{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IPQ2GHZ23SLWHTVZ7WZPMJEXD6","short_pith_number":"pith:IPQ2GHZ2","schema_version":"1.0","canonical_sha256":"43e1a31f3adc9763ceb9fdb2f624971f870ef68ec6aaef87c4b724ad646feeae","source":{"kind":"arxiv","id":"1906.12189","version":1},"attestation_state":"computed","paper":{"title":"Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Andreas Krause, Felix Berkenkamp, Joschka Boedecker, Matteo Turchetta, Torsten Koller","submitted_at":"2019-06-27T11:37:49Z","abstract_excerpt":"Reinforcement learning has been successfully used to solve difficult tasks in complex unknown environments. However, these methods typically do not provide any safety guarantees during the learning process. This is particularly problematic, since reinforcement learning agent actively explore their environment. This prevents their use in safety-critical, real-world applications. In this paper, we present a learning-based model predictive control scheme that provides high-probability safety guarantees throughout the learning process. Based on a reliable statistical model, we construct provably a"},"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":"1906.12189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-06-27T11:37:49Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY"],"title_canon_sha256":"5a87a23ab47540cbb8cedf100afaf61b3c06b01fa6779f104b1671a08c40f525","abstract_canon_sha256":"6533930a6c05d8e85858b69d8a88e65b8bafb4d3c2ba2182501e03a443a159aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:52.631447Z","signature_b64":"t5JhiKeha7K1hPSzb6vBvfZExtFydWiGdpXd43kTfobul4G8v8S3flixZwyBfp4Vt/P3r83ON5v376b7dP6qDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43e1a31f3adc9763ceb9fdb2f624971f870ef68ec6aaef87c4b724ad646feeae","last_reissued_at":"2026-05-17T23:41:52.630943Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:52.630943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Andreas Krause, Felix Berkenkamp, Joschka Boedecker, Matteo Turchetta, Torsten Koller","submitted_at":"2019-06-27T11:37:49Z","abstract_excerpt":"Reinforcement learning has been successfully used to solve difficult tasks in complex unknown environments. However, these methods typically do not provide any safety guarantees during the learning process. This is particularly problematic, since reinforcement learning agent actively explore their environment. This prevents their use in safety-critical, real-world applications. In this paper, we present a learning-based model predictive control scheme that provides high-probability safety guarantees throughout the learning process. Based on a reliable statistical model, we construct provably a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.12189","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":"1906.12189","created_at":"2026-05-17T23:41:52.631021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.12189v1","created_at":"2026-05-17T23:41:52.631021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.12189","created_at":"2026-05-17T23:41:52.631021+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPQ2GHZ23SLW","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPQ2GHZ23SLWHTVZ","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPQ2GHZ2","created_at":"2026-05-18T12:33:18.533446+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/IPQ2GHZ23SLWHTVZ7WZPMJEXD6","json":"https://pith.science/pith/IPQ2GHZ23SLWHTVZ7WZPMJEXD6.json","graph_json":"https://pith.science/api/pith-number/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/graph.json","events_json":"https://pith.science/api/pith-number/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/events.json","paper":"https://pith.science/paper/IPQ2GHZ2"},"agent_actions":{"view_html":"https://pith.science/pith/IPQ2GHZ23SLWHTVZ7WZPMJEXD6","download_json":"https://pith.science/pith/IPQ2GHZ23SLWHTVZ7WZPMJEXD6.json","view_paper":"https://pith.science/paper/IPQ2GHZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.12189&json=true","fetch_graph":"https://pith.science/api/pith-number/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/graph.json","fetch_events":"https://pith.science/api/pith-number/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/action/storage_attestation","attest_author":"https://pith.science/pith/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/action/author_attestation","sign_citation":"https://pith.science/pith/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/action/citation_signature","submit_replication":"https://pith.science/pith/IPQ2GHZ23SLWHTVZ7WZPMJEXD6/action/replication_record"}},"created_at":"2026-05-17T23:41:52.631021+00:00","updated_at":"2026-05-17T23:41:52.631021+00:00"}