{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:PWPR2RYT2IE73BBEBETKRBZ4J2","short_pith_number":"pith:PWPR2RYT","schema_version":"1.0","canonical_sha256":"7d9f1d4713d209fd84240926a8873c4e8b28d807e143916a832b18cc724aa25d","source":{"kind":"arxiv","id":"1301.7380","version":1},"attestation_state":"computed","paper":{"title":"Solving POMDPs by Searching in Policy Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Eric A. Hansen","submitted_at":"2013-01-30T15:04:11Z","abstract_excerpt":"Most algorithms for solving POMDPs iteratively improve a value function that implicitly represents a policy and are said to search in value function space. This paper presents an approach to solving POMDPs that represents a policy explicitly as a finite-state controller and iteratively improves the controller by search in policy space. Two related algorithms illustrate this approach. The first is a policy iteration algorithm that can outperform value iteration in solving infinitehorizon POMDPs. It provides the foundation for a new heuristic search algorithm that promises further speedup by foc"},"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":"1301.7380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-30T15:04:11Z","cross_cats_sorted":[],"title_canon_sha256":"d575fd2e702d66fa4de8b4c4b205009c32c744a8a282a780008759839aa5fa8a","abstract_canon_sha256":"fa7aa1ed112cc8e8d2c85d821b722cd912ca07b31ec4e5094752bb0622fc0662"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:35:00.175628Z","signature_b64":"Ig55eGcR73VMTVatfzIuqteeYoCRxtZZYthKCEC52juo2YTkYqLi4DgeoM35lv6biwkuHsAHrdynO6iZEj2SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d9f1d4713d209fd84240926a8873c4e8b28d807e143916a832b18cc724aa25d","last_reissued_at":"2026-05-18T03:35:00.171480Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:35:00.171480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving POMDPs by Searching in Policy Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Eric A. Hansen","submitted_at":"2013-01-30T15:04:11Z","abstract_excerpt":"Most algorithms for solving POMDPs iteratively improve a value function that implicitly represents a policy and are said to search in value function space. This paper presents an approach to solving POMDPs that represents a policy explicitly as a finite-state controller and iteratively improves the controller by search in policy space. Two related algorithms illustrate this approach. The first is a policy iteration algorithm that can outperform value iteration in solving infinitehorizon POMDPs. It provides the foundation for a new heuristic search algorithm that promises further speedup by foc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.7380","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":"1301.7380","created_at":"2026-05-18T03:35:00.171595+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.7380v1","created_at":"2026-05-18T03:35:00.171595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.7380","created_at":"2026-05-18T03:35:00.171595+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWPR2RYT2IE7","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWPR2RYT2IE73BBE","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWPR2RYT","created_at":"2026-05-18T12:27:57.521954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04732","citing_title":"Using Common Random Numbers for Simulation-based Planning with Rollouts","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2","json":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2.json","graph_json":"https://pith.science/api/pith-number/PWPR2RYT2IE73BBEBETKRBZ4J2/graph.json","events_json":"https://pith.science/api/pith-number/PWPR2RYT2IE73BBEBETKRBZ4J2/events.json","paper":"https://pith.science/paper/PWPR2RYT"},"agent_actions":{"view_html":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2","download_json":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2.json","view_paper":"https://pith.science/paper/PWPR2RYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.7380&json=true","fetch_graph":"https://pith.science/api/pith-number/PWPR2RYT2IE73BBEBETKRBZ4J2/graph.json","fetch_events":"https://pith.science/api/pith-number/PWPR2RYT2IE73BBEBETKRBZ4J2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2/action/storage_attestation","attest_author":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2/action/author_attestation","sign_citation":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2/action/citation_signature","submit_replication":"https://pith.science/pith/PWPR2RYT2IE73BBEBETKRBZ4J2/action/replication_record"}},"created_at":"2026-05-18T03:35:00.171595+00:00","updated_at":"2026-05-18T03:35:00.171595+00:00"}