{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IGVOC7W222H6262VKKGV35AINW","short_pith_number":"pith:IGVOC7W2","schema_version":"1.0","canonical_sha256":"41aae17edad68fed7b55528d5df4086d88430a482c76e7d7eb4e2cafaf51f35a","source":{"kind":"arxiv","id":"1711.10785","version":2},"attestation_state":"computed","paper":{"title":"Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Mogens Graf Plessen","submitted_at":"2017-11-29T11:37:29Z","abstract_excerpt":"Within the context of autonomous driving a model-based reinforcement learning algorithm is proposed for the design of neural network-parameterized controllers. Classical model-based control methods, which include sampling- and lattice-based algorithms and model predictive control, suffer from the trade-off between model complexity and computational burden required for the online solution of expensive optimization or search problems at every short sampling time. To circumvent this trade-off, a 2-step procedure is motivated: first learning of a controller during offline training based on an arbi"},"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":"1711.10785","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-29T11:37:29Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"29cc195ac6829f166d9959fe85fbc420a43a675b93a23d2efe3a523fd2935a04","abstract_canon_sha256":"139d7cd4a56b19e4d2a4cd825c123b1939b7ae6c5006bf13be25bc206643c946"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:04.171128Z","signature_b64":"sMPnZZzgdOUcqIg+bV0UqIjYsyYAWa9jXMLeoXSL8HHuhbt3aWvmOnkKW9RDm9a/RqeJCQQW9jnJIw1fvPRQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41aae17edad68fed7b55528d5df4086d88430a482c76e7d7eb4e2cafaf51f35a","last_reissued_at":"2026-05-18T00:09:04.170427Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:04.170427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Mogens Graf Plessen","submitted_at":"2017-11-29T11:37:29Z","abstract_excerpt":"Within the context of autonomous driving a model-based reinforcement learning algorithm is proposed for the design of neural network-parameterized controllers. Classical model-based control methods, which include sampling- and lattice-based algorithms and model predictive control, suffer from the trade-off between model complexity and computational burden required for the online solution of expensive optimization or search problems at every short sampling time. To circumvent this trade-off, a 2-step procedure is motivated: first learning of a controller during offline training based on an arbi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10785","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":""},"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":"1711.10785","created_at":"2026-05-18T00:09:04.170527+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10785v2","created_at":"2026-05-18T00:09:04.170527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10785","created_at":"2026-05-18T00:09:04.170527+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGVOC7W222H6","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGVOC7W222H6262V","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGVOC7W2","created_at":"2026-05-18T12:31:21.493067+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/IGVOC7W222H6262VKKGV35AINW","json":"https://pith.science/pith/IGVOC7W222H6262VKKGV35AINW.json","graph_json":"https://pith.science/api/pith-number/IGVOC7W222H6262VKKGV35AINW/graph.json","events_json":"https://pith.science/api/pith-number/IGVOC7W222H6262VKKGV35AINW/events.json","paper":"https://pith.science/paper/IGVOC7W2"},"agent_actions":{"view_html":"https://pith.science/pith/IGVOC7W222H6262VKKGV35AINW","download_json":"https://pith.science/pith/IGVOC7W222H6262VKKGV35AINW.json","view_paper":"https://pith.science/paper/IGVOC7W2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10785&json=true","fetch_graph":"https://pith.science/api/pith-number/IGVOC7W222H6262VKKGV35AINW/graph.json","fetch_events":"https://pith.science/api/pith-number/IGVOC7W222H6262VKKGV35AINW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGVOC7W222H6262VKKGV35AINW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGVOC7W222H6262VKKGV35AINW/action/storage_attestation","attest_author":"https://pith.science/pith/IGVOC7W222H6262VKKGV35AINW/action/author_attestation","sign_citation":"https://pith.science/pith/IGVOC7W222H6262VKKGV35AINW/action/citation_signature","submit_replication":"https://pith.science/pith/IGVOC7W222H6262VKKGV35AINW/action/replication_record"}},"created_at":"2026-05-18T00:09:04.170527+00:00","updated_at":"2026-05-18T00:09:04.170527+00:00"}