{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CT56DUHOUWBF6NCR5BKYMO3I57","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5862a4a9cf9d9686f29a70cdeee2a1c7f5a44547537612f4f1a23bdd94ef3f57","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","title_canon_sha256":"20770361605e8bfe0845253a52422d78511ee1138a9aaed396413e6c7424d0ed"},"schema_version":"1.0","source":{"id":"1801.05039","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.05039","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"1801.05039v3","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05039","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"CT56DUHOUWBF","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CT56DUHOUWBF6NCR","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CT56DUHO","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:9f1d16a16ee04066f9a58322d801d8cabdc5498907d6fa2afa4b439c65da20eb","target":"graph","created_at":"2026-05-17T23:50:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Maryam Fazel, Mehran Mesbahi, Rong Ge, Sham M. Kakade","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05039","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8f10c9af0eb70ae76927484af9dcd92717c990d0373605725d3c385e98ecac45","target":"record","created_at":"2026-05-17T23:50:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5862a4a9cf9d9686f29a70cdeee2a1c7f5a44547537612f4f1a23bdd94ef3f57","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","title_canon_sha256":"20770361605e8bfe0845253a52422d78511ee1138a9aaed396413e6c7424d0ed"},"schema_version":"1.0","source":{"id":"1801.05039","kind":"arxiv","version":3}},"canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","first_computed_at":"2026-05-17T23:50:38.792792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:38.792792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wTLEvvCeGp08UvlbZxvR59+RBOIXExnC0E7e3uEKl6VYgQ+/mBPx6ps68mDll07I4IZjVvoeG5QqtGd0mFzUDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:38.793374Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.05039","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f10c9af0eb70ae76927484af9dcd92717c990d0373605725d3c385e98ecac45","sha256:9f1d16a16ee04066f9a58322d801d8cabdc5498907d6fa2afa4b439c65da20eb"],"state_sha256":"7ff67a7ac97b979562e5e9fa127df3fa92b51a04f42dae524e90287322314a4e"}