{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EIV4A6S334UKLK4V7R67W6GSOU","short_pith_number":"pith:EIV4A6S3","schema_version":"1.0","canonical_sha256":"222bc07a5bdf28a5ab95fc7dfb78d275261b5ac51981a6aa6ae73919c844b1d4","source":{"kind":"arxiv","id":"1901.03674","version":1},"attestation_state":"computed","paper":{"title":"On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mingyi Hong, Qi Cai, Yongxin Chen, Zhaoran Wang","submitted_at":"2019-01-11T17:54:47Z","abstract_excerpt":"We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization. To address the challenges arising from non-convex-concave geometry, we analyze the alternating gradient algorithm and establish its Q-linear rate of convergence to a unique saddle point, which simultaneously recovers the globally optimal policy and reward function. We hope our results may serve as a small step towards understanding and taming the instability in imitation learning as well as in more general non-convex-concave alternating minimax o"},"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":"1901.03674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-11T17:54:47Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"04281c1c359037c14dfab2d1b9015f38fa93449ba0b256228fc4f0bf928c9f7c","abstract_canon_sha256":"ee3cdb0d8873c433b673f4793008f81a5307599046153c3f6c6352cab12dd5c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:27.238869Z","signature_b64":"/8zPqHn80CHUKBU0nRtnAoFQ2Emun0KObTcTjqkcnIMGuk4g/hwqhmP7ctpwltOaJ6fHvJchUtTtBs4l3fapCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"222bc07a5bdf28a5ab95fc7dfb78d275261b5ac51981a6aa6ae73919c844b1d4","last_reissued_at":"2026-05-17T23:56:27.238343Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:27.238343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mingyi Hong, Qi Cai, Yongxin Chen, Zhaoran Wang","submitted_at":"2019-01-11T17:54:47Z","abstract_excerpt":"We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization. To address the challenges arising from non-convex-concave geometry, we analyze the alternating gradient algorithm and establish its Q-linear rate of convergence to a unique saddle point, which simultaneously recovers the globally optimal policy and reward function. We hope our results may serve as a small step towards understanding and taming the instability in imitation learning as well as in more general non-convex-concave alternating minimax o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03674","kind":"arxiv","version":1},"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":"1901.03674","created_at":"2026-05-17T23:56:27.238420+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.03674v1","created_at":"2026-05-17T23:56:27.238420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03674","created_at":"2026-05-17T23:56:27.238420+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIV4A6S334UK","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIV4A6S334UKLK4V","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIV4A6S3","created_at":"2026-05-18T12:33:15.570797+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/EIV4A6S334UKLK4V7R67W6GSOU","json":"https://pith.science/pith/EIV4A6S334UKLK4V7R67W6GSOU.json","graph_json":"https://pith.science/api/pith-number/EIV4A6S334UKLK4V7R67W6GSOU/graph.json","events_json":"https://pith.science/api/pith-number/EIV4A6S334UKLK4V7R67W6GSOU/events.json","paper":"https://pith.science/paper/EIV4A6S3"},"agent_actions":{"view_html":"https://pith.science/pith/EIV4A6S334UKLK4V7R67W6GSOU","download_json":"https://pith.science/pith/EIV4A6S334UKLK4V7R67W6GSOU.json","view_paper":"https://pith.science/paper/EIV4A6S3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.03674&json=true","fetch_graph":"https://pith.science/api/pith-number/EIV4A6S334UKLK4V7R67W6GSOU/graph.json","fetch_events":"https://pith.science/api/pith-number/EIV4A6S334UKLK4V7R67W6GSOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIV4A6S334UKLK4V7R67W6GSOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIV4A6S334UKLK4V7R67W6GSOU/action/storage_attestation","attest_author":"https://pith.science/pith/EIV4A6S334UKLK4V7R67W6GSOU/action/author_attestation","sign_citation":"https://pith.science/pith/EIV4A6S334UKLK4V7R67W6GSOU/action/citation_signature","submit_replication":"https://pith.science/pith/EIV4A6S334UKLK4V7R67W6GSOU/action/replication_record"}},"created_at":"2026-05-17T23:56:27.238420+00:00","updated_at":"2026-05-17T23:56:27.238420+00:00"}