{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z44WVPGAXBITEE3J7OWENAGEFP","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":"6b888dd2053927d29c4db4c78605ad6f186441dc0f3de03113730f006b8ea840","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-12T18:58:59Z","title_canon_sha256":"eeb2e66a4900862a5a47f25828e09855c586e1cf93a2a2493f147821431ebe48"},"schema_version":"1.0","source":{"id":"2212.06132","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.06132","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2212.06132v3","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06132","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"Z44WVPGAXBIT","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"Z44WVPGAXBITEE3J","created_at":"2026-07-05T07:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"Z44WVPGA","created_at":"2026-07-05T07:08:54Z"}],"graph_snapshots":[{"event_id":"sha256:bfeec3537ea29ecab7f1008653a0347832adf2f2167bca6c32e13f04965611f8","target":"graph","created_at":"2026-07-05T07:08:54Z","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/2212.06132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-12T18:58:59Z","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06132","kind":"arxiv","version":3},"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":"sha256:7b021727c48c1687a75eadc62c21f8abf8a6fa293bbd44dc7b3b4e00665cf89f","target":"record","created_at":"2026-07-05T07:08:54Z","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":"6b888dd2053927d29c4db4c78605ad6f186441dc0f3de03113730f006b8ea840","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-12T18:58:59Z","title_canon_sha256":"eeb2e66a4900862a5a47f25828e09855c586e1cf93a2a2493f147821431ebe48"},"schema_version":"1.0","source":{"id":"2212.06132","kind":"arxiv","version":3}},"canonical_sha256":"cf396abcc0b851321369fbac4680c42bf2b6b521e86d5637ad4e8c5e0e2af6b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf396abcc0b851321369fbac4680c42bf2b6b521e86d5637ad4e8c5e0e2af6b6","first_computed_at":"2026-07-05T07:08:54.046571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:54.046571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eesQ2fmFb4+DJwDG1x9zN9DRHvp/p+0hTmT9ozcO1SN/qI2NAQ3VfxhWafwELMtIg7F/8OVIOS7xbsH75jwfBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:54.047052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.06132","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b021727c48c1687a75eadc62c21f8abf8a6fa293bbd44dc7b3b4e00665cf89f","sha256:bfeec3537ea29ecab7f1008653a0347832adf2f2167bca6c32e13f04965611f8"],"state_sha256":"620940cbd773501531e2b8f6f07858f9ba50cf1e067436772f42b84c9a5166a2"}