{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R7YWL2TZO6YIJ7FD2VIRCBP7FL","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":"90f073459e3768914410147ae3c85768b41814d3a288de923a33f36780c6505d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-08T12:19:04Z","title_canon_sha256":"1043db61929a171dbf9c9081cbb6d3c5241e86f5453e4fbffd6802e8ac3d4b51"},"schema_version":"1.0","source":{"id":"2404.05440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05440","created_at":"2026-07-05T08:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05440v1","created_at":"2026-07-05T08:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05440","created_at":"2026-07-05T08:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"R7YWL2TZO6YI","created_at":"2026-07-05T08:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"R7YWL2TZO6YIJ7FD","created_at":"2026-07-05T08:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"R7YWL2TZ","created_at":"2026-07-05T08:05:40Z"}],"graph_snapshots":[{"event_id":"sha256:935c888926f32f3dd6e1cfffe86bddbec0c31a7f31b2e58794721f992cdd3dda","target":"graph","created_at":"2026-07-05T08:05:40Z","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/2404.05440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The standard formulation of Markov decision processes (MDPs) assumes that the agent's decisions are executed immediately. However, in numerous realistic applications such as robotics or healthcare, actions are performed with a delay whose value can even be stochastic. In this work, we introduce stochastic delayed execution MDPs, a new formalism addressing random delays without resorting to state augmentation. We show that given observed delay values, it is sufficient to perform a policy search in the class of Markov policies in order to reach optimal performance, thus extending the determinist","authors_text":"David Valensi, Esther Derman, Gal Dalal, Shie Mannor","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-08T12:19:04Z","title":"Tree Search-Based Policy Optimization under Stochastic Execution Delay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05440","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":"sha256:62a08c98cb5cb8d5b3d38932b54766f73bd374bab054af7626747c9ff58c5bc1","target":"record","created_at":"2026-07-05T08:05:40Z","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":"90f073459e3768914410147ae3c85768b41814d3a288de923a33f36780c6505d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-08T12:19:04Z","title_canon_sha256":"1043db61929a171dbf9c9081cbb6d3c5241e86f5453e4fbffd6802e8ac3d4b51"},"schema_version":"1.0","source":{"id":"2404.05440","kind":"arxiv","version":1}},"canonical_sha256":"8ff165ea7977b084fca3d5511105ff2aeb325cc7fdf43511587d16298e9191f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ff165ea7977b084fca3d5511105ff2aeb325cc7fdf43511587d16298e9191f9","first_computed_at":"2026-07-05T08:05:40.987405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:40.987405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YgWgdRhDdnQfodfKYKbnBHMplKBaLFE1ptiBrPgPbLSU0WSDy0DaJuqg9a1WFMmGlWd601EZuoiOdD+4vWOLDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:40.987870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62a08c98cb5cb8d5b3d38932b54766f73bd374bab054af7626747c9ff58c5bc1","sha256:935c888926f32f3dd6e1cfffe86bddbec0c31a7f31b2e58794721f992cdd3dda"],"state_sha256":"a97a57f34d6292bad809c3b6f7a9e71f60bc87c8b53496007f6ba92cc14abaaa"}