{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JOMQO6XYAAHBOFRA5RXFUNVOXR","short_pith_number":"pith:JOMQO6XY","schema_version":"1.0","canonical_sha256":"4b99077af8000e171620ec6e5a36aebc5355ec6ee094582d719f8a0ad542bcf1","source":{"kind":"arxiv","id":"2306.05482","version":1},"attestation_state":"computed","paper":{"title":"Data-Driven Near-Optimal Control of Nonlinear Systems Over Finite Horizon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Almuatazbellah Boker, Hoda Eldardiry, Vasanth Reddy","submitted_at":"2023-06-08T18:06:31Z","abstract_excerpt":"We examine the problem of two-point boundary optimal control of nonlinear systems over finite-horizon time periods with unknown model dynamics by employing reinforcement learning. We use techniques from singular perturbation theory to decompose the control problem over the finite horizon into two sub-problems, each solved over an infinite horizon. In the process, we avoid the need to solve the time-varying Hamilton-Jacobi-Bellman equation. Using a policy iteration method, which is made feasible as a result of this decomposition, it is now possible to learn the controller gains of both sub-prob"},"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":"2306.05482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-08T18:06:31Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"998d930336814485639401cbc5f7cbe0b9661aea8ca11d9ce4be6aa37de8c84e","abstract_canon_sha256":"3ca60142cb66b29e54e7df5baf763b09e838a75d76fe09a583adb344877cc0f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:06.607773Z","signature_b64":"98cUT5uhODV7omT2/FJl3Nw/ndW0JWWuOklq0bkyAZbBXYfRz7R8haPdHJLW17nAvwNQ3qZA3wctv4TTfLtxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b99077af8000e171620ec6e5a36aebc5355ec6ee094582d719f8a0ad542bcf1","last_reissued_at":"2026-07-05T06:19:06.606506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:06.606506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Driven Near-Optimal Control of Nonlinear Systems Over Finite Horizon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Almuatazbellah Boker, Hoda Eldardiry, Vasanth Reddy","submitted_at":"2023-06-08T18:06:31Z","abstract_excerpt":"We examine the problem of two-point boundary optimal control of nonlinear systems over finite-horizon time periods with unknown model dynamics by employing reinforcement learning. We use techniques from singular perturbation theory to decompose the control problem over the finite horizon into two sub-problems, each solved over an infinite horizon. In the process, we avoid the need to solve the time-varying Hamilton-Jacobi-Bellman equation. Using a policy iteration method, which is made feasible as a result of this decomposition, it is now possible to learn the controller gains of both sub-prob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05482","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/2306.05482/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":"2306.05482","created_at":"2026-07-05T06:19:06.606567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05482v1","created_at":"2026-07-05T06:19:06.606567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05482","created_at":"2026-07-05T06:19:06.606567+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOMQO6XYAAHB","created_at":"2026-07-05T06:19:06.606567+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOMQO6XYAAHBOFRA","created_at":"2026-07-05T06:19:06.606567+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOMQO6XY","created_at":"2026-07-05T06:19:06.606567+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/JOMQO6XYAAHBOFRA5RXFUNVOXR","json":"https://pith.science/pith/JOMQO6XYAAHBOFRA5RXFUNVOXR.json","graph_json":"https://pith.science/api/pith-number/JOMQO6XYAAHBOFRA5RXFUNVOXR/graph.json","events_json":"https://pith.science/api/pith-number/JOMQO6XYAAHBOFRA5RXFUNVOXR/events.json","paper":"https://pith.science/paper/JOMQO6XY"},"agent_actions":{"view_html":"https://pith.science/pith/JOMQO6XYAAHBOFRA5RXFUNVOXR","download_json":"https://pith.science/pith/JOMQO6XYAAHBOFRA5RXFUNVOXR.json","view_paper":"https://pith.science/paper/JOMQO6XY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05482&json=true","fetch_graph":"https://pith.science/api/pith-number/JOMQO6XYAAHBOFRA5RXFUNVOXR/graph.json","fetch_events":"https://pith.science/api/pith-number/JOMQO6XYAAHBOFRA5RXFUNVOXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOMQO6XYAAHBOFRA5RXFUNVOXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOMQO6XYAAHBOFRA5RXFUNVOXR/action/storage_attestation","attest_author":"https://pith.science/pith/JOMQO6XYAAHBOFRA5RXFUNVOXR/action/author_attestation","sign_citation":"https://pith.science/pith/JOMQO6XYAAHBOFRA5RXFUNVOXR/action/citation_signature","submit_replication":"https://pith.science/pith/JOMQO6XYAAHBOFRA5RXFUNVOXR/action/replication_record"}},"created_at":"2026-07-05T06:19:06.606567+00:00","updated_at":"2026-07-05T06:19:06.606567+00:00"}