{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QPSLCLJ72JBKSRILS6KAOD3Z22","short_pith_number":"pith:QPSLCLJ7","schema_version":"1.0","canonical_sha256":"83e4b12d3fd242a9450b9794070f79d6bd0b6f4a5fb48804511d336a413316a2","source":{"kind":"arxiv","id":"1811.10928","version":2},"attestation_state":"computed","paper":{"title":"Single-Agent Policy Tree Search With Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Laurent Orseau, Levi H. S. Lelis, Th\\'eophane Weber, Tor Lattimore","submitted_at":"2018-11-27T11:53:33Z","abstract_excerpt":"We introduce two novel tree search algorithms that use a policy to guide search. The first algorithm is a best-first enumeration that uses a cost function that allows us to prove an upper bound on the number of nodes to be expanded before reaching a goal state. We show that this best-first algorithm is particularly well suited for `needle-in-a-haystack' problems. The second algorithm is based on sampling and we prove an upper bound on the expected number of nodes it expands before reaching a set of goal states. We show that this algorithm is better suited for problems where many paths lead to "},"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":"1811.10928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-27T11:53:33Z","cross_cats_sorted":[],"title_canon_sha256":"1045ea74e94b37bd74382d1a09ba94d4039821fe36cb11d77524d800a92453e8","abstract_canon_sha256":"ad8faf08b4bef5cf7213bb27d6bcfffb097ba19b7f2a6005e892d74f3ef2598a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:43.206227Z","signature_b64":"Phmorw0DxB0KR9dm4/lpK+d1jkdKMiV393EgchueuC0VWTAlD1TDw6fsQNpgt7Q1BZ/QJMiOuRc5yr9m9VHUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83e4b12d3fd242a9450b9794070f79d6bd0b6f4a5fb48804511d336a413316a2","last_reissued_at":"2026-05-17T23:59:43.205721Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:43.205721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-Agent Policy Tree Search With Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Laurent Orseau, Levi H. S. Lelis, Th\\'eophane Weber, Tor Lattimore","submitted_at":"2018-11-27T11:53:33Z","abstract_excerpt":"We introduce two novel tree search algorithms that use a policy to guide search. The first algorithm is a best-first enumeration that uses a cost function that allows us to prove an upper bound on the number of nodes to be expanded before reaching a goal state. We show that this best-first algorithm is particularly well suited for `needle-in-a-haystack' problems. The second algorithm is based on sampling and we prove an upper bound on the expected number of nodes it expands before reaching a set of goal states. We show that this algorithm is better suited for problems where many paths lead to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10928","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":"1811.10928","created_at":"2026-05-17T23:59:43.205805+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10928v2","created_at":"2026-05-17T23:59:43.205805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10928","created_at":"2026-05-17T23:59:43.205805+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPSLCLJ72JBK","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPSLCLJ72JBKSRIL","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPSLCLJ7","created_at":"2026-05-18T12:32:46.962924+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/QPSLCLJ72JBKSRILS6KAOD3Z22","json":"https://pith.science/pith/QPSLCLJ72JBKSRILS6KAOD3Z22.json","graph_json":"https://pith.science/api/pith-number/QPSLCLJ72JBKSRILS6KAOD3Z22/graph.json","events_json":"https://pith.science/api/pith-number/QPSLCLJ72JBKSRILS6KAOD3Z22/events.json","paper":"https://pith.science/paper/QPSLCLJ7"},"agent_actions":{"view_html":"https://pith.science/pith/QPSLCLJ72JBKSRILS6KAOD3Z22","download_json":"https://pith.science/pith/QPSLCLJ72JBKSRILS6KAOD3Z22.json","view_paper":"https://pith.science/paper/QPSLCLJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10928&json=true","fetch_graph":"https://pith.science/api/pith-number/QPSLCLJ72JBKSRILS6KAOD3Z22/graph.json","fetch_events":"https://pith.science/api/pith-number/QPSLCLJ72JBKSRILS6KAOD3Z22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPSLCLJ72JBKSRILS6KAOD3Z22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPSLCLJ72JBKSRILS6KAOD3Z22/action/storage_attestation","attest_author":"https://pith.science/pith/QPSLCLJ72JBKSRILS6KAOD3Z22/action/author_attestation","sign_citation":"https://pith.science/pith/QPSLCLJ72JBKSRILS6KAOD3Z22/action/citation_signature","submit_replication":"https://pith.science/pith/QPSLCLJ72JBKSRILS6KAOD3Z22/action/replication_record"}},"created_at":"2026-05-17T23:59:43.205805+00:00","updated_at":"2026-05-17T23:59:43.205805+00:00"}