{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4TQHYRGNJ5PSUQB4JLSW7XCP7F","short_pith_number":"pith:4TQHYRGN","schema_version":"1.0","canonical_sha256":"e4e07c44cd4f5f2a403c4ae56fdc4ff9424e8b9bfdb01f4b0d34bd309c5c83b3","source":{"kind":"arxiv","id":"2009.13405","version":4},"attestation_state":"computed","paper":{"title":"Adaptive Sampling for Best Policy Identification in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandre Proutiere, Aymen Al Marjani","submitted_at":"2020-09-28T15:22:24Z","abstract_excerpt":"We investigate the problem of best-policy identification in discounted Markov Decision Processes (MDPs) when the learner has access to a generative model. The objective is to devise a learning algorithm returning the best policy as early as possible. We first derive a problem-specific lower bound of the sample complexity satisfied by any learning algorithm. This lower bound corresponds to an optimal sample allocation that solves a non-convex program, and hence, is hard to exploit in the design of efficient algorithms. We then provide a simple and tight upper bound of the sample complexity lowe"},"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":"2009.13405","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-09-28T15:22:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b42f9243344116e48c5f36ecd33133c21f2b902455bb73a85becd4cdd287980","abstract_canon_sha256":"024d5d234365c9838b7319da6c2dc80af6934bcfe47323f39e779e31876a000f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:51.868153Z","signature_b64":"T0bLovMgLXepZP5G9y6OgTSr2cMTiW6mayN6ka+fLuQGYrtza8MJc0tFi+Xd2hELuwICNH4wg+YDUa96jonbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4e07c44cd4f5f2a403c4ae56fdc4ff9424e8b9bfdb01f4b0d34bd309c5c83b3","last_reissued_at":"2026-07-05T02:38:51.867621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:51.867621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Sampling for Best Policy Identification in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandre Proutiere, Aymen Al Marjani","submitted_at":"2020-09-28T15:22:24Z","abstract_excerpt":"We investigate the problem of best-policy identification in discounted Markov Decision Processes (MDPs) when the learner has access to a generative model. The objective is to devise a learning algorithm returning the best policy as early as possible. We first derive a problem-specific lower bound of the sample complexity satisfied by any learning algorithm. This lower bound corresponds to an optimal sample allocation that solves a non-convex program, and hence, is hard to exploit in the design of efficient algorithms. We then provide a simple and tight upper bound of the sample complexity lowe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13405","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.13405/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":"2009.13405","created_at":"2026-07-05T02:38:51.867681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13405v4","created_at":"2026-07-05T02:38:51.867681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13405","created_at":"2026-07-05T02:38:51.867681+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TQHYRGNJ5PS","created_at":"2026-07-05T02:38:51.867681+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TQHYRGNJ5PSUQB4","created_at":"2026-07-05T02:38:51.867681+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TQHYRGN","created_at":"2026-07-05T02:38:51.867681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06521","citing_title":"Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F","json":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F.json","graph_json":"https://pith.science/api/pith-number/4TQHYRGNJ5PSUQB4JLSW7XCP7F/graph.json","events_json":"https://pith.science/api/pith-number/4TQHYRGNJ5PSUQB4JLSW7XCP7F/events.json","paper":"https://pith.science/paper/4TQHYRGN"},"agent_actions":{"view_html":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F","download_json":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F.json","view_paper":"https://pith.science/paper/4TQHYRGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13405&json=true","fetch_graph":"https://pith.science/api/pith-number/4TQHYRGNJ5PSUQB4JLSW7XCP7F/graph.json","fetch_events":"https://pith.science/api/pith-number/4TQHYRGNJ5PSUQB4JLSW7XCP7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F/action/storage_attestation","attest_author":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F/action/author_attestation","sign_citation":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F/action/citation_signature","submit_replication":"https://pith.science/pith/4TQHYRGNJ5PSUQB4JLSW7XCP7F/action/replication_record"}},"created_at":"2026-07-05T02:38:51.867681+00:00","updated_at":"2026-07-05T02:38:51.867681+00:00"}