{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:P5YOU6N77LX3Y6424AOUP3MDP5","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":"af3a6354b0623efa578adf3379064861b2634ea9862078c0ff3630168c759327","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T17:59:18Z","title_canon_sha256":"318e54a9ea1132131f57742734b33226f172095397a49a56eccb22bebbaf3f0c"},"schema_version":"1.0","source":{"id":"2205.11507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11507","created_at":"2026-07-05T04:25:37Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11507v1","created_at":"2026-07-05T04:25:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11507","created_at":"2026-07-05T04:25:37Z"},{"alias_kind":"pith_short_12","alias_value":"P5YOU6N77LX3","created_at":"2026-07-05T04:25:37Z"},{"alias_kind":"pith_short_16","alias_value":"P5YOU6N77LX3Y642","created_at":"2026-07-05T04:25:37Z"},{"alias_kind":"pith_short_8","alias_value":"P5YOU6N7","created_at":"2026-07-05T04:25:37Z"}],"graph_snapshots":[{"event_id":"sha256:b2dc785b389ad2dbd9fe3e3b76d49dbd3e32eaa1f71cff7b6f53a9d7a58c94ec","target":"graph","created_at":"2026-07-05T04:25:37Z","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/2205.11507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have shown that episodic reinforcement learning (RL) is not more difficult than contextual bandits, even with a long planning horizon and unknown state transitions. However, these results are limited to either tabular Markov decision processes (MDPs) or computationally inefficient algorithms for linear mixture MDPs. In this paper, we propose the first computationally efficient horizon-free algorithm for linear mixture MDPs, which achieves the optimal $\\tilde O(d\\sqrt{K} +d^2)$ regret up to logarithmic factors. Our algorithm adapts a weighted least square estimator for the unknow","authors_text":"Dongruo Zhou, Quanquan Gu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T17:59:18Z","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11507","kind":"arxiv","version":1},"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:cd6534fa0816fc1b142c281fd3c8c6340dafaf1057825668eda2eca673c19b50","target":"record","created_at":"2026-07-05T04:25:37Z","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":"af3a6354b0623efa578adf3379064861b2634ea9862078c0ff3630168c759327","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T17:59:18Z","title_canon_sha256":"318e54a9ea1132131f57742734b33226f172095397a49a56eccb22bebbaf3f0c"},"schema_version":"1.0","source":{"id":"2205.11507","kind":"arxiv","version":1}},"canonical_sha256":"7f70ea79bffaefbc7b9ae01d47ed837f6f331b01b16c3f5abb5d4aaba310522a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f70ea79bffaefbc7b9ae01d47ed837f6f331b01b16c3f5abb5d4aaba310522a","first_computed_at":"2026-07-05T04:25:37.871646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:37.871646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wbey2K5yX2nZZ/l82sOawrkK0J6X0o+QcP6Z+pn3Z/dImR1tGZ31nvFAAgiayGMVJNQ7GbhssR4NlkCIyYccCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:37.872100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd6534fa0816fc1b142c281fd3c8c6340dafaf1057825668eda2eca673c19b50","sha256:b2dc785b389ad2dbd9fe3e3b76d49dbd3e32eaa1f71cff7b6f53a9d7a58c94ec"],"state_sha256":"43271318e1677418d9fc1d145f67e65ea6196652315dd246f69961a64c7f72c7"}