{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XT74HBVPE6WEEVPHB5XZG44APB","short_pith_number":"pith:XT74HBVP","schema_version":"1.0","canonical_sha256":"bcffc386af27ac4255e70f6f9373807875bc8ffdf59910c4e28e0135a044699f","source":{"kind":"arxiv","id":"2404.13009","version":1},"attestation_state":"computed","paper":{"title":"Online Policy Optimization in Unknown Nonlinear Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Adam Wierman, Emile Anand, Fengze Xie, James A. Preiss, Soon-Jo Chung, Yiheng Lin, Yisong Yue","submitted_at":"2024-04-19T17:13:24Z","abstract_excerpt":"We study online policy optimization in nonlinear time-varying dynamical systems where the true dynamical models are unknown to the controller. This problem is challenging because, unlike in linear systems, the controller cannot obtain globally accurate estimations of the ground-truth dynamics using local exploration. We propose a meta-framework that combines a general online policy optimization algorithm ($\\texttt{ALG}$) with a general online estimator of the dynamical system's model parameters ($\\texttt{EST}$). We show that if the hypothetical joint dynamics induced by $\\texttt{ALG}$ with kno"},"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":"2404.13009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-04-19T17:13:24Z","cross_cats_sorted":[],"title_canon_sha256":"c7d6c4d7cf1d73573797c97a19639447c7edd8fe7b774c04209c976ffb5af2f4","abstract_canon_sha256":"cf408723a7fc972955c5dea09378e377140f437170e556976b5895ae60405fae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:01.927940Z","signature_b64":"MR0xIbnQS+PoZjhji0plgtcvlPDfRx732g197utFIs1+Qdi/RSN8namOR2qbXfYw1TI7hp6F/9oapHboKFpVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcffc386af27ac4255e70f6f9373807875bc8ffdf59910c4e28e0135a044699f","last_reissued_at":"2026-07-05T08:10:01.927488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:01.927488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Policy Optimization in Unknown Nonlinear Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Adam Wierman, Emile Anand, Fengze Xie, James A. Preiss, Soon-Jo Chung, Yiheng Lin, Yisong Yue","submitted_at":"2024-04-19T17:13:24Z","abstract_excerpt":"We study online policy optimization in nonlinear time-varying dynamical systems where the true dynamical models are unknown to the controller. This problem is challenging because, unlike in linear systems, the controller cannot obtain globally accurate estimations of the ground-truth dynamics using local exploration. We propose a meta-framework that combines a general online policy optimization algorithm ($\\texttt{ALG}$) with a general online estimator of the dynamical system's model parameters ($\\texttt{EST}$). We show that if the hypothetical joint dynamics induced by $\\texttt{ALG}$ with kno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13009","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.13009/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":"2404.13009","created_at":"2026-07-05T08:10:01.927554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13009v1","created_at":"2026-07-05T08:10:01.927554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13009","created_at":"2026-07-05T08:10:01.927554+00:00"},{"alias_kind":"pith_short_12","alias_value":"XT74HBVPE6WE","created_at":"2026-07-05T08:10:01.927554+00:00"},{"alias_kind":"pith_short_16","alias_value":"XT74HBVPE6WEEVPH","created_at":"2026-07-05T08:10:01.927554+00:00"},{"alias_kind":"pith_short_8","alias_value":"XT74HBVP","created_at":"2026-07-05T08:10:01.927554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00023","citing_title":"Role Steering of Language Models for Social Simulations","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB","json":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB.json","graph_json":"https://pith.science/api/pith-number/XT74HBVPE6WEEVPHB5XZG44APB/graph.json","events_json":"https://pith.science/api/pith-number/XT74HBVPE6WEEVPHB5XZG44APB/events.json","paper":"https://pith.science/paper/XT74HBVP"},"agent_actions":{"view_html":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB","download_json":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB.json","view_paper":"https://pith.science/paper/XT74HBVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13009&json=true","fetch_graph":"https://pith.science/api/pith-number/XT74HBVPE6WEEVPHB5XZG44APB/graph.json","fetch_events":"https://pith.science/api/pith-number/XT74HBVPE6WEEVPHB5XZG44APB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB/action/storage_attestation","attest_author":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB/action/author_attestation","sign_citation":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB/action/citation_signature","submit_replication":"https://pith.science/pith/XT74HBVPE6WEEVPHB5XZG44APB/action/replication_record"}},"created_at":"2026-07-05T08:10:01.927554+00:00","updated_at":"2026-07-05T08:10:01.927554+00:00"}