{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VLEGU7TIYE3VNIH7BTITNEPJ6N","short_pith_number":"pith:VLEGU7TI","schema_version":"1.0","canonical_sha256":"aac86a7e68c13756a0ff0cd13691e9f37268f06adff72f1f1bbabab599a71d6c","source":{"kind":"arxiv","id":"2102.06548","version":4},"attestation_state":"computed","paper":{"title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Changxiao Cai, Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2021-02-12T14:22:05Z","abstract_excerpt":"Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all state-action pairs are drawn from a generative model in each iteration), substantial progress has been made towards understanding the sample efficiency of Q-learning. Consider a $\\gamma$-discounted infinite-horizon MDP with state space $\\mathcal{S}$ and action space $\\mathcal{A}$: to yield an entrywise $\\varepsilon$-approximation of the optimal Q-function, "},"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":"2102.06548","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-02-12T14:22:05Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"title_canon_sha256":"323ef84db5f912796b4efaa9635ef531538892a931749fccaf2d63753704a640","abstract_canon_sha256":"ad2fb5ad90e5478619785047121d5bb3962620c90f7a3206e1a9a04310e4bcaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:37.486662Z","signature_b64":"Ax0QFCZHx5p0Nb+RHLjtideqQAqtWdmtGvqVK9XBBbLgqaM9g5SuEhdNezLdU7zGglsRKSb08/Ku5rM71XoBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac86a7e68c13756a0ff0cd13691e9f37268f06adff72f1f1bbabab599a71d6c","last_reissued_at":"2026-07-05T10:31:37.485768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:37.485768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Changxiao Cai, Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2021-02-12T14:22:05Z","abstract_excerpt":"Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all state-action pairs are drawn from a generative model in each iteration), substantial progress has been made towards understanding the sample efficiency of Q-learning. Consider a $\\gamma$-discounted infinite-horizon MDP with state space $\\mathcal{S}$ and action space $\\mathcal{A}$: to yield an entrywise $\\varepsilon$-approximation of the optimal Q-function, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06548","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/2102.06548/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":"2102.06548","created_at":"2026-07-05T10:31:37.485883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.06548v4","created_at":"2026-07-05T10:31:37.485883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06548","created_at":"2026-07-05T10:31:37.485883+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLEGU7TIYE3V","created_at":"2026-07-05T10:31:37.485883+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLEGU7TIYE3VNIH7","created_at":"2026-07-05T10:31:37.485883+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLEGU7TI","created_at":"2026-07-05T10:31:37.485883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25170","citing_title":"Minimax PAC Bounds for Learning in Exogenous Contextual MDPs","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N","json":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N.json","graph_json":"https://pith.science/api/pith-number/VLEGU7TIYE3VNIH7BTITNEPJ6N/graph.json","events_json":"https://pith.science/api/pith-number/VLEGU7TIYE3VNIH7BTITNEPJ6N/events.json","paper":"https://pith.science/paper/VLEGU7TI"},"agent_actions":{"view_html":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N","download_json":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N.json","view_paper":"https://pith.science/paper/VLEGU7TI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.06548&json=true","fetch_graph":"https://pith.science/api/pith-number/VLEGU7TIYE3VNIH7BTITNEPJ6N/graph.json","fetch_events":"https://pith.science/api/pith-number/VLEGU7TIYE3VNIH7BTITNEPJ6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N/action/storage_attestation","attest_author":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N/action/author_attestation","sign_citation":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N/action/citation_signature","submit_replication":"https://pith.science/pith/VLEGU7TIYE3VNIH7BTITNEPJ6N/action/replication_record"}},"created_at":"2026-07-05T10:31:37.485883+00:00","updated_at":"2026-07-05T10:31:37.485883+00:00"}