{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:A26H7NF5TSHMRJSADOA5DPAP3K","short_pith_number":"pith:A26H7NF5","schema_version":"1.0","canonical_sha256":"06bc7fb4bd9c8ec8a6401b81d1bc0fdaad32c627d92fa8c8fb504092259b2719","source":{"kind":"arxiv","id":"1204.1227","version":4},"attestation_state":"computed","paper":{"title":"An 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":"David Barber, Thomas Furmston","submitted_at":"2012-04-05T13:44:29Z","abstract_excerpt":"Gradient-based algorithms are one of the methods of choice for the optimisation of Markov Decision Processes. In this article we will present a novel approximate Newton algorithm for the optimisation of such models. The algorithm has various desirable properties over the naive application of Newton's method. Firstly the approximate Hessian is guaranteed to be negative-semidefinite over the entire parameter space in the case where the controller is log-concave in the control parameters. Additionally the inference required for our approximate Newton method is often the same as that required for "},"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":"1204.1227","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2012-04-05T13:44:29Z","cross_cats_sorted":[],"title_canon_sha256":"4e4a7071df5f39208d051e80e6c0bff0d60b6b9ede70ef7e45c1200337f0ade2","abstract_canon_sha256":"cc488bd8f8fe4f70439f1026bfcec0caf5afdb29c3e9296743cfd86543cb7ec5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:57.717291Z","signature_b64":"/KmXJi9VLDrELwMjQ/J06MXswW68mMgsQuTJDkTxt/eH6727yiB0TrJNgKZnAIjxZvgn4wBvTJj6cy2TftIiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06bc7fb4bd9c8ec8a6401b81d1bc0fdaad32c627d92fa8c8fb504092259b2719","last_reissued_at":"2026-05-18T01:35:57.716917Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:57.716917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An 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":"David Barber, Thomas Furmston","submitted_at":"2012-04-05T13:44:29Z","abstract_excerpt":"Gradient-based algorithms are one of the methods of choice for the optimisation of Markov Decision Processes. In this article we will present a novel approximate Newton algorithm for the optimisation of such models. The algorithm has various desirable properties over the naive application of Newton's method. Firstly the approximate Hessian is guaranteed to be negative-semidefinite over the entire parameter space in the case where the controller is log-concave in the control parameters. Additionally the inference required for our approximate Newton method is often the same as that required for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.1227","kind":"arxiv","version":4},"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":"1204.1227","created_at":"2026-05-18T01:35:57.716975+00:00"},{"alias_kind":"arxiv_version","alias_value":"1204.1227v4","created_at":"2026-05-18T01:35:57.716975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.1227","created_at":"2026-05-18T01:35:57.716975+00:00"},{"alias_kind":"pith_short_12","alias_value":"A26H7NF5TSHM","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_16","alias_value":"A26H7NF5TSHMRJSA","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_8","alias_value":"A26H7NF5","created_at":"2026-05-18T12:26:58.693483+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/A26H7NF5TSHMRJSADOA5DPAP3K","json":"https://pith.science/pith/A26H7NF5TSHMRJSADOA5DPAP3K.json","graph_json":"https://pith.science/api/pith-number/A26H7NF5TSHMRJSADOA5DPAP3K/graph.json","events_json":"https://pith.science/api/pith-number/A26H7NF5TSHMRJSADOA5DPAP3K/events.json","paper":"https://pith.science/paper/A26H7NF5"},"agent_actions":{"view_html":"https://pith.science/pith/A26H7NF5TSHMRJSADOA5DPAP3K","download_json":"https://pith.science/pith/A26H7NF5TSHMRJSADOA5DPAP3K.json","view_paper":"https://pith.science/paper/A26H7NF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1204.1227&json=true","fetch_graph":"https://pith.science/api/pith-number/A26H7NF5TSHMRJSADOA5DPAP3K/graph.json","fetch_events":"https://pith.science/api/pith-number/A26H7NF5TSHMRJSADOA5DPAP3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A26H7NF5TSHMRJSADOA5DPAP3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A26H7NF5TSHMRJSADOA5DPAP3K/action/storage_attestation","attest_author":"https://pith.science/pith/A26H7NF5TSHMRJSADOA5DPAP3K/action/author_attestation","sign_citation":"https://pith.science/pith/A26H7NF5TSHMRJSADOA5DPAP3K/action/citation_signature","submit_replication":"https://pith.science/pith/A26H7NF5TSHMRJSADOA5DPAP3K/action/replication_record"}},"created_at":"2026-05-18T01:35:57.716975+00:00","updated_at":"2026-05-18T01:35:57.716975+00:00"}