{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5OKHDN6TZ2JIKMWXFEUIDQ36CI","short_pith_number":"pith:5OKHDN6T","schema_version":"1.0","canonical_sha256":"eb9471b7d3ce928532d7292881c37e12068a2e090472c86c8a211dae35f7a885","source":{"kind":"arxiv","id":"1803.10231","version":3},"attestation_state":"computed","paper":{"title":"Safe end-to-end imitation learning for model predictive control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Evangelos A. Theodorou, Kamil Saigol, Keuntaek Lee","submitted_at":"2018-03-27T15:47:29Z","abstract_excerpt":"We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the training set. Our algorithm combines reinforcement learning and end-to-end imitation learning to simultaneously learn a control policy as well as a threshold over the predictive uncertainty of the learned model, with no hand-tuning required. Corrective action, such as a return of control to the model predictive controller or human expert, is taken when the u"},"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":"1803.10231","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-27T15:47:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6d9d45c098399ed6c0db462a85e513cd78b240e2efdd4efbd1c66a18e405b8f4","abstract_canon_sha256":"180a79ccee3b58305cd96f8e7d5db88326b674c1f783b575fe96c5ebe119f7c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:57.813766Z","signature_b64":"ZgI6SHPorGfN5xgCM1Ml8jJGj+Z77V48r8PH88tJh4KDiN+gnVTvBxU8wM+UuKZUKeETNIHH71sWrsuoWwxZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb9471b7d3ce928532d7292881c37e12068a2e090472c86c8a211dae35f7a885","last_reissued_at":"2026-05-17T23:53:57.813086Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:57.813086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe end-to-end imitation learning for model predictive control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Evangelos A. Theodorou, Kamil Saigol, Keuntaek Lee","submitted_at":"2018-03-27T15:47:29Z","abstract_excerpt":"We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the training set. Our algorithm combines reinforcement learning and end-to-end imitation learning to simultaneously learn a control policy as well as a threshold over the predictive uncertainty of the learned model, with no hand-tuning required. Corrective action, such as a return of control to the model predictive controller or human expert, is taken when the u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10231","kind":"arxiv","version":3},"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":"1803.10231","created_at":"2026-05-17T23:53:57.813180+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10231v3","created_at":"2026-05-17T23:53:57.813180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10231","created_at":"2026-05-17T23:53:57.813180+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OKHDN6TZ2JI","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OKHDN6TZ2JIKMWX","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OKHDN6T","created_at":"2026-05-18T12:32:08.215937+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/5OKHDN6TZ2JIKMWXFEUIDQ36CI","json":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI.json","graph_json":"https://pith.science/api/pith-number/5OKHDN6TZ2JIKMWXFEUIDQ36CI/graph.json","events_json":"https://pith.science/api/pith-number/5OKHDN6TZ2JIKMWXFEUIDQ36CI/events.json","paper":"https://pith.science/paper/5OKHDN6T"},"agent_actions":{"view_html":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI","download_json":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI.json","view_paper":"https://pith.science/paper/5OKHDN6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10231&json=true","fetch_graph":"https://pith.science/api/pith-number/5OKHDN6TZ2JIKMWXFEUIDQ36CI/graph.json","fetch_events":"https://pith.science/api/pith-number/5OKHDN6TZ2JIKMWXFEUIDQ36CI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/action/storage_attestation","attest_author":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/action/author_attestation","sign_citation":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/action/citation_signature","submit_replication":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/action/replication_record"}},"created_at":"2026-05-17T23:53:57.813180+00:00","updated_at":"2026-05-17T23:53:57.813180+00:00"}