{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7WFAOFADDACXS4J4FAGU47VKMX","short_pith_number":"pith:7WFAOFAD","schema_version":"1.0","canonical_sha256":"fd8a071403180579713c280d4e7eaa65c8abe873b289e3cf8168042897bfc462","source":{"kind":"arxiv","id":"1605.04591","version":2},"attestation_state":"computed","paper":{"title":"Ordinary Differential Equation Methods For Markov Decision Processes and Application to Kullback-Leibler Control Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"math.OC","authors_text":"Ana Bu\\v{s}i\\'c, Sean Meyn","submitted_at":"2016-05-15T18:48:55Z","abstract_excerpt":"A new approach to computation of optimal policies for MDP (Markov decision process) models is introduced. The main idea is to solve not one, but an entire family of MDPs, parameterized by a weighting factor $\\zeta$ that appears in the one-step reward function. For an MDP with $d$ states, the family of value functions $\\{ h^*_\\zeta : \\zeta\\in\\Re\\}$ is the solution to an ODE, $$ \\frac{d}{d\\zeta} h^*_\\zeta = {\\cal V}(h^*_\\zeta) $$ where the vector field ${\\cal V}\\colon\\Re^d\\to\\Re^d$ has a simple form, based on a matrix inverse.\n  This general methodology is applied to a family of average-cost opt"},"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":"1605.04591","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-05-15T18:48:55Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"1d5adbeac69c81a80ada35b0d9c386a56c59e9ab09e7ba9c8beff6a21275aaf2","abstract_canon_sha256":"a0eee2421c80fb6dc4b363df80cf20e625ca323135eef3f656aa721075f1f875"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:40.009284Z","signature_b64":"Ez3ntE6abJr9B8fssx8rROOgzCCoVqTdlVaFhso9VoIfnC0WQD32mBzfEaqbo3UEelHBgK+WHG+X5iS5gOwcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd8a071403180579713c280d4e7eaa65c8abe873b289e3cf8168042897bfc462","last_reissued_at":"2026-05-18T00:05:40.008876Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:40.008876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ordinary Differential Equation Methods For Markov Decision Processes and Application to Kullback-Leibler Control Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"math.OC","authors_text":"Ana Bu\\v{s}i\\'c, Sean Meyn","submitted_at":"2016-05-15T18:48:55Z","abstract_excerpt":"A new approach to computation of optimal policies for MDP (Markov decision process) models is introduced. The main idea is to solve not one, but an entire family of MDPs, parameterized by a weighting factor $\\zeta$ that appears in the one-step reward function. For an MDP with $d$ states, the family of value functions $\\{ h^*_\\zeta : \\zeta\\in\\Re\\}$ is the solution to an ODE, $$ \\frac{d}{d\\zeta} h^*_\\zeta = {\\cal V}(h^*_\\zeta) $$ where the vector field ${\\cal V}\\colon\\Re^d\\to\\Re^d$ has a simple form, based on a matrix inverse.\n  This general methodology is applied to a family of average-cost opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.04591","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":""},"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":"1605.04591","created_at":"2026-05-18T00:05:40.008940+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.04591v2","created_at":"2026-05-18T00:05:40.008940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.04591","created_at":"2026-05-18T00:05:40.008940+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WFAOFADDACX","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WFAOFADDACXS4J4","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WFAOFAD","created_at":"2026-05-18T12:30:04.600751+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/7WFAOFADDACXS4J4FAGU47VKMX","json":"https://pith.science/pith/7WFAOFADDACXS4J4FAGU47VKMX.json","graph_json":"https://pith.science/api/pith-number/7WFAOFADDACXS4J4FAGU47VKMX/graph.json","events_json":"https://pith.science/api/pith-number/7WFAOFADDACXS4J4FAGU47VKMX/events.json","paper":"https://pith.science/paper/7WFAOFAD"},"agent_actions":{"view_html":"https://pith.science/pith/7WFAOFADDACXS4J4FAGU47VKMX","download_json":"https://pith.science/pith/7WFAOFADDACXS4J4FAGU47VKMX.json","view_paper":"https://pith.science/paper/7WFAOFAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.04591&json=true","fetch_graph":"https://pith.science/api/pith-number/7WFAOFADDACXS4J4FAGU47VKMX/graph.json","fetch_events":"https://pith.science/api/pith-number/7WFAOFADDACXS4J4FAGU47VKMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WFAOFADDACXS4J4FAGU47VKMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WFAOFADDACXS4J4FAGU47VKMX/action/storage_attestation","attest_author":"https://pith.science/pith/7WFAOFADDACXS4J4FAGU47VKMX/action/author_attestation","sign_citation":"https://pith.science/pith/7WFAOFADDACXS4J4FAGU47VKMX/action/citation_signature","submit_replication":"https://pith.science/pith/7WFAOFADDACXS4J4FAGU47VKMX/action/replication_record"}},"created_at":"2026-05-18T00:05:40.008940+00:00","updated_at":"2026-05-18T00:05:40.008940+00:00"}