{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JIMR4WOIZLMO27HDKMB34QZ763","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":"984b5e4433a48591d57063dcde735baf8f9a2cedb2d1dba694f80bdf09f35c6a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-06-01T02:40:29Z","title_canon_sha256":"f097c7afaa1a2bfa3e3b80a2bd4d661d60965d00687d82c00c58bb5c9ed9b7e6"},"schema_version":"1.0","source":{"id":"2406.00274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00274","created_at":"2026-07-05T08:25:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00274v1","created_at":"2026-07-05T08:25:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00274","created_at":"2026-07-05T08:25:59Z"},{"alias_kind":"pith_short_12","alias_value":"JIMR4WOIZLMO","created_at":"2026-07-05T08:25:59Z"},{"alias_kind":"pith_short_16","alias_value":"JIMR4WOIZLMO27HD","created_at":"2026-07-05T08:25:59Z"},{"alias_kind":"pith_short_8","alias_value":"JIMR4WOI","created_at":"2026-07-05T08:25:59Z"}],"graph_snapshots":[{"event_id":"sha256:964a9302b7b641720838c6cf21781086862cb04b1974c8b6a6ab1e3fb473e551","target":"graph","created_at":"2026-07-05T08:25:59Z","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/2406.00274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust Markov Decision Processes (RMDPs) have recently been recognized as a valuable and promising approach to discovering a policy with creditable performance, particularly in the presence of a dynamic environment and estimation errors in the transition matrix due to limited data. Despite extensive exploration of dynamic programming algorithms for solving RMDPs, there has been a notable upswing in interest in developing efficient algorithms using the policy gradient method. In this paper, we propose the first single-loop robust policy gradient (SRPG) method with the global optimality guarante","authors_text":"Chenyu Xue, Qi Deng, Yinyu Ye, Zhenwei Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-06-01T02:40:29Z","title":"A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00274","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":"sha256:67d69e1de87ab966dc3feaf64725726d84058222191667aea4a14e85434d3ff7","target":"record","created_at":"2026-07-05T08:25:59Z","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":"984b5e4433a48591d57063dcde735baf8f9a2cedb2d1dba694f80bdf09f35c6a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-06-01T02:40:29Z","title_canon_sha256":"f097c7afaa1a2bfa3e3b80a2bd4d661d60965d00687d82c00c58bb5c9ed9b7e6"},"schema_version":"1.0","source":{"id":"2406.00274","kind":"arxiv","version":1}},"canonical_sha256":"4a191e59c8cad8ed7ce35303be433ff6e7d656223fe112f1ce320cca8f5cecf4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a191e59c8cad8ed7ce35303be433ff6e7d656223fe112f1ce320cca8f5cecf4","first_computed_at":"2026-07-05T08:25:59.428582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:59.428582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6NchhTXXl15G4ODTPmDrRau+NmUMgIBqttJ7LsHf8st8QLOjCJdmFktJQ6wIZJZ8t6aYC5AsTAMEiws97X11Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:59.429124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67d69e1de87ab966dc3feaf64725726d84058222191667aea4a14e85434d3ff7","sha256:964a9302b7b641720838c6cf21781086862cb04b1974c8b6a6ab1e3fb473e551"],"state_sha256":"6391a85d105b52cc44c9613f476955645dc45cc620551aff16608044e039ad59"}