{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:D3TNS7BB4RUEDA2GEAIMZY2MOR","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":"e9106fc35f3fa469e52c77a3190d4b7df33f43703be10fb508e26ed071f15c22","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T03:08:59Z","title_canon_sha256":"d0683fdc8b822ec2888c4a1a3f835ce60a37860301789a03ff931934c35cdc27"},"schema_version":"1.0","source":{"id":"2310.08833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08833","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08833v2","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08833","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"D3TNS7BB4RUE","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"D3TNS7BB4RUEDA2G","created_at":"2026-07-05T07:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"D3TNS7BB","created_at":"2026-07-05T07:44:20Z"}],"graph_snapshots":[{"event_id":"sha256:33b34d08d884aae5aca49a7712e8c2657b440e1b11eea500a672205ce87ec09d","target":"graph","created_at":"2026-07-05T07:44:20Z","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/2310.08833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We resolve the open question regarding the sample complexity of policy learning for maximizing the long-run average reward associated with a uniformly ergodic Markov decision process (MDP), assuming a generative model. In this context, the existing literature provides a sample complexity upper bound of $\\widetilde O(|S||A|t_{\\text{mix}}^2 \\epsilon^{-2})$ and a lower bound of $\\Omega(|S||A|t_{\\text{mix}} \\epsilon^{-2})$. In these expressions, $|S|$ and $|A|$ denote the cardinalities of the state and action spaces respectively, $t_{\\text{mix}}$ serves as a uniform upper limit for the total varia","authors_text":"Jose Blanchet, Peter Glynn, Shengbo Wang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T03:08:59Z","title":"Optimal Sample Complexity for Average Reward Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08833","kind":"arxiv","version":2},"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":"sha256:51919cb79695994106effaba493404862bdc87707bfe6c8b04bd62fc0f3f6ff5","target":"record","created_at":"2026-07-05T07:44:20Z","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":"e9106fc35f3fa469e52c77a3190d4b7df33f43703be10fb508e26ed071f15c22","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T03:08:59Z","title_canon_sha256":"d0683fdc8b822ec2888c4a1a3f835ce60a37860301789a03ff931934c35cdc27"},"schema_version":"1.0","source":{"id":"2310.08833","kind":"arxiv","version":2}},"canonical_sha256":"1ee6d97c21e4684183462010cce34c745012cbbec9f21cab79e22f399f947bba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ee6d97c21e4684183462010cce34c745012cbbec9f21cab79e22f399f947bba","first_computed_at":"2026-07-05T07:44:20.695674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:20.695674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hr2M4LhCUN3Wicf+I4P1iJO7mrClV/upOxMOxtA78aatMI3oaJ1SrsJ2E1HoULvvCTIAzRIFIb3+3gsICQy6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:20.696105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51919cb79695994106effaba493404862bdc87707bfe6c8b04bd62fc0f3f6ff5","sha256:33b34d08d884aae5aca49a7712e8c2657b440e1b11eea500a672205ce87ec09d"],"state_sha256":"b19b93248f53dcd78dc1df644cc7304cfb0a8d4d2152dcd31db3da9ccc25f630"}