{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CZJNPCCR5S2SZAFEC3DBBPE6CZ","short_pith_number":"pith:CZJNPCCR","schema_version":"1.0","canonical_sha256":"1652d78851ecb52c80a416c610bc9e16757dc560412a5a17b968997a0d65db7f","source":{"kind":"arxiv","id":"2401.14871","version":4},"attestation_state":"computed","paper":{"title":"Data-Enabled Policy Optimization for Direct Adaptive Learning of the LQR","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Alessandro Chiuso, Feiran Zhao, Florian D\\\"orfler, Keyou You","submitted_at":"2024-01-26T13:58:35Z","abstract_excerpt":"Direct data-driven design methods for the linear quadratic regulator (LQR) mainly use offline or episodic data batches, and their online adaptation has been acknowledged as an open problem. In this paper, we propose a direct adaptive method to learn the LQR from online closed-loop data. First, we propose a new policy parameterization based on the sample covariance to formulate a direct data-driven LQR problem, which is shown to be equivalent to the certainty-equivalence LQR with optimal non-asymptotic guarantees. Second, we design a novel data-enabled policy optimization (DeePO) method to dire"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.14871","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2024-01-26T13:58:35Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"403a9a7e793ce2e5fc2224ae44f45ff0b63fe85e1fa681ba466a46e1d7e40888","abstract_canon_sha256":"ccb1775f713e0e2963a6eb4b6036c91b8ecf0d106c4c325e1704bfe5f8f322f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:29.379065Z","signature_b64":"SyEukfPQu6Rj0C1zg+9jioZu6AEVpUD+Yy6dMo0/IPK3+uw/WtyTnBzR27hi8uZGSFmgGd5S1mPhXzfCgAvoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1652d78851ecb52c80a416c610bc9e16757dc560412a5a17b968997a0d65db7f","last_reissued_at":"2026-07-05T09:15:29.378544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:29.378544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Enabled Policy Optimization for Direct Adaptive Learning of the LQR","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Alessandro Chiuso, Feiran Zhao, Florian D\\\"orfler, Keyou You","submitted_at":"2024-01-26T13:58:35Z","abstract_excerpt":"Direct data-driven design methods for the linear quadratic regulator (LQR) mainly use offline or episodic data batches, and their online adaptation has been acknowledged as an open problem. In this paper, we propose a direct adaptive method to learn the LQR from online closed-loop data. First, we propose a new policy parameterization based on the sample covariance to formulate a direct data-driven LQR problem, which is shown to be equivalent to the certainty-equivalence LQR with optimal non-asymptotic guarantees. Second, we design a novel data-enabled policy optimization (DeePO) method to dire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14871","kind":"arxiv","version":4},"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/2401.14871/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.14871","created_at":"2026-07-05T09:15:29.378607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14871v4","created_at":"2026-07-05T09:15:29.378607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14871","created_at":"2026-07-05T09:15:29.378607+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZJNPCCR5S2S","created_at":"2026-07-05T09:15:29.378607+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZJNPCCR5S2SZAFE","created_at":"2026-07-05T09:15:29.378607+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZJNPCCR","created_at":"2026-07-05T09:15:29.378607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19705","citing_title":"Noise Sensitivity of the Semidefinite Programs for Direct Data-Driven LQR","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ","json":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ.json","graph_json":"https://pith.science/api/pith-number/CZJNPCCR5S2SZAFEC3DBBPE6CZ/graph.json","events_json":"https://pith.science/api/pith-number/CZJNPCCR5S2SZAFEC3DBBPE6CZ/events.json","paper":"https://pith.science/paper/CZJNPCCR"},"agent_actions":{"view_html":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ","download_json":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ.json","view_paper":"https://pith.science/paper/CZJNPCCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14871&json=true","fetch_graph":"https://pith.science/api/pith-number/CZJNPCCR5S2SZAFEC3DBBPE6CZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CZJNPCCR5S2SZAFEC3DBBPE6CZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ/action/storage_attestation","attest_author":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ/action/author_attestation","sign_citation":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ/action/citation_signature","submit_replication":"https://pith.science/pith/CZJNPCCR5S2SZAFEC3DBBPE6CZ/action/replication_record"}},"created_at":"2026-07-05T09:15:29.378607+00:00","updated_at":"2026-07-05T09:15:29.378607+00:00"}