{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ADL7HCFHPFIX6BR37QCMIH2FPO","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":"2283e8505d4b849cd90ff0fdee97ba1b99cf1056ab33258e4f56ac6b4738e588","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T08:08:02Z","title_canon_sha256":"fd43d6235a55d43416ffa768832f68a25343078d674034c5526dd19d5dade749"},"schema_version":"1.0","source":{"id":"2303.08431","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08431","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08431v5","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08431","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"ADL7HCFHPFIX","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"ADL7HCFHPFIX6BR3","created_at":"2026-07-05T10:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"ADL7HCFH","created_at":"2026-07-05T10:46:52Z"}],"graph_snapshots":[{"event_id":"sha256:44bba01b15dbaf69991ab0c1ff04ecf61a156dc6a0faae49879a9e89383549a5","target":"graph","created_at":"2026-07-05T10:46:52Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.08431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Nonlinear control systems with partial information to the decision maker are prevalent in a variety of applications. As a step toward studying such nonlinear systems, this work explores reinforcement learning methods for finding the optimal policy in the nearly linear-quadratic regulator systems. In particular, we consider a dynamic system that combines linear and nonlinear components, and is governed by a policy with the same structure. Assuming that the nonlinear component comprises kernels with small Lipschitz coefficients, we characterize the optimization landscape of the cost function. Al","authors_text":"Meisam Razaviyayn, Renyuan Xu, Yinbin Han","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T08:08:02Z","title":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08431","kind":"arxiv","version":5},"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":"sha256:74fbc8b344ef830794ec3ef6383fda79417de55332c5bef3b68c9314707a339f","target":"record","created_at":"2026-07-05T10:46:52Z","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":"2283e8505d4b849cd90ff0fdee97ba1b99cf1056ab33258e4f56ac6b4738e588","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T08:08:02Z","title_canon_sha256":"fd43d6235a55d43416ffa768832f68a25343078d674034c5526dd19d5dade749"},"schema_version":"1.0","source":{"id":"2303.08431","kind":"arxiv","version":5}},"canonical_sha256":"00d7f388a779517f063bfc04c41f457bbdda96270388dba92eb6dd89180f6a23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00d7f388a779517f063bfc04c41f457bbdda96270388dba92eb6dd89180f6a23","first_computed_at":"2026-07-05T10:46:52.248952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:52.248952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tcjpZnmu+7hOgPvoKFgyRgA/G8cmDdkgvyQ6iI3GNob9O8XjbYuEoiPM9dz97SnKXrgmA1UDlRren1CQIr7wBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:52.249432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.08431","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74fbc8b344ef830794ec3ef6383fda79417de55332c5bef3b68c9314707a339f","sha256:44bba01b15dbaf69991ab0c1ff04ecf61a156dc6a0faae49879a9e89383549a5"],"state_sha256":"52f04554e49a5a9b088e60ba1434930f03088164de63be6a32d30ebe86ebe90e"}