{"paper":{"title":"Data-Driven Linear Quadratic Control Using Output-Feedback via Non-Minimal Realization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An augmented system from Kreisselmeier's adaptive filter recovers the optimal state-feedback gain for the original plant in data-driven LQ control.","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bowen Yi, Hai Lin, Panos J. Antsaklis, Weijian Li","submitted_at":"2026-05-16T02:09:02Z","abstract_excerpt":"In this paper, we investigate a continuous-time linear quadratic control problem for systems with unknown matrices, where only input-output data are available. We propose an output-feedback learning framework based on a canonical nonminimal realization constructed through Kreisselmeier's adaptive filter. The filter admits an observer interpretation, which leads to an augmented system that preserves the input-output response of the realization and provides accessible state trajectories. We show that the optimal gain of this augmented system explicitly recovers the optimal gain associated with t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that the optimal gain of this augmented system explicitly recovers the optimal gain associated with the canonical non-minimal realization, and hence achieves the optimal state-feedback solution of the original plant.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Kreisselmeier's adaptive filter admits an observer interpretation that leads to an augmented system preserving the input-output response of the realization and providing accessible state trajectories (abstract, paragraph describing the filter and augmented system).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Presents a data-driven value iteration algorithm for output-feedback LQR that recovers the optimal state-feedback gain via a non-minimal realization constructed from Kreisselmeier's adaptive filter.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An augmented system from Kreisselmeier's adaptive filter recovers the optimal state-feedback gain for the original plant in data-driven LQ control.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"aa2eda354fcfabde937e24eba323e0b2ef62efbc9bf05402f1fbb844cf888f5f"},"source":{"id":"2605.16752","kind":"arxiv","version":1},"verdict":{"id":"40d859f6-9a0c-403f-9295-9419306fa391","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:24:02.318760Z","strongest_claim":"We show that the optimal gain of this augmented system explicitly recovers the optimal gain associated with the canonical non-minimal realization, and hence achieves the optimal state-feedback solution of the original plant.","one_line_summary":"Presents a data-driven value iteration algorithm for output-feedback LQR that recovers the optimal state-feedback gain via a non-minimal realization constructed from Kreisselmeier's adaptive filter.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Kreisselmeier's adaptive filter admits an observer interpretation that leads to an augmented system preserving the input-output response of the realization and providing accessible state trajectories (abstract, paragraph describing the filter and augmented system).","pith_extraction_headline":"An augmented system from Kreisselmeier's adaptive filter recovers the optimal state-feedback gain for the original plant in data-driven LQ control."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16752/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.374176Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:31:13.943247Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.325707Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.456689Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e057eceb5bbcaf211efe38fd7a8b1e08939964d32ec27a489adf33f8dc6f36f5"},"references":{"count":32,"sample":[{"doi":"","year":2018,"title":"R. S. Sutton and A. G. Barto,Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA: MIT Press, 2018","work_id":"c22bd12f-59aa-4a67-b420-22a6f5074e90","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1974,"title":"Beyond regression: New tools for prediction and analysis in the behavioral sciences,","work_id":"4b623f50-8dae-4db4-a61f-707b2f8af725","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Deep reinforcement learning for autonomous driving: A survey,","work_id":"3e2aa56c-848c-4167-a6a3-207a7187988b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Reinforcement learning in robotics: A survey,","work_id":"7a5b5887-b9a8-4f0a-b783-b0361171714f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Data-driven control based on the behavioral approach from theory to applications in power systems,","work_id":"e8e4c66c-0ce7-429d-b77e-9e7eb07fd438","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"97c31a494d621f4cae195550278c0757fcbf128119f16d6641244b4e8bbab818","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"}