{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CT56DUHOUWBF6NCR5BKYMO3I57","short_pith_number":"pith:CT56DUHO","schema_version":"1.0","canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","source":{"kind":"arxiv","id":"1801.05039","version":3},"attestation_state":"computed","paper":{"title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Maryam Fazel, Mehran Mesbahi, Rong Ge, Sham M. Kakade","submitted_at":"2018-01-15T21:40:50Z","abstract_excerpt":"Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an \"end-to-end\" approach, directly optimizing the performance metric of interest 3) they inherently allow for richly parameterized policies. A notable drawback is that even in the most basic continuous control problem (that of linear quadratic regulators), these methods must solve a non-convex optimization problem, where little is understood about their efficiency f"},"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":"1801.05039","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"20770361605e8bfe0845253a52422d78511ee1138a9aaed396413e6c7424d0ed","abstract_canon_sha256":"5862a4a9cf9d9686f29a70cdeee2a1c7f5a44547537612f4f1a23bdd94ef3f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:38.793374Z","signature_b64":"wTLEvvCeGp08UvlbZxvR59+RBOIXExnC0E7e3uEKl6VYgQ+/mBPx6ps68mDll07I4IZjVvoeG5QqtGd0mFzUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","last_reissued_at":"2026-05-17T23:50:38.792792Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:38.792792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Maryam Fazel, Mehran Mesbahi, Rong Ge, Sham M. Kakade","submitted_at":"2018-01-15T21:40:50Z","abstract_excerpt":"Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an \"end-to-end\" approach, directly optimizing the performance metric of interest 3) they inherently allow for richly parameterized policies. A notable drawback is that even in the most basic continuous control problem (that of linear quadratic regulators), these methods must solve a non-convex optimization problem, where little is understood about their efficiency f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05039","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":""},"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":"1801.05039","created_at":"2026-05-17T23:50:38.792873+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.05039v3","created_at":"2026-05-17T23:50:38.792873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05039","created_at":"2026-05-17T23:50:38.792873+00:00"},{"alias_kind":"pith_short_12","alias_value":"CT56DUHOUWBF","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"CT56DUHOUWBF6NCR","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"CT56DUHO","created_at":"2026-05-18T12:32:19.392346+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/CT56DUHOUWBF6NCR5BKYMO3I57","json":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57.json","graph_json":"https://pith.science/api/pith-number/CT56DUHOUWBF6NCR5BKYMO3I57/graph.json","events_json":"https://pith.science/api/pith-number/CT56DUHOUWBF6NCR5BKYMO3I57/events.json","paper":"https://pith.science/paper/CT56DUHO"},"agent_actions":{"view_html":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57","download_json":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57.json","view_paper":"https://pith.science/paper/CT56DUHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.05039&json=true","fetch_graph":"https://pith.science/api/pith-number/CT56DUHOUWBF6NCR5BKYMO3I57/graph.json","fetch_events":"https://pith.science/api/pith-number/CT56DUHOUWBF6NCR5BKYMO3I57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/action/storage_attestation","attest_author":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/action/author_attestation","sign_citation":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/action/citation_signature","submit_replication":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/action/replication_record"}},"created_at":"2026-05-17T23:50:38.792873+00:00","updated_at":"2026-05-17T23:50:38.792873+00:00"}