{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PZSPUEAA463FCARLENCVE63CID","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":"702f8cf49774fbe33619f47c1957610c1ffd7b6044eee966fc2962bf596c9070","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-27T08:45:57Z","title_canon_sha256":"8b08594864d5a1df92a6dda5cb6d136c0b6f88c3c7f015d62d5e16a4caefd86a"},"schema_version":"1.0","source":{"id":"1703.08972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08972","created_at":"2026-05-18T00:47:55Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08972v1","created_at":"2026-05-18T00:47:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08972","created_at":"2026-05-18T00:47:55Z"},{"alias_kind":"pith_short_12","alias_value":"PZSPUEAA463F","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PZSPUEAA463FCARL","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PZSPUEAA","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:22764393fb9b43e2360a90da974fe7ecfcb8ff0931634b84deccbf7427e77e5a","target":"graph","created_at":"2026-05-18T00:47:55Z","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"},"paper":{"abstract_excerpt":"We consider the exploration-exploitation tradeoff in linear quadratic (LQ) control problems, where the state dynamics is linear and the cost function is quadratic in states and controls. We analyze the regret of Thompson sampling (TS) (a.k.a. posterior-sampling for reinforcement learning) in the frequentist setting, i.e., when the parameters characterizing the LQ dynamics are fixed. Despite the empirical and theoretical success in a wide range of problems from multi-armed bandit to linear bandit, we show that when studying the frequentist regret TS in control problems, we need to trade-off the","authors_text":"Alessandro Lazaric, Marc Abeille","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-27T08:45:57Z","title":"Thompson Sampling for Linear-Quadratic Control Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08972","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":"sha256:5483585b6ac2c30959e8128b90f743fb9a99df42d81087fa4425fbcc150035a0","target":"record","created_at":"2026-05-18T00:47:55Z","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":"702f8cf49774fbe33619f47c1957610c1ffd7b6044eee966fc2962bf596c9070","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-27T08:45:57Z","title_canon_sha256":"8b08594864d5a1df92a6dda5cb6d136c0b6f88c3c7f015d62d5e16a4caefd86a"},"schema_version":"1.0","source":{"id":"1703.08972","kind":"arxiv","version":1}},"canonical_sha256":"7e64fa1000e7b651022b2345527b6240c65afeb260219d545b502a29f90b4c9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e64fa1000e7b651022b2345527b6240c65afeb260219d545b502a29f90b4c9e","first_computed_at":"2026-05-18T00:47:55.059606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:55.059606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fFIAKZ1lB85P5xGv0bQoT5ULAzbZIt2Z9gpUCjVHkGKdtNSkwYxitX26ci/nGD8aME9AzFdJ9pU0mTqomi8WAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:55.060060Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.08972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5483585b6ac2c30959e8128b90f743fb9a99df42d81087fa4425fbcc150035a0","sha256:22764393fb9b43e2360a90da974fe7ecfcb8ff0931634b84deccbf7427e77e5a"],"state_sha256":"c510656949e7ebb7d8dc4f39440b38f1dc5ce1a7d78b032379aed2c77bec942b"}