{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IQKTB46QPA2JA26TISTZQH6C6X","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":"6d9543e1cc0982a03fc37be2f2bc11285ef1a4e155689afc25df02268a09494b","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T22:51:52Z","title_canon_sha256":"f07d3c8ed21e20c93e6a10bbf6485d6de804f1f65d7644d92ba13aa974433847"},"schema_version":"1.0","source":{"id":"2411.10906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10906","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10906v1","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10906","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_12","alias_value":"IQKTB46QPA2J","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_16","alias_value":"IQKTB46QPA2JA26T","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_8","alias_value":"IQKTB46Q","created_at":"2026-07-05T09:36:24Z"}],"graph_snapshots":[{"event_id":"sha256:3d488235832941e65f4885d733f3bbf4661627d3599eee4a7b81f3d116559e7d","target":"graph","created_at":"2026-07-05T09:36:24Z","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/2411.10906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms are usually stated without theoretical guarantees regarding their performance. Recently, Jin, Yang, Wang, and Jordan (COLT 2020) showed a polynomial-time reinforcement learning algorithm (namely, LSVI-UCB) for the setting of linear Markov decision processes, and provided theoretical guarantees regarding its running time and regret. In real-world scenarios, however, the space usage of this algorithm can be prohibitive due to a utilized linear regression step. We propose and analyze two modifications of LSVI-UCB, which alternate periods of learning and not-learn","authors_text":"Arnab Bhattacharyya, Dimitrios Myrisiotis, Philips George John, Silviu Maniu, Zhenan Wu","cross_cats":["cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T22:51:52Z","title":"Efficient, Low-Regret, Online Reinforcement Learning for Linear MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10906","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:aee35570a9749cba928ac1461464027c90b65a79bf5815b5e98c856fa2d616a6","target":"record","created_at":"2026-07-05T09:36:24Z","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":"6d9543e1cc0982a03fc37be2f2bc11285ef1a4e155689afc25df02268a09494b","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T22:51:52Z","title_canon_sha256":"f07d3c8ed21e20c93e6a10bbf6485d6de804f1f65d7644d92ba13aa974433847"},"schema_version":"1.0","source":{"id":"2411.10906","kind":"arxiv","version":1}},"canonical_sha256":"441530f3d07834906bd344a7981fc2f5cd88aa0f441558cef9d9b99004dbf81b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"441530f3d07834906bd344a7981fc2f5cd88aa0f441558cef9d9b99004dbf81b","first_computed_at":"2026-07-05T09:36:24.525112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:24.525112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D9Usebkb4y9uOx+BWQ2iYDgcZal/+qj2Nt0xkNR0MMoxtbe68WPjIwhWCUFMe5Ki6jVS+6RJCz7Ju1fkGThgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:24.525546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aee35570a9749cba928ac1461464027c90b65a79bf5815b5e98c856fa2d616a6","sha256:3d488235832941e65f4885d733f3bbf4661627d3599eee4a7b81f3d116559e7d"],"state_sha256":"0aad33f765aa484d88565fcf5ddeb70ecebbc4845c60d6aa452a2bbd5d55501d"}