{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BH6LVX2N4XF7PMYCSTVLDQSCKA","short_pith_number":"pith:BH6LVX2N","schema_version":"1.0","canonical_sha256":"09fcbadf4de5cbf7b30294eab1c242502f0e9baffa39cbc89165ce6b2a7fec5c","source":{"kind":"arxiv","id":"2607.17201","version":1},"attestation_state":"computed","paper":{"title":"Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aldo Pacchiano, Alessio Russo, Joseph Lazzaro","submitted_at":"2026-07-19T11:48:09Z","abstract_excerpt":"In this work we study the Best Policy Identification (BPI) problem in online, tabular Reinforcement Learning. This is an active sequential hypothesis testing problem in which the learner's objective is to identify an optimal policy in a Markov Decision Process (MDP) with high confidence, while minimizing the expected sample complexity to do so. We consider an online setting with deterministic rewards, where the agent must strategically navigate through the MDP in order to effectively explore. Previous works in the literature have provided asymptotically optimal methods for BPI, such as the Nav"},"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":"2607.17201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-19T11:48:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3c400aae5a8665b07bd8f035ad13f6639fc784da90b6b54c0ac017939b6f4ff3","abstract_canon_sha256":"a73fde28e97b27eed4138e3dbe67ecb3e05cf82c9d4a7547d1156f0d47cd66bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:20.679506Z","signature_b64":"A/PL4yYfwvidE0bvZPkA4bC0G/aJ42DMpxB3dZ4asw9hURMA7AzlM3NlDrovQcgj9gVgkUlupzJ4tWXtvGb7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09fcbadf4de5cbf7b30294eab1c242502f0e9baffa39cbc89165ce6b2a7fec5c","last_reissued_at":"2026-07-21T01:21:20.678642Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:20.678642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aldo Pacchiano, Alessio Russo, Joseph Lazzaro","submitted_at":"2026-07-19T11:48:09Z","abstract_excerpt":"In this work we study the Best Policy Identification (BPI) problem in online, tabular Reinforcement Learning. This is an active sequential hypothesis testing problem in which the learner's objective is to identify an optimal policy in a Markov Decision Process (MDP) with high confidence, while minimizing the expected sample complexity to do so. We consider an online setting with deterministic rewards, where the agent must strategically navigate through the MDP in order to effectively explore. Previous works in the literature have provided asymptotically optimal methods for BPI, such as the Nav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17201","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.17201/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2607.17201","created_at":"2026-07-21T01:21:20.679095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17201v1","created_at":"2026-07-21T01:21:20.679095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17201","created_at":"2026-07-21T01:21:20.679095+00:00"},{"alias_kind":"pith_short_12","alias_value":"BH6LVX2N4XF7","created_at":"2026-07-21T01:21:20.679095+00:00"},{"alias_kind":"pith_short_16","alias_value":"BH6LVX2N4XF7PMYC","created_at":"2026-07-21T01:21:20.679095+00:00"},{"alias_kind":"pith_short_8","alias_value":"BH6LVX2N","created_at":"2026-07-21T01:21:20.679095+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/BH6LVX2N4XF7PMYCSTVLDQSCKA","json":"https://pith.science/pith/BH6LVX2N4XF7PMYCSTVLDQSCKA.json","graph_json":"https://pith.science/api/pith-number/BH6LVX2N4XF7PMYCSTVLDQSCKA/graph.json","events_json":"https://pith.science/api/pith-number/BH6LVX2N4XF7PMYCSTVLDQSCKA/events.json","paper":"https://pith.science/paper/BH6LVX2N"},"agent_actions":{"view_html":"https://pith.science/pith/BH6LVX2N4XF7PMYCSTVLDQSCKA","download_json":"https://pith.science/pith/BH6LVX2N4XF7PMYCSTVLDQSCKA.json","view_paper":"https://pith.science/paper/BH6LVX2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17201&json=true","fetch_graph":"https://pith.science/api/pith-number/BH6LVX2N4XF7PMYCSTVLDQSCKA/graph.json","fetch_events":"https://pith.science/api/pith-number/BH6LVX2N4XF7PMYCSTVLDQSCKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BH6LVX2N4XF7PMYCSTVLDQSCKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BH6LVX2N4XF7PMYCSTVLDQSCKA/action/storage_attestation","attest_author":"https://pith.science/pith/BH6LVX2N4XF7PMYCSTVLDQSCKA/action/author_attestation","sign_citation":"https://pith.science/pith/BH6LVX2N4XF7PMYCSTVLDQSCKA/action/citation_signature","submit_replication":"https://pith.science/pith/BH6LVX2N4XF7PMYCSTVLDQSCKA/action/replication_record"}},"created_at":"2026-07-21T01:21:20.679095+00:00","updated_at":"2026-07-21T01:21:20.679095+00:00"}