{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VORH3IBDJ3JL6HFNO5QAB7SLCK","short_pith_number":"pith:VORH3IBD","schema_version":"1.0","canonical_sha256":"aba27da0234ed2bf1cad776000fe4b12bb61cb009f3d6000a6000d8e87b4b695","source":{"kind":"arxiv","id":"1807.00412","version":2},"attestation_state":"computed","paper":{"title":"Learning to Drive in a Day","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Bewley, Alex Kendall, Amar Shah, Daniele Reda, David Janz, Jeffrey Hawke, John-Mark Allen, Przemyslaw Mazur, Vinh-Dieu Lam","submitted_at":"2018-07-01T22:47:08Z","abstract_excerpt":"We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from rel"},"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":"1807.00412","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-01T22:47:08Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"20f1872a4ba955ca520e3fed60a47ca9dae24766d5cfc0fa4b2eee46c635f602","abstract_canon_sha256":"a1a27d6efe4db9a10bf4552ab3350e78073e19ffb030508dcee7c0b35ff944d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:01.415472Z","signature_b64":"NrzMNATD84c5inTpS/E9KcXj1DL2EUe4Y8RjXHLRpoLX865I4HAiMY67AO2AbNgR8X36x/6wZb7nEKonBLrfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aba27da0234ed2bf1cad776000fe4b12bb61cb009f3d6000a6000d8e87b4b695","last_reissued_at":"2026-05-18T00:06:01.415091Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:01.415091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Drive in a Day","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Bewley, Alex Kendall, Amar Shah, Daniele Reda, David Janz, Jeffrey Hawke, John-Mark Allen, Przemyslaw Mazur, Vinh-Dieu Lam","submitted_at":"2018-07-01T22:47:08Z","abstract_excerpt":"We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from rel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00412","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":"1807.00412","created_at":"2026-05-18T00:06:01.415150+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00412v2","created_at":"2026-05-18T00:06:01.415150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00412","created_at":"2026-05-18T00:06:01.415150+00:00"},{"alias_kind":"pith_short_12","alias_value":"VORH3IBDJ3JL","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VORH3IBDJ3JL6HFN","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VORH3IBD","created_at":"2026-05-18T12:32:59.047623+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/VORH3IBDJ3JL6HFNO5QAB7SLCK","json":"https://pith.science/pith/VORH3IBDJ3JL6HFNO5QAB7SLCK.json","graph_json":"https://pith.science/api/pith-number/VORH3IBDJ3JL6HFNO5QAB7SLCK/graph.json","events_json":"https://pith.science/api/pith-number/VORH3IBDJ3JL6HFNO5QAB7SLCK/events.json","paper":"https://pith.science/paper/VORH3IBD"},"agent_actions":{"view_html":"https://pith.science/pith/VORH3IBDJ3JL6HFNO5QAB7SLCK","download_json":"https://pith.science/pith/VORH3IBDJ3JL6HFNO5QAB7SLCK.json","view_paper":"https://pith.science/paper/VORH3IBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00412&json=true","fetch_graph":"https://pith.science/api/pith-number/VORH3IBDJ3JL6HFNO5QAB7SLCK/graph.json","fetch_events":"https://pith.science/api/pith-number/VORH3IBDJ3JL6HFNO5QAB7SLCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VORH3IBDJ3JL6HFNO5QAB7SLCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VORH3IBDJ3JL6HFNO5QAB7SLCK/action/storage_attestation","attest_author":"https://pith.science/pith/VORH3IBDJ3JL6HFNO5QAB7SLCK/action/author_attestation","sign_citation":"https://pith.science/pith/VORH3IBDJ3JL6HFNO5QAB7SLCK/action/citation_signature","submit_replication":"https://pith.science/pith/VORH3IBDJ3JL6HFNO5QAB7SLCK/action/replication_record"}},"created_at":"2026-05-18T00:06:01.415150+00:00","updated_at":"2026-05-18T00:06:01.415150+00:00"}