06:19:16Z","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":"ddd4c5bd5a6e03ecb13030c2eaaaa3db68fa5cb6ab39e90b0228b5463c1a1fce","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","title_canon_sha256":"3427e28384ce67f481b2315922dbafff2e4aae9cef56353ee02c151033bb55f4"},"schema_version":"1.0","source":{"id":"2209.10579","kind":"arxiv","version":2}},"canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","first_computed_at":"2026-07-05T06:19:16.436765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:16.436765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B/eBrt0HAIzdXIpRjynBkYH5BCNYUwWe7syO6Dou1/c6vOTofIPYnpM9uIf4EaxFifYLIqvqyeHzufZBzVtuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:16.437244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.10579","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96ee7031b8adc4801a15709f0457188591a26b401f1b5b73fe342998ec2ac6d5","sha256:f49286143a4f8c6152ec608bcaafe0541fe3c894e011294088165e9bc90f391f"],"state_sha256":"7136544b3891160d1b2aded1a4379d9a43627c148b7195b8ea6280809674aca3"}