{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:VJ7RAO3SQT5DAM3NF6IWJYT6PI","short_pith_number":"pith:VJ7RAO3S","schema_version":"1.0","canonical_sha256":"aa7f103b7284fa30336d2f9164e27e7a3b3ce0b3a8e8ee9e7bdabe2a663d3386","source":{"kind":"arxiv","id":"1605.09703","version":1},"attestation_state":"computed","paper":{"title":"Policy learning for time-bounded reachability in Continuous-Time Markov Decision Processes via doubly-stochastic gradient ascent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Dimitrios Milios, Ezio Bartocci, Guido Sanguinetti, Luca Bortolussi, Tom\\v{a}\\v{s} Br\\'azdil","submitted_at":"2016-05-31T16:28:02Z","abstract_excerpt":"Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central problem is how to devise a policy to control the system in order to maximise the probability of satisfying a set of temporal logic specifications. Here we present a novel approach based on statistical model checking and an unbiased estimation of a functional gradient in the space of possible policies. The statistical approach has several advantages over conventional approaches based on uniformisation, as it can also be a"},"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":"1605.09703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2016-05-31T16:28:02Z","cross_cats_sorted":[],"title_canon_sha256":"553623d8a78a1c9ae2018baa9d189fc659a834f6516b5517f41c27cfdc549a02","abstract_canon_sha256":"d0ea5702069749f6b01319fcd9e904f8fb87ddd593380744f7ed5cb7a90e74e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:10.328666Z","signature_b64":"zRjMpYtwX48Aapjvfws/fLsJzEh1jIY5f/Pd90qvCUSI2bUn51+NZbYxJVUGTQcmJHxwf96/LyigVS7E6LCnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa7f103b7284fa30336d2f9164e27e7a3b3ce0b3a8e8ee9e7bdabe2a663d3386","last_reissued_at":"2026-05-18T01:13:10.328036Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:10.328036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy learning for time-bounded reachability in Continuous-Time Markov Decision Processes via doubly-stochastic gradient ascent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Dimitrios Milios, Ezio Bartocci, Guido Sanguinetti, Luca Bortolussi, Tom\\v{a}\\v{s} Br\\'azdil","submitted_at":"2016-05-31T16:28:02Z","abstract_excerpt":"Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central problem is how to devise a policy to control the system in order to maximise the probability of satisfying a set of temporal logic specifications. Here we present a novel approach based on statistical model checking and an unbiased estimation of a functional gradient in the space of possible policies. The statistical approach has several advantages over conventional approaches based on uniformisation, as it can also be a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09703","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":""},"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":"1605.09703","created_at":"2026-05-18T01:13:10.328138+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.09703v1","created_at":"2026-05-18T01:13:10.328138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09703","created_at":"2026-05-18T01:13:10.328138+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJ7RAO3SQT5D","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJ7RAO3SQT5DAM3N","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJ7RAO3S","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI","json":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI.json","graph_json":"https://pith.science/api/pith-number/VJ7RAO3SQT5DAM3NF6IWJYT6PI/graph.json","events_json":"https://pith.science/api/pith-number/VJ7RAO3SQT5DAM3NF6IWJYT6PI/events.json","paper":"https://pith.science/paper/VJ7RAO3S"},"agent_actions":{"view_html":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI","download_json":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI.json","view_paper":"https://pith.science/paper/VJ7RAO3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.09703&json=true","fetch_graph":"https://pith.science/api/pith-number/VJ7RAO3SQT5DAM3NF6IWJYT6PI/graph.json","fetch_events":"https://pith.science/api/pith-number/VJ7RAO3SQT5DAM3NF6IWJYT6PI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI/action/storage_attestation","attest_author":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI/action/author_attestation","sign_citation":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI/action/citation_signature","submit_replication":"https://pith.science/pith/VJ7RAO3SQT5DAM3NF6IWJYT6PI/action/replication_record"}},"created_at":"2026-05-18T01:13:10.328138+00:00","updated_at":"2026-05-18T01:13:10.328138+00:00"}