{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VQQ3N7ZFQ5U5NCKBGFENQFQBOS","short_pith_number":"pith:VQQ3N7ZF","schema_version":"1.0","canonical_sha256":"ac21b6ff258769d689413148d8160174912e13e11ac1b62332ef6b41857bc9ab","source":{"kind":"arxiv","id":"2503.00385","version":1},"attestation_state":"computed","paper":{"title":"Model-Agnostic Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Quanyan Zhu, Tao Li, Yunian Pan","submitted_at":"2025-03-01T07:17:39Z","abstract_excerpt":"Meta-learning has been proposed as a promising machine learning topic in recent years, with important applications to image classification, robotics, computer games, and control systems. In this paper, we study the problem of using meta-learning to deal with uncertainty and heterogeneity in ergodic linear quadratic regulators. We integrate the zeroth-order optimization technique with a typical meta-learning method, proposing an algorithm that omits the estimation of policy Hessian, which applies to tasks of learning a set of heterogeneous but similar linear dynamic systems. The induced meta-ob"},"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":"2503.00385","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-03-01T07:17:39Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"c3bafe1784b19cea07be4d91eaf796263f7623fa5634943231b35d5baa3fe6bc","abstract_canon_sha256":"540249dd68400e6feebb578f5fcbe226f600114ce7b070424744759c7e746631"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:21.708129Z","signature_b64":"/5qRtmnOHXFRqgURwSr4ufgqsEcxipNhIn1od46FrqTxSh2twfsLnCt+lQLX7znnCpcidTC87ABU6VA4gpYWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac21b6ff258769d689413148d8160174912e13e11ac1b62332ef6b41857bc9ab","last_reissued_at":"2026-07-05T10:22:21.707428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:21.707428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Agnostic Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Quanyan Zhu, Tao Li, Yunian Pan","submitted_at":"2025-03-01T07:17:39Z","abstract_excerpt":"Meta-learning has been proposed as a promising machine learning topic in recent years, with important applications to image classification, robotics, computer games, and control systems. In this paper, we study the problem of using meta-learning to deal with uncertainty and heterogeneity in ergodic linear quadratic regulators. We integrate the zeroth-order optimization technique with a typical meta-learning method, proposing an algorithm that omits the estimation of policy Hessian, which applies to tasks of learning a set of heterogeneous but similar linear dynamic systems. The induced meta-ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00385","kind":"arxiv","version":1},"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/2503.00385/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":"2503.00385","created_at":"2026-07-05T10:22:21.707525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00385v1","created_at":"2026-07-05T10:22:21.707525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00385","created_at":"2026-07-05T10:22:21.707525+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQQ3N7ZFQ5U5","created_at":"2026-07-05T10:22:21.707525+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQQ3N7ZFQ5U5NCKB","created_at":"2026-07-05T10:22:21.707525+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQQ3N7ZF","created_at":"2026-07-05T10:22:21.707525+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/VQQ3N7ZFQ5U5NCKBGFENQFQBOS","json":"https://pith.science/pith/VQQ3N7ZFQ5U5NCKBGFENQFQBOS.json","graph_json":"https://pith.science/api/pith-number/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/graph.json","events_json":"https://pith.science/api/pith-number/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/events.json","paper":"https://pith.science/paper/VQQ3N7ZF"},"agent_actions":{"view_html":"https://pith.science/pith/VQQ3N7ZFQ5U5NCKBGFENQFQBOS","download_json":"https://pith.science/pith/VQQ3N7ZFQ5U5NCKBGFENQFQBOS.json","view_paper":"https://pith.science/paper/VQQ3N7ZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00385&json=true","fetch_graph":"https://pith.science/api/pith-number/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/graph.json","fetch_events":"https://pith.science/api/pith-number/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/action/storage_attestation","attest_author":"https://pith.science/pith/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/action/author_attestation","sign_citation":"https://pith.science/pith/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/action/citation_signature","submit_replication":"https://pith.science/pith/VQQ3N7ZFQ5U5NCKBGFENQFQBOS/action/replication_record"}},"created_at":"2026-07-05T10:22:21.707525+00:00","updated_at":"2026-07-05T10:22:21.707525+00:00"}