{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:ULOYLN4MTDB6P5D4EQEU4RQ6TD","short_pith_number":"pith:ULOYLN4M","schema_version":"1.0","canonical_sha256":"a2dd85b78c98c3e7f47c24094e461e98d9f0719501447812d772653eed0edeba","source":{"kind":"arxiv","id":"1108.3711","version":2},"attestation_state":"computed","paper":{"title":"Doing Better Than UCT: Rational Monte Carlo Sampling in Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Tolpin, Solomon Eyal Shimony","submitted_at":"2011-08-18T10:47:16Z","abstract_excerpt":"UCT, a state-of-the art algorithm for Monte Carlo tree sampling (MCTS), is based on UCB, a sampling policy for the Multi-armed Bandit Problem (MAB) that minimizes the accumulated regret. However, MCTS differs from MAB in that only the final choice, rather than all arm pulls, brings a reward, that is, the simple regret, as opposite to the cumulative regret, must be minimized. This ongoing work aims at applying meta-reasoning techniques to MCTS, which is non-trivial. We begin by introducing policies for multi-armed bandits with lower simple regret than UCB, and an algorithm for MCTS which combin"},"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":"1108.3711","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-08-18T10:47:16Z","cross_cats_sorted":[],"title_canon_sha256":"deb9cb8cb66d13f34275b4bb35fc4049fad4f5912d7a9f4db4966288af23a400","abstract_canon_sha256":"17bae33fefc4c3b0251cb38c2aeee1ed83e57ae372e08836303ac370098536ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:10.962825Z","signature_b64":"QSVBhku5086NKUxjDR9VvomVlCgVIpQSBWG8Pmg2v/O0UdnpyoUxh2hZTKtmBpMr4fsU3Pp6xjaSTLRKaq8hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2dd85b78c98c3e7f47c24094e461e98d9f0719501447812d772653eed0edeba","last_reissued_at":"2026-05-18T03:50:10.962123Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:10.962123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doing Better Than UCT: Rational Monte Carlo Sampling in Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Tolpin, Solomon Eyal Shimony","submitted_at":"2011-08-18T10:47:16Z","abstract_excerpt":"UCT, a state-of-the art algorithm for Monte Carlo tree sampling (MCTS), is based on UCB, a sampling policy for the Multi-armed Bandit Problem (MAB) that minimizes the accumulated regret. However, MCTS differs from MAB in that only the final choice, rather than all arm pulls, brings a reward, that is, the simple regret, as opposite to the cumulative regret, must be minimized. This ongoing work aims at applying meta-reasoning techniques to MCTS, which is non-trivial. We begin by introducing policies for multi-armed bandits with lower simple regret than UCB, and an algorithm for MCTS which combin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.3711","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":"1108.3711","created_at":"2026-05-18T03:50:10.962237+00:00"},{"alias_kind":"arxiv_version","alias_value":"1108.3711v2","created_at":"2026-05-18T03:50:10.962237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.3711","created_at":"2026-05-18T03:50:10.962237+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULOYLN4MTDB6","created_at":"2026-05-18T12:26:42.757692+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULOYLN4MTDB6P5D4","created_at":"2026-05-18T12:26:42.757692+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULOYLN4M","created_at":"2026-05-18T12:26:42.757692+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/ULOYLN4MTDB6P5D4EQEU4RQ6TD","json":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD.json","graph_json":"https://pith.science/api/pith-number/ULOYLN4MTDB6P5D4EQEU4RQ6TD/graph.json","events_json":"https://pith.science/api/pith-number/ULOYLN4MTDB6P5D4EQEU4RQ6TD/events.json","paper":"https://pith.science/paper/ULOYLN4M"},"agent_actions":{"view_html":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD","download_json":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD.json","view_paper":"https://pith.science/paper/ULOYLN4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1108.3711&json=true","fetch_graph":"https://pith.science/api/pith-number/ULOYLN4MTDB6P5D4EQEU4RQ6TD/graph.json","fetch_events":"https://pith.science/api/pith-number/ULOYLN4MTDB6P5D4EQEU4RQ6TD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/action/storage_attestation","attest_author":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/action/author_attestation","sign_citation":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/action/citation_signature","submit_replication":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/action/replication_record"}},"created_at":"2026-05-18T03:50:10.962237+00:00","updated_at":"2026-05-18T03:50:10.962237+00:00"}