{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z44WVPGAXBITEE3J7OWENAGEFP","short_pith_number":"pith:Z44WVPGA","schema_version":"1.0","canonical_sha256":"cf396abcc0b851321369fbac4680c42bf2b6b521e86d5637ad4e8c5e0e2af6b6","source":{"kind":"arxiv","id":"2212.06132","version":3},"attestation_state":"computed","paper":{"title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu","submitted_at":"2022-12-12T18:58:59Z","abstract_excerpt":"We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition probability can be parameterized as a linear function of a given feature mapping, we propose the first computationally efficient algorithm that achieves the nearly minimax optimal regret $\\tilde O(d\\sqrt{H^3K})$, where $d$ is the dimension of the feature mapping, $H$ is the planning horizon, and $K$ is the number of episodes. Our algorithm is based on a weighted linear regression scheme with a carefully designed weight, which d"},"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":"2212.06132","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-12T18:58:59Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"eeb2e66a4900862a5a47f25828e09855c586e1cf93a2a2493f147821431ebe48","abstract_canon_sha256":"6b888dd2053927d29c4db4c78605ad6f186441dc0f3de03113730f006b8ea840"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:54.047052Z","signature_b64":"eesQ2fmFb4+DJwDG1x9zN9DRHvp/p+0hTmT9ozcO1SN/qI2NAQ3VfxhWafwELMtIg7F/8OVIOS7xbsH75jwfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf396abcc0b851321369fbac4680c42bf2b6b521e86d5637ad4e8c5e0e2af6b6","last_reissued_at":"2026-07-05T07:08:54.046571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:54.046571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu","submitted_at":"2022-12-12T18:58:59Z","abstract_excerpt":"We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition probability can be parameterized as a linear function of a given feature mapping, we propose the first computationally efficient algorithm that achieves the nearly minimax optimal regret $\\tilde O(d\\sqrt{H^3K})$, where $d$ is the dimension of the feature mapping, $H$ is the planning horizon, and $K$ is the number of episodes. Our algorithm is based on a weighted linear regression scheme with a carefully designed weight, which d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06132","kind":"arxiv","version":3},"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/2212.06132/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":"2212.06132","created_at":"2026-07-05T07:08:54.046627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06132v3","created_at":"2026-07-05T07:08:54.046627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06132","created_at":"2026-07-05T07:08:54.046627+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z44WVPGAXBIT","created_at":"2026-07-05T07:08:54.046627+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z44WVPGAXBITEE3J","created_at":"2026-07-05T07:08:54.046627+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z44WVPGA","created_at":"2026-07-05T07:08:54.046627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20107","citing_title":"Quantile of Means: A Bonus-Free Ensemble Method for Minimax Optimal Reinforcement Learning","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP","json":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP.json","graph_json":"https://pith.science/api/pith-number/Z44WVPGAXBITEE3J7OWENAGEFP/graph.json","events_json":"https://pith.science/api/pith-number/Z44WVPGAXBITEE3J7OWENAGEFP/events.json","paper":"https://pith.science/paper/Z44WVPGA"},"agent_actions":{"view_html":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP","download_json":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP.json","view_paper":"https://pith.science/paper/Z44WVPGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06132&json=true","fetch_graph":"https://pith.science/api/pith-number/Z44WVPGAXBITEE3J7OWENAGEFP/graph.json","fetch_events":"https://pith.science/api/pith-number/Z44WVPGAXBITEE3J7OWENAGEFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP/action/storage_attestation","attest_author":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP/action/author_attestation","sign_citation":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP/action/citation_signature","submit_replication":"https://pith.science/pith/Z44WVPGAXBITEE3J7OWENAGEFP/action/replication_record"}},"created_at":"2026-07-05T07:08:54.046627+00:00","updated_at":"2026-07-05T07:08:54.046627+00:00"}