{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J3Y2Y2XXQOHKTRAHBFQWA2CTSD","short_pith_number":"pith:J3Y2Y2XX","schema_version":"1.0","canonical_sha256":"4ef1ac6af7838ea9c407096160685390e0844f6fbe3d06d455d02aa05627e846","source":{"kind":"arxiv","id":"2403.17364","version":2},"attestation_state":"computed","paper":{"title":"A Moreau Envelope Approach for LQR Meta-Policy Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Ashwin Aravind, C\\'esar A. Uribe, Mohammad Taha Toghani","submitted_at":"2024-03-26T04:02:09Z","abstract_excerpt":"We study the problem of policy estimation for the Linear Quadratic Regulator (LQR) in discrete-time linear time-invariant uncertain dynamical systems. We propose a Moreau Envelope-based surrogate LQR cost, built from a finite set of realizations of the uncertain system, to define a meta-policy efficiently adjustable to new realizations. Moreover, we design an algorithm to find an approximate first-order stationary point of the meta-LQR cost function. Numerical results show that the proposed approach outperforms naive averaging of controllers on new realizations of the linear system. We also pr"},"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":"2403.17364","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-03-26T04:02:09Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"456dafae54c58f0f72e2d4638054a56435644a9f1085fd99735128a07cb8d59f","abstract_canon_sha256":"1418d370fda5223ced30288c02108af0b8c132f8d6ec06507c0754d0fa6c5eff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:47.438735Z","signature_b64":"5rF2TZjEU5CrYhhTBWV7K1tNaOMsL+YGFWCS1YROgX2+easSm1YF5VRtpKMUYrhL230/TlfofWF4y6e6vuRrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ef1ac6af7838ea9c407096160685390e0844f6fbe3d06d455d02aa05627e846","last_reissued_at":"2026-07-05T09:16:47.438232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:47.438232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Moreau Envelope Approach for LQR Meta-Policy Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Ashwin Aravind, C\\'esar A. Uribe, Mohammad Taha Toghani","submitted_at":"2024-03-26T04:02:09Z","abstract_excerpt":"We study the problem of policy estimation for the Linear Quadratic Regulator (LQR) in discrete-time linear time-invariant uncertain dynamical systems. We propose a Moreau Envelope-based surrogate LQR cost, built from a finite set of realizations of the uncertain system, to define a meta-policy efficiently adjustable to new realizations. Moreover, we design an algorithm to find an approximate first-order stationary point of the meta-LQR cost function. Numerical results show that the proposed approach outperforms naive averaging of controllers on new realizations of the linear system. We also pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17364","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/2403.17364/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":"2403.17364","created_at":"2026-07-05T09:16:47.438287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17364v2","created_at":"2026-07-05T09:16:47.438287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17364","created_at":"2026-07-05T09:16:47.438287+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3Y2Y2XXQOHK","created_at":"2026-07-05T09:16:47.438287+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3Y2Y2XXQOHKTRAH","created_at":"2026-07-05T09:16:47.438287+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3Y2Y2XX","created_at":"2026-07-05T09:16:47.438287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02332","citing_title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD","json":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD.json","graph_json":"https://pith.science/api/pith-number/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/graph.json","events_json":"https://pith.science/api/pith-number/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/events.json","paper":"https://pith.science/paper/J3Y2Y2XX"},"agent_actions":{"view_html":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD","download_json":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD.json","view_paper":"https://pith.science/paper/J3Y2Y2XX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17364&json=true","fetch_graph":"https://pith.science/api/pith-number/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/graph.json","fetch_events":"https://pith.science/api/pith-number/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/action/storage_attestation","attest_author":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/action/author_attestation","sign_citation":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/action/citation_signature","submit_replication":"https://pith.science/pith/J3Y2Y2XXQOHKTRAHBFQWA2CTSD/action/replication_record"}},"created_at":"2026-07-05T09:16:47.438287+00:00","updated_at":"2026-07-05T09:16:47.438287+00:00"}