{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ADL7HCFHPFIX6BR37QCMIH2FPO","short_pith_number":"pith:ADL7HCFH","schema_version":"1.0","canonical_sha256":"00d7f388a779517f063bfc04c41f457bbdda96270388dba92eb6dd89180f6a23","source":{"kind":"arxiv","id":"2303.08431","version":5},"attestation_state":"computed","paper":{"title":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Meisam Razaviyayn, Renyuan Xu, Yinbin Han","submitted_at":"2023-03-15T08:08:02Z","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"},"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":"2303.08431","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T08:08:02Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fd43d6235a55d43416ffa768832f68a25343078d674034c5526dd19d5dade749","abstract_canon_sha256":"2283e8505d4b849cd90ff0fdee97ba1b99cf1056ab33258e4f56ac6b4738e588"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:52.249432Z","signature_b64":"tcjpZnmu+7hOgPvoKFgyRgA/G8cmDdkgvyQ6iI3GNob9O8XjbYuEoiPM9dz97SnKXrgmA1UDlRren1CQIr7wBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00d7f388a779517f063bfc04c41f457bbdda96270388dba92eb6dd89180f6a23","last_reissued_at":"2026-07-05T10:46:52.248952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:52.248952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Meisam Razaviyayn, Renyuan Xu, Yinbin Han","submitted_at":"2023-03-15T08:08:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08431","kind":"arxiv","version":5},"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/2303.08431/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":"2303.08431","created_at":"2026-07-05T10:46:52.249017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08431v5","created_at":"2026-07-05T10:46:52.249017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08431","created_at":"2026-07-05T10:46:52.249017+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADL7HCFHPFIX","created_at":"2026-07-05T10:46:52.249017+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADL7HCFHPFIX6BR3","created_at":"2026-07-05T10:46:52.249017+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADL7HCFH","created_at":"2026-07-05T10:46:52.249017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18164","citing_title":"Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO","json":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO.json","graph_json":"https://pith.science/api/pith-number/ADL7HCFHPFIX6BR37QCMIH2FPO/graph.json","events_json":"https://pith.science/api/pith-number/ADL7HCFHPFIX6BR37QCMIH2FPO/events.json","paper":"https://pith.science/paper/ADL7HCFH"},"agent_actions":{"view_html":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO","download_json":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO.json","view_paper":"https://pith.science/paper/ADL7HCFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08431&json=true","fetch_graph":"https://pith.science/api/pith-number/ADL7HCFHPFIX6BR37QCMIH2FPO/graph.json","fetch_events":"https://pith.science/api/pith-number/ADL7HCFHPFIX6BR37QCMIH2FPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO/action/storage_attestation","attest_author":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO/action/author_attestation","sign_citation":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO/action/citation_signature","submit_replication":"https://pith.science/pith/ADL7HCFHPFIX6BR37QCMIH2FPO/action/replication_record"}},"created_at":"2026-07-05T10:46:52.249017+00:00","updated_at":"2026-07-05T10:46:52.249017+00:00"}