{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QGYSX5ZR3G6N5DJLEXFCBICQ6X","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":"b86a39615ec0beaca3501d968a26ef28cc990260e6149ddc6cb03d4ff965e6d4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T18:56:46Z","title_canon_sha256":"20c7c9f51de33d43a2ecc644108c074cc9834f1766c5bda4e118c1464347c68c"},"schema_version":"1.0","source":{"id":"2012.08507","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08507","created_at":"2026-07-05T02:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08507v2","created_at":"2026-07-05T02:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08507","created_at":"2026-07-05T02:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"QGYSX5ZR3G6N","created_at":"2026-07-05T02:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"QGYSX5ZR3G6N5DJL","created_at":"2026-07-05T02:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"QGYSX5ZR","created_at":"2026-07-05T02:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:433ec1bda90b430090aca6d2ab35c0c4256b8cd919ff869665c9d9cd1cff94cb","target":"graph","created_at":"2026-07-05T02:05:10Z","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/2012.08507/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 where the underlying transition probability kernel of the Markov decision process (MDP) is a linear mixture model (Jia et al., 2020; Ayoub et al., 2020; Zhou et al., 2020) and the learning agent has access to either an integration or a sampling oracle of the individual basis kernels. We propose a new Bernstein-type concentration inequality for self-normalized martingales for linear bandit problems with bounded noise. Based on the new inequality, we propose a new, computationally efficient algorithm with linear function app","authors_text":"Csaba Szepesvari, 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":"2020-12-15T18:56:46Z","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08507","kind":"arxiv","version":2},"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":"sha256:3bf2de1e9be5c4bb9f9c0a0bee96afefbee456ed1bc8779d679815062c0bea1a","target":"record","created_at":"2026-07-05T02:05:10Z","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":"b86a39615ec0beaca3501d968a26ef28cc990260e6149ddc6cb03d4ff965e6d4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T18:56:46Z","title_canon_sha256":"20c7c9f51de33d43a2ecc644108c074cc9834f1766c5bda4e118c1464347c68c"},"schema_version":"1.0","source":{"id":"2012.08507","kind":"arxiv","version":2}},"canonical_sha256":"81b12bf731d9bcde8d2b25ca20a050f5d996118204035005725dc968a3d166ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81b12bf731d9bcde8d2b25ca20a050f5d996118204035005725dc968a3d166ab","first_computed_at":"2026-07-05T02:05:10.722234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:05:10.722234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cgZrRuJNm9v4l7OIcRFuczCnsV8Fc9rfZK+Oqr5SvUxfx/9/25hgsSvYgX9UN+0Qnz+eVdXZe0ZBTvzI265NAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:05:10.722707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.08507","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bf2de1e9be5c4bb9f9c0a0bee96afefbee456ed1bc8779d679815062c0bea1a","sha256:433ec1bda90b430090aca6d2ab35c0c4256b8cd919ff869665c9d9cd1cff94cb"],"state_sha256":"21825ba028e6365bdffe0ab779eb6cd227cbc5963583e595109d798ddde59537"}