{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R7YWL2TZO6YIJ7FD2VIRCBP7FL","short_pith_number":"pith:R7YWL2TZ","schema_version":"1.0","canonical_sha256":"8ff165ea7977b084fca3d5511105ff2aeb325cc7fdf43511587d16298e9191f9","source":{"kind":"arxiv","id":"2404.05440","version":1},"attestation_state":"computed","paper":{"title":"Tree Search-Based Policy Optimization under Stochastic Execution Delay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Valensi, Esther Derman, Gal Dalal, Shie Mannor","submitted_at":"2024-04-08T12:19:04Z","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"},"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":"2404.05440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-08T12:19:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1043db61929a171dbf9c9081cbb6d3c5241e86f5453e4fbffd6802e8ac3d4b51","abstract_canon_sha256":"90f073459e3768914410147ae3c85768b41814d3a288de923a33f36780c6505d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:40.987870Z","signature_b64":"YgWgdRhDdnQfodfKYKbnBHMplKBaLFE1ptiBrPgPbLSU0WSDy0DaJuqg9a1WFMmGlWd601EZuoiOdD+4vWOLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ff165ea7977b084fca3d5511105ff2aeb325cc7fdf43511587d16298e9191f9","last_reissued_at":"2026-07-05T08:05:40.987405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:40.987405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tree Search-Based Policy Optimization under Stochastic Execution Delay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Valensi, Esther Derman, Gal Dalal, Shie Mannor","submitted_at":"2024-04-08T12:19:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05440","kind":"arxiv","version":1},"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/2404.05440/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":"2404.05440","created_at":"2026-07-05T08:05:40.987465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05440v1","created_at":"2026-07-05T08:05:40.987465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05440","created_at":"2026-07-05T08:05:40.987465+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7YWL2TZO6YI","created_at":"2026-07-05T08:05:40.987465+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7YWL2TZO6YIJ7FD","created_at":"2026-07-05T08:05:40.987465+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7YWL2TZ","created_at":"2026-07-05T08:05:40.987465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.20869","citing_title":"Model-Based Reinforcement Learning under Random Observation Delays","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL","json":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL.json","graph_json":"https://pith.science/api/pith-number/R7YWL2TZO6YIJ7FD2VIRCBP7FL/graph.json","events_json":"https://pith.science/api/pith-number/R7YWL2TZO6YIJ7FD2VIRCBP7FL/events.json","paper":"https://pith.science/paper/R7YWL2TZ"},"agent_actions":{"view_html":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL","download_json":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL.json","view_paper":"https://pith.science/paper/R7YWL2TZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05440&json=true","fetch_graph":"https://pith.science/api/pith-number/R7YWL2TZO6YIJ7FD2VIRCBP7FL/graph.json","fetch_events":"https://pith.science/api/pith-number/R7YWL2TZO6YIJ7FD2VIRCBP7FL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL/action/storage_attestation","attest_author":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL/action/author_attestation","sign_citation":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL/action/citation_signature","submit_replication":"https://pith.science/pith/R7YWL2TZO6YIJ7FD2VIRCBP7FL/action/replication_record"}},"created_at":"2026-07-05T08:05:40.987465+00:00","updated_at":"2026-07-05T08:05:40.987465+00:00"}