{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VHFX4QC5YIFLM37AJOUS6CVAZT","short_pith_number":"pith:VHFX4QC5","schema_version":"1.0","canonical_sha256":"a9cb7e405dc20ab66fe04ba92f0aa0ccc9bd8d0a84a1c0a0a8f3312bbe843995","source":{"kind":"arxiv","id":"1906.00729","version":4},"attestation_state":"computed","paper":{"title":"Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiqing Zhang, Tamer Ba\\c{s}ar, Zhuoran Yang","submitted_at":"2019-05-31T17:28:25Z","abstract_excerpt":"We study the global convergence of policy optimization for finding the Nash equilibria (NE) in zero-sum linear quadratic (LQ) games. To this end, we first investigate the landscape of LQ games, viewing it as a nonconvex-nonconcave saddle-point problem in the policy space. Specifically, we show that despite its nonconvexity and nonconcavity, zero-sum LQ games have the property that the stationary point of the objective function with respect to the linear feedback control policies constitutes the NE of the game. Building upon this, we develop three projected nested-gradient methods that are guar"},"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":"1906.00729","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T17:28:25Z","cross_cats_sorted":["cs.GT","cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"11d6182b8307d2a05c4ca1359088d0146fe87df560b1ffce7be2131064e3d766","abstract_canon_sha256":"173b69f4848c96d0db5231769e11c0590e6a740fcfe1df5102a31f8621bbe6f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T20:14:34.320002Z","signature_b64":"ID48mzs0fNu6ms9YAZBnizpm5LOW4FCd+wm7PqTGikCCgoP3R3M0wQ6vj1LY1PMXBwNLbdjXf8NK7RU35H4HDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9cb7e405dc20ab66fe04ba92f0aa0ccc9bd8d0a84a1c0a0a8f3312bbe843995","last_reissued_at":"2026-06-04T20:14:34.319569Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T20:14:34.319569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiqing Zhang, Tamer Ba\\c{s}ar, Zhuoran Yang","submitted_at":"2019-05-31T17:28:25Z","abstract_excerpt":"We study the global convergence of policy optimization for finding the Nash equilibria (NE) in zero-sum linear quadratic (LQ) games. To this end, we first investigate the landscape of LQ games, viewing it as a nonconvex-nonconcave saddle-point problem in the policy space. Specifically, we show that despite its nonconvexity and nonconcavity, zero-sum LQ games have the property that the stationary point of the objective function with respect to the linear feedback control policies constitutes the NE of the game. Building upon this, we develop three projected nested-gradient methods that are guar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00729","kind":"arxiv","version":4},"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/1906.00729/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":"1906.00729","created_at":"2026-06-04T20:14:34.319646+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00729v4","created_at":"2026-06-04T20:14:34.319646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00729","created_at":"2026-06-04T20:14:34.319646+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHFX4QC5YIFL","created_at":"2026-06-04T20:14:34.319646+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHFX4QC5YIFLM37A","created_at":"2026-06-04T20:14:34.319646+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHFX4QC5","created_at":"2026-06-04T20:14:34.319646+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/VHFX4QC5YIFLM37AJOUS6CVAZT","json":"https://pith.science/pith/VHFX4QC5YIFLM37AJOUS6CVAZT.json","graph_json":"https://pith.science/api/pith-number/VHFX4QC5YIFLM37AJOUS6CVAZT/graph.json","events_json":"https://pith.science/api/pith-number/VHFX4QC5YIFLM37AJOUS6CVAZT/events.json","paper":"https://pith.science/paper/VHFX4QC5"},"agent_actions":{"view_html":"https://pith.science/pith/VHFX4QC5YIFLM37AJOUS6CVAZT","download_json":"https://pith.science/pith/VHFX4QC5YIFLM37AJOUS6CVAZT.json","view_paper":"https://pith.science/paper/VHFX4QC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00729&json=true","fetch_graph":"https://pith.science/api/pith-number/VHFX4QC5YIFLM37AJOUS6CVAZT/graph.json","fetch_events":"https://pith.science/api/pith-number/VHFX4QC5YIFLM37AJOUS6CVAZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHFX4QC5YIFLM37AJOUS6CVAZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHFX4QC5YIFLM37AJOUS6CVAZT/action/storage_attestation","attest_author":"https://pith.science/pith/VHFX4QC5YIFLM37AJOUS6CVAZT/action/author_attestation","sign_citation":"https://pith.science/pith/VHFX4QC5YIFLM37AJOUS6CVAZT/action/citation_signature","submit_replication":"https://pith.science/pith/VHFX4QC5YIFLM37AJOUS6CVAZT/action/replication_record"}},"created_at":"2026-06-04T20:14:34.319646+00:00","updated_at":"2026-06-04T20:14:34.319646+00:00"}