{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:H3XON5JLNMX2FOSZK7ODY5DD2Q","short_pith_number":"pith:H3XON5JL","schema_version":"1.0","canonical_sha256":"3eeee6f52b6b2fa2ba5957dc3c7463d40f179c57bc1cc9eb0adc9a58811a0beb","source":{"kind":"arxiv","id":"1310.7906","version":2},"attestation_state":"computed","paper":{"title":"Convergence Analysis of the Approximate Newton Method for Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Guy Lever, Thomas Furmston","submitted_at":"2013-10-29T18:13:00Z","abstract_excerpt":"Recently two approximate Newton methods were proposed for the optimisation of Markov Decision Processes. While these methods were shown to have desirable properties, such as a guarantee that the preconditioner is negative-semidefinite when the policy is $\\log$-concave with respect to the policy parameters, and were demonstrated to have strong empirical performance in challenging domains, such as the game of Tetris, no convergence analysis was provided. The purpose of this paper is to provide such an analysis. We start by providing a detailed analysis of the Hessian of a Markov Decision Process"},"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":"1310.7906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-10-29T18:13:00Z","cross_cats_sorted":[],"title_canon_sha256":"c962b3990a76bdc4e34d5693c2603c8b51ec875f41f01d0c743248338255729e","abstract_canon_sha256":"49dbf6d6ff5c6fa4e2761ca7a255c10f0bf0b0eba45887cb864efc33751a1f1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:57.481472Z","signature_b64":"2eJno+EYogvtfFurGDCBzW05XeaEa2YlKZ8BnJHhHGdWPerdTfXkRM2cDZRzSxqnHmiSc9P59srLEPSAmAxeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eeee6f52b6b2fa2ba5957dc3c7463d40f179c57bc1cc9eb0adc9a58811a0beb","last_reissued_at":"2026-05-18T01:35:57.481011Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:57.481011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Analysis of the Approximate Newton Method for Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Guy Lever, Thomas Furmston","submitted_at":"2013-10-29T18:13:00Z","abstract_excerpt":"Recently two approximate Newton methods were proposed for the optimisation of Markov Decision Processes. While these methods were shown to have desirable properties, such as a guarantee that the preconditioner is negative-semidefinite when the policy is $\\log$-concave with respect to the policy parameters, and were demonstrated to have strong empirical performance in challenging domains, such as the game of Tetris, no convergence analysis was provided. The purpose of this paper is to provide such an analysis. We start by providing a detailed analysis of the Hessian of a Markov Decision Process"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1310.7906","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":"1310.7906","created_at":"2026-05-18T01:35:57.481075+00:00"},{"alias_kind":"arxiv_version","alias_value":"1310.7906v2","created_at":"2026-05-18T01:35:57.481075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1310.7906","created_at":"2026-05-18T01:35:57.481075+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3XON5JLNMX2","created_at":"2026-05-18T12:27:46.883200+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3XON5JLNMX2FOSZ","created_at":"2026-05-18T12:27:46.883200+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3XON5JL","created_at":"2026-05-18T12:27:46.883200+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/H3XON5JLNMX2FOSZK7ODY5DD2Q","json":"https://pith.science/pith/H3XON5JLNMX2FOSZK7ODY5DD2Q.json","graph_json":"https://pith.science/api/pith-number/H3XON5JLNMX2FOSZK7ODY5DD2Q/graph.json","events_json":"https://pith.science/api/pith-number/H3XON5JLNMX2FOSZK7ODY5DD2Q/events.json","paper":"https://pith.science/paper/H3XON5JL"},"agent_actions":{"view_html":"https://pith.science/pith/H3XON5JLNMX2FOSZK7ODY5DD2Q","download_json":"https://pith.science/pith/H3XON5JLNMX2FOSZK7ODY5DD2Q.json","view_paper":"https://pith.science/paper/H3XON5JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1310.7906&json=true","fetch_graph":"https://pith.science/api/pith-number/H3XON5JLNMX2FOSZK7ODY5DD2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/H3XON5JLNMX2FOSZK7ODY5DD2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3XON5JLNMX2FOSZK7ODY5DD2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3XON5JLNMX2FOSZK7ODY5DD2Q/action/storage_attestation","attest_author":"https://pith.science/pith/H3XON5JLNMX2FOSZK7ODY5DD2Q/action/author_attestation","sign_citation":"https://pith.science/pith/H3XON5JLNMX2FOSZK7ODY5DD2Q/action/citation_signature","submit_replication":"https://pith.science/pith/H3XON5JLNMX2FOSZK7ODY5DD2Q/action/replication_record"}},"created_at":"2026-05-18T01:35:57.481075+00:00","updated_at":"2026-05-18T01:35:57.481075+00:00"}