{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4TQHYRGNJ5PSUQB4JLSW7XCP7F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"024d5d234365c9838b7319da6c2dc80af6934bcfe47323f39e779e31876a000f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-09-28T15:22:24Z","title_canon_sha256":"0b42f9243344116e48c5f36ecd33133c21f2b902455bb73a85becd4cdd287980"},"schema_version":"1.0","source":{"id":"2009.13405","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.13405","created_at":"2026-07-05T02:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2009.13405v4","created_at":"2026-07-05T02:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13405","created_at":"2026-07-05T02:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"4TQHYRGNJ5PS","created_at":"2026-07-05T02:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"4TQHYRGNJ5PSUQB4","created_at":"2026-07-05T02:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"4TQHYRGN","created_at":"2026-07-05T02:38:51Z"}],"graph_snapshots":[{"event_id":"sha256:0161f412e79d73080c5d4e1a4b88093be7f712a824601990a7ea68c09dbd6254","target":"graph","created_at":"2026-07-05T02:38:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.13405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexandre Proutiere, Aymen Al Marjani","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-09-28T15:22:24Z","title":"Adaptive Sampling for Best Policy Identification in Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13405","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a81bc8dfc9efc8e137669d4c00f1499942f9074e7032b592a635c80fbb64a5b5","target":"record","created_at":"2026-07-05T02:38:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"024d5d234365c9838b7319da6c2dc80af6934bcfe47323f39e779e31876a000f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-09-28T15:22:24Z","title_canon_sha256":"0b42f9243344116e48c5f36ecd33133c21f2b902455bb73a85becd4cdd287980"},"schema_version":"1.0","source":{"id":"2009.13405","kind":"arxiv","version":4}},"canonical_sha256":"e4e07c44cd4f5f2a403c4ae56fdc4ff9424e8b9bfdb01f4b0d34bd309c5c83b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4e07c44cd4f5f2a403c4ae56fdc4ff9424e8b9bfdb01f4b0d34bd309c5c83b3","first_computed_at":"2026-07-05T02:38:51.867621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:51.867621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T0bLovMgLXepZP5G9y6OgTSr2cMTiW6mayN6ka+fLuQGYrtza8MJc0tFi+Xd2hELuwICNH4wg+YDUa96jonbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:51.868153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.13405","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a81bc8dfc9efc8e137669d4c00f1499942f9074e7032b592a635c80fbb64a5b5","sha256:0161f412e79d73080c5d4e1a4b88093be7f712a824601990a7ea68c09dbd6254"],"state_sha256":"be09273a23acb87ae1fc0e00227d8a4a8c6169c61e3648f8eecb5b1068de1d96"}