{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WJZYB2YWIRDVWCZYITOEOAL7EG","short_pith_number":"pith:WJZYB2YW","schema_version":"1.0","canonical_sha256":"b27380eb1644475b0b3844dc47017f21b4a05b2ba0ceb94c860e537240500392","source":{"kind":"arxiv","id":"1902.10139","version":3},"attestation_state":"computed","paper":{"title":"Learning Dynamic-Objective Policies from a Class of Optimal Trajectories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Christopher Iliffe Sprague, Dario Izzo, Petter \\\"Ogren","submitted_at":"2019-02-27T17:04:17Z","abstract_excerpt":"Optimal state-feedback controllers, capable of changing between different objective functions, are advantageous to systems in which unexpected situations may arise. However, synthesising such controllers, even for a single objective, is a demanding process. In this paper, we present a novel and straightforward approach to synthesising these policies through a combination of trajectory optimisation, homotopy continuation, and imitation learning. We use numerical continuation to efficiently generate optimal demonstrations across several objectives and boundary conditions, and use these to train "},"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":"1902.10139","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-02-27T17:04:17Z","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"7960d47d00c7094c27baae747fb68fe8f53be3c5dc7ebaf3205bc2bbd39f1f1f","abstract_canon_sha256":"f3c87303bb215b1d7a3040efa2871aaa43f2797146690ab4690ac00e552b15e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T20:13:56.690334Z","signature_b64":"Io1aw4hRwHwHBcuPnhJ+XJyyJoFmLD+VUzfVZWiCkJWtmLTkD0aiaTF5TRygMwvmCToUuAy8xDt0YggByEEqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b27380eb1644475b0b3844dc47017f21b4a05b2ba0ceb94c860e537240500392","last_reissued_at":"2026-06-04T20:13:56.689851Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T20:13:56.689851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Dynamic-Objective Policies from a Class of Optimal Trajectories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Christopher Iliffe Sprague, Dario Izzo, Petter \\\"Ogren","submitted_at":"2019-02-27T17:04:17Z","abstract_excerpt":"Optimal state-feedback controllers, capable of changing between different objective functions, are advantageous to systems in which unexpected situations may arise. However, synthesising such controllers, even for a single objective, is a demanding process. In this paper, we present a novel and straightforward approach to synthesising these policies through a combination of trajectory optimisation, homotopy continuation, and imitation learning. We use numerical continuation to efficiently generate optimal demonstrations across several objectives and boundary conditions, and use these to train "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10139","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1902.10139/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":"1902.10139","created_at":"2026-06-04T20:13:56.689918+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10139v3","created_at":"2026-06-04T20:13:56.689918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10139","created_at":"2026-06-04T20:13:56.689918+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJZYB2YWIRDV","created_at":"2026-06-04T20:13:56.689918+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJZYB2YWIRDVWCZY","created_at":"2026-06-04T20:13:56.689918+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJZYB2YW","created_at":"2026-06-04T20:13:56.689918+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/WJZYB2YWIRDVWCZYITOEOAL7EG","json":"https://pith.science/pith/WJZYB2YWIRDVWCZYITOEOAL7EG.json","graph_json":"https://pith.science/api/pith-number/WJZYB2YWIRDVWCZYITOEOAL7EG/graph.json","events_json":"https://pith.science/api/pith-number/WJZYB2YWIRDVWCZYITOEOAL7EG/events.json","paper":"https://pith.science/paper/WJZYB2YW"},"agent_actions":{"view_html":"https://pith.science/pith/WJZYB2YWIRDVWCZYITOEOAL7EG","download_json":"https://pith.science/pith/WJZYB2YWIRDVWCZYITOEOAL7EG.json","view_paper":"https://pith.science/paper/WJZYB2YW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10139&json=true","fetch_graph":"https://pith.science/api/pith-number/WJZYB2YWIRDVWCZYITOEOAL7EG/graph.json","fetch_events":"https://pith.science/api/pith-number/WJZYB2YWIRDVWCZYITOEOAL7EG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJZYB2YWIRDVWCZYITOEOAL7EG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJZYB2YWIRDVWCZYITOEOAL7EG/action/storage_attestation","attest_author":"https://pith.science/pith/WJZYB2YWIRDVWCZYITOEOAL7EG/action/author_attestation","sign_citation":"https://pith.science/pith/WJZYB2YWIRDVWCZYITOEOAL7EG/action/citation_signature","submit_replication":"https://pith.science/pith/WJZYB2YWIRDVWCZYITOEOAL7EG/action/replication_record"}},"created_at":"2026-06-04T20:13:56.689918+00:00","updated_at":"2026-06-04T20:13:56.689918+00:00"}