{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2NTUNMOH7RNHA6KCYOQYFKX43Q","short_pith_number":"pith:2NTUNMOH","schema_version":"1.0","canonical_sha256":"d36746b1c7fc5a707942c3a182aafcdc2ca491f21b4bf4e61ad27d093ce66a7a","source":{"kind":"arxiv","id":"2007.12291","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Babak Hassibi, Kamyar Azizzadenesheli, Sahin Lale","submitted_at":"2020-07-23T23:06:40Z","abstract_excerpt":"In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems. When learning a dynamical system, one needs to stabilize the unknown dynamics in order to avoid system blow-ups. We propose an algorithm that certifies fast stabilization of the underlying system by effectively exploring the environment with an improved exploration strategy. We show that the proposed algorithm attains $\\tilde{\\mathcal{O}}(\\sqrt{T})$ regret after $T$ time steps of agent-environment interaction. We also show that the regret of the proposed algorithm has only a polynom"},"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":"2007.12291","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-23T23:06:40Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f8cf43a67885483d118756536601c8f19dbbdea1675e91037a21d516a327a2a5","abstract_canon_sha256":"3aad68a97bea4ef60d55ff3e99401783ba3d60531a01407ea864a1ef954cf639"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:39.182886Z","signature_b64":"lpEOfHYL30NpgARWP4U4/3ktJMQhZwjBGwzyY59ZZ2yweLuWms/lTPtWclot6Qzt4vRQgZ6bByrVtV1h9ea5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d36746b1c7fc5a707942c3a182aafcdc2ca491f21b4bf4e61ad27d093ce66a7a","last_reissued_at":"2026-07-05T04:28:39.182401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:39.182401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Babak Hassibi, Kamyar Azizzadenesheli, Sahin Lale","submitted_at":"2020-07-23T23:06:40Z","abstract_excerpt":"In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems. When learning a dynamical system, one needs to stabilize the unknown dynamics in order to avoid system blow-ups. We propose an algorithm that certifies fast stabilization of the underlying system by effectively exploring the environment with an improved exploration strategy. We show that the proposed algorithm attains $\\tilde{\\mathcal{O}}(\\sqrt{T})$ regret after $T$ time steps of agent-environment interaction. We also show that the regret of the proposed algorithm has only a polynom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12291","kind":"arxiv","version":2},"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/2007.12291/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":"2007.12291","created_at":"2026-07-05T04:28:39.182460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12291v2","created_at":"2026-07-05T04:28:39.182460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12291","created_at":"2026-07-05T04:28:39.182460+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NTUNMOH7RNH","created_at":"2026-07-05T04:28:39.182460+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NTUNMOH7RNHA6KC","created_at":"2026-07-05T04:28:39.182460+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NTUNMOH","created_at":"2026-07-05T04:28:39.182460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22223","citing_title":"Regret-Guaranteed Safe Switching: LQR Setting with Unknown Dynamics","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q","json":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q.json","graph_json":"https://pith.science/api/pith-number/2NTUNMOH7RNHA6KCYOQYFKX43Q/graph.json","events_json":"https://pith.science/api/pith-number/2NTUNMOH7RNHA6KCYOQYFKX43Q/events.json","paper":"https://pith.science/paper/2NTUNMOH"},"agent_actions":{"view_html":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q","download_json":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q.json","view_paper":"https://pith.science/paper/2NTUNMOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12291&json=true","fetch_graph":"https://pith.science/api/pith-number/2NTUNMOH7RNHA6KCYOQYFKX43Q/graph.json","fetch_events":"https://pith.science/api/pith-number/2NTUNMOH7RNHA6KCYOQYFKX43Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q/action/storage_attestation","attest_author":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q/action/author_attestation","sign_citation":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q/action/citation_signature","submit_replication":"https://pith.science/pith/2NTUNMOH7RNHA6KCYOQYFKX43Q/action/replication_record"}},"created_at":"2026-07-05T04:28:39.182460+00:00","updated_at":"2026-07-05T04:28:39.182460+00:00"}