{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:P5YOU6N77LX3Y6424AOUP3MDP5","short_pith_number":"pith:P5YOU6N7","canonical_record":{"source":{"id":"2205.11507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T17:59:18Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"318e54a9ea1132131f57742734b33226f172095397a49a56eccb22bebbaf3f0c","abstract_canon_sha256":"af3a6354b0623efa578adf3379064861b2634ea9862078c0ff3630168c759327"},"schema_version":"1.0"},"canonical_sha256":"7f70ea79bffaefbc7b9ae01d47ed837f6f331b01b16c3f5abb5d4aaba310522a","source":{"kind":"arxiv","id":"2205.11507","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:P5YOU6N77LX3Y6424AOUP3MDP5","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T17:59:18Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"318e54a9ea1132131f57742734b33226f172095397a49a56eccb22bebbaf3f0c","abstract_canon_sha256":"af3a6354b0623efa578adf3379064861b2634ea9862078c0ff3630168c759327"},"schema_version":"1.0"},"canonical_sha256":"7f70ea79bffaefbc7b9ae01d47ed837f6f331b01b16c3f5abb5d4aaba310522a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:37.872100Z","signature_b64":"wbey2K5yX2nZZ/l82sOawrkK0J6X0o+QcP6Z+pn3Z/dImR1tGZ31nvFAAgiayGMVJNQ7GbhssR4NlkCIyYccCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f70ea79bffaefbc7b9ae01d47ed837f6f331b01b16c3f5abb5d4aaba310522a","last_reissued_at":"2026-07-05T04:25:37.871646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:37.871646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11507","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:25:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Ge9cU/iOnth9TGPv4U8ESac+G04bu/RxDG+Z2FjnCEm2l7xoCCp/dKwf/ZWZt+x2TB+mvLc03FgGR++nZxZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:42:21.496944Z"},"content_sha256":"cd6534fa0816fc1b142c281fd3c8c6340dafaf1057825668eda2eca673c19b50","schema_version":"1.0","event_id":"sha256:cd6534fa0816fc1b142c281fd3c8c6340dafaf1057825668eda2eca673c19b50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:P5YOU6N77LX3Y6424AOUP3MDP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Quanquan Gu","submitted_at":"2022-05-23T17:59:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11507","kind":"arxiv","version":1},"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/2205.11507/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:25:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zjayLN95UqOhXadv3eV+43DuKpqc0bfUOiARE/S3ATh1OwJtQMVocCSz9Vosq9GZVYq7aBzvxsxQz/xYGHYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:42:21.497907Z"},"content_sha256":"b2dc785b389ad2dbd9fe3e3b76d49dbd3e32eaa1f71cff7b6f53a9d7a58c94ec","schema_version":"1.0","event_id":"sha256:b2dc785b389ad2dbd9fe3e3b76d49dbd3e32eaa1f71cff7b6f53a9d7a58c94ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P5YOU6N77LX3Y6424AOUP3MDP5/bundle.json","state_url":"https://pith.science/pith/P5YOU6N77LX3Y6424AOUP3MDP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P5YOU6N77LX3Y6424AOUP3MDP5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T16:42:21Z","links":{"resolver":"https://pith.science/pith/P5YOU6N77LX3Y6424AOUP3MDP5","bundle":"https://pith.science/pith/P5YOU6N77LX3Y6424AOUP3MDP5/bundle.json","state":"https://pith.science/pith/P5YOU6N77LX3Y6424AOUP3MDP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P5YOU6N77LX3Y6424AOUP3MDP5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xny8G/2WxH9GZFO/uNH8x/SQxOrOJ3uhDr7nYr35aoCqjI189XKYLEuLSO59MPQIaynTyGo31zFHCpwqWC2SDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:42:21.508431Z","bundle_sha256":"5026ae414c80099d661be919fd5d43898f2fd7c21d88bd72ef77715d6d9015bb"}}