{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CBL3UAWEXPLLMBTANS2H2V4AWU","short_pith_number":"pith:CBL3UAWE","schema_version":"1.0","canonical_sha256":"1057ba02c4bbd6b606606cb47d5780b50e1afd259459aa6a6becb560c7bb376a","source":{"kind":"arxiv","id":"1812.08305","version":3},"attestation_state":"computed","paper":{"title":"Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashwin Pananjady, Dhruv Malik, Koulik Khamaru, Kush Bhatia, Martin J. Wainwright, Peter L. Bartlett","submitted_at":"2018-12-20T01:22:44Z","abstract_excerpt":"We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-quadratic systems, and study various settings of driving noise and reward feedback. We show that these methods provably converge to within any pre-specified tolerance of the optimal policy with a number of zero-order evaluations that is an explicit polynomial of the error tolerance, dimension, and curvature properties of the problem. Our analysis reveals some interesting differences between the settings of additive d"},"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":"1812.08305","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-20T01:22:44Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"48278a9e5f02606752ea2b2a15e52a032be8e2972fb5bfa4461b7bed6c9e9ac7","abstract_canon_sha256":"c52da2a5db406ad94c1b48ca2cb2387e6d023a531a4541e3d67d6d6567eaa490"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:18.504473Z","signature_b64":"oSmtCtIfvxh9ZWUv+W/NH3nRm45ZZ0ieBwSk/SEGOS8cdbO3e0QkpjJ1+X7dG9ssb3tJvFIWX8q8GIX+YEFeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1057ba02c4bbd6b606606cb47d5780b50e1afd259459aa6a6becb560c7bb376a","last_reissued_at":"2026-07-05T01:03:18.503995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:18.503995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashwin Pananjady, Dhruv Malik, Koulik Khamaru, Kush Bhatia, Martin J. Wainwright, Peter L. Bartlett","submitted_at":"2018-12-20T01:22:44Z","abstract_excerpt":"We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-quadratic systems, and study various settings of driving noise and reward feedback. We show that these methods provably converge to within any pre-specified tolerance of the optimal policy with a number of zero-order evaluations that is an explicit polynomial of the error tolerance, dimension, and curvature properties of the problem. Our analysis reveals some interesting differences between the settings of additive d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08305","kind":"arxiv","version":3},"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/1812.08305/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":"1812.08305","created_at":"2026-07-05T01:03:18.504052+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08305v3","created_at":"2026-07-05T01:03:18.504052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08305","created_at":"2026-07-05T01:03:18.504052+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBL3UAWEXPLL","created_at":"2026-07-05T01:03:18.504052+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBL3UAWEXPLLMBTA","created_at":"2026-07-05T01:03:18.504052+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBL3UAWE","created_at":"2026-07-05T01:03:18.504052+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/CBL3UAWEXPLLMBTANS2H2V4AWU","json":"https://pith.science/pith/CBL3UAWEXPLLMBTANS2H2V4AWU.json","graph_json":"https://pith.science/api/pith-number/CBL3UAWEXPLLMBTANS2H2V4AWU/graph.json","events_json":"https://pith.science/api/pith-number/CBL3UAWEXPLLMBTANS2H2V4AWU/events.json","paper":"https://pith.science/paper/CBL3UAWE"},"agent_actions":{"view_html":"https://pith.science/pith/CBL3UAWEXPLLMBTANS2H2V4AWU","download_json":"https://pith.science/pith/CBL3UAWEXPLLMBTANS2H2V4AWU.json","view_paper":"https://pith.science/paper/CBL3UAWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08305&json=true","fetch_graph":"https://pith.science/api/pith-number/CBL3UAWEXPLLMBTANS2H2V4AWU/graph.json","fetch_events":"https://pith.science/api/pith-number/CBL3UAWEXPLLMBTANS2H2V4AWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBL3UAWEXPLLMBTANS2H2V4AWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBL3UAWEXPLLMBTANS2H2V4AWU/action/storage_attestation","attest_author":"https://pith.science/pith/CBL3UAWEXPLLMBTANS2H2V4AWU/action/author_attestation","sign_citation":"https://pith.science/pith/CBL3UAWEXPLLMBTANS2H2V4AWU/action/citation_signature","submit_replication":"https://pith.science/pith/CBL3UAWEXPLLMBTANS2H2V4AWU/action/replication_record"}},"created_at":"2026-07-05T01:03:18.504052+00:00","updated_at":"2026-07-05T01:03:18.504052+00:00"}