{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CBJBP2R65SC6PG3NAGIE6OXORU","short_pith_number":"pith:CBJBP2R6","schema_version":"1.0","canonical_sha256":"105217ea3eec85e79b6d01904f3aee8d2119f136bd7e8c2e3cf43934b489d41e","source":{"kind":"arxiv","id":"2311.02679","version":2},"attestation_state":"computed","paper":{"title":"Regret Analysis of Learning-Based Linear Quadratic Gaussian Control with Additive Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Archith Athrey, Bart De Schutter, Meichen Guo, Othmane Mazhar, Shengling Shi","submitted_at":"2023-11-05T15:32:37Z","abstract_excerpt":"In this paper, we analyze the regret incurred by a computationally efficient exploration strategy, known as naive exploration, for controlling unknown partially observable systems within the Linear Quadratic Gaussian (LQG) framework. We introduce a two-phase control algorithm called LQG-NAIVE, which involves an initial phase of injecting Gaussian input signals to obtain a system model, followed by a second phase of an interplay between naive exploration and control in an episodic fashion. We show that LQG-NAIVE achieves a regret growth rate of $\\tilde{\\mathcal{O}}(\\sqrt{T})$, i.e., $\\mathcal{O"},"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":"2311.02679","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2023-11-05T15:32:37Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"cde1249036d13e0f74a7cccc4d357e86a972e1c0ca40fee670fc7ae34d64da3f","abstract_canon_sha256":"ed85f100bc30b9b12648c86eb6ec355d1e107a678e1f4bd9ee058e38c535fa33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:02.482053Z","signature_b64":"J9hjNqPqcOuiDAya8QqFFk5ecyIKMfok4k4Z53Mvb3M0EroWYgPie78RErwZaNilpGlMGXyMbPy+8/4nLhZDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105217ea3eec85e79b6d01904f3aee8d2119f136bd7e8c2e3cf43934b489d41e","last_reissued_at":"2026-07-05T07:16:02.481514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:02.481514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret Analysis of Learning-Based Linear Quadratic Gaussian Control with Additive Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Archith Athrey, Bart De Schutter, Meichen Guo, Othmane Mazhar, Shengling Shi","submitted_at":"2023-11-05T15:32:37Z","abstract_excerpt":"In this paper, we analyze the regret incurred by a computationally efficient exploration strategy, known as naive exploration, for controlling unknown partially observable systems within the Linear Quadratic Gaussian (LQG) framework. We introduce a two-phase control algorithm called LQG-NAIVE, which involves an initial phase of injecting Gaussian input signals to obtain a system model, followed by a second phase of an interplay between naive exploration and control in an episodic fashion. We show that LQG-NAIVE achieves a regret growth rate of $\\tilde{\\mathcal{O}}(\\sqrt{T})$, i.e., $\\mathcal{O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02679","kind":"arxiv","version":2},"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/2311.02679/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":"2311.02679","created_at":"2026-07-05T07:16:02.481573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02679v2","created_at":"2026-07-05T07:16:02.481573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02679","created_at":"2026-07-05T07:16:02.481573+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBJBP2R65SC6","created_at":"2026-07-05T07:16:02.481573+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBJBP2R65SC6PG3N","created_at":"2026-07-05T07:16:02.481573+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBJBP2R6","created_at":"2026-07-05T07:16:02.481573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU","json":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU.json","graph_json":"https://pith.science/api/pith-number/CBJBP2R65SC6PG3NAGIE6OXORU/graph.json","events_json":"https://pith.science/api/pith-number/CBJBP2R65SC6PG3NAGIE6OXORU/events.json","paper":"https://pith.science/paper/CBJBP2R6"},"agent_actions":{"view_html":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU","download_json":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU.json","view_paper":"https://pith.science/paper/CBJBP2R6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02679&json=true","fetch_graph":"https://pith.science/api/pith-number/CBJBP2R65SC6PG3NAGIE6OXORU/graph.json","fetch_events":"https://pith.science/api/pith-number/CBJBP2R65SC6PG3NAGIE6OXORU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU/action/storage_attestation","attest_author":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU/action/author_attestation","sign_citation":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU/action/citation_signature","submit_replication":"https://pith.science/pith/CBJBP2R65SC6PG3NAGIE6OXORU/action/replication_record"}},"created_at":"2026-07-05T07:16:02.481573+00:00","updated_at":"2026-07-05T07:16:02.481573+00:00"}