{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LUYEGKDCK6STFNAR6KWXNETMRX","short_pith_number":"pith:LUYEGKDC","schema_version":"1.0","canonical_sha256":"5d3043286257a532b411f2ad76926c8dcde8333703759dc6cd2d9548311fbe57","source":{"kind":"arxiv","id":"2011.00632","version":2},"attestation_state":"computed","paper":{"title":"Synthesis of Discounted-Reward Optimal Policies for Markov Decision Processes Under Linear Temporal Logic Specifications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL","cs.SY"],"primary_cat":"eess.SY","authors_text":"Krishna C. Kalagarla, Pierluigi Nuzzo, Rahul Jain","submitted_at":"2020-11-01T21:42:57Z","abstract_excerpt":"We present a method to find an optimal policy with respect to a reward function for a discounted Markov decision process under general linear temporal logic (LTL) specifications. Previous work has either focused on maximizing a cumulative reward objective under finite-duration tasks, specified by syntactically co-safe LTL, or maximizing an average reward for persistent (e.g., surveillance) tasks. This paper extends and generalizes these results by introducing a pair of occupancy measures to express the LTL satisfaction objective and the expected discounted reward objective, respectively. These"},"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":"2011.00632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2020-11-01T21:42:57Z","cross_cats_sorted":["cs.FL","cs.SY"],"title_canon_sha256":"bcb5ae19406bb4550324c44ae427c86d1892132006116bf425ca6b3740d82134","abstract_canon_sha256":"cf901084dee69f986eecaf40dd5d025e4e10c2418a54bfe27b0f1da254f4ddbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:27.764650Z","signature_b64":"4dZg+oOfMitSXAP3KR/7S10UN1EIu8Ajqev8OLPlbYUs3SX2Fq4fZcCsASbD08VXlfomeTBN7csbMbwkm1mXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d3043286257a532b411f2ad76926c8dcde8333703759dc6cd2d9548311fbe57","last_reissued_at":"2026-07-05T02:25:27.764207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:27.764207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthesis of Discounted-Reward Optimal Policies for Markov Decision Processes Under Linear Temporal Logic Specifications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL","cs.SY"],"primary_cat":"eess.SY","authors_text":"Krishna C. Kalagarla, Pierluigi Nuzzo, Rahul Jain","submitted_at":"2020-11-01T21:42:57Z","abstract_excerpt":"We present a method to find an optimal policy with respect to a reward function for a discounted Markov decision process under general linear temporal logic (LTL) specifications. Previous work has either focused on maximizing a cumulative reward objective under finite-duration tasks, specified by syntactically co-safe LTL, or maximizing an average reward for persistent (e.g., surveillance) tasks. This paper extends and generalizes these results by introducing a pair of occupancy measures to express the LTL satisfaction objective and the expected discounted reward objective, respectively. These"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.00632","kind":"arxiv","version":2},"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/2011.00632/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":"2011.00632","created_at":"2026-07-05T02:25:27.764255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.00632v2","created_at":"2026-07-05T02:25:27.764255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.00632","created_at":"2026-07-05T02:25:27.764255+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUYEGKDCK6ST","created_at":"2026-07-05T02:25:27.764255+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUYEGKDCK6STFNAR","created_at":"2026-07-05T02:25:27.764255+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUYEGKDC","created_at":"2026-07-05T02:25:27.764255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2103.14600","citing_title":"Model-Free Learning of Safe yet Effective Controllers","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX","json":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX.json","graph_json":"https://pith.science/api/pith-number/LUYEGKDCK6STFNAR6KWXNETMRX/graph.json","events_json":"https://pith.science/api/pith-number/LUYEGKDCK6STFNAR6KWXNETMRX/events.json","paper":"https://pith.science/paper/LUYEGKDC"},"agent_actions":{"view_html":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX","download_json":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX.json","view_paper":"https://pith.science/paper/LUYEGKDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.00632&json=true","fetch_graph":"https://pith.science/api/pith-number/LUYEGKDCK6STFNAR6KWXNETMRX/graph.json","fetch_events":"https://pith.science/api/pith-number/LUYEGKDCK6STFNAR6KWXNETMRX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX/action/storage_attestation","attest_author":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX/action/author_attestation","sign_citation":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX/action/citation_signature","submit_replication":"https://pith.science/pith/LUYEGKDCK6STFNAR6KWXNETMRX/action/replication_record"}},"created_at":"2026-07-05T02:25:27.764255+00:00","updated_at":"2026-07-05T02:25:27.764255+00:00"}