{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FSNBYSEM2GWRGIEBWWASCKWFR5","short_pith_number":"pith:FSNBYSEM","schema_version":"1.0","canonical_sha256":"2c9a1c488cd1ad132081b581212ac58f581a9cb1a14cfe1efbce7674121c19b3","source":{"kind":"arxiv","id":"2409.08382","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","math.DS"],"primary_cat":"eess.SY","authors_text":"Hans De Sterck, Jun Liu, Ruikun Zhou, Thanin Quartz","submitted_at":"2024-09-12T20:07:54Z","abstract_excerpt":"Designing a stabilizing controller for nonlinear systems is a challenging task, especially for high-dimensional problems with unknown dynamics. Traditional reinforcement learning algorithms applied to stabilization tasks tend to drive the system close to the equilibrium point. However, these approaches often fall short of achieving true stabilization and result in persistent oscillations around the equilibrium point. In this work, we propose a reinforcement learning algorithm that stabilizes the system by learning a local linear representation ofthe dynamics. The main component of the algorith"},"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":"2409.08382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-09-12T20:07:54Z","cross_cats_sorted":["cs.LG","cs.SY","math.DS"],"title_canon_sha256":"ca94eec6f7660263d8c55c3cd4ba99ac41c37ad1c44053182aae954c0c5eabfa","abstract_canon_sha256":"9478b0d2765a8594968dcca3382870c05a0b6f78704945dcbee4219f17528086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:30.290784Z","signature_b64":"+8Dc/ZVlnH3oAjTkhsUezwPWDcoCzO6ZireBlAhPFWWulKBvO0Rg2nMN1SnRAYF26s5JE/vCcM+2FPLRxRNLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c9a1c488cd1ad132081b581212ac58f581a9cb1a14cfe1efbce7674121c19b3","last_reissued_at":"2026-07-05T09:06:30.290195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:30.290195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","math.DS"],"primary_cat":"eess.SY","authors_text":"Hans De Sterck, Jun Liu, Ruikun Zhou, Thanin Quartz","submitted_at":"2024-09-12T20:07:54Z","abstract_excerpt":"Designing a stabilizing controller for nonlinear systems is a challenging task, especially for high-dimensional problems with unknown dynamics. Traditional reinforcement learning algorithms applied to stabilization tasks tend to drive the system close to the equilibrium point. However, these approaches often fall short of achieving true stabilization and result in persistent oscillations around the equilibrium point. In this work, we propose a reinforcement learning algorithm that stabilizes the system by learning a local linear representation ofthe dynamics. The main component of the algorith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08382","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/2409.08382/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":"2409.08382","created_at":"2026-07-05T09:06:30.290263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08382v1","created_at":"2026-07-05T09:06:30.290263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08382","created_at":"2026-07-05T09:06:30.290263+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSNBYSEM2GWR","created_at":"2026-07-05T09:06:30.290263+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSNBYSEM2GWRGIEB","created_at":"2026-07-05T09:06:30.290263+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSNBYSEM","created_at":"2026-07-05T09:06:30.290263+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/FSNBYSEM2GWRGIEBWWASCKWFR5","json":"https://pith.science/pith/FSNBYSEM2GWRGIEBWWASCKWFR5.json","graph_json":"https://pith.science/api/pith-number/FSNBYSEM2GWRGIEBWWASCKWFR5/graph.json","events_json":"https://pith.science/api/pith-number/FSNBYSEM2GWRGIEBWWASCKWFR5/events.json","paper":"https://pith.science/paper/FSNBYSEM"},"agent_actions":{"view_html":"https://pith.science/pith/FSNBYSEM2GWRGIEBWWASCKWFR5","download_json":"https://pith.science/pith/FSNBYSEM2GWRGIEBWWASCKWFR5.json","view_paper":"https://pith.science/paper/FSNBYSEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08382&json=true","fetch_graph":"https://pith.science/api/pith-number/FSNBYSEM2GWRGIEBWWASCKWFR5/graph.json","fetch_events":"https://pith.science/api/pith-number/FSNBYSEM2GWRGIEBWWASCKWFR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSNBYSEM2GWRGIEBWWASCKWFR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSNBYSEM2GWRGIEBWWASCKWFR5/action/storage_attestation","attest_author":"https://pith.science/pith/FSNBYSEM2GWRGIEBWWASCKWFR5/action/author_attestation","sign_citation":"https://pith.science/pith/FSNBYSEM2GWRGIEBWWASCKWFR5/action/citation_signature","submit_replication":"https://pith.science/pith/FSNBYSEM2GWRGIEBWWASCKWFR5/action/replication_record"}},"created_at":"2026-07-05T09:06:30.290263+00:00","updated_at":"2026-07-05T09:06:30.290263+00:00"}