{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FUN5GJNVZFYEGYV5ZH67OPL4VT","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":"cc0ec36d19d8fbdc6db0ab7e94947236089b2f623b0856d61a549677687bb688","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T01:25:20Z","title_canon_sha256":"ec19bc947e75fb05fd94817e8ca4cd364619d8a2e0962deba2e93b39aa511a07"},"schema_version":"1.0","source":{"id":"2606.04335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04335","created_at":"2026-06-04T01:09:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04335v1","created_at":"2026-06-04T01:09:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04335","created_at":"2026-06-04T01:09:04Z"},{"alias_kind":"pith_short_12","alias_value":"FUN5GJNVZFYE","created_at":"2026-06-04T01:09:04Z"},{"alias_kind":"pith_short_16","alias_value":"FUN5GJNVZFYEGYV5","created_at":"2026-06-04T01:09:04Z"},{"alias_kind":"pith_short_8","alias_value":"FUN5GJNV","created_at":"2026-06-04T01:09:04Z"}],"graph_snapshots":[{"event_id":"sha256:82626e9929ad8fd4d468a805d9fd6e40572cbad7611959bee1188944ed7455cb","target":"graph","created_at":"2026-06-04T01:09:04Z","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/2606.04335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics. Traditional RMDPs consider discrete-time dynamics and recently, sample-efficient policy gradient algorithms have been considered in this context. This paper investigates policy gradient algorithms within a continuous-time RMDP framework. Policy gradients and adversarial gradients are derived using pathwise and adjoint-based formulas for stochastic and ordinary differential equations. We propose double-loop optimis","authors_text":"Atsushi Nitanda, David M. Bossens, Tanya Veeravalli","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T01:25:20Z","title":"Policy Gradient for Continuous-Time Robust Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04335","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":"sha256:440aa8d51ebfcb476c3184a3dc8ab34b9e2bbf414837c6ba2de05b5620c22b03","target":"record","created_at":"2026-06-04T01:09:04Z","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":"cc0ec36d19d8fbdc6db0ab7e94947236089b2f623b0856d61a549677687bb688","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T01:25:20Z","title_canon_sha256":"ec19bc947e75fb05fd94817e8ca4cd364619d8a2e0962deba2e93b39aa511a07"},"schema_version":"1.0","source":{"id":"2606.04335","kind":"arxiv","version":1}},"canonical_sha256":"2d1bd325b5c9704362bdc9fdf73d7cacf9678429e7b17bd463331dd9aa033914","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d1bd325b5c9704362bdc9fdf73d7cacf9678429e7b17bd463331dd9aa033914","first_computed_at":"2026-06-04T01:09:04.043994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:04.043994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"86UiLg9mTIVwNi9NLyEjf6KU+API1w3TS4u+eCgExohdE66QPKcJxrHVxI+RL5mknFo+17GLzard4hGNmmLDAg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:04.044432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:440aa8d51ebfcb476c3184a3dc8ab34b9e2bbf414837c6ba2de05b5620c22b03","sha256:82626e9929ad8fd4d468a805d9fd6e40572cbad7611959bee1188944ed7455cb"],"state_sha256":"2dae9d9982865a79e36842cf44a239fce21ee9af781f25c996638b51fadabd5b"}