{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IIIT6PTEQZGRBPZ4ZU6HUGGM4E","short_pith_number":"pith:IIIT6PTE","schema_version":"1.0","canonical_sha256":"42113f3e64864d10bf3ccd3c7a18cce112ed24d8bfa23e80496d6ac9d6357652","source":{"kind":"arxiv","id":"1811.08586","version":2},"attestation_state":"computed","paper":{"title":"Urban Driving with Multi-Objective Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changjian Li, Krzysztof Czarnecki","submitted_at":"2018-11-21T03:36:52Z","abstract_excerpt":"Autonomous driving is a challenging domain that entails multiple aspects: a vehicle should be able to drive to its destination as fast as possible while avoiding collision, obeying traffic rules and ensuring the comfort of passengers. In this paper, we present a deep learning variant of thresholded lexicographic Q-learning for the task of urban driving. Our multi-objective DQN agent learns to drive on multi-lane roads and intersections, yielding and changing lanes according to traffic rules. We also propose an extension for factored Markov Decision Processes to the DQN architecture that provid"},"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":"1811.08586","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-11-21T03:36:52Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"bb4b476c3338fcf0cb71f80924264abd0469dc4119fd3f91957635f7a3ef59a4","abstract_canon_sha256":"0a6ff243dbb6c7a81a62bdffc61363e6b901b9e5e485a318dfc0fd4b78a3cd23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:32.022840Z","signature_b64":"UKfzy1knG0duYDvd0c36Xl1AImKyQkmLdwR4B4CXo3nOsyHQZQlxPC6GRYcUbjCh1qp05zMfx/3pE2myIdZoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42113f3e64864d10bf3ccd3c7a18cce112ed24d8bfa23e80496d6ac9d6357652","last_reissued_at":"2026-05-17T23:52:32.022374Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:32.022374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Urban Driving with Multi-Objective Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changjian Li, Krzysztof Czarnecki","submitted_at":"2018-11-21T03:36:52Z","abstract_excerpt":"Autonomous driving is a challenging domain that entails multiple aspects: a vehicle should be able to drive to its destination as fast as possible while avoiding collision, obeying traffic rules and ensuring the comfort of passengers. In this paper, we present a deep learning variant of thresholded lexicographic Q-learning for the task of urban driving. Our multi-objective DQN agent learns to drive on multi-lane roads and intersections, yielding and changing lanes according to traffic rules. We also propose an extension for factored Markov Decision Processes to the DQN architecture that provid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08586","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":"1811.08586","created_at":"2026-05-17T23:52:32.022443+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.08586v2","created_at":"2026-05-17T23:52:32.022443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08586","created_at":"2026-05-17T23:52:32.022443+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIIT6PTEQZGR","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIIT6PTEQZGRBPZ4","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIIT6PTE","created_at":"2026-05-18T12:32:31.084164+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/IIIT6PTEQZGRBPZ4ZU6HUGGM4E","json":"https://pith.science/pith/IIIT6PTEQZGRBPZ4ZU6HUGGM4E.json","graph_json":"https://pith.science/api/pith-number/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/graph.json","events_json":"https://pith.science/api/pith-number/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/events.json","paper":"https://pith.science/paper/IIIT6PTE"},"agent_actions":{"view_html":"https://pith.science/pith/IIIT6PTEQZGRBPZ4ZU6HUGGM4E","download_json":"https://pith.science/pith/IIIT6PTEQZGRBPZ4ZU6HUGGM4E.json","view_paper":"https://pith.science/paper/IIIT6PTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.08586&json=true","fetch_graph":"https://pith.science/api/pith-number/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/graph.json","fetch_events":"https://pith.science/api/pith-number/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/action/storage_attestation","attest_author":"https://pith.science/pith/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/action/author_attestation","sign_citation":"https://pith.science/pith/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/action/citation_signature","submit_replication":"https://pith.science/pith/IIIT6PTEQZGRBPZ4ZU6HUGGM4E/action/replication_record"}},"created_at":"2026-05-17T23:52:32.022443+00:00","updated_at":"2026-05-17T23:52:32.022443+00:00"}